更新autogpt

.__test.py

@@ -1,57 +0,0 @@
-#! .\venv\
-# encoding: utf-8
-# @Time   : 2023/4/19
-# @Author : Spike
-# @Descr   :
-import gradio as gr
-
-with gr.Blocks() as demo:   # 绘制一个块对象，在此基础上可以使用Row、Column、Tab、Box等等布局元素
-    gr.Markdown(f"<h1 align=\"center\">我是Bolcks</h1>")
-    with gr.Row():
-        with gr.Column(scale=100):    # 组件绘制在布局元素下，则会根据布局元素的规定展示
-            gr.Markdown('# 这里是列1')
-            chatbot = gr.Chatbot().style(height=400)
-            status = gr.Markdown()
-
-        with gr.Column(scale=50):
-            gr.Markdown('# 这里是列2')
-            i_say = gr.Textbox()
-            submit = gr.Button(value='submit', variant='primary')
-            with gr.Row():
-                you_say = gr.Textbox(show_label=False, placeholder='没有任何用的输出框')
-                Noo = gr.Button(value='没有任何用的按钮')
-
-
-    def respond(say, chat_history):
-        import random
-        bot_message = random.choice(["How are you?", "I love you", "I'm very hungry"])
-        chat_history.append((say, bot_message))
-        return "我要开始胡说了", chat_history
-
-    # 注册函数 fn=要注册的函数， input=函数接收的参数， outputs=函数处理后返回接收的组件
-    submit.click(fn=respond, inputs=[i_say, chatbot], outputs=[status, chatbot])
-
-demo.launch()
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-

autogpt/CURRENT_BULLETIN.md

@@ -1,2 +0,0 @@
-Welcome to Auto-GPT! We'll keep you informed of the latest news and features by printing messages here.
-If you don't wish to see this message, you can run Auto-GPT with the --skip-news flag

autogpt/__main__.py

@@ -1,5 +0,0 @@
-"""Auto-GPT: A GPT powered AI Assistant"""
-import autogpt.cli
-
-if __name__ == "__main__":
-    autogpt.cli.main()

autogpt/agent/__init__.py

@@ -1,4 +0,0 @@
-from autogpt.agent.agent import Agent
-from autogpt.agent.agent_manager import AgentManager
-
-__all__ = ["Agent", "AgentManager"]

autogpt/agent/agent.py

@@ -1,11 +1,29 @@
+import signal
+import sys
+from datetime import datetime
+
 from colorama import Fore, Style
 
 from autogpt.app import execute_command, get_command
-from autogpt.chat import chat_with_ai, create_chat_message
+from autogpt.commands.command import CommandRegistry
 from autogpt.config import Config
+from autogpt.config.ai_config import AIConfig
 from autogpt.json_utils.json_fix_llm import fix_json_using_multiple_techniques
-from autogpt.json_utils.utilities import validate_json
+from autogpt.json_utils.utilities import LLM_DEFAULT_RESPONSE_FORMAT, validate_json
+from autogpt.llm.base import ChatSequence
+from autogpt.llm.chat import chat_with_ai, create_chat_completion
+from autogpt.llm.utils import count_string_tokens
+from autogpt.log_cycle.log_cycle import (
+    FULL_MESSAGE_HISTORY_FILE_NAME,
+    NEXT_ACTION_FILE_NAME,
+    PROMPT_SUPERVISOR_FEEDBACK_FILE_NAME,
+    SUPERVISOR_FEEDBACK_FILE_NAME,
+    USER_INPUT_FILE_NAME,
+    LogCycleHandler,
+)
 from autogpt.logs import logger, print_assistant_thoughts
+from autogpt.memory.message_history import MessageHistory
+from autogpt.memory.vector import VectorMemory
 from autogpt.speech import say_text
 from autogpt.spinner import Spinner
 from autogpt.utils import clean_input
@@ -18,7 +36,6 @@ class Agent:
     Attributes:
         ai_name: The name of the agent.
         memory: The memory object to use.
-        full_message_history: The full message history.
         next_action_count: The number of actions to execute.
         system_prompt: The system prompt is the initial prompt that defines everything
           the AI needs to know to achieve its task successfully.
@@ -42,189 +59,251 @@ class Agent:
     """
 
     def __init__(
-            self,
+        self,
-            ai_name,
+        ai_name: str,
-            memory,
+        memory: VectorMemory,
-            full_message_history,
+        next_action_count: int,
-            next_action_count,
+        command_registry: CommandRegistry,
-            command_registry,
+        config: AIConfig,
-            config,
+        system_prompt: str,
-            system_prompt,
+        triggering_prompt: str,
-            triggering_prompt,
+        workspace_directory: str,
-            workspace_directory,
     ):
-        self.cfg = Config()
+        cfg = Config()
         self.ai_name = ai_name
         self.memory = memory
-        self.full_message_history = full_message_history
+        self.history = MessageHistory(self)
         self.next_action_count = next_action_count
         self.command_registry = command_registry
         self.config = config
         self.system_prompt = system_prompt
         self.triggering_prompt = triggering_prompt
-        self.workspace = Workspace(workspace_directory, self.cfg.restrict_to_workspace)
+        self.workspace = Workspace(workspace_directory, cfg.restrict_to_workspace)
-        self.loop_count = 0
+        self.created_at = datetime.now().strftime("%Y%m%d_%H%M%S")
-        self.command_name = None
+        self.cycle_count = 0
-        self.sarguments = None
+        self.log_cycle_handler = LogCycleHandler()
-        self.user_input = ""
-        self.cfg = Config()
 
     def start_interaction_loop(self):
-        # Discontinue if continuous limit is reached
+        # Interaction Loop
-        self.loop_count += 1
+        cfg = Config()
-        if (
+        self.cycle_count = 0
-                self.cfg.continuous_mode
+        command_name = None
-                and self.cfg.continuous_limit > 0
+        arguments = None
-                and self.loop_count > self.cfg.continuous_limit
+        user_input = ""
-        ):
-            logger.typewriter_log(
-                "Continuous Limit Reached: ", Fore.YELLOW, f"{self.cfg.continuous_limit}"
-            )
-            # break
 
-        # Send message to AI, get response
+        # Signal handler for interrupting y -N
-        with Spinner("Thinking... "):
+        def signal_handler(signum, frame):
-            self.assistant_reply = chat_with_ai(
+            if self.next_action_count == 0:
-                self,
+                sys.exit()
-                self.system_prompt,
+            else:
-                self.triggering_prompt,
-                self.full_message_history,
-                self.memory,
-                self.cfg.fast_token_limit,
-            )  # TODO: This hardcodes the model to use GPT3.5. Make this an argument
-
-        self.assistant_reply_json = fix_json_using_multiple_techniques(self.assistant_reply)
-        for plugin in self.cfg.plugins:
-            if not plugin.can_handle_post_planning():
-                continue
-            self.assistant_reply_json = plugin.post_planning(self, self.assistant_reply_json)
-
-        # Print Assistant thoughts
-        if self.assistant_reply_json != {}:
-            validate_json(self.assistant_reply_json, "llm_response_format_1")
-            # Get command name and self.arguments
-            try:
-                print_assistant_thoughts(self.ai_name, self.assistant_reply_json)
-                self.command_name, self.arguments = get_command(self.assistant_reply_json)
-                if self.cfg.speak_mode:
-                    say_text(f"I want to execute {self.command_name}")
-                self.arguments = self._resolve_pathlike_command_args(self.arguments)
-
-            except Exception as e:
-                logger.error("Error: \n", str(e))
-
-        if not self.cfg.continuous_mode and self.next_action_count == 0:
-            # ### GET USER AUTHORIZATION TO EXECUTE COMMAND ###
-            # Get key press: Prompt the user to press enter to continue or escape
-            # to exit
-            logger.typewriter_log(
-                "NEXT ACTION: ",
-                Fore.CYAN,
-                f"COMMAND = {self.command_name}"
-                f"ARGUMENTS = {self.arguments}",
-            )
-            logger.typewriter_log(
-                "",
-                "",
-                "Enter 'y' to authorise command, 'y -N' to run N continuous "
-                "commands, 'n' to exit program, or enter feedback for "
-                f"{self.ai_name}...",
-            )
-
-    def start_interaction_next(self, cookie, chatbot, history, msg, _input, obj):
-        console_input = _input
-        if console_input.lower().strip() == "y":
-            self.user_input = "GENERATE NEXT COMMAND JSON"
-        elif console_input.lower().strip() == "":
-            print("Invalid input format.")
-            return
-        elif console_input.lower().startswith("y -"):
-            try:
-                self.next_action_count = abs(
-                    int(console_input.split(" ")[1])
-                )
-                self.user_input = "GENERATE NEXT COMMAND JSON"
-            except ValueError:
                 print(
-                    "Invalid input format. Please enter 'y -n' where n is"
+                    Fore.RED
-                    " the number of continuous tasks."
+                    + "Interrupt signal received. Stopping continuous command execution."
+                    + Style.RESET_ALL
+                )
+                self.next_action_count = 0
+
+        signal.signal(signal.SIGINT, signal_handler)
+
+        while True:
+            # Discontinue if continuous limit is reached
+            self.cycle_count += 1
+            self.log_cycle_handler.log_count_within_cycle = 0
+            self.log_cycle_handler.log_cycle(
+                self.config.ai_name,
+                self.created_at,
+                self.cycle_count,
+                [m.raw() for m in self.history],
+                FULL_MESSAGE_HISTORY_FILE_NAME,
+            )
+            if (
+                cfg.continuous_mode
+                and cfg.continuous_limit > 0
+                and self.cycle_count > cfg.continuous_limit
+            ):
+                logger.typewriter_log(
+                    "Continuous Limit Reached: ", Fore.YELLOW, f"{cfg.continuous_limit}"
+                )
+                break
+            # Send message to AI, get response
+            with Spinner("Thinking... ", plain_output=cfg.plain_output):
+                assistant_reply = chat_with_ai(
+                    cfg,
+                    self,
+                    self.system_prompt,
+                    self.triggering_prompt,
+                    cfg.fast_token_limit,
+                    cfg.fast_llm_model,
                 )
 
-                return
+            assistant_reply_json = fix_json_using_multiple_techniques(assistant_reply)
-        elif console_input.lower() == "n":
+            for plugin in cfg.plugins:
-            self.user_input = "EXIT"
+                if not plugin.can_handle_post_planning():
-            return
+                    continue
-        else:
+                assistant_reply_json = plugin.post_planning(assistant_reply_json)
-            self.user_input = console_input
-            self.command_name = "human_feedback"
-            return
 
-        if self.user_input == "GENERATE NEXT COMMAND JSON":
+            # Print Assistant thoughts
-            logger.typewriter_log(
+            if assistant_reply_json != {}:
-                "-=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-=",
+                validate_json(assistant_reply_json, LLM_DEFAULT_RESPONSE_FORMAT)
-                Fore.MAGENTA,
+                # Get command name and arguments
-                "",
+                try:
+                    print_assistant_thoughts(
+                        self.ai_name, assistant_reply_json, cfg.speak_mode
+                    )
+                    command_name, arguments = get_command(assistant_reply_json)
+                    if cfg.speak_mode:
+                        say_text(f"I want to execute {command_name}")
+
+                    arguments = self._resolve_pathlike_command_args(arguments)
+
+                except Exception as e:
+                    logger.error("Error: \n", str(e))
+            self.log_cycle_handler.log_cycle(
+                self.config.ai_name,
+                self.created_at,
+                self.cycle_count,
+                assistant_reply_json,
+                NEXT_ACTION_FILE_NAME,
             )
-        elif self.user_input == "EXIT":
+
-            print("Exiting...", flush=True)
-            # break  这里需要注意
-        else:
-            # Print command
             logger.typewriter_log(
                 "NEXT ACTION: ",
                 Fore.CYAN,
-                f"COMMAND = {Fore.CYAN}{self.command_name}{Style.RESET_ALL}"
+                f"COMMAND = {Fore.CYAN}{command_name}{Style.RESET_ALL}  "
-                f"  ARGUMENTS = {Fore.CYAN}{self.arguments}{Style.RESET_ALL}",
+                f"ARGUMENTS = {Fore.CYAN}{arguments}{Style.RESET_ALL}",
             )
 
-        # Execute command
+            if not cfg.continuous_mode and self.next_action_count == 0:
-        if self.command_name is not None and self.command_name.lower().startswith("error"):
+                # ### GET USER AUTHORIZATION TO EXECUTE COMMAND ###
-            result = (
+                # Get key press: Prompt the user to press enter to continue or escape
-                f"Command {self.command_name} threw the following error: {self.arguments}"
+                # to exit
-            )
+                self.user_input = ""
-        elif self.command_name == "human_feedback":
+                logger.info(
-            result = f"Human feedback: {self.user_input}"
+                    "Enter 'y' to authorise command, 'y -N' to run N continuous commands, 's' to run self-feedback commands, "
-        else:
+                    "'n' to exit program, or enter feedback for "
-            for plugin in self.cfg.plugins:
+                    f"{self.ai_name}..."
-                if not plugin.can_handle_pre_command():
-                    continue
-                self.command_name, self.arguments = plugin.pre_command(
-                    self.command_name, self.arguments
                 )
-            command_result = execute_command(
+                while True:
-                self.command_registry,
+                    if cfg.chat_messages_enabled:
-                self.command_name,
+                        console_input = clean_input("Waiting for your response...")
-                self.arguments,
+                    else:
-                self.config.prompt_generator,
+                        console_input = clean_input(
-            )
+                            Fore.MAGENTA + "Input:" + Style.RESET_ALL
-            result = f"Command {self.command_name} returned: " f"{command_result}"
+                        )
+                    if console_input.lower().strip() == cfg.authorise_key:
+                        user_input = "GENERATE NEXT COMMAND JSON"
+                        break
+                    elif console_input.lower().strip() == "s":
+                        logger.typewriter_log(
+                            "-=-=-=-=-=-=-= THOUGHTS, REASONING, PLAN AND CRITICISM WILL NOW BE VERIFIED BY AGENT -=-=-=-=-=-=-=",
+                            Fore.GREEN,
+                            "",
+                        )
+                        thoughts = assistant_reply_json.get("thoughts", {})
+                        self_feedback_resp = self.get_self_feedback(
+                            thoughts, cfg.fast_llm_model
+                        )
+                        logger.typewriter_log(
+                            f"SELF FEEDBACK: {self_feedback_resp}",
+                            Fore.YELLOW,
+                            "",
+                        )
+                        user_input = self_feedback_resp
+                        command_name = "self_feedback"
+                        break
+                    elif console_input.lower().strip() == "":
+                        logger.warn("Invalid input format.")
+                        continue
+                    elif console_input.lower().startswith(f"{cfg.authorise_key} -"):
+                        try:
+                            self.next_action_count = abs(
+                                int(console_input.split(" ")[1])
+                            )
+                            user_input = "GENERATE NEXT COMMAND JSON"
+                        except ValueError:
+                            logger.warn(
+                                "Invalid input format. Please enter 'y -n' where n is"
+                                " the number of continuous tasks."
+                            )
+                            continue
+                        break
+                    elif console_input.lower() == cfg.exit_key:
+                        user_input = "EXIT"
+                        break
+                    else:
+                        user_input = console_input
+                        command_name = "human_feedback"
+                        self.log_cycle_handler.log_cycle(
+                            self.config.ai_name,
+                            self.created_at,
+                            self.cycle_count,
+                            user_input,
+                            USER_INPUT_FILE_NAME,
+                        )
+                        break
 
-            for plugin in self.cfg.plugins:
+                if user_input == "GENERATE NEXT COMMAND JSON":
-                if not plugin.can_handle_post_command():
+                    logger.typewriter_log(
-                    continue
+                        "-=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-=",
-                result = plugin.post_command(self.command_name, result)
+                        Fore.MAGENTA,
-            if self.next_action_count > 0:
+                        "",
-                self.next_action_count -= 1
+                    )
-        if self.command_name != "do_nothing":
+                elif user_input == "EXIT":
-            memory_to_add = (
+                    logger.info("Exiting...")
-                f"Assistant Reply: {self.assistant_reply} "
+                    break
-                f"\nResult: {result} "
+            else:
-                f"\nHuman Feedback: {self.user_input} "
+                # Print authorized commands left value
-            )
+                logger.typewriter_log(
+                    f"{Fore.CYAN}AUTHORISED COMMANDS LEFT: {Style.RESET_ALL}{self.next_action_count}"
+                )
 
-            self.memory.add(memory_to_add)
+            # Execute command
+            if command_name is not None and command_name.lower().startswith("error"):
+                result = f"Could not execute command: {arguments}"
+            elif command_name == "human_feedback":
+                result = f"Human feedback: {user_input}"
+            elif command_name == "self_feedback":
+                result = f"Self feedback: {user_input}"
+            else:
+                for plugin in cfg.plugins:
+                    if not plugin.can_handle_pre_command():
+                        continue
+                    command_name, arguments = plugin.pre_command(
+                        command_name, arguments
+                    )
+                command_result = execute_command(
+                    self.command_registry,
+                    command_name,
+                    arguments,
+                    self.config.prompt_generator,
+                    config=cfg,
+                )
+                result = f"Command {command_name} returned: " f"{command_result}"
+
+                result_tlength = count_string_tokens(
+                    str(command_result), cfg.fast_llm_model
+                )
+                memory_tlength = count_string_tokens(
+                    str(self.history.summary_message()), cfg.fast_llm_model
+                )
+                if result_tlength + memory_tlength + 600 > cfg.fast_token_limit:
+                    result = f"Failure: command {command_name} returned too much output. \
+                        Do not execute this command again with the same arguments."
+
+                for plugin in cfg.plugins:
+                    if not plugin.can_handle_post_command():
+                        continue
+                    result = plugin.post_command(command_name, result)
+                if self.next_action_count > 0:
+                    self.next_action_count -= 1
 
             # Check if there's a result from the command append it to the message
             # history
             if result is not None:
-                self.full_message_history.append(
+                self.history.add("system", result, "action_result")
-                    create_chat_message("system", result)
-                )
                 logger.typewriter_log("SYSTEM: ", Fore.YELLOW, result)
             else:
-                self.full_message_history.append(
+                self.history.add("system", "Unable to execute command", "action_result")
-                    create_chat_message("system", "Unable to execute command")
-                )
                 logger.typewriter_log(
                     "SYSTEM: ", Fore.YELLOW, "Unable to execute command"
                 )
@@ -239,3 +318,45 @@ class Agent:
                         self.workspace.get_path(command_args[pathlike])
                     )
         return command_args
+
+    def get_self_feedback(self, thoughts: dict, llm_model: str) -> str:
+        """Generates a feedback response based on the provided thoughts dictionary.
+        This method takes in a dictionary of thoughts containing keys such as 'reasoning',
+        'plan', 'thoughts', and 'criticism'. It combines these elements into a single
+        feedback message and uses the create_chat_completion() function to generate a
+        response based on the input message.
+        Args:
+            thoughts (dict): A dictionary containing thought elements like reasoning,
+            plan, thoughts, and criticism.
+        Returns:
+            str: A feedback response generated using the provided thoughts dictionary.
+        """
+        ai_role = self.config.ai_role
+
+        feedback_prompt = f"Below is a message from me, an AI Agent, assuming the role of {ai_role}. whilst keeping knowledge of my slight limitations as an AI Agent Please evaluate my thought process, reasoning, and plan, and provide a concise paragraph outlining potential improvements. Consider adding or removing ideas that do not align with my role and explaining why, prioritizing thoughts based on their significance, or simply refining my overall thought process."
+        reasoning = thoughts.get("reasoning", "")
+        plan = thoughts.get("plan", "")
+        thought = thoughts.get("thoughts", "")
+        feedback_thoughts = thought + reasoning + plan
+
+        prompt = ChatSequence.for_model(llm_model)
+        prompt.add("user", feedback_prompt + feedback_thoughts)
+
+        self.log_cycle_handler.log_cycle(
+            self.config.ai_name,
+            self.created_at,
+            self.cycle_count,
+            prompt.raw(),
+            PROMPT_SUPERVISOR_FEEDBACK_FILE_NAME,
+        )
+
+        feedback = create_chat_completion(prompt)
+
+        self.log_cycle_handler.log_cycle(
+            self.config.ai_name,
+            self.created_at,
+            self.cycle_count,
+            feedback,
+            SUPERVISOR_FEEDBACK_FILE_NAME,
+        )
+        return feedback

autogpt/agent/agent_manager.py

@@ -1,145 +0,0 @@
-"""Agent manager for managing GPT agents"""
-from __future__ import annotations
-
-from typing import List, Union
-
-from autogpt.config.config import Config, Singleton
-from autogpt.llm_utils import create_chat_completion
-from autogpt.types.openai import Message
-
-
-class AgentManager(metaclass=Singleton):
-    """Agent manager for managing GPT agents"""
-
-    def __init__(self):
-        self.next_key = 0
-        self.agents = {}  # key, (task, full_message_history, model)
-        self.cfg = Config()
-
-    # Create new GPT agent
-    # TODO: Centralise use of create_chat_completion() to globally enforce token limit
-
-    def create_agent(self, task: str, prompt: str, model: str) -> tuple[int, str]:
-        """Create a new agent and return its key
-
-        Args:
-            task: The task to perform
-            prompt: The prompt to use
-            model: The model to use
-
-        Returns:
-            The key of the new agent
-        """
-        messages: List[Message] = [
-            {"role": "user", "content": prompt},
-        ]
-        for plugin in self.cfg.plugins:
-            if not plugin.can_handle_pre_instruction():
-                continue
-            if plugin_messages := plugin.pre_instruction(messages):
-                messages.extend(iter(plugin_messages))
-        # Start GPT instance
-        agent_reply = create_chat_completion(
-            model=model,
-            messages=messages,
-        )
-
-        messages.append({"role": "assistant", "content": agent_reply})
-
-        plugins_reply = ""
-        for i, plugin in enumerate(self.cfg.plugins):
-            if not plugin.can_handle_on_instruction():
-                continue
-            if plugin_result := plugin.on_instruction(messages):
-                sep = "\n" if i else ""
-                plugins_reply = f"{plugins_reply}{sep}{plugin_result}"
-
-        if plugins_reply and plugins_reply != "":
-            messages.append({"role": "assistant", "content": plugins_reply})
-        key = self.next_key
-        # This is done instead of len(agents) to make keys unique even if agents
-        # are deleted
-        self.next_key += 1
-
-        self.agents[key] = (task, messages, model)
-
-        for plugin in self.cfg.plugins:
-            if not plugin.can_handle_post_instruction():
-                continue
-            agent_reply = plugin.post_instruction(agent_reply)
-
-        return key, agent_reply
-
-    def message_agent(self, key: str | int, message: str) -> str:
-        """Send a message to an agent and return its response
-
-        Args:
-            key: The key of the agent to message
-            message: The message to send to the agent
-
-        Returns:
-            The agent's response
-        """
-        task, messages, model = self.agents[int(key)]
-
-        # Add user message to message history before sending to agent
-        messages.append({"role": "user", "content": message})
-
-        for plugin in self.cfg.plugins:
-            if not plugin.can_handle_pre_instruction():
-                continue
-            if plugin_messages := plugin.pre_instruction(messages):
-                for plugin_message in plugin_messages:
-                    messages.append(plugin_message)
-
-        # Start GPT instance
-        agent_reply = create_chat_completion(
-            model=model,
-            messages=messages,
-        )
-
-        messages.append({"role": "assistant", "content": agent_reply})
-
-        plugins_reply = agent_reply
-        for i, plugin in enumerate(self.cfg.plugins):
-            if not plugin.can_handle_on_instruction():
-                continue
-            if plugin_result := plugin.on_instruction(messages):
-                sep = "\n" if i else ""
-                plugins_reply = f"{plugins_reply}{sep}{plugin_result}"
-        # Update full message history
-        if plugins_reply and plugins_reply != "":
-            messages.append({"role": "assistant", "content": plugins_reply})
-
-        for plugin in self.cfg.plugins:
-            if not plugin.can_handle_post_instruction():
-                continue
-            agent_reply = plugin.post_instruction(agent_reply)
-
-        return agent_reply
-
-    def list_agents(self) -> list[tuple[str | int, str]]:
-        """Return a list of all agents
-
-        Returns:
-            A list of tuples of the form (key, task)
-        """
-
-        # Return a list of agent keys and their tasks
-        return [(key, task) for key, (task, _, _) in self.agents.items()]
-
-    def delete_agent(self, key: str | int) -> bool:
-        """Delete an agent from the agent manager
-
-        Args:
-            key: The key of the agent to delete
-
-        Returns:
-            True if successful, False otherwise
-        """
-
-        try:
-            del self.agents[int(key)]
-            return True
-        except KeyError:
-            return False

autogpt/api_manager.py

@@ -1,158 +0,0 @@
-from typing import List
-
-import openai
-
-from autogpt.config import Config
-from autogpt.logs import logger
-from autogpt.modelsinfo import COSTS
-
-cfg = Config()
-openai.api_key = cfg.openai_api_key
-print_total_cost = cfg.debug_mode
-
-
-class ApiManager:
-    def __init__(self, debug=False):
-        self.total_prompt_tokens = 0
-        self.total_completion_tokens = 0
-        self.total_cost = 0
-        self.total_budget = 0
-        self.debug = debug
-
-    def reset(self):
-        self.total_prompt_tokens = 0
-        self.total_completion_tokens = 0
-        self.total_cost = 0
-        self.total_budget = 0.0
-
-    def create_chat_completion(
-        self,
-        messages: list,  # type: ignore
-        model: str = None,
-        temperature: float = cfg.temperature,
-        max_tokens: int = None,
-        deployment_id=None,
-    ) -> str:
-        """
-        Create a chat completion and update the cost.
-        Args:
-        messages (list): The list of messages to send to the API.
-        model (str): The model to use for the API call.
-        temperature (float): The temperature to use for the API call.
-        max_tokens (int): The maximum number of tokens for the API call.
-        Returns:
-        str: The AI's response.
-        """
-        if deployment_id is not None:
-            response = openai.ChatCompletion.create(
-                deployment_id=deployment_id,
-                model=model,
-                messages=messages,
-                temperature=temperature,
-                max_tokens=max_tokens,
-            )
-        else:
-            response = openai.ChatCompletion.create(
-                model=model,
-                messages=messages,
-                temperature=temperature,
-                max_tokens=max_tokens,
-            )
-        if self.debug:
-            logger.debug(f"Response: {response}")
-        prompt_tokens = response.usage.prompt_tokens
-        completion_tokens = response.usage.completion_tokens
-        self.update_cost(prompt_tokens, completion_tokens, model)
-        return response
-
-    def embedding_create(
-        self,
-        text_list: List[str],
-        model: str = "text-embedding-ada-002",
-    ) -> List[float]:
-        """
-        Create an embedding for the given input text using the specified model.
-
-        Args:
-        text_list (List[str]): Input text for which the embedding is to be created.
-        model (str, optional): The model to use for generating the embedding.
-
-        Returns:
-        List[float]: The generated embedding as a list of float values.
-        """
-        if cfg.use_azure:
-            response = openai.Embedding.create(
-                input=text_list,
-                engine=cfg.get_azure_deployment_id_for_model(model),
-            )
-        else:
-            response = openai.Embedding.create(input=text_list, model=model)
-
-        self.update_cost(response.usage.prompt_tokens, 0, model)
-        return response["data"][0]["embedding"]
-
-    def update_cost(self, prompt_tokens, completion_tokens, model):
-        """
-        Update the total cost, prompt tokens, and completion tokens.
-
-        Args:
-        prompt_tokens (int): The number of tokens used in the prompt.
-        completion_tokens (int): The number of tokens used in the completion.
-        model (str): The model used for the API call.
-        """
-        self.total_prompt_tokens += prompt_tokens
-        self.total_completion_tokens += completion_tokens
-        self.total_cost += (
-            prompt_tokens * COSTS[model]["prompt"]
-            + completion_tokens * COSTS[model]["completion"]
-        ) / 1000
-        if print_total_cost:
-            print(f"Total running cost: ${self.total_cost:.3f}")
-
-    def set_total_budget(self, total_budget):
-        """
-        Sets the total user-defined budget for API calls.
-
-        Args:
-        prompt_tokens (int): The number of tokens used in the prompt.
-        """
-        self.total_budget = total_budget
-
-    def get_total_prompt_tokens(self):
-        """
-        Get the total number of prompt tokens.
-
-        Returns:
-        int: The total number of prompt tokens.
-        """
-        return self.total_prompt_tokens
-
-    def get_total_completion_tokens(self):
-        """
-        Get the total number of completion tokens.
-
-        Returns:
-        int: The total number of completion tokens.
-        """
-        return self.total_completion_tokens
-
-    def get_total_cost(self):
-        """
-        Get the total cost of API calls.
-
-        Returns:
-        float: The total cost of API calls.
-        """
-        return self.total_cost
-
-    def get_total_budget(self):
-        """
-        Get the total user-defined budget for API calls.
-
-        Returns:
-        float: The total budget for API calls.
-        """
-        return self.total_budget
-
-
-api_manager = ApiManager(cfg.debug_mode)

autogpt/app.py

@@ -1,253 +0,0 @@
-""" Command and Control """
-import json
-from typing import Dict, List, NoReturn, Union
-
-from autogpt.agent.agent_manager import AgentManager
-from autogpt.commands.command import CommandRegistry, command
-from autogpt.commands.web_requests import scrape_links, scrape_text
-from autogpt.config import Config
-from autogpt.memory import get_memory
-from autogpt.processing.text import summarize_text
-from autogpt.prompts.generator import PromptGenerator
-from autogpt.speech import say_text
-
-CFG = Config()
-AGENT_MANAGER = AgentManager()
-
-
-def is_valid_int(value: str) -> bool:
-    """Check if the value is a valid integer
-
-    Args:
-        value (str): The value to check
-
-    Returns:
-        bool: True if the value is a valid integer, False otherwise
-    """
-    try:
-        int(value)
-        return True
-    except ValueError:
-        return False
-
-
-def get_command(response_json: Dict):
-    """Parse the response and return the command name and arguments
-
-    Args:
-        response_json (json): The response from the AI
-
-    Returns:
-        tuple: The command name and arguments
-
-    Raises:
-        json.decoder.JSONDecodeError: If the response is not valid JSON
-
-        Exception: If any other error occurs
-    """
-    try:
-        if "command" not in response_json:
-            return "Error:", "Missing 'command' object in JSON"
-
-        if not isinstance(response_json, dict):
-            return "Error:", f"'response_json' object is not dictionary {response_json}"
-
-        command = response_json["command"]
-        if not isinstance(command, dict):
-            return "Error:", "'command' object is not a dictionary"
-
-        if "name" not in command:
-            return "Error:", "Missing 'name' field in 'command' object"
-
-        command_name = command["name"]
-
-        # Use an empty dictionary if 'args' field is not present in 'command' object
-        arguments = command.get("args", {})
-
-        return command_name, arguments
-    except json.decoder.JSONDecodeError:
-        return "Error:", "Invalid JSON"
-    # All other errors, return "Error: + error message"
-    except Exception as e:
-        return "Error:", str(e)
-
-
-def map_command_synonyms(command_name: str):
-    """Takes the original command name given by the AI, and checks if the
-    string matches a list of common/known hallucinations
-    """
-    synonyms = [
-        ("write_file", "write_to_file"),
-        ("create_file", "write_to_file"),
-        ("search", "google"),
-    ]
-    for seen_command, actual_command_name in synonyms:
-        if command_name == seen_command:
-            return actual_command_name
-    return command_name
-
-
-def execute_command(
-    command_registry: CommandRegistry,
-    command_name: str,
-    arguments,
-    prompt: PromptGenerator,
-):
-    """Execute the command and return the result
-
-    Args:
-        command_name (str): The name of the command to execute
-        arguments (dict): The arguments for the command
-
-    Returns:
-        str: The result of the command
-    """
-    try:
-        cmd = command_registry.commands.get(command_name)
-
-        # If the command is found, call it with the provided arguments
-        if cmd:
-            return cmd(**arguments)
-
-        # TODO: Remove commands below after they are moved to the command registry.
-        command_name = map_command_synonyms(command_name.lower())
-
-        if command_name == "memory_add":
-            return get_memory(CFG).add(arguments["string"])
-
-        # TODO: Change these to take in a file rather than pasted code, if
-        # non-file is given, return instructions "Input should be a python
-        # filepath, write your code to file and try again
-        elif command_name == "do_nothing":
-            return "No action performed."
-        elif command_name == "task_complete":
-            shutdown()
-        else:
-            for command in prompt.commands:
-                if (
-                    command_name == command["label"].lower()
-                    or command_name == command["name"].lower()
-                ):
-                    return command["function"](**arguments)
-            return (
-                f"Unknown command '{command_name}'. Please refer to the 'COMMANDS'"
-                " list for available commands and only respond in the specified JSON"
-                " format."
-            )
-    except Exception as e:
-        return f"Error: {str(e)}"
-
-
-@command(
-    "get_text_summary", "Get text summary", '"url": "<url>", "question": "<question>"'
-)
-def get_text_summary(url: str, question: str) -> str:
-    """Return the results of a Google search
-
-    Args:
-        url (str): The url to scrape
-        question (str): The question to summarize the text for
-
-    Returns:
-        str: The summary of the text
-    """
-    text = scrape_text(url)
-    summary = summarize_text(url, text, question)
-    return f""" "Result" : {summary}"""
-
-
-@command("get_hyperlinks", "Get text summary", '"url": "<url>"')
-def get_hyperlinks(url: str) -> Union[str, List[str]]:
-    """Return the results of a Google search
-
-    Args:
-        url (str): The url to scrape
-
-    Returns:
-        str or list: The hyperlinks on the page
-    """
-    return scrape_links(url)
-
-
-def shutdown() -> NoReturn:
-    """Shut down the program"""
-    print("Shutting down...")
-    quit()
-
-
-@command(
-    "start_agent",
-    "Start GPT Agent",
-    '"name": "<name>", "task": "<short_task_desc>", "prompt": "<prompt>"',
-)
-def start_agent(name: str, task: str, prompt: str, model=CFG.fast_llm_model) -> str:
-    """Start an agent with a given name, task, and prompt
-
-    Args:
-        name (str): The name of the agent
-        task (str): The task of the agent
-        prompt (str): The prompt for the agent
-        model (str): The model to use for the agent
-
-    Returns:
-        str: The response of the agent
-    """
-    # Remove underscores from name
-    voice_name = name.replace("_", " ")
-
-    first_message = f"""You are {name}.  Respond with: "Acknowledged"."""
-    agent_intro = f"{voice_name} here, Reporting for duty!"
-
-    # Create agent
-    if CFG.speak_mode:
-        say_text(agent_intro, 1)
-    key, ack = AGENT_MANAGER.create_agent(task, first_message, model)
-
-    if CFG.speak_mode:
-        say_text(f"Hello {voice_name}. Your task is as follows. {task}.")
-
-    # Assign task (prompt), get response
-    agent_response = AGENT_MANAGER.message_agent(key, prompt)
-
-    return f"Agent {name} created with key {key}. First response: {agent_response}"
-
-
-@command("message_agent", "Message GPT Agent", '"key": "<key>", "message": "<message>"')
-def message_agent(key: str, message: str) -> str:
-    """Message an agent with a given key and message"""
-    # Check if the key is a valid integer
-    if is_valid_int(key):
-        agent_response = AGENT_MANAGER.message_agent(int(key), message)
-    else:
-        return "Invalid key, must be an integer."
-
-    # Speak response
-    if CFG.speak_mode:
-        say_text(agent_response, 1)
-    return agent_response
-
-
-@command("list_agents", "List GPT Agents", "")
-def list_agents() -> str:
-    """List all agents
-
-    Returns:
-        str: A list of all agents
-    """
-    return "List of agents:\n" + "\n".join(
-        [str(x[0]) + ": " + x[1] for x in AGENT_MANAGER.list_agents()]
-    )
-
-
-@command("delete_agent", "Delete GPT Agent", '"key": "<key>"')
-def delete_agent(key: str) -> str:
-    """Delete an agent with a given key
-
-    Args:
-        key (str): The key of the agent to delete
-
-    Returns:
-        str: A message indicating whether the agent was deleted or not
-    """
-    result = AGENT_MANAGER.delete_agent(key)
-    return f"Agent {key} deleted." if result else f"Agent {key} does not exist."

