Merge pull request #998 from awwaawwa/enable_clear_history_option

增加自动清除历史消息时的提示

.github/workflows/build-with-audio-assistant.yml

@@ -0,0 +1,44 @@
+# https://docs.github.com/en/actions/publishing-packages/publishing-docker-images#publishing-images-to-github-packages
+name: build-with-audio-assistant
+
+on:
+  push:
+    branches:
+      - 'master'
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}_audio_assistant
+
+jobs:
+  build-and-push-image:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@v2
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v4
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v4
+        with:
+          context: .
+          push: true
+          file: docs/GithubAction+NoLocal+AudioAssistant
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}

README.md

@@ -147,6 +147,7 @@ python main.py
 1. 仅ChatGPT（推荐大多数人选择，等价于docker-compose方案1）
 [![basic](https://github.com/binary-husky/gpt_academic/actions/workflows/build-without-local-llms.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-without-local-llms.yml)
 [![basiclatex](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml)
+[![basicaudio](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-audio-assistant.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-audio-assistant.yml)
 
 ``` sh
 git clone --depth=1 https://github.com/binary-husky/gpt_academic.git  # 下载项目
@@ -195,10 +196,12 @@ docker-compose up
 5. 远程云服务器部署（需要云服务器知识与经验）。
 请访问[部署wiki-1](https://github.com/binary-husky/gpt_academic/wiki/%E4%BA%91%E6%9C%8D%E5%8A%A1%E5%99%A8%E8%BF%9C%E7%A8%8B%E9%83%A8%E7%BD%B2%E6%8C%87%E5%8D%97)
 
-6. 使用WSL2（Windows Subsystem for Linux 子系统）。
+6. 使用Sealos[一键部署](https://github.com/binary-husky/gpt_academic/issues/993)。
+
+7. 使用WSL2（Windows Subsystem for Linux 子系统）。
 请访问[部署wiki-2](https://github.com/binary-husky/gpt_academic/wiki/%E4%BD%BF%E7%94%A8WSL2%EF%BC%88Windows-Subsystem-for-Linux-%E5%AD%90%E7%B3%BB%E7%BB%9F%EF%BC%89%E9%83%A8%E7%BD%B2)
 
-7. 如何在二级网址（如`http://localhost/subpath`）下运行。
+8. 如何在二级网址（如`http://localhost/subpath`）下运行。
 请访问[FastAPI运行说明](docs/WithFastapi.md)
 
 

config.py

@@ -132,9 +132,10 @@ put your new bing cookies here
 
 # 阿里云实时语音识别 配置难度较高 仅建议高手用户使用 参考 https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md
 ENABLE_AUDIO = False
-ALIYUN_TOKEN=""    # 例如 f37f30e0f9934c34a992f6f64f7eba4f
-ALIYUN_APPKEY=""   # 例如 RoPlZrM88DnAFkZK
-
+ALIYUN_TOKEN=""     # 例如 f37f30e0f9934c34a992f6f64f7eba4f
+ALIYUN_APPKEY=""    # 例如 RoPlZrM88DnAFkZK
+ALIYUN_ACCESSKEY="" # （无需填写）
+ALIYUN_SECRET=""    # （无需填写）
 
 # Claude API KEY
 ANTHROPIC_API_KEY = ""

core_functional.py

@@ -1,7 +1,7 @@
 # 'primary' 颜色对应 theme.py 中的 primary_hue
 # 'secondary' 颜色对应 theme.py 中的 neutral_hue
 # 'stop' 颜色对应 theme.py 中的 color_er
-# 默认按钮颜色是 secondary
+import importlib
 from toolbox import clear_line_break
 
 
@@ -14,7 +14,12 @@ def get_core_functions():
                         r"Furthermore, list all modification and explain the reasons to do so in markdown table." + "\n\n",
             # 后语
             "Suffix":   r"",
-            "Color":    r"secondary",    # 按钮颜色
+            # 按钮颜色 (默认 secondary)
+            "Color":    r"secondary",
+            # 按钮是否可见 (默认 True，即可见)
+            "Visible": True,
+            # 是否在触发时清除历史 (默认 False，即不处理之前的对话历史)
+            "AutoClearHistory": False
         },
         "中文学术润色": {
