\n", " OPENAI_API_KEY=\"your_api_key\" \n", "
\n", " \n", " \u66ff\u6362\"your_api_key\"\u4e3a\u4f60\u81ea\u5df1\u7684 API Key"]}, {"cell_type": "code", "execution_count": null, "id": "6932bd47-c6d5-4794-8102-a12b84412a93", "metadata": {}, "outputs": [], "source": ["# \u4e0b\u8f7d\u9700\u8981\u7684\u5305python-dotenv\u548copenai\n", "# \u5982\u679c\u4f60\u9700\u8981\u67e5\u770b\u5b89\u88c5\u8fc7\u7a0b\u65e5\u5fd7\uff0c\u53ef\u5220\u9664 -q \n", "!pip install -q python-dotenv\n", "!pip install -q openai"]}, {"cell_type": "code", "execution_count": null, "id": "10446712-9fa6-4d71-94ce-2ea4cf197e54", "metadata": {}, "outputs": [], "source": ["import os\n", "import openai\n", "from dotenv import load_dotenv, find_dotenv\n", "\n", "# \u8bfb\u53d6\u672c\u5730/\u9879\u76ee\u7684\u73af\u5883\u53d8\u91cf\u3002\n", "\n", "# find_dotenv()\u5bfb\u627e\u5e76\u5b9a\u4f4d.env\u6587\u4ef6\u7684\u8def\u5f84\n", "# load_dotenv()\u8bfb\u53d6\u8be5.env\u6587\u4ef6\uff0c\u5e76\u5c06\u5176\u4e2d\u7684\u73af\u5883\u53d8\u91cf\u52a0\u8f7d\u5230\u5f53\u524d\u7684\u8fd0\u884c\u73af\u5883\u4e2d \n", "# \u5982\u679c\u4f60\u8bbe\u7f6e\u7684\u662f\u5168\u5c40\u7684\u73af\u5883\u53d8\u91cf\uff0c\u8fd9\u884c\u4ee3\u7801\u5219\u6ca1\u6709\u4efb\u4f55\u4f5c\u7528\u3002\n", "_ = load_dotenv(find_dotenv())\n", "\n", "# \u83b7\u53d6\u73af\u5883\u53d8\u91cf OPENAI_API_KEY\n", "openai.api_key = os.environ['OPENAI_API_KEY'] "]}, {"cell_type": "markdown", "id": "1297dcd5", "metadata": {}, "source": ["## \u4e8c\u3001\u5bf9\u8bdd\u7f13\u5b58\u50a8\u5b58 \n", " \n", "\u8fd9\u79cd\u8bb0\u5fc6\u5141\u8bb8\u5b58\u50a8\u6d88\u606f\uff0c\u7136\u540e\u4ece\u53d8\u91cf\u4e2d\u63d0\u53d6\u6d88\u606f\u3002"]}, {"cell_type": "code", "execution_count": null, "id": "20ad6fe2", "metadata": {"height": 98}, "outputs": [], "source": ["from langchain.chat_models import ChatOpenAI\n", "from langchain.chains import ConversationChain\n", "from langchain.memory import ConversationBufferMemory"]}, {"cell_type": "code", "execution_count": null, "id": "88bdf13d", "metadata": {"height": 133}, "outputs": [], "source": ["OPENAI_API_KEY = \"********\" #\"\u586b\u5165\u4f60\u7684\u4e13\u5c5e\u7684API key\"\n", "llm = ChatOpenAI(temperature=0.0,openai_api_key=OPENAI_API_KEY) #temperature\uff1a\u9884\u6d4b\u4e0b\u4e00\u4e2atoken\u65f6\uff0c\u6982\u7387\u8d8a\u5927\u7684\u503c\u5c31\u8d8a\u5e73\u6ed1(\u5e73\u6ed1\u4e5f\u5c31\u662f\u8ba9\u5dee\u5f02\u5927\u7684\u503c\u4e4b\u95f4\u7684\u5dee\u5f02\u53d8\u5f97\u6ca1\u90a3\u4e48\u5927)\uff0ctemperature\u503c\u8d8a\u5c0f\u5219\u751f\u6210\u7684\u5185\u5bb9\u8d8a\u7a33\u5b9a\n", "memory = ConversationBufferMemory()\n", "conversation = ConversationChain( #\u65b0\u5efa\u4e00\u4e2a\u5bf9\u8bdd\u94fe\uff08\u5173\u4e8e\u94fe\u540e\u9762\u4f1a\u63d0\u5230\u66f4\u591a\u7684\u7ec6\u8282\uff09\n", " llm=llm, \n", " memory = memory,\n", " verbose=True #\u67e5\u770bLangchain\u5b9e\u9645\u4e0a\u5728\u505a\u4ec0\u4e48\uff0c\u8bbe\u4e3aFALSE\u7684\u8bdd\u53ea\u7ed9\u51fa\u56de\u7b54\uff0c\u770b\u5230\u4e0d\u5230\u4e0b\u9762\u7eff\u8272\u7684\u5185\u5bb9\n", ")"]}, {"cell_type": "markdown", "id": "dea83837", "metadata": {}, "source": ["### 2.1 \u5f00\u59cb\u5bf9\u8bdd\uff0c\u7b2c\u4e00\u8f6e"]}, {"cell_type": "markdown", "id": "1a3b4c42", "metadata": {}, "source": ["\u5f53\u6211\u4eec\u8fd0\u884cpredict\u65f6\uff0c\u751f\u6210\u4e86\u4e00\u4e9b\u63d0\u793a\uff0c\u5982\u4e0b\u6240\u89c1\uff0c\u4ed6\u8bf4\u201c\u4ee5\u4e0b\u662f\u4eba\u7c7b\u548cAI\u4e4b\u95f4\u53cb\u597d\u7684\u5bf9\u8bdd\uff0cAI\u5065\u8c08\u201c\u7b49\u7b49\uff0c\u8fd9\u5b9e\u9645\u4e0a\u662fLangChain\u751f\u6210\u7684\u63d0\u793a\uff0c\u4ee5\u4f7f\u7cfb\u7edf\u8fdb\u884c\u5e0c\u671b\u548c\u53cb\u597d\u7684\u5bf9\u8bdd\uff0c\u5e76\u4e14\u5fc5\u987b\u4fdd\u5b58\u5bf9\u8bdd\uff0c\u5e76\u63d0\u793a\u4e86\u5f53\u524d\u5df2\u5b8c\u6210\u7684\u6a21\u578b\u94fe\u3002"]}, {"cell_type": "code", "execution_count": null, "id": "db24677d", "metadata": {"height": 47}, "outputs": [], "source": ["conversation.predict(input=\"Hi, my