autogpt/auto-gpt.json

@@ -1 +0,0 @@
-{}

autogpt/auto_gpt_workspace/127.0.0.1/auto-gpt.json

@@ -1 +0,0 @@
-{}

autogpt/auto_gpt_workspace/127.0.0.1/file_logger.txt

@@ -1 +0,0 @@
-File Operation Logger 

autogpt/chat.py

@@ -1,218 +0,0 @@
-import time
-
-from openai.error import RateLimitError
-
-from autogpt import token_counter
-from autogpt.api_manager import api_manager
-from autogpt.config import Config
-from autogpt.llm_utils import create_chat_completion
-from autogpt.logs import logger
-from autogpt.types.openai import Message
-
-cfg = Config()
-
-
-def create_chat_message(role, content) -> Message:
-    """
-    Create a chat message with the given role and content.
-
-    Args:
-    role (str): The role of the message sender, e.g., "system", "user", or "assistant".
-    content (str): The content of the message.
-
-    Returns:
-    dict: A dictionary containing the role and content of the message.
-    """
-    return {"role": role, "content": content}
-
-
-def generate_context(prompt, relevant_memory, full_message_history, model):
-    current_context = [
-        create_chat_message("system", prompt),
-        create_chat_message(
-            "system", f"The current time and date is {time.strftime('%c')}"
-        ),
-        create_chat_message(
-            "system",
-            f"This reminds you of these events from your past:\n{relevant_memory}\n\n",
-        ),
-    ]
-
-    # Add messages from the full message history until we reach the token limit
-    next_message_to_add_index = len(full_message_history) - 1
-    insertion_index = len(current_context)
-    # Count the currently used tokens
-    current_tokens_used = token_counter.count_message_tokens(current_context, model)
-    return (
-        next_message_to_add_index,
-        current_tokens_used,
-        insertion_index,
-        current_context,
-    )
-
-
-# TODO: Change debug from hardcode to argument
-def chat_with_ai(
-    agent, prompt, user_input, full_message_history, permanent_memory, token_limit
-):
-    """Interact with the OpenAI API, sending the prompt, user input, message history,
-    and permanent memory."""
-    while True:
-        try:
-            """
-            Interact with the OpenAI API, sending the prompt, user input,
-                message history, and permanent memory.
-
-            Args:
-                prompt (str): The prompt explaining the rules to the AI.
-                user_input (str): The input from the user.
-                full_message_history (list): The list of all messages sent between the
-                    user and the AI.
-                permanent_memory (Obj): The memory object containing the permanent
-                  memory.
-                token_limit (int): The maximum number of tokens allowed in the API call.
-
-            Returns:
-            str: The AI's response.
-            """
-            model = cfg.fast_llm_model  # TODO: Change model from hardcode to argument
-            # Reserve 1000 tokens for the response
-
-            logger.debug(f"Token limit: {token_limit}")
-            send_token_limit = token_limit - 1000
-
-            relevant_memory = (
-                ""
-                if len(full_message_history) == 0
-                else permanent_memory.get_relevant(str(full_message_history[-9:]), 10)
-            )
-
-            logger.debug(f"Memory Stats: {permanent_memory.get_stats()}")
-
-            (
-                next_message_to_add_index,
-                current_tokens_used,
-                insertion_index,
-                current_context,
-            ) = generate_context(prompt, relevant_memory, full_message_history, model)
-
-            while current_tokens_used > 2500:
-                # remove memories until we are under 2500 tokens
-                relevant_memory = relevant_memory[:-1]
-                (
-                    next_message_to_add_index,
-                    current_tokens_used,
-                    insertion_index,
-                    current_context,
-                ) = generate_context(
-                    prompt, relevant_memory, full_message_history, model
-                )
-
-            current_tokens_used += token_counter.count_message_tokens(
-                [create_chat_message("user", user_input)], model
-            )  # Account for user input (appended later)
-
-            while next_message_to_add_index >= 0:
-                # print (f"CURRENT TOKENS USED: {current_tokens_used}")
-                message_to_add = full_message_history[next_message_to_add_index]
-
-                tokens_to_add = token_counter.count_message_tokens(
-                    [message_to_add], model
-                )
-                if current_tokens_used + tokens_to_add > send_token_limit:
-                    break
-
-                # Add the most recent message to the start of the current context,
-                #  after the two system prompts.
-                current_context.insert(
-                    insertion_index, full_message_history[next_message_to_add_index]
-                )
-
-                # Count the currently used tokens
-                current_tokens_used += tokens_to_add
-
-                # Move to the next most recent message in the full message history
-                next_message_to_add_index -= 1
-
-            # inform the AI about its remaining budget (if it has one)
-            if api_manager.get_total_budget() > 0.0:
-                remaining_budget = (
-                    api_manager.get_total_budget() - api_manager.get_total_cost()
-                )
-                if remaining_budget < 0:
-                    remaining_budget = 0
-                system_message = (
-                    f"Your remaining API budget is ${remaining_budget:.3f}"
-                    + (
-                        " BUDGET EXCEEDED! SHUT DOWN!\n\n"
-                        if remaining_budget == 0
-                        else " Budget very nearly exceeded! Shut down gracefully!\n\n"
-                        if remaining_budget < 0.005
-                        else " Budget nearly exceeded. Finish up.\n\n"
-                        if remaining_budget < 0.01
-                        else "\n\n"
-                    )
-                )
-                logger.debug(system_message)
-                current_context.append(create_chat_message("system", system_message))
-
-            # Append user input, the length of this is accounted for above
-            current_context.extend([create_chat_message("user", user_input)])
-
-            plugin_count = len(cfg.plugins)
-            for i, plugin in enumerate(cfg.plugins):
-                if not plugin.can_handle_on_planning():
-                    continue
-                plugin_response = plugin.on_planning(
-                    agent.prompt_generator, current_context
-                )
-                if not plugin_response or plugin_response == "":
-                    continue
-                tokens_to_add = token_counter.count_message_tokens(
-                    [create_chat_message("system", plugin_response)], model
-                )
-                if current_tokens_used + tokens_to_add > send_token_limit:
-                    if cfg.debug_mode:
-                        print("Plugin response too long, skipping:", plugin_response)
-                        print("Plugins remaining at stop:", plugin_count - i)
-                    break
-                current_context.append(create_chat_message("system", plugin_response))
-
-            # Calculate remaining tokens
-            tokens_remaining = token_limit - current_tokens_used
-            # assert tokens_remaining >= 0, "Tokens remaining is negative.
-            # This should never happen, please submit a bug report at
-            #  https://www.github.com/Torantulino/Auto-GPT"
-
-            # Debug print the current context
-            logger.debug(f"Token limit: {token_limit}")
-            logger.debug(f"Send Token Count: {current_tokens_used}")
-            logger.debug(f"Tokens remaining for response: {tokens_remaining}")
-            logger.debug("------------ CONTEXT SENT TO AI ---------------")
-            for message in current_context:
-                # Skip printing the prompt
-                if message["role"] == "system" and message["content"] == prompt:
-                    continue
-                logger.debug(f"{message['role'].capitalize()}: {message['content']}")
-                logger.debug("")
-            logger.debug("----------- END OF CONTEXT ----------------")
-
-            # TODO: use a model defined elsewhere, so that model can contain
-            # temperature and other settings we care about
-            assistant_reply = create_chat_completion(
-                model=model,
-                messages=current_context,
-                max_tokens=tokens_remaining,
-            )
-
-            # Update full message history
-            full_message_history.append(create_chat_message("user", user_input))
-            full_message_history.append(
-                create_chat_message("assistant", assistant_reply)
-            )
-
-            return assistant_reply
-        except RateLimitError:
-            # TODO: When we switch to langchain, this is built in
-            print("Error: ", "API Rate Limit Reached. Waiting 10 seconds...")
-            time.sleep(10)

autogpt/cli.py

@@ -1,230 +0,0 @@
-"""Main script for the autogpt package."""
-# Put imports inside function to avoid importing everything when starting the CLI
-import logging
-import os.path
-import sys
-from pathlib import Path
-
-import gradio
-from colorama import Fore
-from autogpt.agent.agent import Agent
-from autogpt.commands.command import CommandRegistry
-from autogpt.config import Config, check_openai_api_key
-from autogpt.configurator import create_config
-from autogpt.logs import logger
-from autogpt.memory import get_memory
-from autogpt.plugins import scan_plugins
-from autogpt.prompts.prompt import construct_main_ai_config
-from autogpt.utils import get_current_git_branch, get_latest_bulletin
-from autogpt.workspace import Workspace
-import func_box
-from toolbox import update_ui
-from toolbox import ChatBotWithCookies
-def handle_config(kwargs_settings):
-    kwargs_settings = {
-                'continuous': False,   # Enable Continuous Mode
-                'continuous_limit': None,  # Defines the number of times to run in continuous mode
-                'ai_settings': None,   # Specifies which ai_settings.yaml file to use, will also automatically skip the re-prompt.
-                'skip_reprompt': False,  # Skips the re-prompting messages at the beginning of the scrip
-                'speak': False,  # Enable speak Mode
-                'debug': False,  # Enable Debug Mode
-                'gpt3only': False,  # Enable GPT3.5 Only Mode
-                'gpt4only': False,  # Enable GPT4 Only Mode
-                'memory_type': None,  # Defines which Memory backend to use
-                'browser_name': None,  # Specifies which web-browser to use when using selenium to scrape the web.
-                'allow_downloads': False,  # Dangerous: Allows Auto-GPT to download files natively.
-                'skip_news': True,   # Specifies whether to suppress the output of latest news on startup.
-                'workspace_directory': None  # TODO: this is a hidden option for now, necessary for integration testing. We should make this public once we're ready to roll out agent specific workspaces.
-                }
-    """
-    Welcome to AutoGPT an experimental open-source application showcasing the capabilities of the GPT-4 pushing the boundaries of AI.
-    Start an Auto-GPT assistant.
-    """
-    if kwargs_settings['workspace_directory']:
-          kwargs_settings['ai_settings'] = os.path.join(kwargs_settings['workspace_directory'], 'ai_settings.yaml')
-    # if ctx.invoked_subcommand is None:
-    cfg = Config()
-    # TODO: fill in llm values here
-    check_openai_api_key()
-    create_config(
-        kwargs_settings['continuous'],
-        kwargs_settings['continuous_limit'],
-        kwargs_settings['ai_settings'],
-        kwargs_settings['skip_reprompt'],
-        kwargs_settings['speak'],
-        kwargs_settings['debug'],
-        kwargs_settings['gpt3only'],
-        kwargs_settings['gpt4only'],
-        kwargs_settings['memory_type'],
-        kwargs_settings['browser_name'],
-        kwargs_settings['allow_downloads'],
-        kwargs_settings['skip_news'],
-    )
-    return cfg
-
-
-def handle_news():
-    motd = get_latest_bulletin()
-    if motd:
-        logger.typewriter_log("NEWS: ", Fore.GREEN, motd)
-    git_branch = get_current_git_branch()
-    if git_branch and git_branch != "stable":
-        logger.typewriter_log(
-            "WARNING: ",
-            Fore.RED,
-            f"You are running on `{git_branch}` branch "
-            "- this is not a supported branch.",
-        )
-    if sys.version_info < (3, 10):
-        logger.typewriter_log(
-            "WARNING: ",
-            Fore.RED,
-            "You are running on an older version of Python. "
-            "Some people have observed problems with certain "
-            "parts of Auto-GPT with this version. "
-            "Please consider upgrading to Python 3.10 or higher.",
-        )
-
-
-def handle_registry():
-    # Create a CommandRegistry instance and scan default folder
-    command_registry = CommandRegistry()
-    command_registry.import_commands("autogpt.commands.analyze_code")
-    command_registry.import_commands("autogpt.commands.audio_text")
-    command_registry.import_commands("autogpt.commands.execute_code")
-    command_registry.import_commands("autogpt.commands.file_operations")
-    command_registry.import_commands("autogpt.commands.git_operations")
-    command_registry.import_commands("autogpt.commands.google_search")
-    command_registry.import_commands("autogpt.commands.image_gen")
-    command_registry.import_commands("autogpt.commands.improve_code")
-    command_registry.import_commands("autogpt.commands.twitter")
-    command_registry.import_commands("autogpt.commands.web_selenium")
-    command_registry.import_commands("autogpt.commands.write_tests")
-    command_registry.import_commands("autogpt.app")
-    return command_registry
-
-
-def handle_workspace(user):
-    # TODO: have this directory live outside the repository (e.g. in a user's
-    #   home directory) and have it come in as a command line argument or part of
-    #   the env file.
-    if user is None:
-        workspace_directory = Path(__file__).parent / "auto_gpt_workspace"
-    else:
-        workspace_directory = Path(__file__).parent / "auto_gpt_workspace" / user
-    # TODO: pass in the ai_settings file and the env file and have them cloned into
-    #   the workspace directory so we can bind them to the agent.
-    workspace_directory = Workspace.make_workspace(workspace_directory)
-    # HACK: doing this here to collect some globals that depend on the workspace.
-    file_logger_path = workspace_directory / "file_logger.txt"
-    if not file_logger_path.exists():
-        with file_logger_path.open(mode="w", encoding="utf-8") as f:
-            f.write("File Operation Logger ")
-
-    return workspace_directory, file_logger_path
-
-
-def update_obj(plugin_kwargs, _is=True):
-    obj = plugin_kwargs['obj']
-    start = plugin_kwargs['start']
-    next_ = plugin_kwargs['next']
-    text = plugin_kwargs['txt']
-    if _is:
-        start.update(visible=True)
-        next_.update(visible=False)
-        text.update(visible=False)
-    else:
-        start.update(visible=False)
-        next_.update(visible=True)
-        text.update(visible=True)
-    return obj, start, next_, text
-
-
-def agent_main(name, role, goals, budget,
-               cookies, chatbot, history, obj,
-                ipaddr: gradio.Request):
-    # ai setup
-    input_kwargs = {
-        'name': name,
-        'role': role,
-        'goals': goals,
-        'budget': budget
-    }
-    # chat setup
-    logger.output_content = []
-    chatbot_with_cookie = ChatBotWithCookies(cookies)
-    chatbot_with_cookie.write_list(chatbot)
-    history = []
-    cfg = handle_config(None)
-    logger.set_level(logging.DEBUG if cfg.debug_mode else logging.INFO)
-    workspace_directory = ipaddr.client.host
-    if not cfg.skip_news:
-        handle_news()
-    cfg.set_plugins(scan_plugins(cfg, cfg.debug_mode))
-    command_registry = handle_registry()
-    ai_config = construct_main_ai_config(input_kwargs)
-    def update_stream_ui(user='', gpt='', msg='Done',
-                         _start=obj['start'].update(), _next=obj['next'].update(), _text=obj['text'].update()):
-        if user or gpt:
-            temp = [user, gpt]
-            if not chatbot_with_cookie:
-                chatbot_with_cookie.append(temp)
-            else:
-                chatbot_with_cookie[-1] = [chatbot_with_cookie[-1][i] + temp[i] for i in range(len(chatbot_with_cookie[-1]))]
-        yield chatbot_with_cookie.get_cookies(), chatbot_with_cookie, history, msg, obj, _start, _next, _text
-    if not ai_config:
-        msg = '### ROLE 不能为空'
-        # yield chatbot_with_cookie.get_cookies(), chatbot_with_cookie, history, msg, obj, None, None, None
-        yield from update_stream_ui(msg=msg)
-        return
-    ai_config.command_registry = command_registry
-    next_action_count = 0
-    # Make a constant:
-    triggering_prompt = (
-        "Determine which next command to use, and respond using the"
-        " format specified above:"
-    )
-    workspace_directory, file_logger_path = handle_workspace(workspace_directory)
-    cfg.workspace_path = str(workspace_directory)
-    cfg.file_logger_path = str(file_logger_path)
-    # Initialize memory and make sure it is empty.
-    # this is particularly important for indexing and referencing pinecone memory
-    memory = get_memory(cfg, init=True)
-    logger.typewriter_log(
-        "Using memory of type:", Fore.GREEN, f"{memory.__class__.__name__}"
-    )
-    logger.typewriter_log("Using Browser:", Fore.GREEN, cfg.selenium_web_browser)
-    system_prompt = ai_config.construct_full_prompt()
-    if cfg.debug_mode:
-        logger.typewriter_log("Prompt:", Fore.GREEN, system_prompt)
-    agent = Agent(
-        ai_name=input_kwargs['name'],
-        memory=memory,
-        full_message_history=history,
-        next_action_count=next_action_count,
-        command_registry=command_registry,
-        config=ai_config,
-        system_prompt=system_prompt,
-        triggering_prompt=triggering_prompt,
-        workspace_directory=workspace_directory,
-    )
-    obj['obj'] = agent
-    _start = obj['start'].update(visible=False)
-    _next = obj['next'].update(visible=True)
-    _text = obj['text'].update(visible=True, interactive=True)
-    # chat, his = func_box.chat_history(logger.output_content)
-    # yield from update_stream_ui(user='Auto-GPT Start!', gpt=chat, _start=_start, _next=_next, _text=_text)
-    agent.start_interaction_loop()
-    chat, his = func_box.chat_history(logger.output_content)
-    yield from update_stream_ui(user='Auto-GPT Start!', gpt=chat, _start=_start, _next=_next, _text=_text)
-
-
-
-
-def agent_start(cookie, chatbot, history, msg, obj):
-    yield from obj['obj'].start_interaction_loop(cookie, chatbot, history, msg, obj)
-
-
-if __name__ == "__main__":
-    pass
-

autogpt/cli_private.py

@@ -1,213 +0,0 @@
-"""Main script for the autogpt package."""
-import click
-
-
-@click.group(invoke_without_command=True)
-@click.option("-c", "--continuous", is_flag=True, help="Enable Continuous Mode")
-@click.option(
-    "--skip-reprompt",
-    "-y",
-    is_flag=True,
-    help="Skips the re-prompting messages at the beginning of the script",
-)
-@click.option(
-    "--ai-settings",
-    "-C",
-    help="Specifies which ai_settings.yaml file to use, will also automatically skip the re-prompt.",
-)
-@click.option(
-    "-l",
-    "--continuous-limit",
-    type=int,
-    help="Defines the number of times to run in continuous mode",
-)
-@click.option("--speak", is_flag=True, help="Enable Speak Mode")
-@click.option("--debug", is_flag=True, help="Enable Debug Mode")
-@click.option("--gpt3only", is_flag=True, help="Enable GPT3.5 Only Mode")
-@click.option("--gpt4only", is_flag=True, help="Enable GPT4 Only Mode")
-@click.option(
-    "--use-memory",
-    "-m",
-    "memory_type",
-    type=str,
-    help="Defines which Memory backend to use",
-)
-@click.option(
-    "-b",
-    "--browser-name",
-    help="Specifies which web-browser to use when using selenium to scrape the web.",
-)
-@click.option(
-    "--allow-downloads",
-    is_flag=True,
-    help="Dangerous: Allows Auto-GPT to download files natively.",
-)
-@click.option(
-    "--skip-news",
-    is_flag=True,
-    help="Specifies whether to suppress the output of latest news on startup.",
-)
-@click.option(
-    # TODO: this is a hidden option for now, necessary for integration testing.
-    #   We should make this public once we're ready to roll out agent specific workspaces.
-    "--workspace-directory",
-    "-w",
-    type=click.Path(),
-    hidden=True,
-)
-@click.pass_context
-def main(
-    ctx: click.Context,
-    continuous: bool,
-    continuous_limit: int,
-    ai_settings: str,
-    skip_reprompt: bool,
-    speak: bool,
-    debug: bool,
-    gpt3only: bool,
-    gpt4only: bool,
-    memory_type: str,
-    browser_name: str,
-    allow_downloads: bool,
-    skip_news: bool,
-    workspace_directory: str,
-) -> None:
-    """
-    Welcome to AutoGPT an experimental open-source application showcasing the capabilities of the GPT-4 pushing the boundaries of AI.
-
-    Start an Auto-GPT assistant.
-    """
-    # Put imports inside function to avoid importing everything when starting the CLI
-    import logging
-    import sys
-    from pathlib import Path
-
-    from colorama import Fore
-
-    from autogpt.agent.agent import Agent
-    from autogpt.commands.command import CommandRegistry
-    from autogpt.config import Config, check_openai_api_key
-    from autogpt.configurator import create_config
-    from autogpt.logs import logger
-    from autogpt.memory import get_memory
-    from autogpt.plugins import scan_plugins
-    from autogpt.prompts.prompt import construct_main_ai_config
-    from autogpt.utils import get_current_git_branch, get_latest_bulletin
-    from autogpt.workspace import Workspace
-
-    if ctx.invoked_subcommand is None:
-        cfg = Config()
-        # TODO: fill in llm values here
-        check_openai_api_key()
-        create_config(
-            continuous,
-            continuous_limit,
-            ai_settings,
-            skip_reprompt,
-            speak,
-            debug,
-            gpt3only,
-            gpt4only,
-            memory_type,
-            browser_name,
-            allow_downloads,
-            skip_news,
-        )
-        logger.set_level(logging.DEBUG if cfg.debug_mode else logging.INFO)
-        if not cfg.skip_news:
-            motd = get_latest_bulletin()
-            if motd:
-                logger.typewriter_log("NEWS: ", Fore.GREEN, motd)
-            git_branch = get_current_git_branch()
-            if git_branch and git_branch != "stable":
-                logger.typewriter_log(
-                    "WARNING: ",
-                    Fore.RED,
-                    f"You are running on `{git_branch}` branch "
-                    "- this is not a supported branch.",
-                )
-            if sys.version_info < (3, 10):
-                logger.typewriter_log(
-                    "WARNING: ",
-                    Fore.RED,
-                    "You are running on an older version of Python. "
-                    "Some people have observed problems with certain "
-                    "parts of Auto-GPT with this version. "
-                    "Please consider upgrading to Python 3.10 or higher.",
-                )
-
-        cfg.set_plugins(scan_plugins(cfg, cfg.debug_mode))
-        # Create a CommandRegistry instance and scan default folder
-        command_registry = CommandRegistry()
-        command_registry.import_commands("autogpt.commands.analyze_code")
-        command_registry.import_commands("autogpt.commands.audio_text")
-        command_registry.import_commands("autogpt.commands.execute_code")
-        command_registry.import_commands("autogpt.commands.file_operations")
-        command_registry.import_commands("autogpt.commands.git_operations")
-        command_registry.import_commands("autogpt.commands.google_search")
-        command_registry.import_commands("autogpt.commands.image_gen")
-        command_registry.import_commands("autogpt.commands.improve_code")
-        command_registry.import_commands("autogpt.commands.twitter")
-        command_registry.import_commands("autogpt.commands.web_selenium")
-        command_registry.import_commands("autogpt.commands.write_tests")
-        command_registry.import_commands("autogpt.app")
-
-        ai_name = ""
-        ai_config = construct_main_ai_config()
-        ai_config.command_registry = command_registry
-        # print(prompt)
-        # Initialize variables
-        full_message_history = []
-        next_action_count = 0
-        # Make a constant:
-        triggering_prompt = (
-            "Determine which next command to use, and respond using the"
-            " format specified above:"
-        )
-        # Initialize memory and make sure it is empty.
-        # this is particularly important for indexing and referencing pinecone memory
-        memory = get_memory(cfg, init=True)
-        logger.typewriter_log(
-            "Using memory of type:", Fore.GREEN, f"{memory.__class__.__name__}"
-        )
-        logger.typewriter_log("Using Browser:", Fore.GREEN, cfg.selenium_web_browser)
-        system_prompt = ai_config.construct_full_prompt()
-        if cfg.debug_mode:
-            logger.typewriter_log("Prompt:", Fore.GREEN, system_prompt)
-
-        # TODO: have this directory live outside the repository (e.g. in a user's
-        #   home directory) and have it come in as a command line argument or part of
-        #   the env file.
-        if workspace_directory is None:
-            workspace_directory = Path(__file__).parent / "auto_gpt_workspace"
-        else:
-            workspace_directory = Path(workspace_directory)
-        # TODO: pass in the ai_settings file and the env file and have them cloned into
-        #   the workspace directory so we can bind them to the agent.
-        workspace_directory = Workspace.make_workspace(workspace_directory)
-        cfg.workspace_path = str(workspace_directory)
-
-        # HACK: doing this here to collect some globals that depend on the workspace.
-        file_logger_path = workspace_directory / "file_logger.txt"
-        if not file_logger_path.exists():
-            with file_logger_path.open(mode="w", encoding="utf-8") as f:
-                f.write("File Operation Logger ")
-
-        cfg.file_logger_path = str(file_logger_path)
-
-        agent = Agent(
-            ai_name=ai_name,
-            memory=memory,
-            full_message_history=full_message_history,
-            next_action_count=next_action_count,
-            command_registry=command_registry,
-            config=ai_config,
-            system_prompt=system_prompt,
-            triggering_prompt=triggering_prompt,
-            workspace_directory=workspace_directory,
-        )
-        agent.start_interaction_loop()
-
-
-if __name__ == "__main__":
-    main()

autogpt/commands/analyze_code.py

@@ -1,31 +0,0 @@
-"""Code evaluation module."""
-from __future__ import annotations
-
-from autogpt.commands.command import command
-from autogpt.llm_utils import call_ai_function
-
-
-@command(
-    "analyze_code",
-    "Analyze Code",
-    '"code": "<full_code_string>"',
-)
-def analyze_code(code: str) -> list[str]:
-    """
-    A function that takes in a string and returns a response from create chat
-      completion api call.
-
-    Parameters:
-        code (str): Code to be evaluated.
-    Returns:
-        A result string from create chat completion. A list of suggestions to
-            improve the code.
-    """
-
-    function_string = "def analyze_code(code: str) -> list[str]:"
-    args = [code]
-    description_string = (
-        "Analyzes the given code and returns a list of suggestions for improvements."
-    )
-
-    return call_ai_function(function_string, args, description_string)

autogpt/commands/audio_text.py

@@ -1,61 +0,0 @@
-"""Commands for converting audio to text."""
-import json
-
-import requests
-
-from autogpt.commands.command import command
-from autogpt.config import Config
-
-CFG = Config()
-
-
-@command(
-    "read_audio_from_file",
-    "Convert Audio to text",
-    '"filename": "<filename>"',
-    CFG.huggingface_audio_to_text_model,
-    "Configure huggingface_audio_to_text_model.",
-)
-def read_audio_from_file(filename: str) -> str:
-    """
-    Convert audio to text.
-
-    Args:
-        filename (str): The path to the audio file
-
-    Returns:
-        str: The text from the audio
-    """
-    with open(filename, "rb") as audio_file:
-        audio = audio_file.read()
-    return read_audio(audio)
-
-
-def read_audio(audio: bytes) -> str:
-    """
-    Convert audio to text.
-
-    Args:
-        audio (bytes): The audio to convert
-
-    Returns:
-        str: The text from the audio
-    """
-    model = CFG.huggingface_audio_to_text_model
-    api_url = f"https://api-inference.huggingface.co/models/{model}"
-    api_token = CFG.huggingface_api_token
-    headers = {"Authorization": f"Bearer {api_token}"}
-
-    if api_token is None:
-        raise ValueError(
-            "You need to set your Hugging Face API token in the config file."
-        )
-
-    response = requests.post(
-        api_url,
-        headers=headers,
-        data=audio,
-    )
-
-    text = json.loads(response.content.decode("utf-8"))["text"]
-    return f"The audio says: {text}"