             "Prefix":   r"作为一名中文学术论文写作改进助理，你的任务是改进所提供文本的拼写、语法、清晰、简洁和整体可读性，" +
@@ -76,3 +81,14 @@ def get_core_functions():
             "Suffix":   r"",
         }
     }
+
+
+def handle_core_functionality(additional_fn, inputs, history, chatbot):
+    import core_functional
+    importlib.reload(core_functional)    # 热更新prompt
+    core_functional = core_functional.get_core_functions()
+    if "PreProcess" in core_functional[additional_fn]: inputs = core_functional[additional_fn]["PreProcess"](inputs)  # 获取预处理函数（如果有的话）
+    inputs = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"]
+    if core_functional[additional_fn].get("AutoClearHistory", False):
+        history = []
+    return inputs, history

crazy_functions/live_audio/aliyunASR.py

@@ -19,7 +19,7 @@ class AliyunASR():
         pass
 
     def test_on_error(self, message, *args):
-        # print("on_error args=>{}".format(args))
+        print("on_error args=>{}".format(args))
         pass
 
     def test_on_close(self, *args):
@@ -50,6 +50,8 @@ class AliyunASR():
         rad.clean_up()
         temp_folder = tempfile.gettempdir()
         TOKEN, APPKEY = get_conf('ALIYUN_TOKEN', 'ALIYUN_APPKEY')
+        if len(TOKEN) == 0:
+            TOKEN = self.get_token()
         self.aliyun_service_ok = True
         URL="wss://nls-gateway.aliyuncs.com/ws/v1"
         sr = nls.NlsSpeechTranscriber(
@@ -91,3 +93,38 @@ class AliyunASR():
                 self.stop = True
                 self.stop_msg = 'Aliyun音频服务异常，请检查ALIYUN_TOKEN和ALIYUN_APPKEY是否过期。'
         r = sr.stop()
+
+    def get_token(self):
+        from toolbox import get_conf
+        import json
+        from aliyunsdkcore.request import CommonRequest
+        from aliyunsdkcore.client import AcsClient
+        AccessKey_ID, AccessKey_secret = get_conf('ALIYUN_ACCESSKEY', 'ALIYUN_SECRET')
+
+        # 创建AcsClient实例
+        client = AcsClient(
+            AccessKey_ID,
+            AccessKey_secret,
+            "cn-shanghai"
+        )
+
+        # 创建request，并设置参数。
+        request = CommonRequest()
+        request.set_method('POST')
+        request.set_domain('nls-meta.cn-shanghai.aliyuncs.com')
+        request.set_version('2019-02-28')
+        request.set_action_name('CreateToken')
+
+        try:
+            response = client.do_action_with_exception(request)
+            print(response)
+            jss = json.loads(response)
+            if 'Token' in jss and 'Id' in jss['Token']:
+                token = jss['Token']['Id']
+                expireTime = jss['Token']['ExpireTime']
+                print("token = " + token)
+                print("expireTime = " + str(expireTime))
+        except Exception as e:
+            print(e)
+
+        return token

crazy_functions/语音助手.py

@@ -179,12 +179,12 @@ def 语音助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
         import nls
         from scipy import io
     except:
-        chatbot.append(["导入依赖失败", "使用该模块需要额外依赖, 安装方法:```pip install --upgrade pyOpenSSL scipy git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git```"])
+        chatbot.append(["导入依赖失败", "使用该模块需要额外依赖, 安装方法:```pip install --upgrade aliyun-python-sdk-core==2.13.3 pyOpenSSL scipy git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git```"])
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
 