name is Andrew\")"]}, {"cell_type": "code", "execution_count": null, "id": "154561c9", "metadata": {}, "outputs": [], "source": ["#\u4e2d\u6587\n", "conversation.predict(input=\"\u4f60\u597d, \u6211\u53eb\u76ae\u76ae\u9c81\")"]}, {"cell_type": "markdown", "id": "e71564ad", "metadata": {}, "source": ["### 2.2 \u7b2c\u4e8c\u8f6e\u5bf9\u8bdd"]}, {"cell_type": "markdown", "id": "54d006bd", "metadata": {}, "source": ["\u5f53\u6211\u4eec\u8fdb\u884c\u4e0b\u4e00\u8f6e\u5bf9\u8bdd\u65f6\uff0c\u4ed6\u4f1a\u4fdd\u7559\u4e0a\u9762\u7684\u63d0\u793a"]}, {"cell_type": "code", "execution_count": null, "id": "cc3ef937", "metadata": {"height": 31}, "outputs": [], "source": ["conversation.predict(input=\"What is 1+1?\")"]}, {"cell_type": "code", "execution_count": null, "id": "63efc1bb", "metadata": {}, "outputs": [], "source": ["#\u4e2d\u6587\n", "conversation.predict(input=\"1+1\u7b49\u4e8e\u591a\u5c11\uff1f\")"]}, {"cell_type": "markdown", "id": "33cb734b", "metadata": {}, "source": ["### 2.3 \u7b2c\u4e09\u8f6e\u5bf9\u8bdd"]}, {"cell_type": "markdown", "id": "0393df3d", "metadata": {}, "source": ["\u4e3a\u4e86\u9a8c\u8bc1\u4ed6\u662f\u5426\u8bb0\u5fc6\u4e86\u524d\u9762\u7684\u5bf9\u8bdd\u5185\u5bb9\uff0c\u6211\u4eec\u8ba9\u4ed6\u56de\u7b54\u524d\u9762\u5df2\u7ecf\u8bf4\u8fc7\u7684\u5185\u5bb9\uff08\u6211\u7684\u540d\u5b57\uff09\uff0c\u53ef\u4ee5\u770b\u5230\u4ed6\u786e\u5b9e\u8f93\u51fa\u4e86\u6b63\u786e\u7684\u540d\u5b57\uff0c\u56e0\u6b64\u8fd9\u4e2a\u5bf9\u8bdd\u94fe\u968f\u7740\u5f80\u4e0b\u8fdb\u884c\u4f1a\u8d8a\u6765\u8d8a\u957f"]}, {"cell_type": "code", "execution_count": null, "id": "acf3339a", "metadata": {"height": 31}, "outputs": [], "source": ["conversation.predict(input=\"What is my name?\")"]}, {"cell_type": "code", "execution_count": null, "id": "2206e5b7", "metadata": {}, "outputs": [], "source": ["#\u4e2d\u6587\n", "conversation.predict(input=\"\u6211\u53eb\u4ec0\u4e48\u540d\u5b57\uff1f\")"]}, {"cell_type": "markdown", "id": "5a96a8d9", "metadata": {}, "source": ["### 2.4 .memory.buffer\u5b58\u50a8\u4e86\u5f53\u524d\u4e3a\u6b62\u6240\u6709\u7684\u5bf9\u8bdd\u4fe1\u606f"]}, {"cell_type": "code", "execution_count": null, "id": "2529400d", "metadata": {"height": 31}, "outputs": [], "source": ["print(memory.buffer) #\u63d0\u53d6\u5386\u53f2\u6d88\u606f"]}, {"cell_type": "code", "execution_count": null, "id": "d948aeb2", "metadata": {}, "outputs": [], "source": ["# \u4e2d\u6587\n", "print(memory.buffer) #\u63d0\u53d6\u5386\u53f2\u6d88\u606f"]}, {"cell_type": "markdown", "id": "6bd222c3", "metadata": {}, "source": ["### 2.5 \u4e5f\u53ef\u4ee5\u901a\u8fc7memory.load_memory_variables({})\u6253\u5370\u5386\u53f2\u6d88\u606f"]}, {"cell_type": "markdown", "id": "0b5de846", "metadata": {}, "source": ["\u8fd9\u91cc\u7684\u82b1\u62ec\u53f7\u5b9e\u9645\u4e0a\u662f\u4e00\u4e2a\u7a7a\u5b57\u5178\uff0c\u6709\u4e00\u4e9b\u66f4\u9ad8\u7ea7\u7684\u529f\u80fd\uff0c\u4f7f\u7528\u6237\u53ef\u4ee5\u4f7f\u7528\u66f4\u590d\u6742\u7684\u8f93\u5165\uff0c\u4f46\u6211\u4eec\u4e0d\u4f1a\u5728\u8fd9\u4e2a\u77ed\u671f\u8bfe\u7a0b\u4e2d\u8ba8\u8bba\u5b83\u4eec\uff0c\u6240\u4ee5\u4e0d\u8981\u62c5\u5fc3\u4e3a\u4ec0\u4e48\u8fd9\u91cc\u6709\u4e00\u4e2a\u7a7a\u7684\u82b1\u62ec\u53f7\u3002"]}, {"cell_type": "code", "execution_count": null, "id": "5018cb0a", "metadata": {"height": 31}, "outputs": [], "source": ["memory.load_memory_variables({})"]}, {"cell_type": "code", "execution_count": null, "id": "af4b8b12", "metadata": {}, "outputs": [], "source": ["# \u4e2d\u6587\n", "memory.load_memory_variables({})"]}, {"cell_type": "markdown", "id": "07d2e892", "metadata": {}, "source": ["### 2.6 \u6dfb\u52a0\u6307\u5b9a\u7684\u8f93\u5165\u8f93\u51fa\u5185\u5bb9\u5230\u8bb0\u5fc6\u7f13\u5b58\u533a"]}, {"cell_type": "code", "execution_count": null, "id": "14219b70", "metadata": {"height": 31}, "outputs": [], "source": ["memory = ConversationBufferMemory() #\u65b0\u5efa\u4e00\u4e2a\u7a7a\u7684\u5bf9\u8bdd\u7f13\u5b58\u8bb0\u5fc6"]}, {"cell_type": "code", "execution_count": null, "id": "a36e9905", "metadata": {"height": 