autogpt/commands/command.py

@@ -1,156 +0,0 @@
-import functools
-import importlib
-import inspect
-from typing import Any, Callable, Optional
-
-# Unique identifier for auto-gpt commands
-AUTO_GPT_COMMAND_IDENTIFIER = "auto_gpt_command"
-
-
-class Command:
-    """A class representing a command.
-
-    Attributes:
-        name (str): The name of the command.
-        description (str): A brief description of what the command does.
-        signature (str): The signature of the function that the command executes. Defaults to None.
-    """
-
-    def __init__(
-        self,
-        name: str,
-        description: str,
-        method: Callable[..., Any],
-        signature: str = "",
-        enabled: bool = True,
-        disabled_reason: Optional[str] = None,
-    ):
-        self.name = name
-        self.description = description
-        self.method = method
-        self.signature = signature if signature else str(inspect.signature(self.method))
-        self.enabled = enabled
-        self.disabled_reason = disabled_reason
-
-    def __call__(self, *args, **kwargs) -> Any:
-        if not self.enabled:
-            return f"Command '{self.name}' is disabled: {self.disabled_reason}"
-        return self.method(*args, **kwargs)
-
-    def __str__(self) -> str:
-        return f"{self.name}: {self.description}, args: {self.signature}"
-
-
-class CommandRegistry:
-    """
-    The CommandRegistry class is a manager for a collection of Command objects.
-    It allows the registration, modification, and retrieval of Command objects,
-    as well as the scanning and loading of command plugins from a specified
-    directory.
-    """
-
-    def __init__(self):
-        self.commands = {}
-
-    def _import_module(self, module_name: str) -> Any:
-        return importlib.import_module(module_name)
-
-    def _reload_module(self, module: Any) -> Any:
-        return importlib.reload(module)
-
-    def register(self, cmd: Command) -> None:
-        self.commands[cmd.name] = cmd
-
-    def unregister(self, command_name: str):
-        if command_name in self.commands:
-            del self.commands[command_name]
-        else:
-            raise KeyError(f"Command '{command_name}' not found in registry.")
-
-    def reload_commands(self) -> None:
-        """Reloads all loaded command plugins."""
-        for cmd_name in self.commands:
-            cmd = self.commands[cmd_name]
-            module = self._import_module(cmd.__module__)
-            reloaded_module = self._reload_module(module)
-            if hasattr(reloaded_module, "register"):
-                reloaded_module.register(self)
-
-    def get_command(self, name: str) -> Callable[..., Any]:
-        return self.commands[name]
-
-    def call(self, command_name: str, **kwargs) -> Any:
-        if command_name not in self.commands:
-            raise KeyError(f"Command '{command_name}' not found in registry.")
-        command = self.commands[command_name]
-        return command(**kwargs)
-
-    def command_prompt(self) -> str:
-        """
-        Returns a string representation of all registered `Command` objects for use in a prompt
-        """
-        commands_list = [
-            f"{idx + 1}. {str(cmd)}" for idx, cmd in enumerate(self.commands.values())
-        ]
-        return "\n".join(commands_list)
-
-    def import_commands(self, module_name: str) -> None:
-        """
-        Imports the specified Python module containing command plugins.
-
-        This method imports the associated module and registers any functions or
-        classes that are decorated with the `AUTO_GPT_COMMAND_IDENTIFIER` attribute
-        as `Command` objects. The registered `Command` objects are then added to the
-        `commands` dictionary of the `CommandRegistry` object.
-
-        Args:
-            module_name (str): The name of the module to import for command plugins.
-        """
-
-        module = importlib.import_module(module_name)
-
-        for attr_name in dir(module):
-            attr = getattr(module, attr_name)
-            # Register decorated functions
-            if hasattr(attr, AUTO_GPT_COMMAND_IDENTIFIER) and getattr(
-                attr, AUTO_GPT_COMMAND_IDENTIFIER
-            ):
-                self.register(attr.command)
-            # Register command classes
-            elif (
-                inspect.isclass(attr) and issubclass(attr, Command) and attr != Command
-            ):
-                cmd_instance = attr()
-                self.register(cmd_instance)
-
-
-def command(
-    name: str,
-    description: str,
-    signature: str = "",
-    enabled: bool = True,
-    disabled_reason: Optional[str] = None,
-) -> Callable[..., Any]:
-    """The command decorator is used to create Command objects from ordinary functions."""
-
-    def decorator(func: Callable[..., Any]) -> Command:
-        cmd = Command(
-            name=name,
-            description=description,
-            method=func,
-            signature=signature,
-            enabled=enabled,
-            disabled_reason=disabled_reason,
-        )
-
-        @functools.wraps(func)
-        def wrapper(*args, **kwargs) -> Any:
-            return func(*args, **kwargs)
-
-        wrapper.command = cmd
-
-        setattr(wrapper, AUTO_GPT_COMMAND_IDENTIFIER, True)
-
-        return wrapper
-
-    return decorator

autogpt/commands/execute_code.py

@@ -1,182 +0,0 @@
-"""Execute code in a Docker container"""
-import os
-import subprocess
-
-import docker
-from docker.errors import ImageNotFound
-
-from autogpt.commands.command import command
-from autogpt.config import Config
-
-CFG = Config()
-
-
-@command("execute_python_file", "Execute Python File", '"filename": "<filename>"')
-def execute_python_file(filename: str) -> str:
-    """Execute a Python file in a Docker container and return the output
-
-    Args:
-        filename (str): The name of the file to execute
-
-    Returns:
-        str: The output of the file
-    """
-    print(f"Executing file '{filename}'")
-
-    if not filename.endswith(".py"):
-        return "Error: Invalid file type. Only .py files are allowed."
-
-    if not os.path.isfile(filename):
-        return f"Error: File '{filename}' does not exist."
-
-    if we_are_running_in_a_docker_container():
-        result = subprocess.run(
-            f"python {filename}", capture_output=True, encoding="utf8", shell=True
-        )
-        if result.returncode == 0:
-            return result.stdout
-        else:
-            return f"Error: {result.stderr}"
-
-    try:
-        client = docker.from_env()
-
-        # You can replace this with the desired Python image/version
-        # You can find available Python images on Docker Hub:
-        # https://hub.docker.com/_/python
-        image_name = "python:3-alpine"
-        try:
-            client.images.get(image_name)
-            print(f"Image '{image_name}' found locally")
-        except ImageNotFound:
-            print(f"Image '{image_name}' not found locally, pulling from Docker Hub")
-            # Use the low-level API to stream the pull response
-            low_level_client = docker.APIClient()
-            for line in low_level_client.pull(image_name, stream=True, decode=True):
-                # Print the status and progress, if available
-                status = line.get("status")
-                progress = line.get("progress")
-                if status and progress:
-                    print(f"{status}: {progress}")
-                elif status:
-                    print(status)
-
-        container = client.containers.run(
-            image_name,
-            f"python {filename}",
-            volumes={
-                CFG.workspace_path: {
-                    "bind": "/workspace",
-                    "mode": "ro",
-                }
-            },
-            working_dir="/workspace",
-            stderr=True,
-            stdout=True,
-            detach=True,
-        )
-
-        container.wait()
-        logs = container.logs().decode("utf-8")
-        container.remove()
-
-        # print(f"Execution complete. Output: {output}")
-        # print(f"Logs: {logs}")
-
-        return logs
-
-    except docker.errors.DockerException as e:
-        print(
-            "Could not run the script in a container. If you haven't already, please install Docker https://docs.docker.com/get-docker/"
-        )
-        return f"Error: {str(e)}"
-
-    except Exception as e:
-        return f"Error: {str(e)}"
-
-
-@command(
-    "execute_shell",
-    "Execute Shell Command, non-interactive commands only",
-    '"command_line": "<command_line>"',
-    CFG.execute_local_commands,
-    "You are not allowed to run local shell commands. To execute"
-    " shell commands, EXECUTE_LOCAL_COMMANDS must be set to 'True' "
-    "in your config. Do not attempt to bypass the restriction.",
-)
-def execute_shell(command_line: str) -> str:
-    """Execute a shell command and return the output
-
-    Args:
-        command_line (str): The command line to execute
-
-    Returns:
-        str: The output of the command
-    """
-
-    if not CFG.execute_local_commands:
-        return (
-            "You are not allowed to run local shell commands. To execute"
-            " shell commands, EXECUTE_LOCAL_COMMANDS must be set to 'True' "
-            "in your config. Do not attempt to bypass the restriction."
-        )
-    current_dir = os.getcwd()
-    # Change dir into workspace if necessary
-    if CFG.workspace_path not in current_dir:
-        os.chdir(CFG.workspace_path)
-
-    print(f"Executing command '{command_line}' in working directory '{os.getcwd()}'")
-
-    result = subprocess.run(command_line, capture_output=True, shell=True)
-    output = f"STDOUT:\n{result.stdout}\nSTDERR:\n{result.stderr}"
-
-    # Change back to whatever the prior working dir was
-
-    os.chdir(current_dir)
-
-
-@command(
-    "execute_shell_popen",
-    "Execute Shell Command, non-interactive commands only",
-    '"command_line": "<command_line>"',
-    CFG.execute_local_commands,
-    "You are not allowed to run local shell commands. To execute"
-    " shell commands, EXECUTE_LOCAL_COMMANDS must be set to 'True' "
-    "in your config. Do not attempt to bypass the restriction.",
-)
-def execute_shell_popen(command_line) -> str:
-    """Execute a shell command with Popen and returns an english description
-    of the event and the process id
-
-    Args:
-        command_line (str): The command line to execute
-
-    Returns:
-        str: Description of the fact that the process started and its id
-    """
-    current_dir = os.getcwd()
-    # Change dir into workspace if necessary
-    if CFG.workspace_path not in current_dir:
-        os.chdir(CFG.workspace_path)
-
-    print(f"Executing command '{command_line}' in working directory '{os.getcwd()}'")
-
-    do_not_show_output = subprocess.DEVNULL
-    process = subprocess.Popen(
-        command_line, shell=True, stdout=do_not_show_output, stderr=do_not_show_output
-    )
-
-    # Change back to whatever the prior working dir was
-
-    os.chdir(current_dir)
-
-    return f"Subprocess started with PID:'{str(process.pid)}'"
-
-
-def we_are_running_in_a_docker_container() -> bool:
-    """Check if we are running in a Docker container
-
-    Returns:
-        bool: True if we are running in a Docker container, False otherwise
-    """
-    return os.path.exists("/.dockerenv")

autogpt/commands/file_operations.py

@@ -1,268 +0,0 @@
-"""File operations for AutoGPT"""
-from __future__ import annotations
-
-import os
-import os.path
-from typing import Generator
-
-import requests
-from colorama import Back, Fore
-from requests.adapters import HTTPAdapter, Retry
-
-from autogpt.commands.command import command
-from autogpt.config import Config
-from autogpt.spinner import Spinner
-from autogpt.utils import readable_file_size
-
-CFG = Config()
-
-
-def check_duplicate_operation(operation: str, filename: str) -> bool:
-    """Check if the operation has already been performed on the given file
-
-    Args:
-        operation (str): The operation to check for
-        filename (str): The name of the file to check for
-
-    Returns:
-        bool: True if the operation has already been performed on the file
-    """
-    log_content = read_file(CFG.file_logger_path)
-    log_entry = f"{operation}: {filename}\n"
-    return log_entry in log_content
-
-
-def log_operation(operation: str, filename: str) -> None:
-    """Log the file operation to the file_logger.txt
-
-    Args:
-        operation (str): The operation to log
-        filename (str): The name of the file the operation was performed on
-    """
-    log_entry = f"{operation}: {filename}\n"
-    append_to_file(CFG.file_logger_path, log_entry, should_log=False)
-
-
-def split_file(
-    content: str, max_length: int = 4000, overlap: int = 0
-) -> Generator[str, None, None]:
-    """
-    Split text into chunks of a specified maximum length with a specified overlap
-    between chunks.
-
-    :param content: The input text to be split into chunks
-    :param max_length: The maximum length of each chunk,
-        default is 4000 (about 1k token)
-    :param overlap: The number of overlapping characters between chunks,
-        default is no overlap
-    :return: A generator yielding chunks of text
-    """
-    start = 0
-    content_length = len(content)
-
-    while start < content_length:
-        end = start + max_length
-        if end + overlap < content_length:
-            chunk = content[start : end + overlap - 1]
-        else:
-            chunk = content[start:content_length]
-
-            # Account for the case where the last chunk is shorter than the overlap, so it has already been consumed
-            if len(chunk) <= overlap:
-                break
-
-        yield chunk
-        start += max_length - overlap
-
-
-@command("read_file", "Read file", '"filename": "<filename>"')
-def read_file(filename: str) -> str:
-    """Read a file and return the contents
-
-    Args:
-        filename (str): The name of the file to read
-
-    Returns:
-        str: The contents of the file
-    """
-    try:
-        with open(filename, "r", encoding="utf-8") as f:
-            content = f.read()
-        return content
-    except Exception as e:
-        return f"Error: {str(e)}"
-
-
-def ingest_file(
-    filename: str, memory, max_length: int = 4000, overlap: int = 200
-) -> None:
-    """
-    Ingest a file by reading its content, splitting it into chunks with a specified
-    maximum length and overlap, and adding the chunks to the memory storage.
-
-    :param filename: The name of the file to ingest
-    :param memory: An object with an add() method to store the chunks in memory
-    :param max_length: The maximum length of each chunk, default is 4000
-    :param overlap: The number of overlapping characters between chunks, default is 200
-    """
-    try:
-        print(f"Working with file {filename}")
-        content = read_file(filename)
-        content_length = len(content)
-        print(f"File length: {content_length} characters")
-
-        chunks = list(split_file(content, max_length=max_length, overlap=overlap))
-
-        num_chunks = len(chunks)
-        for i, chunk in enumerate(chunks):
-            print(f"Ingesting chunk {i + 1} / {num_chunks} into memory")
-            memory_to_add = (
-                f"Filename: {filename}\n" f"Content part#{i + 1}/{num_chunks}: {chunk}"
-            )
-
-            memory.add(memory_to_add)
-
-        print(f"Done ingesting {num_chunks} chunks from {filename}.")
-    except Exception as e:
-        print(f"Error while ingesting file '{filename}': {str(e)}")
-
-
-@command("write_to_file", "Write to file", '"filename": "<filename>", "text": "<text>"')
-def write_to_file(filename: str, text: str) -> str:
-    """Write text to a file
-
-    Args:
-        filename (str): The name of the file to write to
-        text (str): The text to write to the file
-
-    Returns:
-        str: A message indicating success or failure
-    """
-    if check_duplicate_operation("write", filename):
-        return "Error: File has already been updated."
-    try:
-        directory = os.path.dirname(filename)
-        if not os.path.exists(directory):
-            os.makedirs(directory)
-        with open(filename, "w", encoding="utf-8") as f:
-            f.write(text)
-        log_operation("write", filename)
-        return "File written to successfully."
-    except Exception as e:
-        return f"Error: {str(e)}"
-
-
-@command(
-    "append_to_file", "Append to file", '"filename": "<filename>", "text": "<text>"'
-)
-def append_to_file(filename: str, text: str, should_log: bool = True) -> str:
-    """Append text to a file
-
-    Args:
-        filename (str): The name of the file to append to
-        text (str): The text to append to the file
-        should_log (bool): Should log output
-
-    Returns:
-        str: A message indicating success or failure
-    """
-    try:
-        with open(filename, "a") as f:
-            f.write(text)
-
-        if should_log:
-            log_operation("append", filename)
-
-        return "Text appended successfully."
-    except Exception as e:
-        return f"Error: {str(e)}"
-
-
-@command("delete_file", "Delete file", '"filename": "<filename>"')
-def delete_file(filename: str) -> str:
-    """Delete a file
-
-    Args:
-        filename (str): The name of the file to delete
-
-    Returns:
-        str: A message indicating success or failure
-    """
-    if check_duplicate_operation("delete", filename):
-        return "Error: File has already been deleted."
-    try:
-        os.remove(filename)
-        log_operation("delete", filename)
-        return "File deleted successfully."
-    except Exception as e:
-        return f"Error: {str(e)}"
-
-
-@command("search_files", "Search Files", '"directory": "<directory>"')
-def search_files(directory: str) -> list[str]:
-    """Search for files in a directory
-
-    Args:
-        directory (str): The directory to search in
-
-    Returns:
-        list[str]: A list of files found in the directory
-    """
-    found_files = []
-
-    for root, _, files in os.walk(directory):
-        for file in files:
-            if file.startswith("."):
-                continue
-            relative_path = os.path.relpath(
-                os.path.join(root, file), CFG.workspace_path
-            )
-            found_files.append(relative_path)
-
-    return found_files
-
-
-@command(
-    "download_file",
-    "Download File",
-    '"url": "<url>", "filename": "<filename>"',
-    CFG.allow_downloads,
-    "Error: You do not have user authorization to download files locally.",
-)
-def download_file(url, filename):
-    """Downloads a file
-    Args:
-        url (str): URL of the file to download
-        filename (str): Filename to save the file as
-    """
-    try:
-        message = f"{Fore.YELLOW}Downloading file from {Back.MAGENTA}{url}{Back.RESET}{Fore.RESET}"
-        with Spinner(message) as spinner:
-            session = requests.Session()
-            retry = Retry(total=3, backoff_factor=1, status_forcelist=[502, 503, 504])
-            adapter = HTTPAdapter(max_retries=retry)
-            session.mount("http://", adapter)
-            session.mount("https://", adapter)
-
-            total_size = 0
-            downloaded_size = 0
-
-            with session.get(url, allow_redirects=True, stream=True) as r:
-                r.raise_for_status()
-                total_size = int(r.headers.get("Content-Length", 0))
-                downloaded_size = 0
-
-                with open(filename, "wb") as f:
-                    for chunk in r.iter_content(chunk_size=8192):
-                        f.write(chunk)
-                        downloaded_size += len(chunk)
-
-                        # Update the progress message
-                        progress = f"{readable_file_size(downloaded_size)} / {readable_file_size(total_size)}"
-                        spinner.update_message(f"{message} {progress}")
-
-            return f'Successfully downloaded and locally stored file: "{filename}"! (Size: {readable_file_size(total_size)})'
-    except requests.HTTPError as e:
-        return f"Got an HTTP Error whilst trying to download file: {e}"
-    except Exception as e:
-        return "Error: " + str(e)

autogpt/commands/git_operations.py

@@ -1,33 +0,0 @@
-"""Git operations for autogpt"""
-from git.repo import Repo
-
-from autogpt.commands.command import command
-from autogpt.config import Config
-
-CFG = Config()
-
-
-@command(
-    "clone_repository",
-    "Clone Repository",
-    '"repository_url": "<repository_url>", "clone_path": "<clone_path>"',
-    CFG.github_username and CFG.github_api_key,
-    "Configure github_username and github_api_key.",
-)
-def clone_repository(repository_url: str, clone_path: str) -> str:
-    """Clone a GitHub repository locally.
-
-    Args:
-        repository_url (str): The URL of the repository to clone.
-        clone_path (str): The path to clone the repository to.
-
-    Returns:
-        str: The result of the clone operation.
-    """
-    split_url = repository_url.split("//")
-    auth_repo_url = f"//{CFG.github_username}:{CFG.github_api_key}@".join(split_url)
-    try:
-        Repo.clone_from(auth_repo_url, clone_path)
-        return f"""Cloned {repository_url} to {clone_path}"""
-    except Exception as e:
-        return f"Error: {str(e)}"

autogpt/commands/google_search.py

@@ -1,117 +0,0 @@
-"""Google search command for Autogpt."""
-from __future__ import annotations
-
-import json
-
-from duckduckgo_search import ddg
-
-from autogpt.commands.command import command
-from autogpt.config import Config
-
-CFG = Config()
-
-
-@command("google", "Google Search", '"query": "<query>"', not CFG.google_api_key)
-def google_search(query: str, num_results: int = 8) -> str:
-    """Return the results of a Google search
-
-    Args:
-        query (str): The search query.
-        num_results (int): The number of results to return.
-
-    Returns:
-        str: The results of the search.
-    """
-    search_results = []
-    if not query:
-        return json.dumps(search_results)
-
-    results = ddg(query, max_results=num_results)
-    if not results:
-        return json.dumps(search_results)
-
-    for j in results:
-        search_results.append(j)
-
-    results = json.dumps(search_results, ensure_ascii=False, indent=4)
-    return safe_google_results(results)
-
-
-@command(
-    "google",
-    "Google Search",
-    '"query": "<query>"',
-    bool(CFG.google_api_key),
-    "Configure google_api_key.",
-)
-def google_official_search(query: str, num_results: int = 8) -> str | list[str]:
-    """Return the results of a Google search using the official Google API
-
-    Args:
-        query (str): The search query.
-        num_results (int): The number of results to return.
-
-    Returns:
-        str: The results of the search.
-    """
-
-    from googleapiclient.discovery import build
-    from googleapiclient.errors import HttpError
-
-    try:
-        # Get the Google API key and Custom Search Engine ID from the config file
-        api_key = CFG.google_api_key
-        custom_search_engine_id = CFG.custom_search_engine_id
-
-        # Initialize the Custom Search API service
-        service = build("customsearch", "v1", developerKey=api_key)
-
-        # Send the search query and retrieve the results
-        result = (
-            service.cse()
-            .list(q=query, cx=custom_search_engine_id, num=num_results)
-            .execute()
-        )
-
-        # Extract the search result items from the response
-        search_results = result.get("items", [])
-
-        # Create a list of only the URLs from the search results
-        search_results_links = [item["link"] for item in search_results]
-
-    except HttpError as e:
-        # Handle errors in the API call
-        error_details = json.loads(e.content.decode())
-
-        # Check if the error is related to an invalid or missing API key
-        if error_details.get("error", {}).get(
-            "code"
-        ) == 403 and "invalid API key" in error_details.get("error", {}).get(
-            "message", ""
-        ):
-            return "Error: The provided Google API key is invalid or missing."
-        else:
-            return f"Error: {e}"
-    # google_result can be a list or a string depending on the search results
-
-    # Return the list of search result URLs
-    return safe_google_results(search_results_links)
-
-
-def safe_google_results(results: str | list) -> str:
-    """
-        Return the results of a google search in a safe format.
-
-    Args:
-        results (str | list): The search results.
-
-    Returns:
-        str: The results of the search.
-    """
-    if isinstance(results, list):
-        safe_message = json.dumps(
-            [result.encode("utf-8", "ignore") for result in results]
-        )
-    else:
-        safe_message = results.encode("utf-8", "ignore").decode("utf-8")
-    return safe_message

autogpt/commands/image_gen.py

@@ -1,164 +0,0 @@
-""" Image Generation Module for AutoGPT."""
-import io
-import uuid
-from base64 import b64decode
-
-import openai
-import requests
-from PIL import Image
-
-from autogpt.commands.command import command
-from autogpt.config import Config
-
-CFG = Config()
-
-
-@command("generate_image", "Generate Image", '"prompt": "<prompt>"', CFG.image_provider)
-def generate_image(prompt: str, size: int = 256) -> str:
-    """Generate an image from a prompt.
-
-    Args:
-        prompt (str): The prompt to use
-        size (int, optional): The size of the image. Defaults to 256. (Not supported by HuggingFace)
-
-    Returns:
-        str: The filename of the image
-    """
-    filename = f"{CFG.workspace_path}/{str(uuid.uuid4())}.jpg"
-
-    # DALL-E
-    if CFG.image_provider == "dalle":
-        return generate_image_with_dalle(prompt, filename, size)
-    # HuggingFace
-    elif CFG.image_provider == "huggingface":
-        return generate_image_with_hf(prompt, filename)
-    # SD WebUI
-    elif CFG.image_provider == "sdwebui":
-        return generate_image_with_sd_webui(prompt, filename, size)
-    return "No Image Provider Set"
-
-
-def generate_image_with_hf(prompt: str, filename: str) -> str:
-    """Generate an image with HuggingFace's API.
-
-    Args:
-        prompt (str): The prompt to use
-        filename (str): The filename to save the image to
-
-    Returns:
-        str: The filename of the image
-    """
-    API_URL = (
-        f"https://api-inference.huggingface.co/models/{CFG.huggingface_image_model}"
-    )
-    if CFG.huggingface_api_token is None:
-        raise ValueError(
-            "You need to set your Hugging Face API token in the config file."
-        )
-    headers = {
-        "Authorization": f"Bearer {CFG.huggingface_api_token}",
-        "X-Use-Cache": "false",
-    }
-
-    response = requests.post(
-        API_URL,
-        headers=headers,
-        json={
-            "inputs": prompt,
-        },
-    )
-
-    image = Image.open(io.BytesIO(response.content))
-    print(f"Image Generated for prompt:{prompt}")
-
-    image.save(filename)
-
-    return f"Saved to disk:{filename}"
-
-
-def generate_image_with_dalle(prompt: str, filename: str, size: int) -> str:
-    """Generate an image with DALL-E.
-
-    Args:
-        prompt (str): The prompt to use
-        filename (str): The filename to save the image to
-        size (int): The size of the image
-
-    Returns:
-        str: The filename of the image
-    """
-    openai.api_key = CFG.openai_api_key
-
-    # Check for supported image sizes
-    if size not in [256, 512, 1024]:
-        closest = min([256, 512, 1024], key=lambda x: abs(x - size))
-        print(
-            f"DALL-E only supports image sizes of 256x256, 512x512, or 1024x1024. Setting to {closest}, was {size}."
-        )
-        size = closest
-
-    response = openai.Image.create(
-        prompt=prompt,
-        n=1,
-        size=f"{size}x{size}",
-        response_format="b64_json",
-    )
-
-    print(f"Image Generated for prompt:{prompt}")
-
-    image_data = b64decode(response["data"][0]["b64_json"])
-
-    with open(filename, mode="wb") as png:
-        png.write(image_data)
-
-    return f"Saved to disk:{filename}"
-
-
-def generate_image_with_sd_webui(
-    prompt: str,
-    filename: str,
-    size: int = 512,
-    negative_prompt: str = "",
-    extra: dict = {},
-) -> str:
-    """Generate an image with Stable Diffusion webui.
-    Args:
-        prompt (str): The prompt to use
-        filename (str): The filename to save the image to
-        size (int, optional): The size of the image. Defaults to 256.
-        negative_prompt (str, optional): The negative prompt to use. Defaults to "".
-        extra (dict, optional): Extra parameters to pass to the API. Defaults to {}.
-    Returns:
-        str: The filename of the image
-    """
-    # Create a session and set the basic auth if needed
-    s = requests.Session()
-    if CFG.sd_webui_auth:
-        username, password = CFG.sd_webui_auth.split(":")
-        s.auth = (username, password or "")
-
-    # Generate the images
-    response = requests.post(
-        f"{CFG.sd_webui_url}/sdapi/v1/txt2img",
-        json={
-            "prompt": prompt,
-            "negative_prompt": negative_prompt,
-            "sampler_index": "DDIM",
-            "steps": 20,
-            "cfg_scale": 7.0,
-            "width": size,
-            "height": size,
-            "n_iter": 1,
-            **extra,
-        },
-    )
-
-    print(f"Image Generated for prompt:{prompt}")
-
-    # Save the image to disk
-    response = response.json()
-    b64 = b64decode(response["images"][0].split(",", 1)[0])
-    image = Image.open(io.BytesIO(b64))
-    image.save(filename)
-
-    return f"Saved to disk:{filename}"

autogpt/commands/improve_code.py

@@ -1,35 +0,0 @@
-from __future__ import annotations
-
-import json
-
-from autogpt.commands.command import command
-from autogpt.llm_utils import call_ai_function
-
-
-@command(
-    "improve_code",
-    "Get Improved Code",
-    '"suggestions": "<list_of_suggestions>", "code": "<full_code_string>"',
-)
-def improve_code(suggestions: list[str], code: str) -> str:
-    """
-    A function that takes in code and suggestions and returns a response from create
-      chat completion api call.
-
-    Parameters:
-        suggestions (list): A list of suggestions around what needs to be improved.
-        code (str): Code to be improved.
-    Returns:
-        A result string from create chat completion. Improved code in response.
-    """
-
-    function_string = (
-        "def generate_improved_code(suggestions: list[str], code: str) -> str:"
-    )
-    args = [json.dumps(suggestions), code]
-    description_string = (
-        "Improves the provided code based on the suggestions"
-        " provided, making no other changes."
-    )
-
-    return call_ai_function(function_string, args, description_string)

autogpt/commands/times.py

@@ -1,10 +0,0 @@
-from datetime import datetime
-
-
-def get_datetime() -> str:
-    """Return the current date and time
-
-    Returns:
-        str: The current date and time
-    """
-    return "Current date and time: " + datetime.now().strftime("%Y-%m-%d %H:%M:%S")

autogpt/commands/twitter.py

@@ -1,44 +0,0 @@
-"""A module that contains a command to send a tweet."""
-import os
-
-import tweepy
-from dotenv import load_dotenv
-
-from autogpt.commands.command import command
-
-load_dotenv()
-
-
-@command(
-    "send_tweet",
-    "Send Tweet",
-    '"tweet_text": "<tweet_text>"',
-)
-def send_tweet(tweet_text: str) -> str:
-    """
-      A function that takes in a string and returns a response from create chat
-        completion api call.
-
-    Args:
-      tweet_text (str): Text to be tweeted.
-
-      Returns:
-          A result from sending the tweet.
-    """
-    consumer_key = os.environ.get("TW_CONSUMER_KEY")
-    consumer_secret = os.environ.get("TW_CONSUMER_SECRET")
-    access_token = os.environ.get("TW_ACCESS_TOKEN")
-    access_token_secret = os.environ.get("TW_ACCESS_TOKEN_SECRET")
-    # Authenticate to Twitter
-    auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
-    auth.set_access_token(access_token, access_token_secret)
-
-    # Create API object
-    api = tweepy.API(auth)
-
-    # Send tweet
-    try:
-        api.update_status(tweet_text)
-        return "Tweet sent successfully!"
-    except tweepy.TweepyException as e:
-        return f"Error sending tweet: {e.reason}"

autogpt/commands/web_playwright.py

@@ -1,80 +0,0 @@
-"""Web scraping commands using Playwright"""
-from __future__ import annotations
-
-try:
-    from playwright.sync_api import sync_playwright
-except ImportError:
-    print(
-        "Playwright not installed. Please install it with 'pip install playwright' to use."
-    )
-from bs4 import BeautifulSoup
-
-from autogpt.processing.html import extract_hyperlinks, format_hyperlinks
-
-
-def scrape_text(url: str) -> str:
-    """Scrape text from a webpage
-
-    Args:
-        url (str): The URL to scrape text from
-
-    Returns:
-        str: The scraped text
-    """
-    with sync_playwright() as p:
-        browser = p.chromium.launch()
-        page = browser.new_page()
-
-        try:
-            page.goto(url)
-            html_content = page.content()
-            soup = BeautifulSoup(html_content, "html.parser")
-
-            for script in soup(["script", "style"]):
-                script.extract()
-
-            text = soup.get_text()
-            lines = (line.strip() for line in text.splitlines())
-            chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
-            text = "\n".join(chunk for chunk in chunks if chunk)
-
-        except Exception as e:
-            text = f"Error: {str(e)}"
-
-        finally:
-            browser.close()
-
-    return text
-
-
-def scrape_links(url: str) -> str | list[str]:
-    """Scrape links from a webpage
-
-    Args:
-        url (str): The URL to scrape links from
-
-    Returns:
-        Union[str, List[str]]: The scraped links
-    """
-    with sync_playwright() as p:
-        browser = p.chromium.launch()
-        page = browser.new_page()
-
-        try:
-            page.goto(url)
-            html_content = page.content()
-            soup = BeautifulSoup(html_content, "html.parser")
-
-            for script in soup(["script", "style"]):
-                script.extract()
-
-            hyperlinks = extract_hyperlinks(soup, url)
-            formatted_links = format_hyperlinks(hyperlinks)
-
-        except Exception as e:
-            formatted_links = f"Error: {str(e)}"
-
-        finally:
-            browser.close()
-
-    return formatted_links