-    TOKEN, APPKEY = get_conf('ALIYUN_TOKEN', 'ALIYUN_APPKEY')
-    if TOKEN == "" or APPKEY == "":
+    APPKEY = get_conf('ALIYUN_APPKEY')
+    if APPKEY == "":
         chatbot.append(["导入依赖失败", "没有阿里云语音识别APPKEY和TOKEN, 详情见https://help.aliyun.com/document_detail/450255.html"])
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return

docker-compose.yml

@@ -115,3 +115,36 @@ services:
     command: >
       bash -c "python3 -u main.py"
 
+
+## ===================================================
+## 【方案五】 ChatGPT + 语音助手 （请先阅读 docs/use_audio.md）
+## ===================================================
+version: '3'
+services:
+  gpt_academic_with_audio:
+    image: ghcr.io/binary-husky/gpt_academic_audio_assistant:master
+    environment:
+      # 请查阅 `config.py` 以查看所有的配置信息
+      API_KEY:                  '    fk195831-IdP0Pb3W6DCMUIbQwVX6MsSiyxwqybyS                        '
+      USE_PROXY:                '    False                                                            '
+      proxies:                  '    None                                                             '
+      LLM_MODEL:                '    gpt-3.5-turbo                                                    '
+      AVAIL_LLM_MODELS:         '    ["gpt-3.5-turbo", "gpt-4"]                                       '
+      ENABLE_AUDIO:             '    True                                                             '
+      LOCAL_MODEL_DEVICE:       '    cuda                                                             '
+      DEFAULT_WORKER_NUM:       '    20                                                               '
+      WEB_PORT:                 '    12343                                                            '
+      ADD_WAIFU:                '    True                                                             '
+      THEME:                    '    Chuanhu-Small-and-Beautiful                                      '
+      ALIYUN_APPKEY:            '    RoP1ZrM84DnAFkZK                                                 '
+      ALIYUN_TOKEN:             '    f37f30e0f9934c34a992f6f64f7eba4f                                 '
+      # (无需填写) ALIYUN_ACCESSKEY:         '    LTAI5q6BrFUzoRXVGUWnekh1                                         '
+      # (无需填写) ALIYUN_SECRET:            '    eHmI20AVWIaQZ0CiTD2bGQVsaP9i68                                   '
+
+    # 与宿主的网络融合
+    network_mode: "host"
+
+    # 不使用代理网络拉取最新代码
+    command: >
+      bash -c "python3 -u main.py"
+

docs/GithubAction+NoLocal+AudioAssistant

@@ -0,0 +1,22 @@
+# 此Dockerfile适用于“无本地模型”的环境构建，如果需要使用chatglm等本地模型，请参考 docs/Dockerfile+ChatGLM
+# 如何构建: 先修改 `config.py`， 然后 docker build -t gpt-academic-nolocal -f docs/Dockerfile+NoLocal .
+# 如何运行: docker run --rm -it --net=host gpt-academic-nolocal
+FROM python:3.11
+
+# 指定路径
+WORKDIR /gpt
+
+# 装载项目文件
+COPY . .
+
+# 安装依赖
+RUN pip3 install -r requirements.txt
+
+# 安装语音插件的额外依赖
+RUN pip3 install pyOpenSSL scipy git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git
+
+# 可选步骤，用于预热模块
+RUN python3  -c 'from check_proxy import warm_up_modules; warm_up_modules()'
+
+# 启动
+CMD ["python3", "-u", "main.py"]

docs/use_audio.md

@@ -28,6 +28,16 @@ ALIYUN_APPKEY = "RoPlZrM88DnAFkZK"   # 此appkey已经失效
 参考 https://help.aliyun.com/document_detail/450255.html
 先有阿里云开发者账号，登录之后，需要开通 智能语音交互 的功能，可以免费获得一个token，然后在 全部项目 中，创建一个项目，可以获得一个appkey.