48}, "outputs": [], "source": ["memory.save_context({\"input\": \"Hi\"}, #\u5411\u7f13\u5b58\u533a\u6dfb\u52a0\u6307\u5b9a\u5bf9\u8bdd\u7684\u8f93\u5165\u8f93\u51fa\n", " {\"output\": \"What's up\"})"]}, {"cell_type": "code", "execution_count": null, "id": "61631b1f", "metadata": {"height": 31}, "outputs": [], "source": ["print(memory.buffer) #\u67e5\u770b\u7f13\u5b58\u533a\u7ed3\u679c"]}, {"cell_type": "code", "execution_count": null, "id": "a2fdf9ec", "metadata": {"height": 31}, "outputs": [], "source": ["memory.load_memory_variables({}) #\u518d\u6b21\u52a0\u8f7d\u8bb0\u5fc6\u53d8\u91cf"]}, {"cell_type": "code", "execution_count": null, "id": "27d8dd2f", "metadata": {}, "outputs": [], "source": ["#\u4e2d\u6587\n", "memory = ConversationBufferMemory()\n", "memory.save_context({\"input\": \"\u4f60\u597d\uff0c\u6211\u53eb\u76ae\u76ae\u9c81\"}, \n", " {\"output\": \"\u4f60\u597d\u554a\uff0c\u6211\u53eb\u9c81\u897f\u897f\"})\n", "memory.load_memory_variables({})"]}, {"cell_type": "markdown", "id": "2ac544f2", "metadata": {}, "source": ["\u7ee7\u7eed\u6dfb\u52a0\u65b0\u7684\u5185\u5bb9\uff0c\u5bf9\u8bdd\u5386\u53f2\u90fd\u4fdd\u5b58\u4e0b\u6765\u5728\u4e86\uff01"]}, {"cell_type": "code", "execution_count": null, "id": "7ca79256", "metadata": {"height": 64}, "outputs": [], "source": ["memory.save_context({\"input\": \"Not much, just hanging\"}, \n", " {\"output\": \"Cool\"})"]}, {"cell_type": "code", "execution_count": null, "id": "890a4497", "metadata": {"height": 31}, "outputs": [], "source": ["memory.load_memory_variables({})"]}, {"cell_type": "code", "execution_count": null, "id": "2b614406", "metadata": {}, "outputs": [], "source": ["#\u4e2d\u6587\n", "memory.save_context({\"input\": \"\u5f88\u9ad8\u5174\u548c\u4f60\u6210\u4e3a\u670b\u53cb\uff01\"}, \n", " {\"output\": \"\u662f\u7684\uff0c\u8ba9\u6211\u4eec\u4e00\u8d77\u53bb\u5192\u9669\u5427\uff01\"})\n", "memory.load_memory_variables({})"]}, {"cell_type": "markdown", "id": "8839314a", "metadata": {}, "source": ["\u5f53\u6211\u4eec\u5728\u4f7f\u7528\u5927\u578b\u8bed\u8a00\u6a21\u578b\u8fdb\u884c\u804a\u5929\u5bf9\u8bdd\u65f6\uff0c**\u5927\u578b\u8bed\u8a00\u6a21\u578b\u672c\u8eab\u5b9e\u9645\u4e0a\u662f\u65e0\u72b6\u6001\u7684\u3002\u8bed\u8a00\u6a21\u578b\u672c\u8eab\u5e76\u4e0d\u8bb0\u5f97\u5230\u76ee\u524d\u4e3a\u6b62\u7684\u5386\u53f2\u5bf9\u8bdd**\u3002\u6bcf\u6b21\u8c03\u7528API\u7ed3\u70b9\u90fd\u662f\u72ec\u7acb\u7684\u3002\n", "\n", "\u804a\u5929\u673a\u5668\u4eba\u4f3c\u4e4e\u6709\u8bb0\u5fc6\uff0c\u53ea\u662f\u56e0\u4e3a\u901a\u5e38\u6709\u5feb\u901f\u7684\u4ee3\u7801\u53ef\u4ee5\u5411LLM\u63d0\u4f9b\u8fc4\u4eca\u4e3a\u6b62\u7684\u5b8c\u6574\u5bf9\u8bdd\u4ee5\u53ca\u4e0a\u4e0b\u6587\u3002\u56e0\u6b64\uff0cMemory\u53ef\u4ee5\u660e\u786e\u5730\u5b58\u50a8\u5230\u76ee\u524d\u4e3a\u6b62\u7684\u6240\u6709\u672f\u8bed\u6216\u5bf9\u8bdd\u3002\u8fd9\u4e2aMemory\u5b58\u50a8\u5668\u88ab\u7528\u4f5c\u8f93\u5165\u6216\u9644\u52a0\u4e0a\u4e0b\u6587\u5230LLM\u4e2d\uff0c\u4ee5\u4fbf\u5b83\u53ef\u4ee5\u751f\u6210\u4e00\u4e2a\u8f93\u51fa\uff0c\u5c31\u597d\u50cf\u5b83\u53ea\u6709\u5728\u8fdb\u884c\u4e0b\u4e00\u8f6e\u5bf9\u8bdd\u7684\u65f6\u5019\uff0c\u624d\u77e5\u9053\u4e4b\u524d\u8bf4\u8fc7\u4ec0\u4e48\u3002\n"]}, {"cell_type": "markdown", "id": "cf98e9ff", "metadata": {}, "source": ["## \u4e09\u3001\u5bf9\u8bdd\u7f13\u5b58\u7a97\u53e3\u50a8\u5b58\n", " \n", "\u968f\u7740\u5bf9\u8bdd\u53d8\u5f97\u8d8a\u6765\u8d8a\u957f\uff0c\u6240\u9700\u7684\u5185\u5b58\u91cf\u4e5f\u53d8\u5f97\u975e\u5e38\u957f\u3002\u5c06\u5927\u91cf\u7684tokens\u53d1\u9001\u5230LLM\u7684\u6210\u672c\uff0c\u4e5f\u4f1a\u53d8\u5f97\u66f4\u52a0\u6602\u8d35,\u8fd9\u4e5f\u5c31\u662f\u4e3a\u4ec0\u4e48API\u7684\u8c03\u7528\u8d39\u7528\uff0c\u901a\u5e38\u662f\u57fa\u4e8e\u5b83\u9700\u8981\u5904\u7406\u7684tokens\u6570\u91cf\u800c\u6536\u8d39\u7684\u3002\n", " \n", "\u9488\u5bf9\u4ee5\u4e0a\u95ee\u9898\uff0cLangChain\u4e5f\u63d0\u4f9b\u4e86\u51e0\u79cd\u65b9\u4fbf\u7684memory\u6765\u4fdd\u5b58\u5386\u53f2\u5bf9\u8bdd\u3002\n", "\u5176\u4e2d\uff0c\u5bf9\u8bdd\u7f13\u5b58\u7a97\u53e3\u8bb0\u5fc6\u53ea\u4fdd\u7559\u4e00\u4e2a\u7a97\u53e3\u5927\u5c0f\u7684\u5bf9\u8bdd\u7f13\u5b58\u533a\u7a97\u53e3\u8bb0\u5fc6\u3002\u5b83\u53ea\u4f7f\u7528\u6700\u8fd1\u7684n\u6b21\u4ea4\u4e92\u3002\u8fd9\u53ef\u4ee5\u7528\u4e8e\u4fdd\u6301\u6700\u8fd1\u4ea4\u4e92\u7684\u6ed1\u52a8\u7a97\u53e3\uff0c\u4ee5\u4fbf\u7f13\u51b2\u533a\u4e0d\u4f1a\u8fc7\u5927"]}, {"cell_type": "code", "execution_count": null, "id": "66eeccc3", "metadata": {"height": 