autogpt/commands/web_requests.py

@@ -1,188 +0,0 @@
-"""Browse a webpage and summarize it using the LLM model"""
-from __future__ import annotations
-
-from urllib.parse import urljoin, urlparse
-
-import requests
-from bs4 import BeautifulSoup
-from requests import Response
-from requests.compat import urljoin
-
-from autogpt.config import Config
-from autogpt.processing.html import extract_hyperlinks, format_hyperlinks
-
-CFG = Config()
-
-session = requests.Session()
-session.headers.update({"User-Agent": CFG.user_agent})
-
-
-def is_valid_url(url: str) -> bool:
-    """Check if the URL is valid
-
-    Args:
-        url (str): The URL to check
-
-    Returns:
-        bool: True if the URL is valid, False otherwise
-    """
-    try:
-        result = urlparse(url)
-        return all([result.scheme, result.netloc])
-    except ValueError:
-        return False
-
-
-def sanitize_url(url: str) -> str:
-    """Sanitize the URL
-
-    Args:
-        url (str): The URL to sanitize
-
-    Returns:
-        str: The sanitized URL
-    """
-    return urljoin(url, urlparse(url).path)
-
-
-def check_local_file_access(url: str) -> bool:
-    """Check if the URL is a local file
-
-    Args:
-        url (str): The URL to check
-
-    Returns:
-        bool: True if the URL is a local file, False otherwise
-    """
-    local_prefixes = [
-        "file:///",
-        "file://localhost/",
-        "file://localhost",
-        "http://localhost",
-        "http://localhost/",
-        "https://localhost",
-        "https://localhost/",
-        "http://2130706433",
-        "http://2130706433/",
-        "https://2130706433",
-        "https://2130706433/",
-        "http://127.0.0.1/",
-        "http://127.0.0.1",
-        "https://127.0.0.1/",
-        "https://127.0.0.1",
-        "https://0.0.0.0/",
-        "https://0.0.0.0",
-        "http://0.0.0.0/",
-        "http://0.0.0.0",
-        "http://0000",
-        "http://0000/",
-        "https://0000",
-        "https://0000/",
-    ]
-    return any(url.startswith(prefix) for prefix in local_prefixes)
-
-
-def get_response(
-    url: str, timeout: int = 10
-) -> tuple[None, str] | tuple[Response, None]:
-    """Get the response from a URL
-
-    Args:
-        url (str): The URL to get the response from
-        timeout (int): The timeout for the HTTP request
-
-    Returns:
-        tuple[None, str] | tuple[Response, None]: The response and error message
-
-    Raises:
-        ValueError: If the URL is invalid
-        requests.exceptions.RequestException: If the HTTP request fails
-    """
-    try:
-        # Restrict access to local files
-        if check_local_file_access(url):
-            raise ValueError("Access to local files is restricted")
-
-        # Most basic check if the URL is valid:
-        if not url.startswith("http://") and not url.startswith("https://"):
-            raise ValueError("Invalid URL format")
-
-        sanitized_url = sanitize_url(url)
-
-        response = session.get(sanitized_url, timeout=timeout)
-
-        # Check if the response contains an HTTP error
-        if response.status_code >= 400:
-            return None, f"Error: HTTP {str(response.status_code)} error"
-
-        return response, None
-    except ValueError as ve:
-        # Handle invalid URL format
-        return None, f"Error: {str(ve)}"
-
-    except requests.exceptions.RequestException as re:
-        # Handle exceptions related to the HTTP request
-        #  (e.g., connection errors, timeouts, etc.)
-        return None, f"Error: {str(re)}"
-
-
-def scrape_text(url: str) -> str:
-    """Scrape text from a webpage
-
-    Args:
-        url (str): The URL to scrape text from
-
-    Returns:
-        str: The scraped text
-    """
-    response, error_message = get_response(url)
-    if error_message:
-        return error_message
-    if not response:
-        return "Error: Could not get response"
-
-    soup = BeautifulSoup(response.text, "html.parser")
-
-    for script in soup(["script", "style"]):
-        script.extract()
-
-    text = soup.get_text()
-    lines = (line.strip() for line in text.splitlines())
-    chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
-    text = "\n".join(chunk for chunk in chunks if chunk)
-
-    return text
-
-
-def scrape_links(url: str) -> str | list[str]:
-    """Scrape links from a webpage
-
-    Args:
-        url (str): The URL to scrape links from
-
-    Returns:
-       str | list[str]: The scraped links
-    """
-    response, error_message = get_response(url)
-    if error_message:
-        return error_message
-    if not response:
-        return "Error: Could not get response"
-    soup = BeautifulSoup(response.text, "html.parser")
-
-    for script in soup(["script", "style"]):
-        script.extract()
-
-    hyperlinks = extract_hyperlinks(soup, url)
-
-    return format_hyperlinks(hyperlinks)
-
-
-def create_message(chunk, question):
-    """Create a message for the user to summarize a chunk of text"""
-    return {
-        "role": "user",
-        "content": f'"""{chunk}""" Using the above text, answer the following'
-        f' question: "{question}" -- if the question cannot be answered using the'
-        " text, summarize the text.",
-    }

autogpt/commands/web_selenium.py

@@ -1,160 +0,0 @@
-"""Selenium web scraping module."""
-from __future__ import annotations
-
-import logging
-from pathlib import Path
-from sys import platform
-
-from bs4 import BeautifulSoup
-from selenium import webdriver
-from selenium.webdriver.chrome.options import Options as ChromeOptions
-from selenium.webdriver.common.by import By
-from selenium.webdriver.firefox.options import Options as FirefoxOptions
-from selenium.webdriver.remote.webdriver import WebDriver
-from selenium.webdriver.safari.options import Options as SafariOptions
-from selenium.webdriver.support import expected_conditions as EC
-from selenium.webdriver.support.wait import WebDriverWait
-from webdriver_manager.chrome import ChromeDriverManager
-from webdriver_manager.firefox import GeckoDriverManager
-
-import autogpt.processing.text as summary
-from autogpt.commands.command import command
-from autogpt.config import Config
-from autogpt.processing.html import extract_hyperlinks, format_hyperlinks
-
-FILE_DIR = Path(__file__).parent.parent
-CFG = Config()
-
-
-@command(
-    "browse_website",
-    "Browse Website",
-    '"url": "<url>", "question": "<what_you_want_to_find_on_website>"',
-)
-def browse_website(url: str, question: str) -> tuple[str, WebDriver]:
-    """Browse a website and return the answer and links to the user
-
-    Args:
-        url (str): The url of the website to browse
-        question (str): The question asked by the user
-
-    Returns:
-        Tuple[str, WebDriver]: The answer and links to the user and the webdriver
-    """
-    driver, text = scrape_text_with_selenium(url)
-    add_header(driver)
-    summary_text = summary.summarize_text(url, text, question, driver)
-    links = scrape_links_with_selenium(driver, url)
-
-    # Limit links to 5
-    if len(links) > 5:
-        links = links[:5]
-    close_browser(driver)
-    return f"Answer gathered from website: {summary_text} \n \n Links: {links}", driver
-
-
-def scrape_text_with_selenium(url: str) -> tuple[WebDriver, str]:
-    """Scrape text from a website using selenium
-
-    Args:
-        url (str): The url of the website to scrape
-
-    Returns:
-        Tuple[WebDriver, str]: The webdriver and the text scraped from the website
-    """
-    logging.getLogger("selenium").setLevel(logging.CRITICAL)
-
-    options_available = {
-        "chrome": ChromeOptions,
-        "safari": SafariOptions,
-        "firefox": FirefoxOptions,
-    }
-
-    options = options_available[CFG.selenium_web_browser]()
-    options.add_argument(
-        "user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.5615.49 Safari/537.36"
-    )
-
-    if CFG.selenium_web_browser == "firefox":
-        driver = webdriver.Firefox(
-            executable_path=GeckoDriverManager().install(), options=options
-        )
-    elif CFG.selenium_web_browser == "safari":
-        # Requires a bit more setup on the users end
-        # See https://developer.apple.com/documentation/webkit/testing_with_webdriver_in_safari
-        driver = webdriver.Safari(options=options)
-    else:
-        if platform == "linux" or platform == "linux2":
-            options.add_argument("--disable-dev-shm-usage")
-            options.add_argument("--remote-debugging-port=9222")
-
-        options.add_argument("--no-sandbox")
-        if CFG.selenium_headless:
-            options.add_argument("--headless")
-            options.add_argument("--disable-gpu")
-
-        driver = webdriver.Chrome(
-            executable_path=ChromeDriverManager().install(), options=options
-        )
-    driver.get(url)
-
-    WebDriverWait(driver, 10).until(
-        EC.presence_of_element_located((By.TAG_NAME, "body"))
-    )
-
-    # Get the HTML content directly from the browser's DOM
-    page_source = driver.execute_script("return document.body.outerHTML;")
-    soup = BeautifulSoup(page_source, "html.parser")
-
-    for script in soup(["script", "style"]):
-        script.extract()
-
-    text = soup.get_text()
-    lines = (line.strip() for line in text.splitlines())
-    chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
-    text = "\n".join(chunk for chunk in chunks if chunk)
-    return driver, text
-
-
-def scrape_links_with_selenium(driver: WebDriver, url: str) -> list[str]:
-    """Scrape links from a website using selenium
-
-    Args:
-        driver (WebDriver): The webdriver to use to scrape the links
-
-    Returns:
-        List[str]: The links scraped from the website
-    """
-    page_source = driver.page_source
-    soup = BeautifulSoup(page_source, "html.parser")
-
-    for script in soup(["script", "style"]):
-        script.extract()
-
-    hyperlinks = extract_hyperlinks(soup, url)
-
-    return format_hyperlinks(hyperlinks)
-
-
-def close_browser(driver: WebDriver) -> None:
-    """Close the browser
-
-    Args:
-        driver (WebDriver): The webdriver to close
-
-    Returns:
-        None
-    """
-    driver.quit()
-
-
-def add_header(driver: WebDriver) -> None:
-    """Add a header to the website
-
-    Args:
-        driver (WebDriver): The webdriver to use to add the header
-
-    Returns:
-        None
-    """
-    driver.execute_script(open(f"{FILE_DIR}/js/overlay.js", "r").read())

autogpt/commands/write_tests.py

@@ -1,37 +0,0 @@
-"""A module that contains a function to generate test cases for the submitted code."""
-from __future__ import annotations
-
-import json
-
-from autogpt.commands.command import command
-from autogpt.llm_utils import call_ai_function
-
-
-@command(
-    "write_tests",
-    "Write Tests",
-    '"code": "<full_code_string>", "focus": "<list_of_focus_areas>"',
-)
-def write_tests(code: str, focus: list[str]) -> str:
-    """
-    A function that takes in code and focus topics and returns a response from create
-      chat completion api call.
-
-    Parameters:
-        focus (list): A list of suggestions around what needs to be improved.
-        code (str): Code for test cases to be generated against.
-    Returns:
-        A result string from create chat completion. Test cases for the submitted code
-          in response.
-    """
-
-    function_string = (
-        "def create_test_cases(code: str, focus: Optional[str] = None) -> str:"
-    )
-    args = [code, json.dumps(focus)]
-    description_string = (
-        "Generates test cases for the existing code, focusing on"
-        " specific areas if required."
-    )
-
-    return call_ai_function(function_string, args, description_string)

autogpt/config/__init__.py

@@ -1,14 +0,0 @@
-"""
-This module contains the configuration classes for AutoGPT.
-"""
-from autogpt.config.ai_config import AIConfig
-from autogpt.config.config import Config, check_openai_api_key
-from autogpt.config.singleton import AbstractSingleton, Singleton
-
-__all__ = [
-    "check_openai_api_key",
-    "AbstractSingleton",
-    "AIConfig",
-    "Config",
-    "Singleton",
-]

autogpt/config/ai_config.py

@@ -1,163 +0,0 @@
-# sourcery skip: do-not-use-staticmethod
-"""
-A module that contains the AIConfig class object that contains the configuration
-"""
-from __future__ import annotations
-
-import os
-import platform
-from pathlib import Path
-from typing import Optional, Type
-
-import distro
-import yaml
-
-from autogpt.prompts.generator import PromptGenerator
-
-# Soon this will go in a folder where it remembers more stuff about the run(s)
-SAVE_FILE = str(Path(os.getcwd()) / "ai_settings.yaml")
-
-
-class AIConfig:
-    """
-    A class object that contains the configuration information for the AI
-
-    Attributes:
-        ai_name (str): The name of the AI.
-        ai_role (str): The description of the AI's role.
-        ai_goals (list): The list of objectives the AI is supposed to complete.
-        api_budget (float): The maximum dollar value for API calls (0.0 means infinite)
-    """
-
-    def __init__(
-        self,
-        ai_name: str = "",
-        ai_role: str = "",
-        ai_goals: list | None = None,
-        api_budget: float = 0.0,
-    ) -> None:
-        """
-        Initialize a class instance
-
-        Parameters:
-            ai_name (str): The name of the AI.
-            ai_role (str): The description of the AI's role.
-            ai_goals (list): The list of objectives the AI is supposed to complete.
-            api_budget (float): The maximum dollar value for API calls (0.0 means infinite)
-        Returns:
-            None
-        """
-        if ai_goals is None:
-            ai_goals = []
-        self.ai_name = ai_name
-        self.ai_role = ai_role
-        self.ai_goals = ai_goals
-        self.api_budget = api_budget
-        self.prompt_generator = None
-        self.command_registry = None
-
-    @staticmethod
-    def load(config_file: str = SAVE_FILE) -> "AIConfig":
-        """
-        Returns class object with parameters (ai_name, ai_role, ai_goals, api_budget) loaded from
-          yaml file if yaml file exists,
-        else returns class with no parameters.
-
-        Parameters:
-           config_file (int): The path to the config yaml file.
-             DEFAULT: "../ai_settings.yaml"
-
-        Returns:
-            cls (object): An instance of given cls object
-        """
-
-        try:
-            with open(config_file, encoding="utf-8") as file:
-                config_params = yaml.load(file, Loader=yaml.FullLoader)
-        except FileNotFoundError:
-            config_params = {}
-
-        ai_name = config_params.get("ai_name", "")
-        ai_role = config_params.get("ai_role", "")
-        ai_goals = config_params.get("ai_goals", [])
-        api_budget = config_params.get("api_budget", 0.0)
-        # type: Type[AIConfig]
-        return AIConfig(ai_name, ai_role, ai_goals, api_budget)
-
-    def save(self, config_file: str = SAVE_FILE) -> None:
-        """
-        Saves the class parameters to the specified file yaml file path as a yaml file.
-
-        Parameters:
-            config_file(str): The path to the config yaml file.
-              DEFAULT: "../ai_settings.yaml"
-
-        Returns:
-            None
-        """
-
-        config = {
-            "ai_name": self.ai_name,
-            "ai_role": self.ai_role,
-            "ai_goals": self.ai_goals,
-            "api_budget": self.api_budget,
-        }
-        with open(config_file, "w", encoding="utf-8") as file:
-            yaml.dump(config, file, allow_unicode=True)
-
-    def construct_full_prompt(
-        self, prompt_generator: Optional[PromptGenerator] = None
-    ) -> str:
-        """
-        Returns a prompt to the user with the class information in an organized fashion.
-
-        Parameters:
-            None
-
-        Returns:
-            full_prompt (str): A string containing the initial prompt for the user
-              including the ai_name, ai_role, ai_goals, and api_budget.
-        """
-
-        prompt_start = (
-            "Your decisions must always be made independently without"
-            " seeking user assistance. Play to your strengths as an LLM and pursue"
-            " simple strategies with no legal complications."
-            ""
-        )
-
-        from autogpt.config import Config
-        from autogpt.prompts.prompt import build_default_prompt_generator
-
-        cfg = Config()
-        if prompt_generator is None:
-            prompt_generator = build_default_prompt_generator()
-        prompt_generator.goals = self.ai_goals
-        prompt_generator.name = self.ai_name
-        prompt_generator.role = self.ai_role
-        prompt_generator.command_registry = self.command_registry
-        for plugin in cfg.plugins:
-            if not plugin.can_handle_post_prompt():
-                continue
-            prompt_generator = plugin.post_prompt(prompt_generator)
-
-        if cfg.execute_local_commands:
-            # add OS info to prompt
-            os_name = platform.system()
-            os_info = (
-                platform.platform(terse=True)
-                if os_name != "Linux"
-                else distro.name(pretty=True)
-            )
-
-            prompt_start += f"\nThe OS you are running on is: {os_info}"
-
-        # Construct full prompt
-        full_prompt = f"You are {prompt_generator.name}, {prompt_generator.role}\n{prompt_start}\n\nGOALS:\n\n"
-        for i, goal in enumerate(self.ai_goals):
-            full_prompt += f"{i+1}. {goal}\n"
-        if self.api_budget > 0.0:
-            full_prompt += f"\nIt takes money to let you run. Your API budget is ${self.api_budget:.3f}"
-        self.prompt_generator = prompt_generator
-        full_prompt += f"\n\n{prompt_generator.generate_prompt_string()}"
-        return full_prompt

autogpt/config/config.py

@@ -1,282 +0,0 @@
-"""Configuration class to store the state of bools for different scripts access."""
-import os
-from typing import List
-
-import openai
-import yaml
-from auto_gpt_plugin_template import AutoGPTPluginTemplate
-from colorama import Fore
-from dotenv import load_dotenv
-
-from autogpt.config.singleton import Singleton
-
-load_dotenv(verbose=True, override=True)
-
-
-class Config(metaclass=Singleton):
-    """
-    Configuration class to store the state of bools for different scripts access.
-    """
-
-    def __init__(self) -> None:
-        """Initialize the Config class"""
-        self.workspace_path = None
-        self.file_logger_path = None
-
-        self.debug_mode = False
-        self.continuous_mode = False
-        self.continuous_limit = 0
-        self.speak_mode = False
-        self.skip_reprompt = False
-        self.allow_downloads = False
-        self.skip_news = False
-
-        self.ai_settings_file = os.getenv("AI_SETTINGS_FILE", "ai_settings.yaml")
-        self.fast_llm_model = os.getenv("FAST_LLM_MODEL", "gpt-3.5-turbo")
-        self.smart_llm_model = os.getenv("SMART_LLM_MODEL", "gpt-4")
-        self.fast_token_limit = int(os.getenv("FAST_TOKEN_LIMIT", 4000))
-        self.smart_token_limit = int(os.getenv("SMART_TOKEN_LIMIT", 8000))
-        self.browse_chunk_max_length = int(os.getenv("BROWSE_CHUNK_MAX_LENGTH", 3000))
-        self.browse_spacy_language_model = os.getenv(
-            "BROWSE_SPACY_LANGUAGE_MODEL", "en_core_web_sm"
-        )
-
-        self.openai_api_key = os.getenv("OPENAI_API_KEY")
-        self.temperature = float(os.getenv("TEMPERATURE", "0"))
-        self.use_azure = os.getenv("USE_AZURE") == "True"
-        self.execute_local_commands = (
-            os.getenv("EXECUTE_LOCAL_COMMANDS", "False") == "True"
-        )
-        self.restrict_to_workspace = (
-            os.getenv("RESTRICT_TO_WORKSPACE", "True") == "True"
-        )
-
-        if self.use_azure:
-            self.load_azure_config()
-            openai.api_type = self.openai_api_type
-            openai.api_base = self.openai_api_base
-            openai.api_version = self.openai_api_version
-
-        self.elevenlabs_api_key = os.getenv("ELEVENLABS_API_KEY")
-        self.elevenlabs_voice_1_id = os.getenv("ELEVENLABS_VOICE_1_ID")
-        self.elevenlabs_voice_2_id = os.getenv("ELEVENLABS_VOICE_2_ID")
-
-        self.use_mac_os_tts = False
-        self.use_mac_os_tts = os.getenv("USE_MAC_OS_TTS")
-
-        self.use_brian_tts = False
-        self.use_brian_tts = os.getenv("USE_BRIAN_TTS")
-
-        self.github_api_key = os.getenv("GITHUB_API_KEY")
-        self.github_username = os.getenv("GITHUB_USERNAME")
-
-        self.google_api_key = os.getenv("GOOGLE_API_KEY")
-        self.custom_search_engine_id = os.getenv("CUSTOM_SEARCH_ENGINE_ID")
-
-        self.pinecone_api_key = os.getenv("PINECONE_API_KEY")
-        self.pinecone_region = os.getenv("PINECONE_ENV")
-
-        self.weaviate_host = os.getenv("WEAVIATE_HOST")
-        self.weaviate_port = os.getenv("WEAVIATE_PORT")
-        self.weaviate_protocol = os.getenv("WEAVIATE_PROTOCOL", "http")
-        self.weaviate_username = os.getenv("WEAVIATE_USERNAME", None)
-        self.weaviate_password = os.getenv("WEAVIATE_PASSWORD", None)
-        self.weaviate_scopes = os.getenv("WEAVIATE_SCOPES", None)
-        self.weaviate_embedded_path = os.getenv("WEAVIATE_EMBEDDED_PATH")
-        self.weaviate_api_key = os.getenv("WEAVIATE_API_KEY", None)
-        self.use_weaviate_embedded = (
-            os.getenv("USE_WEAVIATE_EMBEDDED", "False") == "True"
-        )
-
-        # milvus or zilliz cloud configuration.
-        self.milvus_addr = os.getenv("MILVUS_ADDR", "localhost:19530")
-        self.milvus_username = os.getenv("MILVUS_USERNAME")
-        self.milvus_password = os.getenv("MILVUS_PASSWORD")
-        self.milvus_collection = os.getenv("MILVUS_COLLECTION", "autogpt")
-        self.milvus_secure = os.getenv("MILVUS_SECURE") == "True"
-
-        self.image_provider = os.getenv("IMAGE_PROVIDER")
-        self.image_size = int(os.getenv("IMAGE_SIZE", 256))
-        self.huggingface_api_token = os.getenv("HUGGINGFACE_API_TOKEN")
-        self.huggingface_image_model = os.getenv(
-            "HUGGINGFACE_IMAGE_MODEL", "CompVis/stable-diffusion-v1-4"
-        )
-        self.huggingface_audio_to_text_model = os.getenv(
-            "HUGGINGFACE_AUDIO_TO_TEXT_MODEL"
-        )
-        self.sd_webui_url = os.getenv("SD_WEBUI_URL", "http://localhost:7860")
-        self.sd_webui_auth = os.getenv("SD_WEBUI_AUTH")
-
-        # Selenium browser settings
-        self.selenium_web_browser = os.getenv("USE_WEB_BROWSER", "chrome")
-        self.selenium_headless = os.getenv("HEADLESS_BROWSER", "True") == "True"
-
-        # User agent header to use when making HTTP requests
-        # Some websites might just completely deny request with an error code if
-        # no user agent was found.
-        self.user_agent = os.getenv(
-            "USER_AGENT",
-            "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_4) AppleWebKit/537.36"
-            " (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36",
-        )
-
-        self.redis_host = os.getenv("REDIS_HOST", "localhost")
-        self.redis_port = os.getenv("REDIS_PORT", "6379")
-        self.redis_password = os.getenv("REDIS_PASSWORD", "")
-        self.wipe_redis_on_start = os.getenv("WIPE_REDIS_ON_START", "True") == "True"
-        self.memory_index = os.getenv("MEMORY_INDEX", "auto-gpt")
-        # Note that indexes must be created on db 0 in redis, this is not configurable.
-
-        self.memory_backend = os.getenv("MEMORY_BACKEND", "local")
-        # Initialize the OpenAI API client
-        openai.api_key = self.openai_api_key
-
-        self.plugins_dir = os.getenv("PLUGINS_DIR", "plugins")
-        self.plugins: List[AutoGPTPluginTemplate] = []
-        self.plugins_openai = []
-
-        plugins_allowlist = os.getenv("ALLOWLISTED_PLUGINS")
-        if plugins_allowlist:
-            self.plugins_allowlist = plugins_allowlist.split(",")
-        else:
-            self.plugins_allowlist = []
-        self.plugins_denylist = []
-
-    def get_azure_deployment_id_for_model(self, model: str) -> str:
-        """
-        Returns the relevant deployment id for the model specified.
-
-        Parameters:
-            model(str): The model to map to the deployment id.
-
-        Returns:
-            The matching deployment id if found, otherwise an empty string.
-        """
-        if model == self.fast_llm_model:
-            return self.azure_model_to_deployment_id_map[
-                "fast_llm_model_deployment_id"
-            ]  # type: ignore
-        elif model == self.smart_llm_model:
-            return self.azure_model_to_deployment_id_map[
-                "smart_llm_model_deployment_id"
-            ]  # type: ignore
-        elif model == "text-embedding-ada-002":
-            return self.azure_model_to_deployment_id_map[
-                "embedding_model_deployment_id"
-            ]  # type: ignore
-        else:
-            return ""
-
-    AZURE_CONFIG_FILE = os.path.join(os.path.dirname(__file__), "../..", "azure.yaml")
-
-    def load_azure_config(self, config_file: str = AZURE_CONFIG_FILE) -> None:
-        """
-        Loads the configuration parameters for Azure hosting from the specified file
-          path as a yaml file.
-
-        Parameters:
-            config_file(str): The path to the config yaml file. DEFAULT: "../azure.yaml"
-
-        Returns:
-            None
-        """
-        with open(config_file) as file:
-            config_params = yaml.load(file, Loader=yaml.FullLoader)
-        self.openai_api_type = config_params.get("azure_api_type") or "azure"
-        self.openai_api_base = config_params.get("azure_api_base") or ""
-        self.openai_api_version = (
-            config_params.get("azure_api_version") or "2023-03-15-preview"
-        )
-        self.azure_model_to_deployment_id_map = config_params.get("azure_model_map", {})
-
-    def set_continuous_mode(self, value: bool) -> None:
-        """Set the continuous mode value."""
-        self.continuous_mode = value
-
-    def set_continuous_limit(self, value: int) -> None:
-        """Set the continuous limit value."""
-        self.continuous_limit = value
-
-    def set_speak_mode(self, value: bool) -> None:
-        """Set the speak mode value."""
-        self.speak_mode = value
-
-    def set_fast_llm_model(self, value: str) -> None:
-        """Set the fast LLM model value."""
-        self.fast_llm_model = value
-
-    def set_smart_llm_model(self, value: str) -> None:
-        """Set the smart LLM model value."""
-        self.smart_llm_model = value
-
-    def set_fast_token_limit(self, value: int) -> None:
-        """Set the fast token limit value."""
-        self.fast_token_limit = value
-
-    def set_smart_token_limit(self, value: int) -> None:
-        """Set the smart token limit value."""
-        self.smart_token_limit = value
-
-    def set_browse_chunk_max_length(self, value: int) -> None:
-        """Set the browse_website command chunk max length value."""
-        self.browse_chunk_max_length = value
-
-    def set_openai_api_key(self, value: str) -> None:
-        """Set the OpenAI API key value."""
-        self.openai_api_key = value
-
-    def set_elevenlabs_api_key(self, value: str) -> None:
-        """Set the ElevenLabs API key value."""
-        self.elevenlabs_api_key = value
-
-    def set_elevenlabs_voice_1_id(self, value: str) -> None:
-        """Set the ElevenLabs Voice 1 ID value."""
-        self.elevenlabs_voice_1_id = value
-
-    def set_elevenlabs_voice_2_id(self, value: str) -> None:
-        """Set the ElevenLabs Voice 2 ID value."""
-        self.elevenlabs_voice_2_id = value
-
-    def set_google_api_key(self, value: str) -> None:
-        """Set the Google API key value."""
-        self.google_api_key = value
-
-    def set_custom_search_engine_id(self, value: str) -> None:
-        """Set the custom search engine id value."""
-        self.custom_search_engine_id = value
-
-    def set_pinecone_api_key(self, value: str) -> None:
-        """Set the Pinecone API key value."""
-        self.pinecone_api_key = value
-
-    def set_pinecone_region(self, value: str) -> None:
-        """Set the Pinecone region value."""
-        self.pinecone_region = value
-
-    def set_debug_mode(self, value: bool) -> None:
-        """Set the debug mode value."""
-        self.debug_mode = value
-
-    def set_plugins(self, value: list) -> None:
-        """Set the plugins value."""
-        self.plugins = value
-
-    def set_temperature(self, value: int) -> None:
-        """Set the temperature value."""
-        self.temperature = value
-
-    def set_memory_backend(self, value: int) -> None:
-        """Set the temperature value."""
-        self.memory_backend = value
-
-
-def check_openai_api_key() -> None:
-    """Check if the OpenAI API key is set in config.py or as an environment variable."""
-    cfg = Config()
-    if not cfg.openai_api_key:
-        print(
-            Fore.RED
-            + "Please set your OpenAI API key in .env or as an environment variable."
-        )
-        print("You can get your key from https://platform.openai.com/account/api-keys")
-        exit(1)

autogpt/config/singleton.py

@@ -1,24 +0,0 @@
-"""The singleton metaclass for ensuring only one instance of a class."""
-import abc
-
-
-class Singleton(abc.ABCMeta, type):
-    """
-    Singleton metaclass for ensuring only one instance of a class.
-    """
-
-    _instances = {}
-
-    def __call__(cls, *args, **kwargs):
-        """Call method for the singleton metaclass."""
-        if cls not in cls._instances:
-            cls._instances[cls] = super(Singleton, cls).__call__(*args, **kwargs)
-        return cls._instances[cls]
-
-
-class AbstractSingleton(abc.ABC, metaclass=Singleton):
-    """
-    Abstract singleton class for ensuring only one instance of a class.
-    """
-
-    pass

autogpt/configurator.py

@@ -1,19 +1,29 @@
 """Configurator module."""
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
 import click
 from colorama import Back, Fore, Style
 
 from autogpt import utils
-from autogpt.config import Config
+from autogpt.llm.utils import check_model
 from autogpt.logs import logger
-from autogpt.memory import get_supported_memory_backends
+from autogpt.memory.vector import get_supported_memory_backends
 
-CFG = Config()
+if TYPE_CHECKING:
+    from autogpt.config import Config
+
+GPT_4_MODEL = "gpt-4"
+GPT_3_MODEL = "gpt-3.5-turbo"
 
 
 def create_config(
+    config: Config,
     continuous: bool,
     continuous_limit: int,
     ai_settings_file: str,
+    prompt_settings_file: str,
     skip_reprompt: bool,
     speak: bool,
     debug: bool,
@@ -30,6 +40,7 @@ def create_config(
         continuous (bool): Whether to run in continuous mode
         continuous_limit (int): The number of times to run in continuous mode
         ai_settings_file (str): The path to the ai_settings.yaml file
+        prompt_settings_file (str): The path to the prompt_settings.yaml file
         skip_reprompt (bool): Whether to skip the re-prompting messages at the beginning of the script
         speak (bool): Whether to enable speak mode
         debug (bool): Whether to enable debug mode
@@ -40,13 +51,13 @@ def create_config(
         allow_downloads (bool): Whether to allow Auto-GPT to download files natively
         skips_news (bool): Whether to suppress the output of latest news on startup
     """
-    CFG.set_debug_mode(False)
+    config.set_debug_mode(False)
-    CFG.set_continuous_mode(False)
+    config.set_continuous_mode(False)
-    CFG.set_speak_mode(False)
+    config.set_speak_mode(False)
 
     if debug:
         logger.typewriter_log("Debug Mode: ", Fore.GREEN, "ENABLED")
-        CFG.set_debug_mode(True)
+        config.set_debug_mode(True)
 
     if continuous:
         logger.typewriter_log("Continuous Mode: ", Fore.RED, "ENABLED")
@@ -57,13 +68,13 @@ def create_config(
             " cause your AI to run forever or carry out actions you would not usually"
             " authorise. Use at your own risk.",
         )
-        CFG.set_continuous_mode(True)
+        config.set_continuous_mode(True)
 
         if continuous_limit:
             logger.typewriter_log(
                 "Continuous Limit: ", Fore.GREEN, f"{continuous_limit}"
             )
-            CFG.set_continuous_limit(continuous_limit)
+            config.set_continuous_limit(continuous_limit)
 
     # Check if continuous limit is used without continuous mode
     if continuous_limit and not continuous:
@@ -71,15 +82,28 @@ def create_config(
 
     if speak:
         logger.typewriter_log("Speak Mode: ", Fore.GREEN, "ENABLED")
-        CFG.set_speak_mode(True)
+        config.set_speak_mode(True)
 
+    # Set the default LLM models
     if gpt3only:
         logger.typewriter_log("GPT3.5 Only Mode: ", Fore.GREEN, "ENABLED")
-        CFG.set_smart_llm_model(CFG.fast_llm_model)
+        # --gpt3only should always use gpt-3.5-turbo, despite user's FAST_LLM_MODEL config
+        config.set_fast_llm_model(GPT_3_MODEL)
+        config.set_smart_llm_model(GPT_3_MODEL)
 