 
+- 进阶功能
+进一步填写ALIYUN_ACCESSKEY和ALIYUN_SECRET实现自动获取ALIYUN_TOKEN
+```
+ALIYUN_APPKEY = "RoP1ZrM84DnAFkZK"
+ALIYUN_TOKEN = ""
+ALIYUN_ACCESSKEY = "LTAI5q6BrFUzoRXVGUWnekh1"
+ALIYUN_SECRET = "eHmI20AVWIaQZ0CiTD2bGQVsaP9i68"
+```
+
+
 ## 3.启动
 
 启动gpt-academic `python main.py`
@@ -48,7 +58,7 @@ III `[把特殊软件（如腾讯会议）的外放声音用VoiceMeeter截留]`
 
 VI 两种音频监听模式切换时，需要刷新页面才有效。
 
+VII 非localhost运行+非https情况下无法打开录音功能的坑：https://blog.csdn.net/weixin_39461487/article/details/109594434
+
 ## 5.点击函数插件区“实时音频采集” 或者其他音频交互功能
 
-
-

request_llm/bridge_chatglm.py

@@ -144,11 +144,8 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
             return
 
     if additional_fn is not None:
-        import core_functional
-        importlib.reload(core_functional)    # 热更新prompt
-        core_functional = core_functional.get_core_functions()
-        if "PreProcess" in core_functional[additional_fn]: inputs = core_functional[additional_fn]["PreProcess"](inputs)  # 获取预处理函数（如果有的话）
-        inputs = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"]
+        from core_functional import handle_core_functionality
+        inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
 
     # 处理历史信息
     history_feedin = []

request_llm/bridge_chatglmft.py

@@ -185,11 +185,8 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
             return
 
     if additional_fn is not None:
-        import core_functional
-        importlib.reload(core_functional)    # 热更新prompt
-        core_functional = core_functional.get_core_functions()
-        if "PreProcess" in core_functional[additional_fn]: inputs = core_functional[additional_fn]["PreProcess"](inputs)  # 获取预处理函数（如果有的话）
-        inputs = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"]
+        from core_functional import handle_core_functionality
+        inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
 
     # 处理历史信息
     history_feedin = []

request_llm/bridge_chatgpt.py

@@ -129,11 +129,8 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
         return
 
     if additional_fn is not None:
-        import core_functional
-        importlib.reload(core_functional)    # 热更新prompt
-        core_functional = core_functional.get_core_functions()
-        if "PreProcess" in core_functional[additional_fn]: inputs = core_functional[additional_fn]["PreProcess"](inputs)  # 获取预处理函数（如果有的话）
-        inputs = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"]
+        from core_functional import handle_core_functionality
+        inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
 
     raw_input = inputs
     logging.info(f'[raw_input] {raw_input}')

request_llm/bridge_claude.py

@@ -116,11 +116,8 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
         return
     
     if additional_fn is not None:
-        import core_functional
-        importlib.reload(core_functional)    # 热更新prompt
-        core_functional = core_functional.get_core_functions()
-        if "PreProcess" in core_functional[additional_fn]: inputs = core_functional[additional_fn]["PreProcess"](inputs)  # 获取预处理函数（如果有的话）
-        inputs = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"]
+        from core_functional import handle_core_functionality
+        inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
 
     raw_input = inputs
     logging.info(f'[raw_input] {raw_input}')

request_llm/bridge_internlm.py

@@ -290,11 +290,8 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
         return
 
     if additional_fn is not None:
-        import core_functional
-        importlib.reload(core_functional)    # 热更新prompt
-        core_functional = core_functional.get_core_functions()
-        if "PreProcess" in core_functional[additional_fn]: inputs = core_functional[additional_fn]["PreProcess"](inputs)  # 获取预处理函数（如果有的话）
-        inputs = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"]
+        from core_functional import handle_core_functionality
+        inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
 
     # 处理历史信息
     history_feedin = []

request_llm/bridge_jittorllms_llama.py

@@ -154,11 +154,8 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
             return
 
     if additional_fn is not None:
-        import core_functional
-        importlib.reload(core_functional)    # 热更新prompt
-        core_functional = core_functional.get_core_functions()
-        if "PreProcess" in core_functional[additional_fn]: inputs = core_functional[additional_fn]["PreProcess"](inputs)  # 获取预处理函数（如果有的话）
-        inputs = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"]
+        from core_functional import handle_core_functionality