47}, "outputs": [], "source": ["from langchain.memory import ConversationBufferWindowMemory"]}, {"cell_type": "markdown", "id": "641477a4", "metadata": {}, "source": ["### 3.1 \u5411memory\u6dfb\u52a0\u4e24\u8f6e\u5bf9\u8bdd\uff0c\u5e76\u67e5\u770b\u8bb0\u5fc6\u53d8\u91cf\u5f53\u524d\u7684\u8bb0\u5f55"]}, {"cell_type": "code", "execution_count": null, "id": "3ea6233e", "metadata": {"height": 47}, "outputs": [], "source": ["memory = ConversationBufferWindowMemory(k=1) # k=1\u8868\u660e\u53ea\u4fdd\u7559\u4e00\u4e2a\u5bf9\u8bdd\u8bb0\u5fc6 "]}, {"cell_type": "code", "execution_count": null, "id": "dc4553fb", "metadata": {"height": 115}, "outputs": [], "source": ["memory.save_context({\"input\": \"Hi\"},\n", " {\"output\": \"What's up\"})\n", "memory.save_context({\"input\": \"Not much, just hanging\"},\n", " {\"output\": \"Cool\"})\n"]}, {"cell_type": "code", "execution_count": null, "id": "6a788403", "metadata": {"height": 31}, "outputs": [], "source": ["memory.load_memory_variables({})"]}, {"cell_type": "markdown", "id": "9b401f0b", "metadata": {}, "source": ["### 3.2 \u5728\u770b\u4e00\u4e2a\u4f8b\u5b50\uff0c\u53d1\u73b0\u548c\u4e0a\u9762\u7684\u7ed3\u679c\u4e00\u6837\uff0c\u53ea\u4fdd\u7559\u4e86\u4e00\u8f6e\u5bf9\u8bdd\u8bb0\u5fc6"]}, {"cell_type": "code", "execution_count": null, "id": "68a2907c", "metadata": {}, "outputs": [], "source": ["#\u4e2d\u6587\n", "memory = ConversationBufferWindowMemory(k=1) # k=1\u8868\u660e\u53ea\u4fdd\u7559\u4e00\u4e2a\u5bf9\u8bdd\u8bb0\u5fc6 \n", "memory.save_context({\"input\": \"\u4f60\u597d\uff0c\u6211\u53eb\u76ae\u76ae\u9c81\"}, \n", " {\"output\": \"\u4f60\u597d\u554a\uff0c\u6211\u53eb\u9c81\u897f\u897f\"})\n", "memory.save_context({\"input\": \"\u5f88\u9ad8\u5174\u548c\u4f60\u6210\u4e3a\u670b\u53cb\uff01\"}, \n", " {\"output\": \"\u662f\u7684\uff0c\u8ba9\u6211\u4eec\u4e00\u8d77\u53bb\u5192\u9669\u5427\uff01\"})\n", "memory.load_memory_variables({})"]}, {"cell_type": "markdown", "id": "63bda148", "metadata": {}, "source": ["### 3.3 \u5c06\u5bf9\u8bdd\u7f13\u5b58\u7a97\u53e3\u8bb0\u5fc6\u5e94\u7528\u5230\u5bf9\u8bdd\u94fe\u4e2d"]}, {"cell_type": "code", "execution_count": null, "id": "4087bc87", "metadata": {"height": 133}, "outputs": [], "source": ["OPENAI_API_KEY = \"********\" #\"\u586b\u5165\u4f60\u7684\u4e13\u5c5e\u7684API key\"\n", "llm = ChatOpenAI(temperature=0.0,openai_api_key=OPENAI_API_KEY)\n", "memory = ConversationBufferWindowMemory(k=1)\n", "conversation = ConversationChain( \n", " llm=llm, \n", " memory = memory,\n", " verbose=False #\u8fd9\u91cc\u6539\u4e3aFALSE\u4e0d\u663e\u793a\u63d0\u793a\uff0c\u4f60\u53ef\u4ee5\u5c1d\u8bd5\u4fee\u6539\u4e3aTRUE\u540e\u7684\u7ed3\u679c\n", ")"]}, {"cell_type": "markdown", "id": "b6d661e3", "metadata": {}, "source": ["\u6ce8\u610f\u6b64\u5904\uff01\u7531\u4e8e\u8fd9\u91cc\u7528\u7684\u662f\u4e00\u4e2a\u7a97\u53e3\u7684\u8bb0\u5fc6\uff0c\u56e0\u6b64\u53ea\u80fd\u4fdd\u5b58\u4e00\u8f6e\u7684\u5386\u53f2\u6d88\u606f\uff0c\u56e0\u6b64AI\u5e76\u4e0d\u80fd\u77e5\u9053\u4f60\u7b2c\u4e00\u8f6e\u5bf9\u8bdd\u4e2d\u63d0\u5230\u7684\u540d\u5b57\uff0c\u4ed6\u6700\u591a\u53ea\u80fd\u8bb0\u4f4f\u4e0a\u4e00\u8f6e\uff08\u7b2c\u4e8c\u8f6e\uff09\u7684\u5bf9\u8bdd\u4fe1\u606f"]}, {"cell_type": "code", "execution_count": null, "id": "4faaa952", "metadata": {"height": 47}, "outputs": [], "source": ["conversation.predict(input=\"Hi, my name is Andrew\")"]}, {"cell_type": "code", "execution_count": null, "id": "bb20ddaa", "metadata": {"height": 31}, "outputs": [], "source": ["conversation.predict(input=\"What is 1+1?