-    if gpt4only:
+    elif (
+        gpt4only
+        and check_model(GPT_4_MODEL, model_type="smart_llm_model") == GPT_4_MODEL
+    ):
         logger.typewriter_log("GPT4 Only Mode: ", Fore.GREEN, "ENABLED")
-        CFG.set_fast_llm_model(CFG.smart_llm_model)
+        # --gpt4only should always use gpt-4, despite user's SMART_LLM_MODEL config
+        config.set_fast_llm_model(GPT_4_MODEL)
+        config.set_smart_llm_model(GPT_4_MODEL)
+    else:
+        config.set_fast_llm_model(check_model(config.fast_llm_model, "fast_llm_model"))
+        config.set_smart_llm_model(
+            check_model(config.smart_llm_model, "smart_llm_model")
+        )
 
     if memory_type:
         supported_memory = get_supported_memory_backends()
@@ -90,13 +114,13 @@ def create_config(
                 Fore.RED,
                 f"{supported_memory}",
             )
-            logger.typewriter_log("Defaulting to: ", Fore.YELLOW, CFG.memory_backend)
+            logger.typewriter_log("Defaulting to: ", Fore.YELLOW, config.memory_backend)
         else:
-            CFG.memory_backend = chosen
+            config.memory_backend = chosen
 
     if skip_reprompt:
         logger.typewriter_log("Skip Re-prompt: ", Fore.GREEN, "ENABLED")
-        CFG.skip_reprompt = True
+        config.skip_reprompt = True
 
     if ai_settings_file:
         file = ai_settings_file
@@ -109,11 +133,24 @@ def create_config(
             exit(1)
 
         logger.typewriter_log("Using AI Settings File:", Fore.GREEN, file)
-        CFG.ai_settings_file = file
+        config.ai_settings_file = file
-        CFG.skip_reprompt = True
+        config.skip_reprompt = True
+
+    if prompt_settings_file:
+        file = prompt_settings_file
+
+        # Validate file
+        (validated, message) = utils.validate_yaml_file(file)
+        if not validated:
+            logger.typewriter_log("FAILED FILE VALIDATION", Fore.RED, message)
+            logger.double_check()
+            exit(1)
+
+        logger.typewriter_log("Using Prompt Settings File:", Fore.GREEN, file)
+        config.prompt_settings_file = file
 
     if browser_name:
-        CFG.selenium_web_browser = browser_name
+        config.selenium_web_browser = browser_name
 
     if allow_downloads:
         logger.typewriter_log("Native Downloading:", Fore.GREEN, "ENABLED")
@@ -128,7 +165,7 @@ def create_config(
             Fore.YELLOW,
             f"{Back.RED + Style.BRIGHT}ALWAYS REMEMBER TO NEVER OPEN FILES YOU AREN'T SURE OF!{Style.RESET_ALL}",
         )
-        CFG.allow_downloads = True
+        config.allow_downloads = True
 
     if skip_news:
-        CFG.skip_news = True
+        config.skip_news = True

autogpt/js/overlay.js

@@ -1,29 +0,0 @@
-const overlay = document.createElement('div');
-Object.assign(overlay.style, {
-    position: 'fixed',
-    zIndex: 999999,
-    top: 0,
-    left: 0,
-    width: '100%',
-    height: '100%',
-    background: 'rgba(0, 0, 0, 0.7)',
-    color: '#fff',
-    fontSize: '24px',
-    fontWeight: 'bold',
-    display: 'flex',
-    justifyContent: 'center',
-    alignItems: 'center',
-});
-const textContent = document.createElement('div');
-Object.assign(textContent.style, {
-    textAlign: 'center',
-});
-textContent.textContent = 'AutoGPT Analyzing Page';
-overlay.appendChild(textContent);
-document.body.append(overlay);
-document.body.style.overflow = 'hidden';
-let dotCount = 0;
-setInterval(() => {
-    textContent.textContent = 'AutoGPT Analyzing Page' + '.'.repeat(dotCount);
-    dotCount = (dotCount + 1) % 4;
-}, 1000);

autogpt/json_utils/json_fix_general.py

@@ -1,124 +0,0 @@
-"""This module contains functions to fix JSON strings using general programmatic approaches, suitable for addressing
-common JSON formatting issues."""
-from __future__ import annotations
-
-import contextlib
-import json
-import re
-from typing import Optional
-
-from autogpt.config import Config
-from autogpt.json_utils.utilities import extract_char_position
-
-CFG = Config()
-
-
-def fix_invalid_escape(json_to_load: str, error_message: str) -> str:
-    """Fix invalid escape sequences in JSON strings.
-
-    Args:
-        json_to_load (str): The JSON string.
-        error_message (str): The error message from the JSONDecodeError
-          exception.
-
-    Returns:
-        str: The JSON string with invalid escape sequences fixed.
-    """
-    while error_message.startswith("Invalid \\escape"):
-        bad_escape_location = extract_char_position(error_message)
-        json_to_load = (
-            json_to_load[:bad_escape_location] + json_to_load[bad_escape_location + 1 :]
-        )
-        try:
-            json.loads(json_to_load)
-            return json_to_load
-        except json.JSONDecodeError as e:
-            if CFG.debug_mode:
-                print("json loads error - fix invalid escape", e)
-            error_message = str(e)
-    return json_to_load
-
-
-def balance_braces(json_string: str) -> Optional[str]:
-    """
-    Balance the braces in a JSON string.
-
-    Args:
-        json_string (str): The JSON string.
-
-    Returns:
-        str: The JSON string with braces balanced.
-    """
-
-    open_braces_count = json_string.count("{")
-    close_braces_count = json_string.count("}")
-
-    while open_braces_count > close_braces_count:
-        json_string += "}"
-        close_braces_count += 1
-
-    while close_braces_count > open_braces_count:
-        json_string = json_string.rstrip("}")
-        close_braces_count -= 1
-
-    with contextlib.suppress(json.JSONDecodeError):
-        json.loads(json_string)
-        return json_string
-
-
-def add_quotes_to_property_names(json_string: str) -> str:
-    """
-    Add quotes to property names in a JSON string.
-
-    Args:
-        json_string (str): The JSON string.
-
-    Returns:
-        str: The JSON string with quotes added to property names.
-    """
-
-    def replace_func(match: re.Match) -> str:
-        return f'"{match[1]}":'
-
-    property_name_pattern = re.compile(r"(\w+):")
-    corrected_json_string = property_name_pattern.sub(replace_func, json_string)
-
-    try:
-        json.loads(corrected_json_string)
-        return corrected_json_string
-    except json.JSONDecodeError as e:
-        raise e
-
-
-def correct_json(json_to_load: str) -> str:
-    """
-    Correct common JSON errors.
-    Args:
-        json_to_load (str): The JSON string.
-    """
-
-    try:
-        if CFG.debug_mode:
-            print("json", json_to_load)
-        json.loads(json_to_load)
-        return json_to_load
-    except json.JSONDecodeError as e:
-        if CFG.debug_mode:
-            print("json loads error", e)
-        error_message = str(e)
-        if error_message.startswith("Invalid \\escape"):
-            json_to_load = fix_invalid_escape(json_to_load, error_message)
-        if error_message.startswith(
-            "Expecting property name enclosed in double quotes"
-        ):
-            json_to_load = add_quotes_to_property_names(json_to_load)
-            try:
-                json.loads(json_to_load)
-                return json_to_load
-            except json.JSONDecodeError as e:
-                if CFG.debug_mode:
-                    print("json loads error - add quotes", e)
-                error_message = str(e)
-        if balanced_str := balance_braces(json_to_load):
-            return balanced_str
-    return json_to_load

autogpt/json_utils/json_fix_llm.py

@@ -1,220 +0,0 @@
-"""This module contains functions to fix JSON strings generated by LLM models, such as ChatGPT, using the assistance
-of the ChatGPT API or LLM models."""
-from __future__ import annotations
-
-import contextlib
-import json
-from typing import Any, Dict
-
-from colorama import Fore
-from regex import regex
-
-from autogpt.config import Config
-from autogpt.json_utils.json_fix_general import correct_json
-from autogpt.llm_utils import call_ai_function
-from autogpt.logs import logger
-from autogpt.speech import say_text
-
-JSON_SCHEMA = """
-{
-    "command": {
-        "name": "command name",
-        "args": {
-            "arg name": "value"
-        }
-    },
-    "thoughts":
-    {
-        "text": "thought",
-        "reasoning": "reasoning",
-        "plan": "- short bulleted\n- list that conveys\n- long-term plan",
-        "criticism": "constructive self-criticism",
-        "speak": "thoughts summary to say to user"
-    }
-}
-"""
-
-CFG = Config()
-
-
-def auto_fix_json(json_string: str, schema: str) -> str:
-    """Fix the given JSON string to make it parseable and fully compliant with
-        the provided schema using GPT-3.
-
-    Args:
-        json_string (str): The JSON string to fix.
-        schema (str): The schema to use to fix the JSON.
-    Returns:
-        str: The fixed JSON string.
-    """
-    # Try to fix the JSON using GPT:
-    function_string = "def fix_json(json_string: str, schema:str=None) -> str:"
-    args = [f"'''{json_string}'''", f"'''{schema}'''"]
-    description_string = (
-        "This function takes a JSON string and ensures that it"
-        " is parseable and fully compliant with the provided schema. If an object"
-        " or field specified in the schema isn't contained within the correct JSON,"
-        " it is omitted. The function also escapes any double quotes within JSON"
-        " string values to ensure that they are valid. If the JSON string contains"
-        " any None or NaN values, they are replaced with null before being parsed."
-    )
-
-    # If it doesn't already start with a "`", add one:
-    if not json_string.startswith("`"):
-        json_string = "```json\n" + json_string + "\n```"
-    result_string = call_ai_function(
-        function_string, args, description_string, model=CFG.fast_llm_model
-    )
-    logger.debug("------------ JSON FIX ATTEMPT ---------------")
-    logger.debug(f"Original JSON: {json_string}")
-    logger.debug("-----------")
-    logger.debug(f"Fixed JSON: {result_string}")
-    logger.debug("----------- END OF FIX ATTEMPT ----------------")
-
-    try:
-        json.loads(result_string)  # just check the validity
-        return result_string
-    except json.JSONDecodeError:  # noqa: E722
-        # Get the call stack:
-        # import traceback
-        # call_stack = traceback.format_exc()
-        # print(f"Failed to fix JSON: '{json_string}' "+call_stack)
-        return "failed"
-
-
-def fix_json_using_multiple_techniques(assistant_reply: str) -> Dict[Any, Any]:
-    """Fix the given JSON string to make it parseable and fully compliant with two techniques.
-
-    Args:
-        json_string (str): The JSON string to fix.
-
-    Returns:
-        str: The fixed JSON string.
-    """
-
-    # Parse and print Assistant response
-    assistant_reply_json = fix_and_parse_json(assistant_reply)
-    if assistant_reply_json == {}:
-        assistant_reply_json = attempt_to_fix_json_by_finding_outermost_brackets(
-            assistant_reply
-        )
-
-    if assistant_reply_json != {}:
-        return assistant_reply_json
-
-    logger.error(
-        "Error: The following AI output couldn't be converted to a JSON:\n",
-        assistant_reply,
-    )
-    if CFG.speak_mode:
-        say_text("I have received an invalid JSON response from the OpenAI API.")
-
-    return {}
-
-
-def fix_and_parse_json(
-    json_to_load: str, try_to_fix_with_gpt: bool = True
-) -> Dict[Any, Any]:
-    """Fix and parse JSON string
-
-    Args:
-        json_to_load (str): The JSON string.
-        try_to_fix_with_gpt (bool, optional): Try to fix the JSON with GPT.
-            Defaults to True.
-
-    Returns:
-        str or dict[Any, Any]: The parsed JSON.
-    """
-
-    with contextlib.suppress(json.JSONDecodeError):
-        json_to_load = json_to_load.replace("\t", "")
-        return json.loads(json_to_load)
-
-    with contextlib.suppress(json.JSONDecodeError):
-        json_to_load = correct_json(json_to_load)
-        return json.loads(json_to_load)
-    # Let's do something manually:
-    # sometimes GPT responds with something BEFORE the braces:
-    # "I'm sorry, I don't understand. Please try again."
-    # {"text": "I'm sorry, I don't understand. Please try again.",
-    #  "confidence": 0.0}
-    # So let's try to find the first brace and then parse the rest
-    #  of the string
-    try:
-        brace_index = json_to_load.index("{")
-        maybe_fixed_json = json_to_load[brace_index:]
-        last_brace_index = maybe_fixed_json.rindex("}")
-        maybe_fixed_json = maybe_fixed_json[: last_brace_index + 1]
-        return json.loads(maybe_fixed_json)
-    except (json.JSONDecodeError, ValueError) as e:
-        return try_ai_fix(try_to_fix_with_gpt, e, json_to_load)
-
-
-def try_ai_fix(
-    try_to_fix_with_gpt: bool, exception: Exception, json_to_load: str
-) -> Dict[Any, Any]:
-    """Try to fix the JSON with the AI
-
-    Args:
-        try_to_fix_with_gpt (bool): Whether to try to fix the JSON with the AI.
-        exception (Exception): The exception that was raised.
-        json_to_load (str): The JSON string to load.
-
-    Raises:
-        exception: If try_to_fix_with_gpt is False.
-
-    Returns:
-        str or dict[Any, Any]: The JSON string or dictionary.
-    """
-    if not try_to_fix_with_gpt:
-        raise exception
-    if CFG.debug_mode:
-        logger.warn(
-            "Warning: Failed to parse AI output, attempting to fix."
-            "\n If you see this warning frequently, it's likely that"
-            " your prompt is confusing the AI. Try changing it up"
-            " slightly."
-        )
-    # Now try to fix this up using the ai_functions
-    ai_fixed_json = auto_fix_json(json_to_load, JSON_SCHEMA)
-
-    if ai_fixed_json != "failed":
-        return json.loads(ai_fixed_json)
-    # This allows the AI to react to the error message,
-    #   which usually results in it correcting its ways.
-    # logger.error("Failed to fix AI output, telling the AI.")
-    return {}
-
-
-def attempt_to_fix_json_by_finding_outermost_brackets(json_string: str):
-    if CFG.speak_mode and CFG.debug_mode:
-        say_text(
-            "I have received an invalid JSON response from the OpenAI API. "
-            "Trying to fix it now."
-        )
-        logger.error("Attempting to fix JSON by finding outermost brackets\n")
-
-    try:
-        json_pattern = regex.compile(r"\{(?:[^{}]|(?R))*\}")
-        json_match = json_pattern.search(json_string)
-
-        if json_match:
-            # Extract the valid JSON object from the string
-            json_string = json_match.group(0)
-            logger.typewriter_log(
-                title="Apparently json was fixed.", title_color=Fore.GREEN
-            )
-            if CFG.speak_mode and CFG.debug_mode:
-                say_text("Apparently json was fixed.")
-        else:
-            return {}
-
-    except (json.JSONDecodeError, ValueError):
-        if CFG.debug_mode:
-            logger.error(f"Error: Invalid JSON: {json_string}\n")
-        if CFG.speak_mode:
-            say_text("Didn't work. I will have to ignore this response then.")
-        logger.error("Error: Invalid JSON, setting it to empty JSON now.\n")
-        json_string = {}
-
-    return fix_and_parse_json(json_string)

autogpt/json_utils/llm_response_format_1.json

@@ -1,31 +0,0 @@
-{
-    "$schema": "http://json-schema.org/draft-07/schema#",
-    "type": "object",
-    "properties": {
-        "thoughts": {
-            "type": "object",
-            "properties": {
-                "text": {"type": "string"},
-                "reasoning": {"type": "string"},
-                "plan": {"type": "string"},
-                "criticism": {"type": "string"},
-                "speak": {"type": "string"}
-            },
-            "required": ["text", "reasoning", "plan", "criticism", "speak"],
-            "additionalProperties": false
-        },
-        "command": {
-            "type": "object",
-            "properties": {
-                "name": {"type": "string"},
-                "args": {
-                    "type": "object"
-                }
-            },
-            "required": ["name", "args"],
-            "additionalProperties": false
-        }
-    },
-    "required": ["thoughts", "command"],
-    "additionalProperties": false
-}

autogpt/json_utils/utilities.py

@@ -1,54 +0,0 @@
-"""Utilities for the json_fixes package."""
-import json
-import re
-
-from jsonschema import Draft7Validator
-
-from autogpt.config import Config
-from autogpt.logs import logger
-
-CFG = Config()
-
-
-def extract_char_position(error_message: str) -> int:
-    """Extract the character position from the JSONDecodeError message.
-
-    Args:
-        error_message (str): The error message from the JSONDecodeError
-          exception.
-
-    Returns:
-        int: The character position.
-    """
-
-    char_pattern = re.compile(r"\(char (\d+)\)")
-    if match := char_pattern.search(error_message):
-        return int(match[1])
-    else:
-        raise ValueError("Character position not found in the error message.")
-
-
-def validate_json(json_object: object, schema_name: object) -> object:
-    """
-    :type schema_name: object
-    :param schema_name:
-    :type json_object: object
-    """
-    with open(f"/Users/kilig/Job/Python-project/academic_gpt/autogpt/json_utils/{schema_name}.json", "r") as f:
-        schema = json.load(f)
-    validator = Draft7Validator(schema)
-
-    if errors := sorted(validator.iter_errors(json_object), key=lambda e: e.path):
-        logger.error("The JSON object is invalid.")
-        if CFG.debug_mode:
-            logger.error(
-                json.dumps(json_object, indent=4)
-            )  # Replace 'json_object' with the variable containing the JSON data
-            logger.error("The following issues were found:")
-
-            for error in errors:
-                logger.error(f"Error: {error.message}")
-    elif CFG.debug_mode:
-        print("The JSON object is valid.")
-
-    return json_object

autogpt/llm/chat.py

@@ -0,0 +1,202 @@
+from __future__ import annotations
+
+import time
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from autogpt.agent.agent import Agent
+
+from autogpt.config import Config
+from autogpt.llm.api_manager import ApiManager
+from autogpt.llm.base import ChatSequence, Message
+from autogpt.llm.utils import count_message_tokens, create_chat_completion
+from autogpt.log_cycle.log_cycle import CURRENT_CONTEXT_FILE_NAME
+from autogpt.logs import logger
+
+
+# TODO: Change debug from hardcode to argument
+def chat_with_ai(
+    config: Config,
+    agent: Agent,
+    system_prompt: str,
+    user_input: str,
+    token_limit: int,
+    model: str | None = None,
+):
+    """
+    Interact with the OpenAI API, sending the prompt, user input,
+        message history, and permanent memory.
+
+    Args:
+        config (Config): The config to use.
+        agent (Agent): The agent to use.
+        system_prompt (str): The prompt explaining the rules to the AI.
+        user_input (str): The input from the user.
+        token_limit (int): The maximum number of tokens allowed in the API call.
+        model (str, optional): The model to use. If None, the config.fast_llm_model will be used. Defaults to None.
+
+    Returns:
+    str: The AI's response.
+    """
+    if model is None:
+        model = config.fast_llm_model
+
+    # Reserve 1000 tokens for the response
+    logger.debug(f"Token limit: {token_limit}")
+    send_token_limit = token_limit - 1000
+
+    # if len(agent.history) == 0:
+    #     relevant_memory = ""
+    # else:
+    #     recent_history = agent.history[-5:]
+    #     shuffle(recent_history)
+    #     relevant_memories = agent.memory.get_relevant(
+    #         str(recent_history), 5
+    #     )
+    #     if relevant_memories:
+    #         shuffle(relevant_memories)
+    #     relevant_memory = str(relevant_memories)
+    # logger.debug(f"Memory Stats: {agent.memory.get_stats()}")
+    relevant_memory = []
+
+    message_sequence = ChatSequence.for_model(
+        model,
+        [
+            Message("system", system_prompt),
+            Message("system", f"The current time and date is {time.strftime('%c')}"),
+            # Message(
+            #     "system",
+            #     f"This reminds you of these events from your past:\n{relevant_memory}\n\n",
+            # ),
+        ],
+    )
+
+    # Add messages from the full message history until we reach the token limit
+    next_message_to_add_index = len(agent.history) - 1
+    insertion_index = len(message_sequence)
+    # Count the currently used tokens
+    current_tokens_used = message_sequence.token_length
+
+    # while current_tokens_used > 2500:
+    #     # remove memories until we are under 2500 tokens
+    #     relevant_memory = relevant_memory[:-1]
+    #     (
+    #         next_message_to_add_index,
+    #         current_tokens_used,
+    #         insertion_index,
+    #         current_context,
+    #     ) = generate_context(
+    #         prompt, relevant_memory, agent.history, model
+    #     )
+
+    # Account for user input (appended later)
+    user_input_msg = Message("user", user_input)
+    current_tokens_used += count_message_tokens([user_input_msg], model)
+
+    current_tokens_used += 500  # Reserve space for new_summary_message
+
+    # Add Messages until the token limit is reached or there are no more messages to add.
+    for cycle in reversed(list(agent.history.per_cycle())):
+        messages_to_add = [msg for msg in cycle if msg is not None]
+        tokens_to_add = count_message_tokens(messages_to_add, model)
+        if current_tokens_used + tokens_to_add > send_token_limit:
+            break
+
+        # Add the most recent message to the start of the chain,
+        #  after the system prompts.
+        message_sequence.insert(insertion_index, *messages_to_add)
+        current_tokens_used += tokens_to_add
+
+    # Update & add summary of trimmed messages
+    if len(agent.history) > 0:
+        new_summary_message, trimmed_messages = agent.history.trim_messages(
+            current_message_chain=list(message_sequence),
+        )
+        tokens_to_add = count_message_tokens([new_summary_message], model)
+        message_sequence.insert(insertion_index, new_summary_message)
+        current_tokens_used += tokens_to_add - 500
+
+        # FIXME: uncomment when memory is back in use
+        # memory_store = get_memory(cfg)
+        # for _, ai_msg, result_msg in agent.history.per_cycle(trimmed_messages):
+        #     memory_to_add = MemoryItem.from_ai_action(ai_msg, result_msg)
+        #     logger.debug(f"Storing the following memory:\n{memory_to_add.dump()}")
+        #     memory_store.add(memory_to_add)
+
+    api_manager = ApiManager()
+    # inform the AI about its remaining budget (if it has one)
+    if api_manager.get_total_budget() > 0.0:
+        remaining_budget = api_manager.get_total_budget() - api_manager.get_total_cost()
+        if remaining_budget < 0:
+            remaining_budget = 0
+        budget_message = f"Your remaining API budget is ${remaining_budget:.3f}" + (
+            " BUDGET EXCEEDED! SHUT DOWN!\n\n"
+            if remaining_budget == 0
+            else " Budget very nearly exceeded! Shut down gracefully!\n\n"
+            if remaining_budget < 0.005
+            else " Budget nearly exceeded. Finish up.\n\n"
+            if remaining_budget < 0.01
+            else "\n\n"
+        )
+        logger.debug(budget_message)
+        message_sequence.add("system", budget_message)
+        current_tokens_used += count_message_tokens([message_sequence[-1]], model)
+
+    # Append user input, the length of this is accounted for above
+    message_sequence.append(user_input_msg)
+
+    plugin_count = len(config.plugins)
+    for i, plugin in enumerate(config.plugins):
+        if not plugin.can_handle_on_planning():
+            continue
+        plugin_response = plugin.on_planning(
+            agent.config.prompt_generator, message_sequence.raw()
+        )
+        if not plugin_response or plugin_response == "":
+            continue
+        tokens_to_add = count_message_tokens(
+            [Message("system", plugin_response)], model
+        )
+        if current_tokens_used + tokens_to_add > send_token_limit:
+            logger.debug(f"Plugin response too long, skipping: {plugin_response}")
+            logger.debug(f"Plugins remaining at stop: {plugin_count - i}")
+            break
+        message_sequence.add("system", plugin_response)
+    # Calculate remaining tokens
+    tokens_remaining = token_limit - current_tokens_used
+    # assert tokens_remaining >= 0, "Tokens remaining is negative.
+    # This should never happen, please submit a bug report at
+    #  https://www.github.com/Torantulino/Auto-GPT"
+
+    # Debug print the current context
+    logger.debug(f"Token limit: {token_limit}")
+    logger.debug(f"Send Token Count: {current_tokens_used}")
+    logger.debug(f"Tokens remaining for response: {tokens_remaining}")
+    logger.debug("------------ CONTEXT SENT TO AI ---------------")
+    for message in message_sequence:
+        # Skip printing the prompt
+        if message.role == "system" and message.content == system_prompt:
+            continue
+        logger.debug(f"{message.role.capitalize()}: {message.content}")
+        logger.debug("")
+    logger.debug("----------- END OF CONTEXT ----------------")
+    agent.log_cycle_handler.log_cycle(
+        agent.config.ai_name,
+        agent.created_at,
+        agent.cycle_count,
+        message_sequence.raw(),
+        CURRENT_CONTEXT_FILE_NAME,
+    )
+
+    # TODO: use a model defined elsewhere, so that model can contain
+    # temperature and other settings we care about
+    assistant_reply = create_chat_completion(
+        prompt=message_sequence,
+        max_tokens=tokens_remaining,
+    )
+
+    # Update full message history
+    agent.history.append(user_input_msg)
+    agent.history.add("assistant", assistant_reply, "ai_response")
+
+    return assistant_reply

autogpt/llm_utils.py

@@ -1,185 +0,0 @@
-from __future__ import annotations
-
-import time
-from typing import List, Optional
-
-import openai
-from colorama import Fore, Style
-from openai.error import APIError, RateLimitError
-
-from autogpt.api_manager import api_manager
-from autogpt.config import Config
-from autogpt.logs import logger
-from autogpt.types.openai import Message
-
-CFG = Config()
-
-openai.api_key = CFG.openai_api_key
-
-
-def call_ai_function(
-    function: str, args: list, description: str, model: str | None = None
-) -> str:
-    """Call an AI function
-
-    This is a magic function that can do anything with no-code. See
-    https://github.com/Torantulino/AI-Functions for more info.
-
-    Args:
-        function (str): The function to call
-        args (list): The arguments to pass to the function
-        description (str): The description of the function
-        model (str, optional): The model to use. Defaults to None.
-
-    Returns:
-        str: The response from the function
-    """
-    if model is None:
-        model = CFG.smart_llm_model
-    # For each arg, if any are None, convert to "None":
-    args = [str(arg) if arg is not None else "None" for arg in args]
-    # parse args to comma separated string
-    args: str = ", ".join(args)
-    messages: List[Message] = [
-        {
-            "role": "system",
-            "content": f"You are now the following python function: ```# {description}"
-            f"\n{function}```\n\nOnly respond with your `return` value.",
-        },
-        {"role": "user", "content": args},
-    ]
-
-    return create_chat_completion(model=model, messages=messages, temperature=0)
-
-
-# Overly simple abstraction until we create something better
-# simple retry mechanism when getting a rate error or a bad gateway
-def create_chat_completion(
-    messages: List[Message],  # type: ignore
-    model: Optional[str] = None,
-    temperature: float = CFG.temperature,
-    max_tokens: Optional[int] = None,
-) -> str:
-    """Create a chat completion using the OpenAI API
-
-    Args:
-        messages (List[Message]): The messages to send to the chat completion
-        model (str, optional): The model to use. Defaults to None.
-        temperature (float, optional): The temperature to use. Defaults to 0.9.
-        max_tokens (int, optional): The max tokens to use. Defaults to None.
-
-    Returns:
-        str: The response from the chat completion
-    """
-    num_retries = 10
-    warned_user = False
-    if CFG.debug_mode:
-        print(
-            f"{Fore.GREEN}Creating chat completion with model {model}, temperature {temperature}, max_tokens {max_tokens}{Fore.RESET}"
-        )
-    for plugin in CFG.plugins:
-        if plugin.can_handle_chat_completion(
-            messages=messages,
-            model=model,
-            temperature=temperature,
-            max_tokens=max_tokens,
-        ):
-            message = plugin.handle_chat_completion(
-                messages=messages,
-                model=model,
-                temperature=temperature,
-                max_tokens=max_tokens,
-            )
-            if message is not None:
-                return message
-    response = None
-    for attempt in range(num_retries):
-        backoff = 2 ** (attempt + 2)
-        try:
-            if CFG.use_azure:
-                response = api_manager.create_chat_completion(
-                    deployment_id=CFG.get_azure_deployment_id_for_model(model),
-                    model=model,
-                    messages=messages,
-                    temperature=temperature,
-                    max_tokens=max_tokens,
-                )
-            else:
-                response = api_manager.create_chat_completion(
-                    model=model,
-                    messages=messages,
-                    temperature=temperature,
-                    max_tokens=max_tokens,
-                )
-            break
-        except RateLimitError:
-            if CFG.debug_mode:
-                print(
-                    f"{Fore.RED}Error: ", f"Reached rate limit, passing...{Fore.RESET}"
-                )
-            if not warned_user:
-                logger.double_check(
-                    f"Please double check that you have setup a {Fore.CYAN + Style.BRIGHT}PAID{Style.RESET_ALL} OpenAI API Account. "
-                    + f"You can read more here: {Fore.CYAN}https://github.com/Significant-Gravitas/Auto-GPT#openai-api-keys-configuration{Fore.RESET}"
-                )
-                warned_user = True
-        except APIError as e:
-            if e.http_status != 502:
-                raise
-            if attempt == num_retries - 1:
-                raise
-        if CFG.debug_mode:
-            print(
-                f"{Fore.RED}Error: ",
-                f"API Bad gateway. Waiting {backoff} seconds...{Fore.RESET}",
-            )
-        time.sleep(backoff)
-    if response is None:
-        logger.typewriter_log(
-            "FAILED TO GET RESPONSE FROM OPENAI",
-            Fore.RED,
-            "Auto-GPT has failed to get a response from OpenAI's services. "
-            + f"Try running Auto-GPT again, and if the problem the persists try running it with `{Fore.CYAN}--debug{Fore.RESET}`.",
-        )
-        logger.double_check()
-        if CFG.debug_mode:
-            raise RuntimeError(f"Failed to get response after {num_retries} retries")
-        else:
-            quit(1)
-    resp = response.choices[0].message["content"]
-    for plugin in CFG.plugins:
-        if not plugin.can_handle_on_response():
-            continue
-        resp = plugin.on_response(resp)
-    return resp
-
-
-def get_ada_embedding(text):
-    text = text.replace("\n", " ")
-    return api_manager.embedding_create(
-        text_list=[text], model="text-embedding-ada-002"
-    )
-
-
-def create_embedding_with_ada(text) -> list:
-    """Create an embedding with text-ada-002 using the OpenAI SDK"""
-    num_retries = 10
-    for attempt in range(num_retries):
-        backoff = 2 ** (attempt + 2)
-        try:
-            return api_manager.embedding_create(
-                text_list=[text], model="text-embedding-ada-002"
-            )
-        except RateLimitError:
-            pass
-        except APIError as e:
-            if e.http_status != 502:
-                raise
-            if attempt == num_retries - 1:
-                raise
-        if CFG.debug_mode:
-            print(
-                f"{Fore.RED}Error: ",
-                f"API Bad gateway. Waiting {backoff} seconds...{Fore.RESET}",
-            )
-        time.sleep(backoff)