+        inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
 
     # 处理历史信息
     history_feedin = []

request_llm/bridge_jittorllms_pangualpha.py

@@ -154,11 +154,8 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
             return
 
     if additional_fn is not None:
-        import core_functional
-        importlib.reload(core_functional)    # 热更新prompt
-        core_functional = core_functional.get_core_functions()
-        if "PreProcess" in core_functional[additional_fn]: inputs = core_functional[additional_fn]["PreProcess"](inputs)  # 获取预处理函数（如果有的话）
-        inputs = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"]
+        from core_functional import handle_core_functionality
+        inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
 
     # 处理历史信息
     history_feedin = []

request_llm/bridge_jittorllms_rwkv.py

@@ -154,11 +154,8 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
             return
 
     if additional_fn is not None:
-        import core_functional
-        importlib.reload(core_functional)    # 热更新prompt
-        core_functional = core_functional.get_core_functions()
-        if "PreProcess" in core_functional[additional_fn]: inputs = core_functional[additional_fn]["PreProcess"](inputs)  # 获取预处理函数（如果有的话）
-        inputs = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"]
+        from core_functional import handle_core_functionality
+        inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
 
     # 处理历史信息
     history_feedin = []

request_llm/bridge_moss.py

@@ -224,11 +224,8 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
         yield from update_ui(chatbot=chatbot, history=history)
 
     if additional_fn is not None:
-        import core_functional
-        importlib.reload(core_functional)    # 热更新prompt
-        core_functional = core_functional.get_core_functions()
-        if "PreProcess" in core_functional[additional_fn]: inputs = core_functional[additional_fn]["PreProcess"](inputs)  # 获取预处理函数（如果有的话）
-        inputs = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"]
+        from core_functional import handle_core_functionality
+        inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
 
     # 处理历史信息
     history_feedin = []

request_llm/bridge_newbingfree.py

@@ -224,11 +224,8 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
             return
 
     if additional_fn is not None:
-        import core_functional
-        importlib.reload(core_functional)    # 热更新prompt
-        core_functional = core_functional.get_core_functions()
-        if "PreProcess" in core_functional[additional_fn]: inputs = core_functional[additional_fn]["PreProcess"](inputs)  # 获取预处理函数（如果有的话）
-        inputs = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"]
+        from core_functional import handle_core_functionality
+        inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
 
     history_feedin = []
     for i in range(len(history)//2):

request_llm/bridge_stackclaude.py

@@ -248,14 +248,8 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
             return
 
     if additional_fn is not None:
-        import core_functional
-        importlib.reload(core_functional)    # 热更新prompt
-        core_functional = core_functional.get_core_functions()
-        if "PreProcess" in core_functional[additional_fn]:
-            inputs = core_functional[additional_fn]["PreProcess"](
-                inputs)  # 获取预处理函数（如果有的话）
-        inputs = core_functional[additional_fn]["Prefix"] + \
-            inputs + core_functional[additional_fn]["Suffix"]
+        from core_functional import handle_core_functionality
+        inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
 
     history_feedin = []
     for i in range(len(history)//2):

request_llm/bridge_tgui.py

@@ -96,11 +96,8 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
         additional_fn代表点击的哪个按钮，按钮见functional.py
     """
     if additional_fn is not None:
-        import core_functional
-        importlib.reload(core_functional)    # 热更新prompt
-        core_functional = core_functional.get_core_functions()
-        if "PreProcess" in core_functional[additional_fn]: inputs = core_functional[additional_fn]["PreProcess"](inputs)  # 获取预处理函数（如果有的话）
-        inputs = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"]
+        from core_functional import handle_core_functionality
+        inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
 
     raw_input = "What I would like to say is the following: " + inputs
     history.extend([inputs, ""])