\")"]}, {"cell_type": "code", "execution_count": null, "id": "489b2194", "metadata": {"height": 31}, "outputs": [], "source": ["conversation.predict(input=\"What is my name?\")"]}, {"cell_type": "markdown", "id": "a1080168", "metadata": {}, "source": ["\u518d\u770b\u4e00\u4e2a\u4f8b\u5b50\uff0c\u53d1\u73b0\u548c\u4e0a\u9762\u7684\u7ed3\u679c\u4e00\u6837\uff01"]}, {"cell_type": "code", "execution_count": null, "id": "1ee854d9", "metadata": {}, "outputs": [], "source": ["#\u4e2d\u6587\n", "conversation.predict(input=\"\u4f60\u597d, \u6211\u53eb\u76ae\u76ae\u9c81\")\n", "conversation.predict(input=\"1+1\u7b49\u4e8e\u591a\u5c11\uff1f\")\n", "conversation.predict(input=\"\u6211\u53eb\u4ec0\u4e48\u540d\u5b57\uff1f\")"]}, {"cell_type": "markdown", "id": "d2931b92", "metadata": {}, "source": ["## \u56db\u3001\u5bf9\u8bddtoken\u7f13\u5b58\u50a8\u5b58"]}, {"cell_type": "markdown", "id": "dff5b4c7", "metadata": {}, "source": ["\u4f7f\u7528\u5bf9\u8bddtoken\u7f13\u5b58\u8bb0\u5fc6\uff0c\u5185\u5b58\u5c06\u9650\u5236\u4fdd\u5b58\u7684token\u6570\u91cf\u3002\u5982\u679ctoken\u6570\u91cf\u8d85\u51fa\u6307\u5b9a\u6570\u76ee\uff0c\u5b83\u4f1a\u5207\u6389\u8fd9\u4e2a\u5bf9\u8bdd\u7684\u65e9\u671f\u90e8\u5206\n", "\u4ee5\u4fdd\u7559\u4e0e\u6700\u8fd1\u7684\u4ea4\u6d41\u76f8\u5bf9\u5e94\u7684token\u6570\u91cf\uff0c\u4f46\u4e0d\u8d85\u8fc7token\u9650\u5236\u3002"]}, {"cell_type": "code", "execution_count": null, "id": "9f6d063c", "metadata": {"height": 31}, "outputs": [], "source": ["#!pip install tiktoken #\u9700\u8981\u7528\u5230tiktoken\u5305\uff0c\u6ca1\u6709\u7684\u53ef\u4ee5\u5148\u5b89\u88c5\u4e00\u4e0b"]}, {"cell_type": "markdown", "id": "2187cfe6", "metadata": {}, "source": ["### 4.1 \u5bfc\u5165\u76f8\u5173\u5305\u548cAPI\u5bc6\u94a5"]}, {"cell_type": "code", "execution_count": null, "id": "fb9020ed", "metadata": {"height": 81}, "outputs": [], "source": ["from langchain.memory import ConversationTokenBufferMemory\n", "from langchain.llms import OpenAI\n", "\n", "OPENAI_API_KEY = \"********\" #\"\u586b\u5165\u4f60\u7684\u4e13\u5c5e\u7684API key\"\n", "llm = ChatOpenAI(temperature=0.0,openai_api_key=OPENAI_API_KEY)"]}, {"cell_type": "markdown", "id": "f3a84112", "metadata": {}, "source": ["### 4.2 \u9650\u5236token\u6570\u91cf\uff0c\u8fdb\u884c\u6d4b\u8bd5"]}, {"cell_type": "code", "execution_count": null, "id": "43582ee6", "metadata": {"height": 149}, "outputs": [], "source": ["memory = ConversationTokenBufferMemory(llm=llm, max_token_limit=30)\n", "memory.save_context({\"input\": \"AI is what?!\"},\n", " {\"output\": \"Amazing!\"})\n", "memory.save_context({\"input\": \"Backpropagation is what?\"},\n", " {\"output\": \"Beautiful!\"})\n", "memory.save_context({\"input\": \"Chatbots are what?\"}, \n", " {\"output\": \"Charming!\"})"]}, {"cell_type": "markdown", "id": "7b62b2e1", "metadata": {}, "source": ["\u53ef\u4ee5\u770b\u5230\u524d\u9762\u8d85\u51fa\u7684\u7684token\u5df2\u7ecf\u88ab\u820d\u5f03\u4e86\uff01\uff01\uff01"]}, {"cell_type": "code", "execution_count": null, "id": "284288e1", "metadata": {"height": 31}, "outputs": [], "source": ["memory.load_memory_variables({})"]}, {"cell_type": "markdown", "id": "f7f6be43", "metadata": {}, "source": ["### 4.3 \u4e2d\u6587\u4f8b\u5b50"]}, {"cell_type": "code", "execution_count": null, "id": "e9191020", "metadata": {}, "outputs": [], "source": ["memory = ConversationTokenBufferMemory(llm=llm, max_token_limit=30)\n", "memory.save_context({\"input\": \"\u671d\u8f9e\u767d\u5e1d\u5f69\u4e91\u95f4\uff0c\"}, \n", " {\"output\": \"\u5343\u91cc\u6c5f\u9675\u4e00\u65e5\u8fd8\u3002\"})\n", "memory.save_context({\"input\": \"\u4e24\u5cb8\u733f\u58f0\u557c\u4e0d\u4f4f\uff0c\"},\n", " {\"output\": \"\u8f7b\u821f\u5df2\u8fc7\u4e07\u91cd\u5c71\u3002\"})\n", "memory.load_memory_variables({})"]}, {"cell_type": "markdown", "id": "5e4d918b", "metadata": {}, "source": ["\u8865\u5145\uff1a \n", "\n", "ChatGPT\u4f7f\u7528\u4e00\u79cd\u57fa\u4e8e\u5b57\u8282\u5bf9\u7f16\u7801\uff08Byte Pair Encoding\uff0cBPE\uff09\u7684\u65b9\u6cd5\u6765\u8fdb\u884ctokenization\uff08\u5c06\u8f93\u5165\u6587\u672c\u62c6\u5206\u4e3atoken\uff09\u3002 \n", "BPE\u662f\u4e00\u79cd\u5e38\u89c1\u7684tokenization\u6280\u672f\uff0c\u5b83\u5c06\u8f93\u5165\u6587\u672c\u5206\u5272\u6210\u8f83\u5c0f\u7684\u5b50\u8bcd\u5355\u5143\u3002 \n", "\n", "OpenAI\u5728\u5176\u5b98\u65b9GitHub\u4e0a\u516c\u5f00\u4e86\u4e00\u4e2a\u6700\u65b0\u7684\u5f00\u6e90Python\u5e93\uff1atiktoken\uff0c\u8fd9\u4e2a\u5e93\u4e3b\u8981\u662f\u7528\u6765\u8ba1\u7b97tokens\u6570\u91cf\u7684\u3002\u76f8\u6bd4\u8f83Hugging Face\u7684tokenizer\uff0c\u5176\u901f\u5ea6\u63d0\u5347\u4e86\u597d\u51e0\u500d\n"," OPENAI_API_KEY=\"your_api_key\" \n","
\n"," \n"," 替换\"your_api_key\"为你自己的 API Key"]},{"cell_type":"code","execution_count":null,"id":"6932bd47-c6d5-4794-8102-a12b84412a93","metadata":{},"outputs":[],"source":["# 下载需要的包python-dotenv和openai\n","# 如果你需要查看安装过程日志，可删除 -q \n","!pip install -q python-dotenv\n","!pip install -q openai"]},{"cell_type":"code","execution_count":6,"id":"10446712-9fa6-4d71-94ce-2ea4cf197e54","metadata":{},"outputs":[],"source":["import os\n","import openai\n","from dotenv import load_dotenv, find_dotenv\n","\n","# 读取本地/项目的环境变量。\n","\n","# find_dotenv()寻找并定位.env文件的路径\n","# load_dotenv()读取该.env文件，并将其中的环境变量加载到当前的运行环境中 \n","# 如果你设置的是全局的环境变量，这行代码则没有任何作用。\n","_ = load_dotenv(find_dotenv())\n","\n","# 获取环境变量 OPENAI_API_KEY\n","openai.api_key = os.environ['OPENAI_API_KEY'] \n"]},{"cell_type":"markdown","id":"1297dcd5","metadata":{},"source":["## 二、对话缓存储存 \n"," \n","这种记忆允许存储消息，然后从变量中提取消息。"]},{"cell_type":"code","execution_count":2,"id":"20ad6fe2","metadata":{"height":98},"outputs":[],"source":["from langchain.chat_models import ChatOpenAI\n","from langchain.chains import ConversationChain\n","from langchain.memory import ConversationBufferMemory"]},{"cell_type":"code","execution_count":31,"id":"88bdf13d","metadata":{"height":133},"outputs":[],"source":["# 英文链\n","llm = ChatOpenAI(temperature=0.0) #temperature：预测下一个token时，概率越大的值就越平滑(平滑也就是让差异大的值之间的差异变得没那么大)，temperature值越小则生成的内容越稳定\n","memory = ConversationBufferMemory()\n","conversation = ConversationChain( #新建一个对话链（关于链后面会提到更多的细节）\n"," llm=llm, \n"," memory = memory,\n"," verbose=True #查看Langchain实际上在做什么，设为FALSE的话只给出回答，看到不到下面绿色的内容\n",")"]},{"cell_type":"code","execution_count":32,"id":"bb4968d9","metadata":{},"outputs":[],"source":["# 中文链\n","llm = ChatOpenAI(temperature=0.0) #temperature：预测下一个token时，概率越大的值就越平滑(平滑也就是让差异大的值之间的差异变得没那么大)，temperature值越小则生成的内容越稳定\n","memory_zh = ConversationBufferMemory()\n","conversation_zh = ConversationChain( #新建一个对话链（关于链后面会提到更多的细节）\n"," llm=llm, \n"," memory = memory_zh,\n"," verbose=True #查看Langchain实际上在做什么，设为FALSE的话只给出回答，看到不到下面绿色的内容\n",")"]},{"cell_type":"markdown","id":"dea83837","metadata":{},"source":["### 2.1 开始对话，第一轮"]},{"cell_type":"markdown","id":"1a3b4c42","metadata":{},"source":["当我们运行predict时，生成了一些提示，如下所见，他说“以下是人类和AI之间友好的对话，AI健谈“等等，这实际上是LangChain生成的提示，以使系统进行希望和友好的对话，并且必须保存对话，并提示了当前已完成的模型链。"]},{"cell_type":"code","execution_count":33,"id":"db24677d","metadata":{"height":47},"outputs":[{"name":"stdout","output_type":"stream","text":["\n","\n","\u001b[1m> Entering new chain...\u001b[0m\n","Prompt after formatting:\n","\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n","\n","Current conversation:\n","\n","Human: Hi, my name is Andrew\n","AI:\u001b[0m\n","\n","\u001b[1m> Finished chain.\u001b[0m\n"]},{"data":{"text/plain":["\"Hello Andrew! It's nice to meet you. How can I assist you today?\""]},"execution_count":33,"metadata":{},"output_type":"execute_result"}],"source":["conversation.predict(input=\"Hi, my name is Andrew\")"]},{"cell_type":"code","execution_count":34,"id":"154561c9","metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["\n","\n","\u001b[1m> Entering new chain...