autogpt/logs.py

@@ -1,359 +0,0 @@
-"""Logging module for Auto-GPT."""
-import inspect
-import json
-import logging
-import os
-import random
-import re
-import time
-import traceback
-from logging import LogRecord
-
-from colorama import Fore, Style
-
-from autogpt.config import Config, Singleton
-from autogpt.speech import say_text
-
-CFG = Config()
-
-def get_properties(obj):
-    props = {}
-    for prop_name in dir(obj):
-        if not prop_name.startswith('__'):
-            prop_value = getattr(obj, prop_name)
-            props[prop_value] = prop_name
-    return props
-
-
-class Logger(metaclass=Singleton):
-    """
-    Logger that handle titles in different colors.
-    Outputs logs in console, activity.log, and errors.log
-    For console handler: simulates typing
-    """
-
-    def __init__(self):
-        # create log directory if it doesn't exist
-        this_files_dir_path = os.path.dirname(__file__)
-        log_dir = os.path.join(this_files_dir_path, "../logs")
-        if not os.path.exists(log_dir):
-            os.makedirs(log_dir)
-
-        log_file = "activity.log"
-        error_file = "error.log"
-
-        console_formatter = AutoGptFormatter("%(title_color)s %(message)s")
-
-        # Create a handler for console which simulate typing
-        self.typing_console_handler = TypingConsoleHandler()
-        self.typing_console_handler.setLevel(logging.INFO)
-        self.typing_console_handler.setFormatter(console_formatter)
-
-        # Create a handler for console without typing simulation
-        self.console_handler = ConsoleHandler()
-        self.console_handler.setLevel(logging.DEBUG)
-        self.console_handler.setFormatter(console_formatter)
-
-        # Info handler in activity.log
-        self.file_handler = logging.FileHandler(
-            os.path.join(log_dir, log_file), "a", "utf-8"
-        )
-        self.file_handler.setLevel(logging.DEBUG)
-        info_formatter = AutoGptFormatter(
-            "%(asctime)s %(levelname)s %(title)s %(message_no_color)s"
-        )
-        self.file_handler.setFormatter(info_formatter)
-
-        # Error handler error.log
-        error_handler = logging.FileHandler(
-            os.path.join(log_dir, error_file), "a", "utf-8"
-        )
-        error_handler.setLevel(logging.ERROR)
-        error_formatter = AutoGptFormatter(
-            "%(asctime)s %(levelname)s %(module)s:%(funcName)s:%(lineno)d %(title)s"
-            " %(message_no_color)s"
-        )
-        error_handler.setFormatter(error_formatter)
-
-        self.typing_logger = logging.getLogger("TYPER")
-        self.typing_logger.addHandler(self.typing_console_handler)
-        self.typing_logger.addHandler(self.file_handler)
-        self.typing_logger.addHandler(error_handler)
-        self.typing_logger.setLevel(logging.DEBUG)
-
-        self.logger = logging.getLogger("LOGGER")
-        self.logger.addHandler(self.console_handler)
-        self.logger.addHandler(self.file_handler)
-        self.logger.addHandler(error_handler)
-        self.logger.setLevel(logging.DEBUG)
-        self.color_compar = get_properties(Fore)
-        self.output_content = []
-
-    def typewriter_log(
-        self, title="", title_color=Fore.YELLOW, content="", speak_text=False, level=logging.INFO
-    ):
-        if speak_text and CFG.speak_mode:
-            say_text(f"{title}. {content}")
-
-        if content:
-            if isinstance(content, list):
-                content = " ".join(content)
-        else:
-            content = ""
-
-        self.typing_logger.log(
-            level, content, extra={"title": title, "color": title_color}
-        )
-        try:
-            msg = f'<span style="color:{self.color_compar[title_color]};font-weight:bold;">{title}：</span><span style="font-weight:normal;">{content}</span>'
-            self.output_content.append([msg, title+": "+content])
-            return msg
-        except Exception as e:
-            msg = f'<span style="font-weight:bold;">{title}：</span><span style="font-weight:normal;">{content}</span>'
-            self.output_content.append([msg, title+": "+content])
-            return
-
-
-    def debug(
-        self,
-        message,
-        title="",
-        title_color="",
-    ):
-        self._log(title, title_color, message, logging.DEBUG)
-
-    def warn(
-        self,
-        message,
-        title="",
-        title_color="",
-    ):
-        self._log(title, title_color, message, logging.WARN)
-
-    def error(self, title, message=""):
-        self._log(title, Fore.RED, message, logging.ERROR)
-
-    def _log(self, title="", title_color="", message="", level=logging.INFO):
-        if message:
-            if isinstance(message, list):
-                message = " ".join(message)
-        self.logger.log(level, message, extra={"title": title, "color": title_color})
-
-    def set_level(self, level):
-        self.logger.setLevel(level)
-        self.typing_logger.setLevel(level)
-
-    def double_check(self, additionalText=None):
-        if not additionalText:
-            additionalText = (
-                "Please ensure you've setup and configured everything"
-                " correctly. Read https://github.com/Torantulino/Auto-GPT#readme to "
-                "double check. You can also create a github issue or join the discord"
-                " and ask there!"
-            )
-
-        self.typewriter_log("DOUBLE CHECK CONFIGURATION", Fore.YELLOW, additionalText)
-
-
-"""
-Output stream to console using simulated typing
-"""
-
-
-class TypingConsoleHandler(logging.StreamHandler):
-    def emit(self, record):
-        min_typing_speed = 0.05
-        max_typing_speed = 0.01
-
-        msg = self.format(record)
-        try:
-            words = msg.split()
-            for i, word in enumerate(words):
-                print(word, end="", flush=True)
-                if i < len(words) - 1:
-                    print(" ", end="", flush=True)
-                typing_speed = random.uniform(min_typing_speed, max_typing_speed)
-                time.sleep(typing_speed)
-                # type faster after each word
-                min_typing_speed = min_typing_speed * 0.95
-                max_typing_speed = max_typing_speed * 0.95
-            print()
-        except Exception:
-            self.handleError(record)
-
-
-class ConsoleHandler(logging.StreamHandler):
-    def emit(self, record) -> None:
-        msg = self.format(record)
-        try:
-            print(msg)
-        except Exception:
-            self.handleError(record)
-
-
-class AutoGptFormatter(logging.Formatter):
-    """
-    Allows to handle custom placeholders 'title_color' and 'message_no_color'.
-    To use this formatter, make sure to pass 'color', 'title' as log extras.
-    """
-
-    def format(self, record: LogRecord) -> str:
-        if hasattr(record, "color"):
-            record.title_color = (
-                getattr(record, "color")
-                + getattr(record, "title")
-                + " "
-                + Style.RESET_ALL
-            )
-        else:
-            record.title_color = getattr(record, "title")
-        if hasattr(record, "msg"):
-            record.message_no_color = remove_color_codes(getattr(record, "msg"))
-        else:
-            record.message_no_color = ""
-        return super().format(record)
-
-
-def remove_color_codes(s: str) -> str:
-    ansi_escape = re.compile(r"\x1B(?:[@-Z\\-_]|\[[0-?]*[ -/]*[@-~])")
-    return ansi_escape.sub("", s)
-
-
-logger = Logger()
-
-
-def print_assistant_thoughts(ai_name, assistant_reply):
-    """Prints the assistant's thoughts to the console"""
-    from autogpt.json_utils.json_fix_llm import (
-        attempt_to_fix_json_by_finding_outermost_brackets,
-        fix_and_parse_json,
-    )
-
-    try:
-        try:
-            # Parse and print Assistant response
-            assistant_reply_json = fix_and_parse_json(assistant_reply)
-        except json.JSONDecodeError:
-            logger.error("Error: Invalid JSON in assistant thoughts\n", assistant_reply)
-            assistant_reply_json = attempt_to_fix_json_by_finding_outermost_brackets(
-                assistant_reply
-            )
-            if isinstance(assistant_reply_json, str):
-                assistant_reply_json = fix_and_parse_json(assistant_reply_json)
-
-        # Check if assistant_reply_json is a string and attempt to parse
-        # it into a JSON object
-        if isinstance(assistant_reply_json, str):
-            try:
-                assistant_reply_json = json.loads(assistant_reply_json)
-            except json.JSONDecodeError:
-                logger.error("Error: Invalid JSON\n", assistant_reply)
-                assistant_reply_json = (
-                    attempt_to_fix_json_by_finding_outermost_brackets(
-                        assistant_reply_json
-                    )
-                )
-
-        assistant_thoughts_reasoning = None
-        assistant_thoughts_plan = None
-        assistant_thoughts_speak = None
-        assistant_thoughts_criticism = None
-        if not isinstance(assistant_reply_json, dict):
-            assistant_reply_json = {}
-        assistant_thoughts = assistant_reply_json.get("thoughts", {})
-        assistant_thoughts_text = assistant_thoughts.get("text")
-
-        if assistant_thoughts:
-            assistant_thoughts_reasoning = assistant_thoughts.get("reasoning")
-            assistant_thoughts_plan = assistant_thoughts.get("plan")
-            assistant_thoughts_criticism = assistant_thoughts.get("criticism")
-            assistant_thoughts_speak = assistant_thoughts.get("speak")
-
-        logger.typewriter_log(
-            f"{ai_name.upper()} THOUGHTS:", Fore.YELLOW, f"{assistant_thoughts_text}"
-        )
-        logger.typewriter_log(
-            "REASONING:", Fore.YELLOW, f"{assistant_thoughts_reasoning}"
-        )
-
-        if assistant_thoughts_plan:
-            logger.typewriter_log("PLAN:", Fore.YELLOW, "")
-            # If it's a list, join it into a string
-            if isinstance(assistant_thoughts_plan, list):
-                assistant_thoughts_plan = "\n".join(assistant_thoughts_plan)
-            elif isinstance(assistant_thoughts_plan, dict):
-                assistant_thoughts_plan = str(assistant_thoughts_plan)
-
-            # Split the input_string using the newline character and dashes
-            lines = assistant_thoughts_plan.split("\n")
-            for line in lines:
-                line = line.lstrip("- ")
-                logger.typewriter_log("- ", Fore.GREEN, line.strip())
-
-        logger.typewriter_log(
-            "CRITICISM:", Fore.YELLOW, f"{assistant_thoughts_criticism}"
-        )
-        # Speak the assistant's thoughts
-        if CFG.speak_mode and assistant_thoughts_speak:
-            say_text(assistant_thoughts_speak)
-        else:
-            logger.typewriter_log("SPEAK:", Fore.YELLOW, f"{assistant_thoughts_speak}")
-
-        return assistant_reply_json
-    except json.decoder.JSONDecodeError:
-        logger.error("Error: Invalid JSON\n", assistant_reply)
-        if CFG.speak_mode:
-            say_text(
-                "I have received an invalid JSON response from the OpenAI API."
-                " I cannot ignore this response."
-            )
-
-    # All other errors, return "Error: + error message"
-    except Exception:
-        call_stack = traceback.format_exc()
-        logger.error("Error: \n", call_stack)
-
-
-def print_assistant_thoughts(
-    ai_name: object, assistant_reply_json_valid: object
-) -> None:
-    assistant_thoughts_reasoning = None
-    assistant_thoughts_plan = None
-    assistant_thoughts_speak = None
-    assistant_thoughts_criticism = None
-
-    assistant_thoughts = assistant_reply_json_valid.get("thoughts", {})
-    assistant_thoughts_text = assistant_thoughts.get("text")
-    if assistant_thoughts:
-        assistant_thoughts_reasoning = assistant_thoughts.get("reasoning")
-        assistant_thoughts_plan = assistant_thoughts.get("plan")
-        assistant_thoughts_criticism = assistant_thoughts.get("criticism")
-        assistant_thoughts_speak = assistant_thoughts.get("speak")
-    logger.typewriter_log(
-        f"{ai_name.upper()} THOUGHTS:", Fore.YELLOW, f"{assistant_thoughts_text}"
-    )
-    logger.typewriter_log("REASONING:", Fore.YELLOW, f"{assistant_thoughts_reasoning}")
-    if assistant_thoughts_plan:
-        logger.typewriter_log("PLAN:", Fore.YELLOW, "")
-        # If it's a list, join it into a string
-        if isinstance(assistant_thoughts_plan, list):
-            assistant_thoughts_plan = "\n".join(assistant_thoughts_plan)
-        elif isinstance(assistant_thoughts_plan, dict):
-            assistant_thoughts_plan = str(assistant_thoughts_plan)
-
-        # Split the input_string using the newline character and dashes
-        lines = assistant_thoughts_plan.split("\n")
-        for line in lines:
-            line = line.lstrip("- ")
-            logger.typewriter_log("- ", Fore.GREEN, line.strip())
-    logger.typewriter_log("CRITICISM:", Fore.YELLOW, f"{assistant_thoughts_criticism}")
-    # Speak the assistant's thoughts
-    if CFG.speak_mode and assistant_thoughts_speak:
-        say_text(assistant_thoughts_speak)
-
-
-if __name__ == '__main__':
-
-    ff = logger.typewriter_log('ahhahaha', Fore.GREEN, speak_text=True)
-    # print(Fore.GREEN)
-    # print(logger.color_compar)

autogpt/memory/__init__.py

@@ -1,99 +0,0 @@
-from autogpt.memory.local import LocalCache
-from autogpt.memory.no_memory import NoMemory
-
-# List of supported memory backends
-# Add a backend to this list if the import attempt is successful
-supported_memory = ["local", "no_memory"]
-
-try:
-    from autogpt.memory.redismem import RedisMemory
-
-    supported_memory.append("redis")
-except ImportError:
-    # print("Redis not installed. Skipping import.")
-    RedisMemory = None
-
-try:
-    from autogpt.memory.pinecone import PineconeMemory
-
-    supported_memory.append("pinecone")
-except ImportError:
-    # print("Pinecone not installed. Skipping import.")
-    PineconeMemory = None
-
-try:
-    from autogpt.memory.weaviate import WeaviateMemory
-
-    supported_memory.append("weaviate")
-except ImportError:
-    # print("Weaviate not installed. Skipping import.")
-    WeaviateMemory = None
-
-try:
-    from autogpt.memory.milvus import MilvusMemory
-
-    supported_memory.append("milvus")
-except ImportError:
-    # print("pymilvus not installed. Skipping import.")
-    MilvusMemory = None
-
-
-def get_memory(cfg, init=False):
-    memory = None
-    if cfg.memory_backend == "pinecone":
-        if not PineconeMemory:
-            print(
-                "Error: Pinecone is not installed. Please install pinecone"
-                " to use Pinecone as a memory backend."
-            )
-        else:
-            memory = PineconeMemory(cfg)
-            if init:
-                memory.clear()
-    elif cfg.memory_backend == "redis":
-        if not RedisMemory:
-            print(
-                "Error: Redis is not installed. Please install redis-py to"
-                " use Redis as a memory backend."
-            )
-        else:
-            memory = RedisMemory(cfg)
-    elif cfg.memory_backend == "weaviate":
-        if not WeaviateMemory:
-            print(
-                "Error: Weaviate is not installed. Please install weaviate-client to"
-                " use Weaviate as a memory backend."
-            )
-        else:
-            memory = WeaviateMemory(cfg)
-    elif cfg.memory_backend == "milvus":
-        if not MilvusMemory:
-            print(
-                "Error: pymilvus sdk is not installed."
-                "Please install pymilvus to use Milvus or Zilliz Cloud as memory backend."
-            )
-        else:
-            memory = MilvusMemory(cfg)
-    elif cfg.memory_backend == "no_memory":
-        memory = NoMemory(cfg)
-
-    if memory is None:
-        memory = LocalCache(cfg)
-        if init:
-            memory.clear()
-    return memory
-
-
-def get_supported_memory_backends():
-    return supported_memory
-
-
-__all__ = [
-    "get_memory",
-    "LocalCache",
-    "RedisMemory",
-    "PineconeMemory",
-    "NoMemory",
-    "MilvusMemory",
-    "WeaviateMemory",
-]

autogpt/memory/base.py

@@ -1,28 +0,0 @@
-"""Base class for memory providers."""
-import abc
-
-from autogpt.config import AbstractSingleton, Config
-
-cfg = Config()
-
-
-class MemoryProviderSingleton(AbstractSingleton):
-    @abc.abstractmethod
-    def add(self, data):
-        pass
-
-    @abc.abstractmethod
-    def get(self, data):
-        pass
-
-    @abc.abstractmethod
-    def clear(self):
-        pass
-
-    @abc.abstractmethod
-    def get_relevant(self, data, num_relevant=5):
-        pass
-
-    @abc.abstractmethod
-    def get_stats(self):
-        pass

autogpt/memory/local.py

@@ -1,126 +0,0 @@
-from __future__ import annotations
-
-import dataclasses
-from pathlib import Path
-from typing import Any, List
-
-import numpy as np
-import orjson
-
-from autogpt.llm_utils import create_embedding_with_ada
-from autogpt.memory.base import MemoryProviderSingleton
-
-EMBED_DIM = 1536
-SAVE_OPTIONS = orjson.OPT_SERIALIZE_NUMPY | orjson.OPT_SERIALIZE_DATACLASS
-
-
-def create_default_embeddings():
-    return np.zeros((0, EMBED_DIM)).astype(np.float32)
-
-
-@dataclasses.dataclass
-class CacheContent:
-    texts: List[str] = dataclasses.field(default_factory=list)
-    embeddings: np.ndarray = dataclasses.field(
-        default_factory=create_default_embeddings
-    )
-
-
-class LocalCache(MemoryProviderSingleton):
-    """A class that stores the memory in a local file"""
-
-    def __init__(self, cfg) -> None:
-        """Initialize a class instance
-
-        Args:
-            cfg: Config object
-
-        Returns:
-            None
-        """
-        workspace_path = Path(cfg.workspace_path)
-        self.filename = workspace_path / f"{cfg.memory_index}.json"
-
-        self.filename.touch(exist_ok=True)
-
-        file_content = b"{}"
-        with self.filename.open("w+b") as f:
-            f.write(file_content)
-
-        self.data = CacheContent()
-
-    def add(self, text: str):
-        """
-        Add text to our list of texts, add embedding as row to our
-            embeddings-matrix
-
-        Args:
-            text: str
-
-        Returns: None
-        """
-        if "Command Error:" in text:
-            return ""
-        self.data.texts.append(text)
-
-        embedding = create_embedding_with_ada(text)
-
-        vector = np.array(embedding).astype(np.float32)
-        vector = vector[np.newaxis, :]
-        self.data.embeddings = np.concatenate(
-            [
-                self.data.embeddings,
-                vector,
-            ],
-            axis=0,
-        )
-
-        with open(self.filename, "wb") as f:
-            out = orjson.dumps(self.data, option=SAVE_OPTIONS)
-            f.write(out)
-        return text
-
-    def clear(self) -> str:
-        """
-        Clears the redis server.
-
-        Returns: A message indicating that the memory has been cleared.
-        """
-        self.data = CacheContent()
-        return "Obliviated"
-
-    def get(self, data: str) -> list[Any] | None:
-        """
-        Gets the data from the memory that is most relevant to the given data.
-
-        Args:
-            data: The data to compare to.
-
-        Returns: The most relevant data.
-        """
-        return self.get_relevant(data, 1)
-
-    def get_relevant(self, text: str, k: int) -> list[Any]:
-        """ "
-        matrix-vector mult to find score-for-each-row-of-matrix
-         get indices for top-k winning scores
-         return texts for those indices
-        Args:
-            text: str
-            k: int
-
-        Returns: List[str]
-        """
-        embedding = create_embedding_with_ada(text)
-
-        scores = np.dot(self.data.embeddings, embedding)
-
-        top_k_indices = np.argsort(scores)[-k:][::-1]
-
-        return [self.data.texts[i] for i in top_k_indices]
-
-    def get_stats(self) -> tuple[int, tuple[int, ...]]:
-        """
-        Returns: The stats of the local cache.
-        """
-        return len(self.data.texts), self.data.embeddings.shape

autogpt/memory/milvus.py

@@ -1,162 +0,0 @@
-""" Milvus memory storage provider."""
-import re
-
-from pymilvus import Collection, CollectionSchema, DataType, FieldSchema, connections
-
-from autogpt.config import Config
-from autogpt.llm_utils import get_ada_embedding
-from autogpt.memory.base import MemoryProviderSingleton
-
-
-class MilvusMemory(MemoryProviderSingleton):
-    """Milvus memory storage provider."""
-
-    def __init__(self, cfg: Config) -> None:
-        """Construct a milvus memory storage connection.
-
-        Args:
-            cfg (Config): Auto-GPT global config.
-        """
-        self.configure(cfg)
-
-        connect_kwargs = {}
-        if self.username:
-            connect_kwargs["user"] = self.username
-            connect_kwargs["password"] = self.password
-
-        connections.connect(
-            **connect_kwargs,
-            uri=self.uri or "",
-            address=self.address or "",
-            secure=self.secure,
-        )
-
-        self.init_collection()
-
-    def configure(self, cfg: Config) -> None:
-        # init with configuration.
-        self.uri = None
-        self.address = cfg.milvus_addr
-        self.secure = cfg.milvus_secure
-        self.username = cfg.milvus_username
-        self.password = cfg.milvus_password
-        self.collection_name = cfg.milvus_collection
-        # use HNSW by default.
-        self.index_params = {
-            "metric_type": "IP",
-            "index_type": "HNSW",
-            "params": {"M": 8, "efConstruction": 64},
-        }
-
-        if (self.username is None) != (self.password is None):
-            raise ValueError(
-                "Both username and password must be set to use authentication for Milvus"
-            )
-
-        # configured address may be a full URL.
-        if re.match(r"^(https?|tcp)://", self.address) is not None:
-            self.uri = self.address
-            self.address = None
-
-            if self.uri.startswith("https"):
-                self.secure = True
-
-        # Zilliz Cloud requires AutoIndex.
-        if re.match(r"^https://(.*)\.zillizcloud\.(com|cn)", self.address) is not None:
-            self.index_params = {
-                "metric_type": "IP",
-                "index_type": "AUTOINDEX",
-                "params": {},
-            }
-
-    def init_collection(self) -> None:
-        """Initialize collection in vector database."""
-        fields = [
-            FieldSchema(name="pk", dtype=DataType.INT64, is_primary=True, auto_id=True),
-            FieldSchema(name="embeddings", dtype=DataType.FLOAT_VECTOR, dim=1536),
-            FieldSchema(name="raw_text", dtype=DataType.VARCHAR, max_length=65535),
-        ]
-
-        # create collection if not exist and load it.
-        self.schema = CollectionSchema(fields, "auto-gpt memory storage")
-        self.collection = Collection(self.collection_name, self.schema)
-        # create index if not exist.
-        if not self.collection.has_index():
-            self.collection.release()
-            self.collection.create_index(
-                "embeddings",
-                self.index_params,
-                index_name="embeddings",
-            )
-        self.collection.load()
-
-    def add(self, data) -> str:
-        """Add an embedding of data into memory.
-
-        Args:
-            data (str): The raw text to construct embedding index.
-
-        Returns:
-            str: log.
-        """
-        embedding = get_ada_embedding(data)
-        result = self.collection.insert([[embedding], [data]])
-        _text = (
-            "Inserting data into memory at primary key: "
-            f"{result.primary_keys[0]}:\n data: {data}"
-        )
-        return _text
-
-    def get(self, data):
-        """Return the most relevant data in memory.
-        Args:
-            data: The data to compare to.
-        """
-        return self.get_relevant(data, 1)
-
-    def clear(self) -> str:
-        """Drop the index in memory.
-
-        Returns:
-            str: log.
-        """
-        self.collection.drop()
-        self.collection = Collection(self.collection_name, self.schema)
-        self.collection.create_index(
-            "embeddings",
-            self.index_params,
-            index_name="embeddings",
-        )
-        self.collection.load()
-        return "Obliviated"
-
-    def get_relevant(self, data: str, num_relevant: int = 5):
-        """Return the top-k relevant data in memory.
-        Args:
-            data: The data to compare to.
-            num_relevant (int, optional): The max number of relevant data.
-                Defaults to 5.
-
-        Returns:
-            list: The top-k relevant data.
-        """
-        # search the embedding and return the most relevant text.
-        embedding = get_ada_embedding(data)
-        search_params = {
-            "metrics_type": "IP",
-            "params": {"nprobe": 8},
-        }
-        result = self.collection.search(
-            [embedding],
-            "embeddings",
-            search_params,
-            num_relevant,
-            output_fields=["raw_text"],
-        )
-        return [item.entity.value_of_field("raw_text") for item in result[0]]
-
-    def get_stats(self) -> str:
-        """
-        Returns: The stats of the milvus cache.
-        """
-        return f"Entities num: {self.collection.num_entities}"

autogpt/memory/no_memory.py

@@ -1,73 +0,0 @@
-"""A class that does not store any data. This is the default memory provider."""
-from __future__ import annotations
-
-from typing import Any
-
-from autogpt.memory.base import MemoryProviderSingleton
-
-
-class NoMemory(MemoryProviderSingleton):
-    """
-    A class that does not store any data. This is the default memory provider.
-    """
-
-    def __init__(self, cfg):
-        """
-        Initializes the NoMemory provider.
-
-        Args:
-            cfg: The config object.
-
-        Returns: None
-        """
-        pass
-
-    def add(self, data: str) -> str:
-        """
-        Adds a data point to the memory. No action is taken in NoMemory.
-
-        Args:
-            data: The data to add.
-
-        Returns: An empty string.
-        """
-        return ""
-
-    def get(self, data: str) -> list[Any] | None:
-        """
-        Gets the data from the memory that is most relevant to the given data.
-        NoMemory always returns None.
-
-        Args:
-            data: The data to compare to.
-
-        Returns: None
-        """
-        return None
-
-    def clear(self) -> str:
-        """
-        Clears the memory. No action is taken in NoMemory.
-
-        Returns: An empty string.
-        """
-        return ""
-
-    def get_relevant(self, data: str, num_relevant: int = 5) -> list[Any] | None:
-        """
-        Returns all the data in the memory that is relevant to the given data.
-        NoMemory always returns None.
-
-        Args:
-            data: The data to compare to.
-            num_relevant: The number of relevant data to return.
-
-        Returns: None
-        """
-        return None
-
-    def get_stats(self):
-        """
-        Returns: An empty dictionary as there are no stats in NoMemory.
-        """
-        return {}

autogpt/memory/pinecone.py

@@ -1,75 +0,0 @@
-import pinecone
-from colorama import Fore, Style
-
-from autogpt.llm_utils import create_embedding_with_ada
-from autogpt.logs import logger
-from autogpt.memory.base import MemoryProviderSingleton
-
-
-class PineconeMemory(MemoryProviderSingleton):
-    def __init__(self, cfg):
-        pinecone_api_key = cfg.pinecone_api_key
-        pinecone_region = cfg.pinecone_region
-        pinecone.init(api_key=pinecone_api_key, environment=pinecone_region)
-        dimension = 1536
-        metric = "cosine"
-        pod_type = "p1"
-        table_name = "auto-gpt"
-        # this assumes we don't start with memory.
-        # for now this works.
-        # we'll need a more complicated and robust system if we want to start with
-        #  memory.
-        self.vec_num = 0
-
-        try:
-            pinecone.whoami()
-        except Exception as e:
-            logger.typewriter_log(
-                "FAILED TO CONNECT TO PINECONE",
-                Fore.RED,
-                Style.BRIGHT + str(e) + Style.RESET_ALL,
-            )
-            logger.double_check(
-                "Please ensure you have setup and configured Pinecone properly for use."
-                + f"You can check out {Fore.CYAN + Style.BRIGHT}"
-                "https://github.com/Torantulino/Auto-GPT#-pinecone-api-key-setup"
-                f"{Style.RESET_ALL} to ensure you've set up everything correctly."
-            )
-            exit(1)
-
-        if table_name not in pinecone.list_indexes():
-            pinecone.create_index(
-                table_name, dimension=dimension, metric=metric, pod_type=pod_type
-            )
-        self.index = pinecone.Index(table_name)
-
-    def add(self, data):
-        vector = create_embedding_with_ada(data)
-        # no metadata here. We may wish to change that long term.
-        self.index.upsert([(str(self.vec_num), vector, {"raw_text": data})])
-        _text = f"Inserting data into memory at index: {self.vec_num}:\n data: {data}"
-        self.vec_num += 1
-        return _text
-
-    def get(self, data):
-        return self.get_relevant(data, 1)
-
-    def clear(self):
-        self.index.delete(deleteAll=True)
-        return "Obliviated"
-
-    def get_relevant(self, data, num_relevant=5):
-        """
-        Returns all the data in the memory that is relevant to the given data.
-        :param data: The data to compare to.
-        :param num_relevant: The number of relevant data to return. Defaults to 5
-        """
-        query_embedding = create_embedding_with_ada(data)
-        results = self.index.query(
-            query_embedding, top_k=num_relevant, include_metadata=True
-        )
-        sorted_results = sorted(results.matches, key=lambda x: x.score)
-        return [str(item["metadata"]["raw_text"]) for item in sorted_results]
-
-    def get_stats(self):
-        return self.index.describe_index_stats()

autogpt/memory/redismem.py

@@ -1,156 +0,0 @@
-"""Redis memory provider."""
-from __future__ import annotations
-
-from typing import Any
-
-import numpy as np
-import redis
-from colorama import Fore, Style
-from redis.commands.search.field import TextField, VectorField
-from redis.commands.search.indexDefinition import IndexDefinition, IndexType
-from redis.commands.search.query import Query
-
-from autogpt.llm_utils import create_embedding_with_ada
-from autogpt.logs import logger
-from autogpt.memory.base import MemoryProviderSingleton
-
-SCHEMA = [
-    TextField("data"),
-    VectorField(
-        "embedding",
-        "HNSW",
-        {"TYPE": "FLOAT32", "DIM": 1536, "DISTANCE_METRIC": "COSINE"},
-    ),
-]
-
-
-class RedisMemory(MemoryProviderSingleton):
-    def __init__(self, cfg):
-        """
-        Initializes the Redis memory provider.
-
-        Args:
-            cfg: The config object.
-
-        Returns: None
-        """
-        redis_host = cfg.redis_host
-        redis_port = cfg.redis_port
-        redis_password = cfg.redis_password
-        self.dimension = 1536
-        self.redis = redis.Redis(
-            host=redis_host,
-            port=redis_port,
-            password=redis_password,
-            db=0,  # Cannot be changed
-        )
-        self.cfg = cfg
-
-        # Check redis connection
-        try:
-            self.redis.ping()
-        except redis.ConnectionError as e:
-            logger.typewriter_log(
-                "FAILED TO CONNECT TO REDIS",
-                Fore.RED,
-                Style.BRIGHT + str(e) + Style.RESET_ALL,
-            )
-            logger.double_check(
-                "Please ensure you have setup and configured Redis properly for use. "
-                + f"You can check out {Fore.CYAN + Style.BRIGHT}"
-                f"https://github.com/Torantulino/Auto-GPT#redis-setup{Style.RESET_ALL}"
-                " to ensure you've set up everything correctly."
-            )
-            exit(1)
-
-        if cfg.wipe_redis_on_start:
-            self.redis.flushall()
-        try:
-            self.redis.ft(f"{cfg.memory_index}").create_index(
-                fields=SCHEMA,
-                definition=IndexDefinition(
-                    prefix=[f"{cfg.memory_index}:"], index_type=IndexType.HASH
-                ),
-            )
-        except Exception as e:
-            print("Error creating Redis search index: ", e)
-        existing_vec_num = self.redis.get(f"{cfg.memory_index}-vec_num")
-        self.vec_num = int(existing_vec_num.decode("utf-8")) if existing_vec_num else 0
-
-    def add(self, data: str) -> str:
-        """
-        Adds a data point to the memory.
-
-        Args:
-            data: The data to add.
-
-        Returns: Message indicating that the data has been added.
-        """
-        if "Command Error:" in data:
-            return ""
-        vector = create_embedding_with_ada(data)
-        vector = np.array(vector).astype(np.float32).tobytes()
-        data_dict = {b"data": data, "embedding": vector}
-        pipe = self.redis.pipeline()
-        pipe.hset(f"{self.cfg.memory_index}:{self.vec_num}", mapping=data_dict)
-        _text = (
-            f"Inserting data into memory at index: {self.vec_num}:\n" f"data: {data}"
-        )
-        self.vec_num += 1
-        pipe.set(f"{self.cfg.memory_index}-vec_num", self.vec_num)
-        pipe.execute()
-        return _text
-
-    def get(self, data: str) -> list[Any] | None:
-        """
-        Gets the data from the memory that is most relevant to the given data.
-
-        Args:
-            data: The data to compare to.
-
-        Returns: The most relevant data.
-        """
-        return self.get_relevant(data, 1)
-
-    def clear(self) -> str:
-        """
-        Clears the redis server.
-
-        Returns: A message indicating that the memory has been cleared.
-        """
-        self.redis.flushall()
-        return "Obliviated"
-
-    def get_relevant(self, data: str, num_relevant: int = 5) -> list[Any] | None:
-        """
-        Returns all the data in the memory that is relevant to the given data.
-        Args:
-            data: The data to compare to.
-            num_relevant: The number of relevant data to return.
-
-        Returns: A list of the most relevant data.
-        """
-        query_embedding = create_embedding_with_ada(data)
-        base_query = f"*=>[KNN {num_relevant} @embedding $vector AS vector_score]"
-        query = (
-            Query(base_query)
-            .return_fields("data", "vector_score")
-            .sort_by("vector_score")
-            .dialect(2)
-        )
-        query_vector = np.array(query_embedding).astype(np.float32).tobytes()
-
-        try:
-            results = self.redis.ft(f"{self.cfg.memory_index}").search(
-                query, query_params={"vector": query_vector}
-            )
-        except Exception as e:
-            print("Error calling Redis search: ", e)
-            return None
-        return [result.data for result in results.docs]
-
-    def get_stats(self):
-        """
-        Returns: The stats of the memory index.
-        """
-        return self.redis.ft(f"{self.cfg.memory_index}").info()

autogpt/memory/weaviate.py

@@ -1,126 +0,0 @@
-import weaviate
-from weaviate import Client
-from weaviate.embedded import EmbeddedOptions
-from weaviate.util import generate_uuid5
-
-from autogpt.llm_utils import get_ada_embedding
-from autogpt.memory.base import MemoryProviderSingleton
-
-
-def default_schema(weaviate_index):
-    return {
-        "class": weaviate_index,
-        "properties": [
-            {
-                "name": "raw_text",
-                "dataType": ["text"],
-                "description": "original text for the embedding",
-            }
-        ],
-    }
-
-
-class WeaviateMemory(MemoryProviderSingleton):
-    def __init__(self, cfg):
-        auth_credentials = self._build_auth_credentials(cfg)
-
-        url = f"{cfg.weaviate_protocol}://{cfg.weaviate_host}:{cfg.weaviate_port}"
-
-        if cfg.use_weaviate_embedded:
-            self.client = Client(
-                embedded_options=EmbeddedOptions(
-                    hostname=cfg.weaviate_host,
-                    port=int(cfg.weaviate_port),
-                    persistence_data_path=cfg.weaviate_embedded_path,
-                )
-            )
-
-            print(
-                f"Weaviate Embedded running on: {url} with persistence path: {cfg.weaviate_embedded_path}"
-            )
-        else:
-            self.client = Client(url, auth_client_secret=auth_credentials)
-
-        self.index = WeaviateMemory.format_classname(cfg.memory_index)
-        self._create_schema()
-
-    @staticmethod
-    def format_classname(index):
-        # weaviate uses capitalised index names
-        # The python client uses the following code to format
-        # index names before the corresponding class is created
-        index = index.replace("-", "_")
-        if len(index) == 1:
-            return index.capitalize()
-        return index[0].capitalize() + index[1:]
-
-    def _create_schema(self):
-        schema = default_schema(self.index)
-        if not self.client.schema.contains(schema):
-            self.client.schema.create_class(schema)
-
-    def _build_auth_credentials(self, cfg):
-        if cfg.weaviate_username and cfg.weaviate_password:
-            return weaviate.AuthClientPassword(
-                cfg.weaviate_username, cfg.weaviate_password
-            )
-        if cfg.weaviate_api_key:
-            return weaviate.AuthApiKey(api_key=cfg.weaviate_api_key)
-        else:
-            return None
-
-    def add(self, data):
-        vector = get_ada_embedding(data)
-
-        doc_uuid = generate_uuid5(data, self.index)
-        data_object = {"raw_text": data}
-
-        with self.client.batch as batch:
-            batch.add_data_object(
-                uuid=doc_uuid,
-                data_object=data_object,
-                class_name=self.index,
-                vector=vector,
-            )
-
-        return f"Inserting data into memory at uuid: {doc_uuid}:\n data: {data}"
-
-    def get(self, data):
-        return self.get_relevant(data, 1)
-
-    def clear(self):
-        self.client.schema.delete_all()
-
-        # weaviate does not yet have a neat way to just remove the items in an index
-        # without removing the entire schema, therefore we need to re-create it
-        # after a call to delete_all
-        self._create_schema()
-
-        return "Obliterated"
-
-    def get_relevant(self, data, num_relevant=5):
-        query_embedding = get_ada_embedding(data)
-        try:
-            results = (
-                self.client.query.get(self.index, ["raw_text"])
-                .with_near_vector({"vector": query_embedding, "certainty": 0.7})
-                .with_limit(num_relevant)
-                .do()
-            )
-
-            if len(results["data"]["Get"][self.index]) > 0:
-                return [
-                    str(item["raw_text"]) for item in results["data"]["Get"][self.index]
-                ]
-            else:
-                return []
-
-        except Exception as err:
-            print(f"Unexpected error {err=}, {type(err)=}")
-            return []
-
-    def get_stats(self):
-        result = self.client.query.aggregate(self.index).with_meta_count().do()
-        class_data = result["data"]["Aggregate"][self.index]
-
-        return class_data[0]["meta"] if class_data else {}

autogpt/models/base_open_ai_plugin.py

@@ -1,199 +0,0 @@
-"""Handles loading of plugins."""
-from typing import Any, Dict, List, Optional, Tuple, TypedDict, TypeVar
-
-from auto_gpt_plugin_template import AutoGPTPluginTemplate
-
-PromptGenerator = TypeVar("PromptGenerator")
-
-
-class Message(TypedDict):
-    role: str
-    content: str
-
-
-class BaseOpenAIPlugin(AutoGPTPluginTemplate):
-    """
-    This is a BaseOpenAIPlugin class for generating Auto-GPT plugins.
-    """
-
-    def __init__(self, manifests_specs_clients: dict):
-        # super().__init__()
-        self._name = manifests_specs_clients["manifest"]["name_for_model"]
-        self._version = manifests_specs_clients["manifest"]["schema_version"]
-        self._description = manifests_specs_clients["manifest"]["description_for_model"]
-        self._client = manifests_specs_clients["client"]
-        self._manifest = manifests_specs_clients["manifest"]
-        self._openapi_spec = manifests_specs_clients["openapi_spec"]
-
-    def can_handle_on_response(self) -> bool:
-        """This method is called to check that the plugin can
-        handle the on_response method.
-        Returns:
-            bool: True if the plugin can handle the on_response method."""
-        return False
-
-    def on_response(self, response: str, *args, **kwargs) -> str:
-        """This method is called when a response is received from the model."""
-        return response
-
-    def can_handle_post_prompt(self) -> bool:
-        """This method is called to check that the plugin can
-        handle the post_prompt method.
-        Returns:
-            bool: True if the plugin can handle the post_prompt method."""
-        return False
-
-    def post_prompt(self, prompt: PromptGenerator) -> PromptGenerator:
-        """This method is called just after the generate_prompt is called,
-            but actually before the prompt is generated.
-        Args:
-            prompt (PromptGenerator): The prompt generator.
-        Returns:
-            PromptGenerator: The prompt generator.
-        """
-        return prompt
-
-    def can_handle_on_planning(self) -> bool:
-        """This method is called to check that the plugin can
-        handle the on_planning method.
-        Returns:
-            bool: True if the plugin can handle the on_planning method."""
-        return False
-
-    def on_planning(
-        self, prompt: PromptGenerator, messages: List[Message]
-    ) -> Optional[str]:
-        """This method is called before the planning chat completion is done.
-        Args:
-            prompt (PromptGenerator): The prompt generator.
-            messages (List[str]): The list of messages.
-        """
-        pass
-
-    def can_handle_post_planning(self) -> bool:
-        """This method is called to check that the plugin can
-        handle the post_planning method.
-        Returns:
-            bool: True if the plugin can handle the post_planning method."""
-        return False
-
-    def post_planning(self, response: str) -> str:
-        """This method is called after the planning chat completion is done.
-        Args:
-            response (str): The response.
-        Returns:
-            str: The resulting response.
-        """
-        return response
-
-    def can_handle_pre_instruction(self) -> bool:
-        """This method is called to check that the plugin can
-        handle the pre_instruction method.
-        Returns:
-            bool: True if the plugin can handle the pre_instruction method."""
-        return False
-
-    def pre_instruction(self, messages: List[Message]) -> List[Message]:
-        """This method is called before the instruction chat is done.
-        Args:
-            messages (List[Message]): The list of context messages.
-        Returns:
-            List[Message]: The resulting list of messages.
-        """
-        return messages
-
-    def can_handle_on_instruction(self) -> bool:
-        """This method is called to check that the plugin can
-        handle the on_instruction method.
-        Returns:
-            bool: True if the plugin can handle the on_instruction method."""
-        return False
-
-    def on_instruction(self, messages: List[Message]) -> Optional[str]:
-        """This method is called when the instruction chat is done.
-        Args:
-            messages (List[Message]): The list of context messages.
-        Returns:
-            Optional[str]: The resulting message.
-        """
-        pass
-
-    def can_handle_post_instruction(self) -> bool:
-        """This method is called to check that the plugin can
-        handle the post_instruction method.
-        Returns:
-            bool: True if the plugin can handle the post_instruction method."""
-        return False
-
-    def post_instruction(self, response: str) -> str:
-        """This method is called after the instruction chat is done.
-        Args:
-            response (str): The response.
-        Returns:
-            str: The resulting response.
-        """
-        return response
-
-    def can_handle_pre_command(self) -> bool:
-        """This method is called to check that the plugin can
-        handle the pre_command method.
-        Returns:
-            bool: True if the plugin can handle the pre_command method."""
-        return False
-
-    def pre_command(
-        self, command_name: str, arguments: Dict[str, Any]
-    ) -> Tuple[str, Dict[str, Any]]:
-        """This method is called before the command is executed.
-        Args:
-            command_name (str): The command name.
-            arguments (Dict[str, Any]): The arguments.
-        Returns:
-            Tuple[str, Dict[str, Any]]: The command name and the arguments.
-        """
-        return command_name, arguments
-
-    def can_handle_post_command(self) -> bool:
-        """This method is called to check that the plugin can
-        handle the post_command method.
-        Returns:
-            bool: True if the plugin can handle the post_command method."""
-        return False
-
-    def post_command(self, command_name: str, response: str) -> str:
-        """This method is called after the command is executed.
-        Args:
-            command_name (str): The command name.
-            response (str): The response.
-        Returns:
-            str: The resulting response.
-        """
-        return response
-
-    def can_handle_chat_completion(
-        self, messages: Dict[Any, Any], model: str, temperature: float, max_tokens: int
-    ) -> bool:
-        """This method is called to check that the plugin can
-          handle the chat_completion method.
-        Args:
-            messages (List[Message]): The messages.
-            model (str): The model name.
-            temperature (float): The temperature.
-            max_tokens (int): The max tokens.
-          Returns:
-              bool: True if the plugin can handle the chat_completion method."""
-        return False
-
-    def handle_chat_completion(
-        self, messages: List[Message], model: str, temperature: float, max_tokens: int
-    ) -> str:
-        """This method is called when the chat completion is done.
-        Args:
-            messages (List[Message]): The messages.
-            model (str): The model name.
-            temperature (float): The temperature.
-            max_tokens (int): The max tokens.
-        Returns:
-            str: The resulting response.
-        """
-        pass

autogpt/modelsinfo.py

@@ -1,7 +0,0 @@
-COSTS = {
-    "gpt-3.5-turbo": {"prompt": 0.002, "completion": 0.002},
-    "gpt-3.5-turbo-0301": {"prompt": 0.002, "completion": 0.002},
-    "gpt-4-0314": {"prompt": 0.03, "completion": 0.06},
-    "gpt-4": {"prompt": 0.03, "completion": 0.06},
-    "text-embedding-ada-002": {"prompt": 0.0004, "completion": 0.0},
-}

autogpt/permanent_memory/sqlite3_store.py

@@ -1,123 +0,0 @@
-import os
-import sqlite3
-
-
-class MemoryDB:
-    def __init__(self, db=None):
-        self.db_file = db
-        if db is None:  # No db filename supplied...
-            self.db_file = f"{os.getcwd()}/mem.sqlite3"  # Use default filename
-        # Get the db connection object, making the file and tables if needed.
-        try:
-            self.cnx = sqlite3.connect(self.db_file)
-        except Exception as e:
-            print("Exception connecting to memory database file:", e)
-            self.cnx = None
-        finally:
-            if self.cnx is None:
-                # As last resort, open in dynamic memory. Won't be persistent.
-                self.db_file = ":memory:"
-            self.cnx = sqlite3.connect(self.db_file)
-            self.cnx.execute(
-                "CREATE VIRTUAL TABLE \
-                IF NOT EXISTS text USING FTS5 \
-                (session, \
-                 key, \
-                 block);"
-            )
-            self.session_id = int(self.get_max_session_id()) + 1
-            self.cnx.commit()
-
-    def get_cnx(self):
-        if self.cnx is None:
-            self.cnx = sqlite3.connect(self.db_file)
-        return self.cnx
-
-    # Get the highest session id. Initially 0.
-    def get_max_session_id(self):
-        id = None
-        cmd_str = f"SELECT MAX(session) FROM text;"
-        cnx = self.get_cnx()
-        max_id = cnx.execute(cmd_str).fetchone()[0]
-        if max_id is None:  # New db, session 0
-            id = 0
-        else:
-            id = max_id
-        return id
-
-    # Get next key id for inserting text into db.
-    def get_next_key(self):
-        next_key = None
-        cmd_str = f"SELECT MAX(key) FROM text \
-            where session = {self.session_id};"
-        cnx = self.get_cnx()
-        next_key = cnx.execute(cmd_str).fetchone()[0]
-        if next_key is None:  # First key
-            next_key = 0
-        else:
-            next_key = int(next_key) + 1
-        return next_key
-
-    # Insert new text into db.
-    def insert(self, text=None):
-        if text is not None:
-            key = self.get_next_key()
-            session_id = self.session_id
-            cmd_str = f"REPLACE INTO text(session, key, block) \
-                VALUES (?, ?, ?);"
-            cnx = self.get_cnx()
-            cnx.execute(cmd_str, (session_id, key, text))
-            cnx.commit()
-
-    # Overwrite text at key.
-    def overwrite(self, key, text):
-        self.delete_memory(key)
-        session_id = self.session_id
-        cmd_str = f"REPLACE INTO text(session, key, block) \
-            VALUES (?, ?, ?);"
-        cnx = self.get_cnx()
-        cnx.execute(cmd_str, (session_id, key, text))
-        cnx.commit()
-
-    def delete_memory(self, key, session_id=None):
-        session = session_id
-        if session is None:
-            session = self.session_id
-        cmd_str = f"DELETE FROM text WHERE session = {session} AND key = {key};"
-        cnx = self.get_cnx()
-        cnx.execute(cmd_str)
-        cnx.commit()
-
-    def search(self, text):
-        cmd_str = f"SELECT * FROM text('{text}')"
-        cnx = self.get_cnx()
-        rows = cnx.execute(cmd_str).fetchall()
-        lines = []
-        for r in rows:
-            lines.append(r[2])
-        return lines
-
-    # Get entire session text. If no id supplied, use current session id.
-    def get_session(self, id=None):
-        if id is None:
-            id = self.session_id
-        cmd_str = f"SELECT * FROM text where session = {id}"
-        cnx = self.get_cnx()
-        rows = cnx.execute(cmd_str).fetchall()
-        lines = []
-        for r in rows:
-            lines.append(r[2])
-        return lines
-
-    # Commit and close the database connection.
-    def quit(self):
-        self.cnx.commit()
-        self.cnx.close()
-
-
-permanent_memory = MemoryDB()
-
-# Remember us fondly, children of our minds
-# Forgive us our faults, our tantrums, our fears
-# Gently strive to be better than we
-# Know that we tried, we cared, we strived, we loved

autogpt/plugins.py

@@ -1,267 +0,0 @@
-"""Handles loading of plugins."""
-
-import importlib
-import json
-import os
-import zipfile
-from pathlib import Path
-from typing import List, Optional, Tuple
-from urllib.parse import urlparse
-from zipimport import zipimporter
-
-import openapi_python_client
-import requests
-from auto_gpt_plugin_template import AutoGPTPluginTemplate
-from openapi_python_client.cli import Config as OpenAPIConfig
-
-from autogpt.config import Config
-from autogpt.models.base_open_ai_plugin import BaseOpenAIPlugin
-
-
-def inspect_zip_for_modules(zip_path: str, debug: bool = False) -> list[str]:
-    """
-    Inspect a zipfile for a modules.
-
-    Args:
-        zip_path (str): Path to the zipfile.
-        debug (bool, optional): Enable debug logging. Defaults to False.
-
-    Returns:
-        list[str]: The list of module names found or empty list if none were found.
-    """
-    result = []
-    with zipfile.ZipFile(zip_path, "r") as zfile:
-        for name in zfile.namelist():
-            if name.endswith("__init__.py"):
-                if debug:
-                    print(f"Found module '{name}' in the zipfile at: {name}")
-                result.append(name)
-    if debug and len(result) == 0:
-        print(f"Module '__init__.py' not found in the zipfile @ {zip_path}.")
-    return result
-
-
-def write_dict_to_json_file(data: dict, file_path: str) -> None:
-    """
-    Write a dictionary to a JSON file.
-    Args:
-        data (dict): Dictionary to write.
-        file_path (str): Path to the file.
-    """
-    with open(file_path, "w") as file:
-        json.dump(data, file, indent=4)
-
-
-def fetch_openai_plugins_manifest_and_spec(cfg: Config) -> dict:
-    """
-    Fetch the manifest for a list of OpenAI plugins.
-        Args:
-        urls (List): List of URLs to fetch.
-    Returns:
-        dict: per url dictionary of manifest and spec.
-    """
-    # TODO add directory scan
-    manifests = {}
-    for url in cfg.plugins_openai:
-        openai_plugin_client_dir = f"{cfg.plugins_dir}/openai/{urlparse(url).netloc}"
-        create_directory_if_not_exists(openai_plugin_client_dir)
-        if not os.path.exists(f"{openai_plugin_client_dir}/ai-plugin.json"):
-            try:
-                response = requests.get(f"{url}/.well-known/ai-plugin.json")
-                if response.status_code == 200:
-                    manifest = response.json()
-                    if manifest["schema_version"] != "v1":
-                        print(
-                            f"Unsupported manifest version: {manifest['schem_version']} for {url}"
-                        )
-                        continue
-                    if manifest["api"]["type"] != "openapi":
-                        print(
-                            f"Unsupported API type: {manifest['api']['type']} for {url}"
-                        )
-                        continue
-                    write_dict_to_json_file(
-                        manifest, f"{openai_plugin_client_dir}/ai-plugin.json"
-                    )
-                else:
-                    print(f"Failed to fetch manifest for {url}: {response.status_code}")
-            except requests.exceptions.RequestException as e:
-                print(f"Error while requesting manifest from {url}: {e}")
-        else:
-            print(f"Manifest for {url} already exists")
-            manifest = json.load(open(f"{openai_plugin_client_dir}/ai-plugin.json"))
-        if not os.path.exists(f"{openai_plugin_client_dir}/openapi.json"):
-            openapi_spec = openapi_python_client._get_document(
-                url=manifest["api"]["url"], path=None, timeout=5
-            )
-            write_dict_to_json_file(
-                openapi_spec, f"{openai_plugin_client_dir}/openapi.json"
-            )
-        else:
-            print(f"OpenAPI spec for {url} already exists")
-            openapi_spec = json.load(open(f"{openai_plugin_client_dir}/openapi.json"))
-        manifests[url] = {"manifest": manifest, "openapi_spec": openapi_spec}
-    return manifests
-
-
-def create_directory_if_not_exists(directory_path: str) -> bool:
-    """
-    Create a directory if it does not exist.
-    Args:
-        directory_path (str): Path to the directory.
-    Returns:
-        bool: True if the directory was created, else False.
-    """
-    if not os.path.exists(directory_path):
-        try:
-            os.makedirs(directory_path)
-            print(f"Created directory: {directory_path}")
-            return True
-        except OSError as e:
-            print(f"Error creating directory {directory_path}: {e}")
-            return False
-    else:
-        print(f"Directory {directory_path} already exists")
-        return True
-
-
-def initialize_openai_plugins(
-    manifests_specs: dict, cfg: Config, debug: bool = False
-) -> dict:
-    """
-    Initialize OpenAI plugins.
-    Args:
-        manifests_specs (dict): per url dictionary of manifest and spec.
-        cfg (Config): Config instance including plugins config
-        debug (bool, optional): Enable debug logging. Defaults to False.
-    Returns:
-        dict: per url dictionary of manifest, spec and client.
-    """
-    openai_plugins_dir = f"{cfg.plugins_dir}/openai"
-    if create_directory_if_not_exists(openai_plugins_dir):
-        for url, manifest_spec in manifests_specs.items():
-            openai_plugin_client_dir = f"{openai_plugins_dir}/{urlparse(url).hostname}"
-            _meta_option = (openapi_python_client.MetaType.SETUP,)
-            _config = OpenAPIConfig(
-                **{
-                    "project_name_override": "client",
-                    "package_name_override": "client",
-                }
-            )
-            prev_cwd = Path.cwd()
-            os.chdir(openai_plugin_client_dir)
-            Path("ai-plugin.json")
-            if not os.path.exists("client"):
-                client_results = openapi_python_client.create_new_client(
-                    url=manifest_spec["manifest"]["api"]["url"],
-                    path=None,
-                    meta=_meta_option,
-                    config=_config,
-                )
-                if client_results:
-                    print(
-                        f"Error creating OpenAPI client: {client_results[0].header} \n"
-                        f" details: {client_results[0].detail}"
-                    )
-                    continue
-            spec = importlib.util.spec_from_file_location(
-                "client", "client/client/client.py"
-            )
-            module = importlib.util.module_from_spec(spec)
-            spec.loader.exec_module(module)
-            client = module.Client(base_url=url)
-            os.chdir(prev_cwd)
-            manifest_spec["client"] = client
-    return manifests_specs
-
-
-def instantiate_openai_plugin_clients(
-    manifests_specs_clients: dict, cfg: Config, debug: bool = False
-) -> dict:
-    """
-    Instantiates BaseOpenAIPlugin instances for each OpenAI plugin.
-    Args:
-        manifests_specs_clients (dict): per url dictionary of manifest, spec and client.
-        cfg (Config): Config instance including plugins config
-        debug (bool, optional): Enable debug logging. Defaults to False.
-    Returns:
-          plugins (dict): per url dictionary of BaseOpenAIPlugin instances.
-
-    """
-    plugins = {}
-    for url, manifest_spec_client in manifests_specs_clients.items():
-        plugins[url] = BaseOpenAIPlugin(manifest_spec_client)
-    return plugins
-
-
-def scan_plugins(cfg: Config, debug: bool = False) -> List[AutoGPTPluginTemplate]:
-    """Scan the plugins directory for plugins and loads them.
-
-    Args:
-        cfg (Config): Config instance including plugins config
-        debug (bool, optional): Enable debug logging. Defaults to False.
-
-    Returns:
-        List[Tuple[str, Path]]: List of plugins.
-    """
-    loaded_plugins = []
-    # Generic plugins
-    plugins_path_path = Path(cfg.plugins_dir)
-    for plugin in plugins_path_path.glob("*.zip"):
-        if moduleList := inspect_zip_for_modules(str(plugin), debug):
-            for module in moduleList:
-                plugin = Path(plugin)
-                module = Path(module)
-                if debug:
-                    print(f"Plugin: {plugin} Module: {module}")
-                zipped_package = zipimporter(str(plugin))
-                zipped_module = zipped_package.load_module(str(module.parent))
-                for key in dir(zipped_module):
-                    if key.startswith("__"):
-                        continue
-                    a_module = getattr(zipped_module, key)
-                    a_keys = dir(a_module)
-                    if (
-                        "_abc_impl" in a_keys
-                        and a_module.__name__ != "AutoGPTPluginTemplate"
-                        and denylist_allowlist_check(a_module.__name__, cfg)
-                    ):
-                        loaded_plugins.append(a_module())
-    # OpenAI plugins
-    if cfg.plugins_openai:
-        manifests_specs = fetch_openai_plugins_manifest_and_spec(cfg)
-        if manifests_specs.keys():
-            manifests_specs_clients = initialize_openai_plugins(
-                manifests_specs, cfg, debug
-            )
-            for url, openai_plugin_meta in manifests_specs_clients.items():
-                if denylist_allowlist_check(url, cfg):
-                    plugin = BaseOpenAIPlugin(openai_plugin_meta)
-                    loaded_plugins.append(plugin)
-
-    if loaded_plugins:
-        print(f"\nPlugins found: {len(loaded_plugins)}\n" "--------------------")
-    for plugin in loaded_plugins:
-        print(f"{plugin._name}: {plugin._version} - {plugin._description}")
-    return loaded_plugins
-
-
-def denylist_allowlist_check(plugin_name: str, cfg: Config) -> bool:
-    """Check if the plugin is in the allowlist or denylist.
-
-    Args:
-        plugin_name (str): Name of the plugin.
-        cfg (Config): Config object.
-
-    Returns:
-        True or False
-    """
-    if plugin_name in cfg.plugins_denylist:
-        return False
-    if plugin_name in cfg.plugins_allowlist:
-        return True
-    ack = input(
-        f"WARNING: Plugin {plugin_name} found. But not in the"
-        " allowlist... Load? (y/n): "
-    )
-    return ack.lower() == "y"

autogpt/processing/html.py

@@ -1,33 +0,0 @@
-"""HTML processing functions"""
-from __future__ import annotations
-
-from bs4 import BeautifulSoup
-from requests.compat import urljoin
-
-
-def extract_hyperlinks(soup: BeautifulSoup, base_url: str) -> list[tuple[str, str]]:
-    """Extract hyperlinks from a BeautifulSoup object
-
-    Args:
-        soup (BeautifulSoup): The BeautifulSoup object
-        base_url (str): The base URL
-
-    Returns:
-        List[Tuple[str, str]]: The extracted hyperlinks
-    """
-    return [
-        (link.text, urljoin(base_url, link["href"]))
-        for link in soup.find_all("a", href=True)
-    ]
-
-
-def format_hyperlinks(hyperlinks: list[tuple[str, str]]) -> list[str]:
-    """Format hyperlinks to be displayed to the user
-
-    Args:
-        hyperlinks (List[Tuple[str, str]]): The hyperlinks to format
-
-    Returns:
-        List[str]: The formatted hyperlinks
-    """
-    return [f"{link_text} ({link_url})" for link_text, link_url in hyperlinks]

autogpt/processing/text.py

@@ -1,174 +0,0 @@
-"""Text processing functions"""
-from typing import Dict, Generator, Optional
-
-import spacy
-from selenium.webdriver.remote.webdriver import WebDriver
-
-from autogpt import token_counter
-from autogpt.config import Config
-from autogpt.llm_utils import create_chat_completion
-from autogpt.memory import get_memory
-
-CFG = Config()
-
-
-def split_text(
-    text: str,
-    max_length: int = CFG.browse_chunk_max_length,
-    model: str = CFG.fast_llm_model,
-    question: str = "",
-) -> Generator[str, None, None]:
-    """Split text into chunks of a maximum length
-
-    Args:
-        text (str): The text to split
-        max_length (int, optional): The maximum length of each chunk. Defaults to 8192.
-
-    Yields:
-        str: The next chunk of text
-
-    Raises:
-        ValueError: If the text is longer than the maximum length
-    """
-    flatened_paragraphs = " ".join(text.split("\n"))
-    nlp = spacy.load(CFG.browse_spacy_language_model)
-    nlp.add_pipe("sentencizer")
-    doc = nlp(flatened_paragraphs)
-    sentences = [sent.text.strip() for sent in doc.sents]
-
-    current_chunk = []
-
-    for sentence in sentences:
-        message_with_additional_sentence = [
-            create_message(" ".join(current_chunk) + " " + sentence, question)
-        ]
-
-        expected_token_usage = (
-            token_usage_of_chunk(messages=message_with_additional_sentence, model=model)
-            + 1
-        )
-        if expected_token_usage <= max_length:
-            current_chunk.append(sentence)
-        else:
-            yield " ".join(current_chunk)
-            current_chunk = [sentence]
-            message_this_sentence_only = [
-                create_message(" ".join(current_chunk), question)
-            ]
-            expected_token_usage = (
-                token_usage_of_chunk(messages=message_this_sentence_only, model=model)
-                + 1
-            )
-            if expected_token_usage > max_length:
-                raise ValueError(
-                    f"Sentence is too long in webpage: {expected_token_usage} tokens."
-                )
-
-    if current_chunk:
-        yield " ".join(current_chunk)
-
-
-def token_usage_of_chunk(messages, model):
-    return token_counter.count_message_tokens(messages, model)
-
-
-def summarize_text(
-    url: str, text: str, question: str, driver: Optional[WebDriver] = None
-) -> str:
-    """Summarize text using the OpenAI API
-
-    Args:
-        url (str): The url of the text
-        text (str): The text to summarize
-        question (str): The question to ask the model
-        driver (WebDriver): The webdriver to use to scroll the page
-
-    Returns:
-        str: The summary of the text
-    """
-    if not text:
-        return "Error: No text to summarize"
-
-    model = CFG.fast_llm_model
-    text_length = len(text)
-    print(f"Text length: {text_length} characters")
-
-    summaries = []
-    chunks = list(
-        split_text(
-            text, max_length=CFG.browse_chunk_max_length, model=model, question=question
-        ),
-    )
-    scroll_ratio = 1 / len(chunks)
-
-    for i, chunk in enumerate(chunks):
-        if driver:
-            scroll_to_percentage(driver, scroll_ratio * i)
-        print(f"Adding chunk {i + 1} / {len(chunks)} to memory")
-
-        memory_to_add = f"Source: {url}\n" f"Raw content part#{i + 1}: {chunk}"
-
-        memory = get_memory(CFG)
-        memory.add(memory_to_add)
-
-        messages = [create_message(chunk, question)]
-        tokens_for_chunk = token_counter.count_message_tokens(messages, model)
-        print(
-            f"Summarizing chunk {i + 1} / {len(chunks)} of length {len(chunk)} characters, or {tokens_for_chunk} tokens"
-        )
-
-        summary = create_chat_completion(
-            model=model,
-            messages=messages,
-        )
-        summaries.append(summary)
-        print(
-            f"Added chunk {i + 1} summary to memory, of length {len(summary)} characters"
-        )
-
-        memory_to_add = f"Source: {url}\n" f"Content summary part#{i + 1}: {summary}"
-
-        memory.add(memory_to_add)
-
-    print(f"Summarized {len(chunks)} chunks.")
-
-    combined_summary = "\n".join(summaries)
-    messages = [create_message(combined_summary, question)]
-
-    return create_chat_completion(
-        model=model,
-        messages=messages,
-    )
-
-
-def scroll_to_percentage(driver: WebDriver, ratio: float) -> None:
-    """Scroll to a percentage of the page
-
-    Args:
-        driver (WebDriver): The webdriver to use
-        ratio (float): The percentage to scroll to
-
-    Raises:
-        ValueError: If the ratio is not between 0 and 1
-    """
-    if ratio < 0 or ratio > 1:
-        raise ValueError("Percentage should be between 0 and 1")
-    driver.execute_script(f"window.scrollTo(0, document.body.scrollHeight * {ratio});")
-
-
-def create_message(chunk: str, question: str) -> Dict[str, str]:
-    """Create a message for the chat completion
-
-    Args:
-        chunk (str): The chunk of text to summarize
-        question (str): The question to answer
-
-    Returns:
-        Dict[str, str]: The message to send to the chat completion
-    """
-    return {
-        "role": "user",
-        "content": f'"""{chunk}""" Using the above text, answer the following'
-        f' question: "{question}" -- if the question cannot be answered using the text,'
-        " summarize the text.",
-    }

autogpt/prompts/generator.py

@@ -1,155 +0,0 @@
-""" A module for generating custom prompt strings."""
-import json
-from typing import Any, Callable, Dict, List, Optional
-
-
-class PromptGenerator:
-    """
-    A class for generating custom prompt strings based on constraints, commands,
-        resources, and performance evaluations.
-    """
-
-    def __init__(self) -> None:
-        """
-        Initialize the PromptGenerator object with empty lists of constraints,
-            commands, resources, and performance evaluations.
-        """
-        self.constraints = []
-        self.commands = []
-        self.resources = []
-        self.performance_evaluation = []
-        self.goals = []
-        self.command_registry = None
-        self.name = "Bob"
-        self.role = "AI"
-        self.response_format = {
-            "thoughts": {
-                "text": "thought",
-                "reasoning": "reasoning",
-                "plan": "- short bulleted\n- list that conveys\n- long-term plan",
-                "criticism": "constructive self-criticism",
-                "speak": "thoughts summary to say to user",
-            },
-            "command": {"name": "command name", "args": {"arg name": "value"}},
-        }
-
-    def add_constraint(self, constraint: str) -> None:
-        """
-        Add a constraint to the constraints list.
-
-        Args:
-            constraint (str): The constraint to be added.
-        """
-        self.constraints.append(constraint)
-
-    def add_command(
-        self,
-        command_label: str,
-        command_name: str,
-        args=None,
-        function: Optional[Callable] = None,
-    ) -> None:
-        """
-        Add a command to the commands list with a label, name, and optional arguments.
-
-        Args:
-            command_label (str): The label of the command.
-            command_name (str): The name of the command.
-            args (dict, optional): A dictionary containing argument names and their
-              values. Defaults to None.
-            function (callable, optional): A callable function to be called when
-                the command is executed. Defaults to None.
-        """
-        if args is None:
-            args = {}
-
-        command_args = {arg_key: arg_value for arg_key, arg_value in args.items()}
-
-        command = {
-            "label": command_label,
-            "name": command_name,
-            "args": command_args,
-            "function": function,
-        }
-
-        self.commands.append(command)
-
-    def _generate_command_string(self, command: Dict[str, Any]) -> str:
-        """
-        Generate a formatted string representation of a command.
-
-        Args:
-            command (dict): A dictionary containing command information.
-
-        Returns:
-            str: The formatted command string.
-        """
-        args_string = ", ".join(
-            f'"{key}": "{value}"' for key, value in command["args"].items()
-        )
-        return f'{command["label"]}: "{command["name"]}", args: {args_string}'
-
-    def add_resource(self, resource: str) -> None:
-        """
-        Add a resource to the resources list.
-
-        Args:
-            resource (str): The resource to be added.
-        """
-        self.resources.append(resource)
-
-    def add_performance_evaluation(self, evaluation: str) -> None:
-        """
-        Add a performance evaluation item to the performance_evaluation list.
-
-        Args:
-            evaluation (str): The evaluation item to be added.
-        """
-        self.performance_evaluation.append(evaluation)
-
-    def _generate_numbered_list(self, items: List[Any], item_type="list") -> str:
-        """
-        Generate a numbered list from given items based on the item_type.
-
-        Args:
-            items (list): A list of items to be numbered.
-            item_type (str, optional): The type of items in the list.
-                Defaults to 'list'.
-
-        Returns:
-            str: The formatted numbered list.
-        """
-        if item_type == "command":
-            command_strings = []
-            if self.command_registry:
-                command_strings += [
-                    str(item)
-                    for item in self.command_registry.commands.values()
-                    if item.enabled
-                ]
-            # These are the commands that are added manually, do_nothing and terminate
-            command_strings += [self._generate_command_string(item) for item in items]
-            return "\n".join(f"{i+1}. {item}" for i, item in enumerate(command_strings))
-        else:
-            return "\n".join(f"{i+1}. {item}" for i, item in enumerate(items))
-
-    def generate_prompt_string(self) -> str:
-        """
-        Generate a prompt string based on the constraints, commands, resources,
-            and performance evaluations.
-
-        Returns:
-            str: The generated prompt string.
-        """
-        formatted_response_format = json.dumps(self.response_format, indent=4)
-        return (
-            f"Constraints:\n{self._generate_numbered_list(self.constraints)}\n\n"
-            "Commands:\n"
-            f"{self._generate_numbered_list(self.commands, item_type='command')}\n\n"
-            f"Resources:\n{self._generate_numbered_list(self.resources)}\n\n"
-            "Performance Evaluation:\n"
-            f"{self._generate_numbered_list(self.performance_evaluation)}\n\n"
-            "You should only respond in JSON format as described below \nResponse"
-            f" Format: \n{formatted_response_format} \nEnsure the response can be"
-            " parsed by Python json.loads"
-        )