\u001b[0m\n","Prompt after formatting:\n","\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n","\n","Current conversation:\n","\n","Human: 你好, 我叫皮皮鲁\n","AI:\u001b[0m\n","\n","\u001b[1m> Finished chain.\u001b[0m\n"]},{"data":{"text/plain":["'你好，皮皮鲁！很高兴认识你。我是一个AI助手，可以回答你的问题和提供帮助。有什么我可以帮你的吗？'"]},"execution_count":34,"metadata":{},"output_type":"execute_result"}],"source":["#中文\n","conversation_zh.predict(input=\"你好, 我叫皮皮鲁\")"]},{"cell_type":"markdown","id":"e71564ad","metadata":{},"source":["### 2.2 第二轮对话"]},{"cell_type":"markdown","id":"54d006bd","metadata":{},"source":["当我们进行下一轮对话时，他会保留上面的提示"]},{"cell_type":"code","execution_count":35,"id":"cc3ef937","metadata":{"height":31},"outputs":[{"name":"stdout","output_type":"stream","text":["\n","\n","\u001b[1m> Entering new chain...\u001b[0m\n","Prompt after formatting:\n","\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n","\n","Current conversation:\n","Human: Hi, my name is Andrew\n","AI: Hello Andrew! It's nice to meet you. How can I assist you today?\n","Human: What is 1+1?\n","AI:\u001b[0m\n","\n","\u001b[1m> Finished chain.\u001b[0m\n"]},{"data":{"text/plain":["'1+1 is equal to 2.'"]},"execution_count":35,"metadata":{},"output_type":"execute_result"}],"source":["conversation.predict(input=\"What is 1+1?\")"]},{"cell_type":"code","execution_count":36,"id":"63efc1bb","metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["\n","\n","\u001b[1m> Entering new chain...\u001b[0m\n","Prompt after formatting:\n","\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n","\n","Current conversation:\n","Human: 你好, 我叫皮皮鲁\n","AI: 你好，皮皮鲁！很高兴认识你。我是一个AI助手，可以回答你的问题和提供帮助。有什么我可以帮你的吗？\n","Human: 1+1等于多少？\n","AI:\u001b[0m\n","\n","\u001b[1m> Finished chain.\u001b[0m\n"]},{"data":{"text/plain":["'1+1等于2。'"]},"execution_count":36,"metadata":{},"output_type":"execute_result"}],"source":["#中文\n","conversation_zh.predict(input=\"1+1等于多少？\")"]},{"cell_type":"markdown","id":"33cb734b","metadata":{},"source":["### 2.3 第三轮对话"]},{"cell_type":"markdown","id":"0393df3d","metadata":{},"source":["为了验证他是否记忆了前面的对话内容，我们让他回答前面已经说过的内容（我的名字），可以看到他确实输出了正确的名字，因此这个对话链随着往下进行会越来越长"]},{"cell_type":"code","execution_count":37,"id":"acf3339a","metadata":{"height":31},"outputs":[{"name":"stdout","output_type":"stream","text":["\n","\n","\u001b[1m> Entering new chain...\u001b[0m\n","Prompt after formatting:\n","\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n","\n","Current conversation:\n","Human: Hi, my name is Andrew\n","AI: Hello Andrew! It's nice to meet you. How can I assist you today?\n","Human: What is 1+1?\n","AI: 1+1 is equal to 2.\n","Human: What is my name?\n","AI:\u001b[0m\n","\n","\u001b[1m> Finished chain.\u001b[0m\n"]},{"data":{"text/plain":["'Your name is Andrew.'"]},"execution_count":37,"metadata":{},"output_type":"execute_result"}],"source":["conversation.predict(input=\"What is my name?\")"]},{"cell_type":"code","execution_count":38,"id":"2206e5b7","metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["\n","\n","\u001b[1m> Entering new chain...\u001b[0m\n","Prompt after formatting:\n","\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n","\n","Current conversation:\n","Human: 你好, 我叫皮皮鲁\n","AI: 你好，皮皮鲁！很高兴认识你。我是一个AI助手，可以回答你的问题和提供帮助。有什么我可以帮你的吗？\n","Human: 1+1等于多少？\n","AI: 1+1等于2。\n","Human: 我叫什么名字？\n","AI:\u001b[0m\n","\n","\u001b[1m> Finished chain.\u001b[0m\n"]},{"data":{"text/plain":["'你叫皮皮鲁。'"]},"execution_count":38,"metadata":{},"output_type":"execute_result"}],"source":["#中文\n","conversation_zh.predict(input=\"我叫什么名字？\")"]},{"cell_type":"markdown","id":"5a96a8d9","metadata":{},"source":["### 2.4 .memory.buffer存储了当前为止所有的对话信息"]},{"cell_type":"code","execution_count":39,"id":"2529400d","metadata":{"height":31},"outputs":[{"name":"stdout","output_type":"stream","text":["Human: Hi, my name is Andrew\n","AI: Hello Andrew! It's nice to meet you. How can I assist you today?\n","Human: What is 1+1?\n","AI: 1+1 is equal to 2.\n","Human: What is my name?\n","AI: Your name is Andrew.