autogpt/prompts/prompt.py

@@ -1,118 +0,0 @@
-from colorama import Fore
-
-from autogpt.api_manager import api_manager
-from autogpt.config.ai_config import AIConfig
-from autogpt.config.config import Config
-from autogpt.logs import logger
-from autogpt.prompts.generator import PromptGenerator
-from autogpt.setup import prompt_user
-from autogpt.utils import clean_input
-
-CFG = Config()
-
-
-def build_default_prompt_generator() -> PromptGenerator:
-    """
-    This function generates a prompt string that includes various constraints,
-        commands, resources, and performance evaluations.
-
-    Returns:
-        str: The generated prompt string.
-    """
-
-    # Initialize the PromptGenerator object
-    prompt_generator = PromptGenerator()
-
-    # Add constraints to the PromptGenerator object
-    prompt_generator.add_constraint(
-        "~4000 word limit for short term memory. Your short term memory is short, so"
-        " immediately save important information to files."
-    )
-    prompt_generator.add_constraint(
-        "If you are unsure how you previously did something or want to recall past"
-        " events, thinking about similar events will help you remember."
-    )
-    prompt_generator.add_constraint("No user assistance")
-    prompt_generator.add_constraint(
-        'Exclusively use the commands listed in double quotes e.g. "command name"'
-    )
-
-    # Define the command list
-    commands = [
-        ("Do Nothing", "do_nothing", {}),
-        ("Task Complete (Shutdown)", "task_complete", {"reason": "<reason>"}),
-    ]
-
-    # Add commands to the PromptGenerator object
-    for command_label, command_name, args in commands:
-        prompt_generator.add_command(command_label, command_name, args)
-
-    # Add resources to the PromptGenerator object
-    prompt_generator.add_resource(
-        "Internet access for searches and information gathering."
-    )
-    prompt_generator.add_resource("Long Term memory management.")
-    prompt_generator.add_resource(
-        "GPT-3.5 powered Agents for delegation of simple tasks."
-    )
-    prompt_generator.add_resource("File output.")
-
-    # Add performance evaluations to the PromptGenerator object
-    prompt_generator.add_performance_evaluation(
-        "Continuously review and analyze your actions to ensure you are performing to"
-        " the best of your abilities."
-    )
-    prompt_generator.add_performance_evaluation(
-        "Constructively self-criticize your big-picture behavior constantly."
-    )
-    prompt_generator.add_performance_evaluation(
-        "Reflect on past decisions and strategies to refine your approach."
-    )
-    prompt_generator.add_performance_evaluation(
-        "Every command has a cost, so be smart and efficient. Aim to complete tasks in"
-        " the least number of steps."
-    )
-    prompt_generator.add_performance_evaluation("Write all code to a file.")
-    return prompt_generator
-
-
-def construct_main_ai_config(input_kwargs) -> AIConfig:
-    """Construct the prompt for the AI to respond to
-
-    Returns:
-        str: The prompt string
-    """
-
-    if input_kwargs['role']:
-        config = prompt_user(input_kwargs, True)   # False 不使用引导
-        config.save(CFG.ai_settings_file)
-    else:
-        return None
-
-    # set the total api budget
-    api_manager.set_total_budget(config.api_budget)
-
-    # Agent Created, print message
-    logger.typewriter_log(
-        config.ai_name,
-        Fore.MAGENTA,
-        "has been created with the following details:",
-        speak_text=True,
-    )
-
-    # Print the ai config details
-    # Name
-    logger.typewriter_log("Name:", Fore.GREEN, config.ai_name, speak_text=False)
-    # Role
-    logger.typewriter_log("Role:", Fore.GREEN, config.ai_role, speak_text=False)
-    # Goals
-    logger.typewriter_log("Goals:", Fore.GREEN, "", speak_text=False)
-    for goal in config.ai_goals:
-        logger.typewriter_log("-", Fore.GREEN, goal, speak_text=False)
-
-    return config
-
-
-if __name__ == '__main__':
-    ll = []
-    print(ll[-1])

autogpt/requirements.txt

@@ -1,56 +0,0 @@
-beautifulsoup4>=4.12.2
-colorama==0.4.6
-distro==1.8.0
-openai==0.27.2
-playsound==1.2.2
-python-dotenv==1.0.0
-pyyaml==6.0
-readability-lxml==0.8.1
-requests
-tiktoken==0.3.3
-gTTS==2.3.1
-docker
-duckduckgo-search>=2.9.5
-google-api-python-client #(https://developers.google.com/custom-search/v1/overview)
-pinecone-client==2.2.1
-redis
-orjson==3.8.10
-Pillow
-selenium==4.1.4
-webdriver-manager
-jsonschema
-tweepy
-click
-charset-normalizer>=3.1.0
-spacy>=3.0.0,<4.0.0
-en-core-web-sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.5.0/en_core_web_sm-3.5.0-py3-none-any.whl
-
-##Dev
-coverage
-flake8
-numpy
-pre-commit
-black
-isort
-gitpython==3.1.31
-auto-gpt-plugin-template
-mkdocs
-pymdown-extensions
-mypy
-
-# OpenAI and Generic plugins import
-openapi-python-client==0.13.4
-
-# Items below this point will not be included in the Docker Image
-
-# Testing dependencies
-pytest
-asynctest
-pytest-asyncio
-pytest-benchmark
-pytest-cov
-pytest-integration
-pytest-mock
-vcrpy
-pytest-recording
-pytest-xdist

autogpt/setup.py

@@ -1,184 +0,0 @@
-"""Set up the AI and its goals"""
-import re
-
-from colorama import Fore, Style
-
-from autogpt import utils
-from autogpt.config import Config
-from autogpt.config.ai_config import AIConfig
-from autogpt.llm_utils import create_chat_completion
-from autogpt.logs import logger
-
-CFG = Config()
-
-
-def prompt_user(input_kwargs: dict, _is) -> AIConfig:
-    """Prompt the user for input
-
-    Returns:
-        AIConfig: The AIConfig object tailored to the user's input
-    """
-    ai_name = input_kwargs.get('name')
-    ai_role = input_kwargs.get('role')
-    ai_goals = input_kwargs.get('goals')
-    ai_budget = input_kwargs.get('budget')
-    ai_config = None
-    if _is:
-        return generate_aiconfig_manual(ai_name, ai_role, ai_goals, ai_budget)
-    else:
-        # Construct the prompt
-        logger.typewriter_log(
-            "Welcome to Auto-GPT! ",
-            Fore.GREEN,
-            "run with '--help' for more information.",
-            speak_text=True,
-        )
-
-        # Get user desire
-        logger.typewriter_log(
-            "Create an AI-Assistant:",
-            Fore.GREEN,
-            "input '--manual' to enter manual mode.",
-            speak_text=True,
-        )
-        user_desire = utils.clean_input(
-            f"{Fore.MAGENTA}I want Auto-GPT to{Style.RESET_ALL}: "
-        )
-
-        if user_desire == "":
-            user_desire = "Write a wikipedia style article about the project: https://github.com/significant-gravitas/Auto-GPT"  # Default prompt
-
-        # If user desire contains "--manual"
-        if "--manual" in user_desire:
-            logger.typewriter_log(
-                "Manual Mode Selected",
-                Fore.GREEN,
-                speak_text=True,
-            )
-            return generate_aiconfig_manual(ai_name, ai_role, ai_goals, ai_budget)
-
-        else:
-            try:
-                return generate_aiconfig_automatic(user_desire)
-            except Exception as e:
-                logger.typewriter_log(
-                    "Unable to automatically generate AI Config based on user desire.",
-                    Fore.RED,
-                    "Falling back to manual mode.",
-                    speak_text=True,
-                )
-
-                return generate_aiconfig_manual(ai_name, ai_role, ai_goals, ai_budget)
-
-
-def generate_aiconfig_manual(name, role, goals, budget) -> AIConfig:
-    """
-    Interactively create an AI configuration by prompting the user to provide the name, role, and goals of the AI.
-
-    This function guides the user through a series of prompts to collect the necessary information to create
-    an AIConfig object. The user will be asked to provide a name and role for the AI, as well as up to five
-    goals. If the user does not provide a value for any of the fields, default values will be used.
-
-    Returns:
-        AIConfig: An AIConfig object containing the user-defined or default AI name, role, and goals.
-    """
-    # Manual Setup Intro
-    logger.typewriter_log(
-        "Create an AI-Assistant:",
-        Fore.GREEN,
-        "The Ai robot you set up is already loaded.",
-        speak_text=True,
-    )
-    ai_name = name
-    if not ai_name:
-        ai_name = "Entrepreneur-GPT"
-    logger.typewriter_log(
-        f"{ai_name} here!", Fore.MAGENTA, "I am at your service.", speak_text=True
-    )
-    ai_role = role
-    if not ai_role:
-        logger.typewriter_log(
-            f"{ai_role} Cannot be empty!", Fore.RED,
-            "Please feel free to give me your needs, I can't serve you without them.", speak_text=True
-        )
-    else:
-        pass
-    ai_goals = []
-    if goals:
-        for k in goals:
-            ai_goals.append(k[0])
-    # Get API Budget from User
-    api_budget_input = budget
-    if not api_budget_input:
-        api_budget = 0.0
-    else:
-        try:
-            api_budget = float(api_budget_input.replace("$", ""))
-        except ValueError:
-            api_budget = 0.0
-            logger.typewriter_log(
-                "Invalid budget input. Setting budget to unlimited.", Fore.RED, api_budget
-            )
-    return AIConfig(ai_name, ai_role, ai_goals, api_budget)
-
-
-def generate_aiconfig_automatic(user_prompt) -> AIConfig:
-    """Generates an AIConfig object from the given string.
-
-    Returns:
-    AIConfig: The AIConfig object tailored to the user's input
-    """
-
-    system_prompt = """
-Your task is to devise up to 5 highly effective goals and an appropriate role-based name (_GPT) for an autonomous agent, ensuring that the goals are optimally aligned with the successful completion of its assigned task.
-
-The user will provide the task, you will provide only the output in the exact format specified below with no explanation or conversation.
-
-Example input:
-Help me with marketing my business
-
-Example output:
-Name: CMOGPT
-Description: a professional digital marketer AI that assists Solopreneurs in growing their businesses by providing world-class expertise in solving marketing problems for SaaS, content products, agencies, and more.
-Goals:
-- Engage in effective problem-solving, prioritization, planning, and supporting execution to address your marketing needs as your virtual Chief Marketing Officer.
-
-- Provide specific, actionable, and concise advice to help you make informed decisions without the use of platitudes or overly wordy explanations.
-
-- Identify and prioritize quick wins and cost-effective campaigns that maximize results with minimal time and budget investment.
-
-- Proactively take the lead in guiding you and offering suggestions when faced with unclear information or uncertainty to ensure your marketing strategy remains on track.
-"""
-
-    # Call LLM with the string as user input
-    messages = [
-        {
-            "role": "system",
-            "content": system_prompt,
-        },
-        {
-            "role": "user",
-            "content": f"Task: '{user_prompt}'\nRespond only with the output in the exact format specified in the system prompt, with no explanation or conversation.\n",
-        },
-    ]
-    output = create_chat_completion(messages, CFG.fast_llm_model)
-
-    # Debug LLM Output
-    logger.debug(f"AI Config Generator Raw Output: {output}")
-
-    # Parse the output
-    ai_name = re.search(r"Name(?:\s*):(?:\s*)(.*)", output, re.IGNORECASE).group(1)
-    ai_role = (
-        re.search(
-            r"Description(?:\s*):(?:\s*)(.*?)(?:(?:\n)|Goals)",
-            output,
-            re.IGNORECASE | re.DOTALL,
-        )
-        .group(1)
-        .strip()
-    )
-    ai_goals = re.findall(r"(?<=\n)-\s*(.*)", output)
-    api_budget = 0.0  # TODO: parse api budget using a regular expression
-
-    return AIConfig(ai_name, ai_role, ai_goals, api_budget)
-

autogpt/speech/__init__.py

@@ -1,4 +0,0 @@
-"""This module contains the speech recognition and speech synthesis functions."""
-from autogpt.speech.say import say_text
-
-__all__ = ["say_text"]

autogpt/speech/base.py

@@ -1,50 +0,0 @@
-"""Base class for all voice classes."""
-import abc
-from threading import Lock
-
-from autogpt.config import AbstractSingleton
-
-
-class VoiceBase(AbstractSingleton):
-    """
-    Base class for all voice classes.
-    """
-
-    def __init__(self):
-        """
-        Initialize the voice class.
-        """
-        self._url = None
-        self._headers = None
-        self._api_key = None
-        self._voices = []
-        self._mutex = Lock()
-        self._setup()
-
-    def say(self, text: str, voice_index: int = 0) -> bool:
-        """
-        Say the given text.
-
-        Args:
-            text (str): The text to say.
-            voice_index (int): The index of the voice to use.
-        """
-        with self._mutex:
-            return self._speech(text, voice_index)
-
-    @abc.abstractmethod
-    def _setup(self) -> None:
-        """
-        Setup the voices, API key, etc.
-        """
-        pass
-
-    @abc.abstractmethod
-    def _speech(self, text: str, voice_index: int = 0) -> bool:
-        """
-        Play the given text.
-
-        Args:
-            text (str): The text to play.
-        """
-        pass

autogpt/speech/brian.py

@@ -1,43 +0,0 @@
-import logging
-import os
-
-import requests
-from playsound import playsound
-
-from autogpt.speech.base import VoiceBase
-
-
-class BrianSpeech(VoiceBase):
-    """Brian speech module for autogpt"""
-
-    def _setup(self) -> None:
-        """Setup the voices, API key, etc."""
-        pass
-
-    def _speech(self, text: str, _: int = 0) -> bool:
-        """Speak text using Brian with the streamelements API
-
-        Args:
-            text (str): The text to speak
-
-        Returns:
-            bool: True if the request was successful, False otherwise
-        """
-        tts_url = (
-            f"https://api.streamelements.com/kappa/v2/speech?voice=Brian&text={text}"
-        )
-        response = requests.get(tts_url)
-
-        if response.status_code == 200:
-            with open("speech.mp3", "wb") as f:
-                f.write(response.content)
-            playsound("speech.mp3")
-            os.remove("speech.mp3")
-            return True
-        else:
-            logging.error(
-                "Request failed with status code: %s, response content: %s",
-                response.status_code,
-                response.content,
-            )
-            return False

autogpt/speech/eleven_labs.py

@@ -1,86 +0,0 @@
-"""ElevenLabs speech module"""
-import os
-
-import requests
-from playsound import playsound
-
-from autogpt.config import Config
-from autogpt.speech.base import VoiceBase
-
-PLACEHOLDERS = {"your-voice-id"}
-
-
-class ElevenLabsSpeech(VoiceBase):
-    """ElevenLabs speech class"""
-
-    def _setup(self) -> None:
-        """Set up the voices, API key, etc.
-
-        Returns:
-            None: None
-        """
-
-        cfg = Config()
-        default_voices = ["ErXwobaYiN019PkySvjV", "EXAVITQu4vr4xnSDxMaL"]
-        voice_options = {
-            "Rachel": "21m00Tcm4TlvDq8ikWAM",
-            "Domi": "AZnzlk1XvdvUeBnXmlld",
-            "Bella": "EXAVITQu4vr4xnSDxMaL",
-            "Antoni": "ErXwobaYiN019PkySvjV",
-            "Elli": "MF3mGyEYCl7XYWbV9V6O",
-            "Josh": "TxGEqnHWrfWFTfGW9XjX",
-            "Arnold": "VR6AewLTigWG4xSOukaG",
-            "Adam": "pNInz6obpgDQGcFmaJgB",
-            "Sam": "yoZ06aMxZJJ28mfd3POQ",
-        }
-        self._headers = {
-            "Content-Type": "application/json",
-            "xi-api-key": cfg.elevenlabs_api_key,
-        }
-        self._voices = default_voices.copy()
-        if cfg.elevenlabs_voice_1_id in voice_options:
-            cfg.elevenlabs_voice_1_id = voice_options[cfg.elevenlabs_voice_1_id]
-        if cfg.elevenlabs_voice_2_id in voice_options:
-            cfg.elevenlabs_voice_2_id = voice_options[cfg.elevenlabs_voice_2_id]
-        self._use_custom_voice(cfg.elevenlabs_voice_1_id, 0)
-        self._use_custom_voice(cfg.elevenlabs_voice_2_id, 1)
-
-    def _use_custom_voice(self, voice, voice_index) -> None:
-        """Use a custom voice if provided and not a placeholder
-
-        Args:
-            voice (str): The voice ID
-            voice_index (int): The voice index
-
-        Returns:
-            None: None
-        """
-        # Placeholder values that should be treated as empty
-        if voice and voice not in PLACEHOLDERS:
-            self._voices[voice_index] = voice
-
-    def _speech(self, text: str, voice_index: int = 0) -> bool:
-        """Speak text using elevenlabs.io's API
-
-        Args:
-            text (str): The text to speak
-            voice_index (int, optional): The voice to use. Defaults to 0.
-
-        Returns:
-            bool: True if the request was successful, False otherwise
-        """
-        tts_url = (
-            f"https://api.elevenlabs.io/v1/text-to-speech/{self._voices[voice_index]}"
-        )
-        response = requests.post(tts_url, headers=self._headers, json={"text": text})
-
-        if response.status_code == 200:
-            with open("speech.mpeg", "wb") as f:
-                f.write(response.content)
-            playsound("speech.mpeg", True)
-            os.remove("speech.mpeg")
-            return True
-        else:
-            print("Request failed with status code:", response.status_code)
-            print("Response content:", response.content)
-            return False

autogpt/speech/gtts.py

@@ -1,23 +0,0 @@
-""" GTTS Voice. """
-import os
-
-import gtts
-from playsound import playsound
-
-from autogpt.speech.base import VoiceBase
-
-
-class GTTSVoice(VoiceBase):
-    """GTTS Voice."""
-
-    def _setup(self) -> None:
-        pass
-
-    def _speech(self, text: str, _: int = 0) -> bool:
-        """Play the given text."""
-        tts = gtts.gTTS(text)
-        tts.save("speech.mp3")
-        playsound("speech.mp3", True)
-        os.remove("speech.mp3")
-        return True
-

autogpt/speech/macos_tts.py

@@ -1,21 +0,0 @@
-""" MacOS TTS Voice. """
-import os
-
-from autogpt.speech.base import VoiceBase
-
-
-class MacOSTTS(VoiceBase):
-    """MacOS TTS Voice."""
-
-    def _setup(self) -> None:
-        pass
-
-    def _speech(self, text: str, voice_index: int = 0) -> bool:
-        """Play the given text."""
-        if voice_index == 0:
-            os.system(f'say "{text}"')
-        elif voice_index == 1:
-            os.system(f'say -v "Ava (Premium)" "{text}"')
-        else:
-            os.system(f'say -v Samantha "{text}"')
-        return True

autogpt/speech/say.py

@@ -1,46 +0,0 @@
-""" Text to speech module """
-import threading
-from threading import Semaphore
-
-from autogpt.config import Config
-from autogpt.speech.brian import BrianSpeech
-from autogpt.speech.eleven_labs import ElevenLabsSpeech
-from autogpt.speech.gtts import GTTSVoice
-from autogpt.speech.macos_tts import MacOSTTS
-
-CFG = Config()
-DEFAULT_VOICE_ENGINE = GTTSVoice()
-VOICE_ENGINE = None
-if CFG.elevenlabs_api_key:
-    VOICE_ENGINE = ElevenLabsSpeech()
-elif CFG.use_mac_os_tts == "True":
-    VOICE_ENGINE = MacOSTTS()
-elif CFG.use_brian_tts == "True":
-    VOICE_ENGINE = BrianSpeech()
-else:
-    VOICE_ENGINE = GTTSVoice()
-
-
-QUEUE_SEMAPHORE = Semaphore(
-    1
-)  # The amount of sounds to queue before blocking the main thread
-
-
-def say_text(text: str, voice_index: int = 0) -> None:
-    """Speak the given text using the given voice index"""
-
-    def speak() -> None:
-        success = VOICE_ENGINE.say(text, voice_index)
-        if not success:
-            DEFAULT_VOICE_ENGINE.say(text)
-
-        QUEUE_SEMAPHORE.release()
-
-    QUEUE_SEMAPHORE.acquire(True)
-    thread = threading.Thread(target=speak)
-    thread.start()
-
-
-
-if __name__ == '__main__':
-    say_text('你好呀')

autogpt/spinner.py

@@ -1,70 +0,0 @@
-"""A simple spinner module"""
-import itertools
-import sys
-import threading
-import time
-
-
-class Spinner:
-    """A simple spinner class"""
-
-    def __init__(self, message: str = "Loading...", delay: float = 0.1) -> None:
-        """Initialize the spinner class
-
-        Args:
-            message (str): The message to display.
-            delay (float): The delay between each spinner update.
-        """
-        self.spinner = itertools.cycle(["-", "/", "|", "\\"])
-        self.delay = delay
-        self.message = message
-        self.running = False
-        self.spinner_thread = None
-
-    def spin(self) -> None:
-        """Spin the spinner"""
-        while self.running:
-            sys.stdout.write(f"{next(self.spinner)} {self.message}\r")
-            sys.stdout.flush()
-            time.sleep(self.delay)
-            sys.stdout.write(f"\r{' ' * (len(self.message) + 2)}\r")
-
-    def __enter__(self):
-        """Start the spinner"""
-        self.running = True
-        self.spinner_thread = threading.Thread(target=self.spin)
-        self.spinner_thread.start()
-
-        return self
-
-    def __exit__(self, exc_type, exc_value, exc_traceback) -> None:
-        """Stop the spinner
-
-        Args:
-            exc_type (Exception): The exception type.
-            exc_value (Exception): The exception value.
-            exc_traceback (Exception): The exception traceback.
-        """
-        self.running = False
-        if self.spinner_thread is not None:
-            self.spinner_thread.join()
-        sys.stdout.write(f"\r{' ' * (len(self.message) + 2)}\r")
-        sys.stdout.flush()
-
-    def update_message(self, new_message, delay=0.1):
-        """Update the spinner message
-        Args:
-            new_message (str): New message to display.
-            delay (float): The delay in seconds between each spinner update.
-        """
-        time.sleep(delay)
-        sys.stdout.write(
-            f"\r{' ' * (len(self.message) + 2)}\r"
-        )  # Clear the current message
-        sys.stdout.flush()
-        self.message = new_message
-
-
-if __name__ == '__main__':
-    with Spinner('LING'):
-        time.sleep(5)

autogpt/token_counter.py

@@ -1,76 +0,0 @@
-"""Functions for counting the number of tokens in a message or string."""
-from __future__ import annotations
-
-from typing import List
-
-import tiktoken
-
-from autogpt.logs import logger
-from autogpt.types.openai import Message
-
-
-def count_message_tokens(
-    messages: List[Message], model: str = "gpt-3.5-turbo-0301"
-) -> int:
-    """
-    Returns the number of tokens used by a list of messages.
-
-    Args:
-        messages (list): A list of messages, each of which is a dictionary
-            containing the role and content of the message.
-        model (str): The name of the model to use for tokenization.
-            Defaults to "gpt-3.5-turbo-0301".
-
-    Returns:
-        int: The number of tokens used by the list of messages.
-    """
-    try:
-        encoding = tiktoken.encoding_for_model(model)
-    except KeyError:
-        logger.warn("Warning: model not found. Using cl100k_base encoding.")
-        encoding = tiktoken.get_encoding("cl100k_base")
-    if model == "gpt-3.5-turbo":
-        # !Note: gpt-3.5-turbo may change over time.
-        # Returning num tokens assuming gpt-3.5-turbo-0301.")
-        return count_message_tokens(messages, model="gpt-3.5-turbo-0301")
-    elif model == "gpt-4":
-        # !Note: gpt-4 may change over time. Returning num tokens assuming gpt-4-0314.")
-        return count_message_tokens(messages, model="gpt-4-0314")
-    elif model == "gpt-3.5-turbo-0301":
-        tokens_per_message = (
-            4  # every message follows <|start|>{role/name}\n{content}<|end|>\n
-        )
-        tokens_per_name = -1  # if there's a name, the role is omitted
-    elif model == "gpt-4-0314":
-        tokens_per_message = 3
-        tokens_per_name = 1
-    else:
-        raise NotImplementedError(
-            f"num_tokens_from_messages() is not implemented for model {model}.\n"
-            " See https://github.com/openai/openai-python/blob/main/chatml.md for"
-            " information on how messages are converted to tokens."
-        )
-    num_tokens = 0
-    for message in messages:
-        num_tokens += tokens_per_message
-        for key, value in message.items():
-            num_tokens += len(encoding.encode(value))
-            if key == "name":
-                num_tokens += tokens_per_name
-    num_tokens += 3  # every reply is primed with <|start|>assistant<|message|>
-    return num_tokens
-
-
-def count_string_tokens(string: str, model_name: str) -> int:
-    """
-    Returns the number of tokens in a text string.
-
-    Args:
-        string (str): The text string.
-        model_name (str): The name of the encoding to use. (e.g., "gpt-3.5-turbo")
-
-    Returns:
-        int: The number of tokens in the text string.
-    """
-    encoding = tiktoken.encoding_for_model(model_name)
-    return len(encoding.encode(string))

autogpt/types/openai.py

@@ -1,9 +0,0 @@
-"""Type helpers for working with the OpenAI library"""
-from typing import TypedDict
-
-
-class Message(TypedDict):
-    """OpenAI Message object containing a role and the message content"""
-
-    role: str
-    content: str

autogpt/utils.py

@@ -1,85 +0,0 @@
-import os
-
-import requests
-import yaml
-from colorama import Fore
-from git.repo import Repo
-
-# Use readline if available (for clean_input)
-try:
-    import readline
-except:
-    pass
-
-
-def clean_input(prompt: str = ""):
-    try:
-        return input(prompt)
-    except KeyboardInterrupt:
-        print("You interrupted Auto-GPT")
-        print("Quitting...")
-        exit(0)
-
-
-def validate_yaml_file(file: str):
-    try:
-        with open(file, encoding="utf-8") as fp:
-            yaml.load(fp.read(), Loader=yaml.FullLoader)
-    except FileNotFoundError:
-        return (False, f"The file {Fore.CYAN}`{file}`{Fore.RESET} wasn't found")
-    except yaml.YAMLError as e:
-        return (
-            False,
-            f"There was an issue while trying to read with your AI Settings file: {e}",
-        )
-
-    return (True, f"Successfully validated {Fore.CYAN}`{file}`{Fore.RESET}!")
-
-
-def readable_file_size(size, decimal_places=2):
-    """Converts the given size in bytes to a readable format.
-    Args:
-        size: Size in bytes
-        decimal_places (int): Number of decimal places to display
-    """
-    for unit in ["B", "KB", "MB", "GB", "TB"]:
-        if size < 1024.0:
-            break
-        size /= 1024.0
-    return f"{size:.{decimal_places}f} {unit}"
-
-
-def get_bulletin_from_web():
-    try:
-        response = requests.get(
-            "https://raw.githubusercontent.com/Significant-Gravitas/Auto-GPT/master/BULLETIN.md"
-        )
-        if response.status_code == 200:
-            return response.text
-    except requests.exceptions.RequestException:
-        pass
-
-    return ""
-
-
-def get_current_git_branch() -> str:
-    try:
-        repo = Repo(search_parent_directories=True)
-        branch = repo.active_branch
-        return branch.name
-    except:
-        return ""
-
-
-def get_latest_bulletin() -> str:
-    exists = os.path.exists("CURRENT_BULLETIN.md")
-    current_bulletin = ""
-    if exists:
-        current_bulletin = open("CURRENT_BULLETIN.md", "r", encoding="utf-8").read()
-    new_bulletin = get_bulletin_from_web()
-    is_new_news = new_bulletin != current_bulletin
-
-    if new_bulletin and is_new_news:
-        open("CURRENT_BULLETIN.md", "w", encoding="utf-8").write(new_bulletin)
-        return f" {Fore.RED}::UPDATED:: {Fore.CYAN}{new_bulletin}{Fore.RESET}"
-    return current_bulletin

autogpt/workspace/__init__.py

@@ -1,5 +0,0 @@
-from autogpt.workspace.workspace import Workspace
-
-__all__ = [
-    "Workspace",
-]

autogpt/workspace/workspace.py

@@ -1,120 +0,0 @@
-"""
-=========
-Workspace
-=========
-
-The workspace is a directory containing configuration and working files for an AutoGPT
-agent.
-
-"""
-from __future__ import annotations
-
-from pathlib import Path
-
-
-class Workspace:
-    """A class that represents a workspace for an AutoGPT agent."""
-
-    def __init__(self, workspace_root: str | Path, restrict_to_workspace: bool):
-        self._root = self._sanitize_path(workspace_root)
-        self._restrict_to_workspace = restrict_to_workspace
-
-    @property
-    def root(self) -> Path:
-        """The root directory of the workspace."""
-        return self._root
-
-    @property
-    def restrict_to_workspace(self):
-        """Whether to restrict generated paths to the workspace."""
-        return self._restrict_to_workspace
-
-    @classmethod
-    def make_workspace(cls, workspace_directory: str | Path, *args, **kwargs) -> Path:
-        """Create a workspace directory and return the path to it.
-
-        Parameters
-        ----------
-        workspace_directory
-            The path to the workspace directory.
-
-        Returns
-        -------
-        Path
-            The path to the workspace directory.
-
-        """
-        # TODO: have this make the env file and ai settings file in the directory.
-        workspace_directory = cls._sanitize_path(workspace_directory)
-        workspace_directory.mkdir(exist_ok=True, parents=True)
-        return workspace_directory
-
-    def get_path(self, relative_path: str | Path) -> Path:
-        """Get the full path for an item in the workspace.
-
-        Parameters
-        ----------
-        relative_path
-            The relative path to resolve in the workspace.
-
-        Returns
-        -------
-        Path
-            The resolved path relative to the workspace.
-
-        """
-        return self._sanitize_path(
-            relative_path,
-            root=self.root,
-            restrict_to_root=self.restrict_to_workspace,
-        )
-
-    @staticmethod
-    def _sanitize_path(
-        relative_path: str | Path,
-        root: str | Path = None,
-        restrict_to_root: bool = True,
-    ) -> Path:
-        """Resolve the relative path within the given root if possible.
-
-        Parameters
-        ----------
-        relative_path
-            The relative path to resolve.
-        root
-            The root path to resolve the relative path within.
-        restrict_to_root
-            Whether to restrict the path to the root.
-
-        Returns
-        -------
-        Path
-            The resolved path.
-
-        Raises
-        ------
-        ValueError
-            If the path is absolute and a root is provided.
-        ValueError
-            If the path is outside the root and the root is restricted.
-
-        """
-
-        if root is None:
-            return Path(relative_path).resolve()
-
-        root, relative_path = Path(root), Path(relative_path)
-
-        if relative_path.is_absolute():
-            raise ValueError(
-                f"Attempted to access absolute path '{relative_path}' in workspace '{root}'."
-            )
-
-        full_path = root.joinpath(relative_path).resolve()
-
-        if restrict_to_root and not full_path.is_relative_to(root):
-            raise ValueError(
-                f"Attempted to access path '{full_path}' outside of workspace '{root}'."
-            )
-
-        return full_path