\n"]}],"source":["print(memory.buffer) #提取历史消息"]},{"cell_type":"code","execution_count":40,"id":"d948aeb2","metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["Human: 你好, 我叫皮皮鲁\n","AI: 你好，皮皮鲁！很高兴认识你。我是一个AI助手，可以回答你的问题和提供帮助。有什么我可以帮你的吗？\n","Human: 1+1等于多少？\n","AI: 1+1等于2。\n","Human: 我叫什么名字？\n","AI: 你叫皮皮鲁。\n"]}],"source":["# 中文\n","print(memory_zh.buffer) #提取历史消息"]},{"cell_type":"markdown","id":"6bd222c3","metadata":{},"source":["### 2.5 也可以通过memory.load_memory_variables({})打印历史消息"]},{"cell_type":"markdown","id":"0b5de846","metadata":{},"source":["这里的花括号实际上是一个空字典，有一些更高级的功能，使用户可以使用更复杂的输入，但我们不会在这个短期课程中讨论它们，所以不要担心为什么这里有一个空的花括号。"]},{"cell_type":"code","execution_count":41,"id":"5018cb0a","metadata":{"height":31},"outputs":[{"data":{"text/plain":["{'history': \"Human: Hi, my name is Andrew\\nAI: Hello Andrew! It's nice to meet you. How can I assist you today?\\nHuman: What is 1+1?\\nAI: 1+1 is equal to 2.\\nHuman: What is my name?\\nAI: Your name is Andrew.\"}"]},"execution_count":41,"metadata":{},"output_type":"execute_result"}],"source":["memory.load_memory_variables({})"]},{"cell_type":"code","execution_count":42,"id":"af4b8b12","metadata":{},"outputs":[{"data":{"text/plain":["{'history': 'Human: 你好, 我叫皮皮鲁\\nAI: 你好，皮皮鲁！很高兴认识你。我是一个AI助手，可以回答你的问题和提供帮助。有什么我可以帮你的吗？\\nHuman: 1+1等于多少？\\nAI: 1+1等于2。\\nHuman: 我叫什么名字？\\nAI: 你叫皮皮鲁。'}"]},"execution_count":42,"metadata":{},"output_type":"execute_result"}],"source":["# 中文\n","memory_zh.load_memory_variables({})"]},{"cell_type":"markdown","id":"07d2e892","metadata":{},"source":["### 2.6 添加指定的输入输出内容到记忆缓存区"]},{"cell_type":"code","execution_count":43,"id":"14219b70","metadata":{"height":31},"outputs":[],"source":["memory = ConversationBufferMemory() #新建一个空的对话缓存记忆"]},{"cell_type":"code","execution_count":45,"id":"a36e9905","metadata":{"height":48},"outputs":[],"source":["memory.save_context({\"input\": \"Hi\"}, #向缓存区添加指定对话的输入输出\n"," {\"output\": \"What's up\"})"]},{"cell_type":"code","execution_count":46,"id":"61631b1f","metadata":{"height":31},"outputs":[{"name":"stdout","output_type":"stream","text":["Human: Hi\n","AI: What's up\n","Human: Hi\n","AI: What's up\n"]}],"source":["print(memory.buffer) #查看缓存区结果"]},{"cell_type":"code","execution_count":47,"id":"a2fdf9ec","metadata":{"height":31},"outputs":[{"data":{"text/plain":["{'history': \"Human: Hi\\nAI: What's up\\nHuman: Hi\\nAI: What's up\"}"]},"execution_count":47,"metadata":{},"output_type":"execute_result"}],"source":["memory.load_memory_variables({}) #再次加载记忆变量"]},{"cell_type":"code","execution_count":48,"id":"27d8dd2f","metadata":{},"outputs":[{"data":{"text/plain":["{'history': 'Human: 你好，我叫皮皮鲁\\nAI: 你好啊，我叫鲁西西'}"]},"execution_count":48,"metadata":{},"output_type":"execute_result"}],"source":["#中文\n","memory = ConversationBufferMemory()\n","memory.save_context({\"input\": \"你好，我叫皮皮鲁\"}, \n"," {\"output\": \"你好啊，我叫鲁西西\"})\n","memory.load_memory_variables({})"]},{"cell_type":"markdown","id":"2ac544f2","metadata":{},"source":["继续添加新的内容，对话历史都保存下来在了！"]},{"cell_type":"code","execution_count":49,"id":"7ca79256","metadata":{"height":64},"outputs":[],"source":["memory.save_context({\"input\": \"Not much, just hanging\"}, \n"," {\"output\": \"Cool\"})"]},{"cell_type":"code","execution_count":50,"id":"890a4497","metadata":{"height":31},"outputs":[{"data":{"text/plain":["{'history': 'Human: 你好，我叫皮皮鲁\\nAI: 你好啊，我叫鲁西西\\nHuman: Not much, just hanging\\nAI: Cool'}"]},"execution_count":50,"metadata":{},"output_type":"execute_result"}],"source":["memory.load_memory_variables({})"]},{"cell_type":"code","execution_count":51,"id":"2b614406","metadata":{},"outputs":[{"data":{"text/plain":["{'history': 'Human: 你好，我叫皮皮鲁\\nAI: 你好啊，我叫鲁西西\\nHuman: Not much, just hanging\\nAI: Cool\\nHuman: 很高兴和你成为朋友！\\nAI: 是的，让我们一起去冒险吧！'}"]},"execution_count":51,"metadata":{},"output_type":"execute_result"}],"source":["#中文\n","memory.save_context({\"input\": \"很高兴和你成为朋友！\"}, \n"," {\"output\": \"是的，让我们一起去冒险吧！\"})\n","memory.load_memory_variables({})"]},{"cell_type":"markdown","id":"8839314a","metadata":{},"source":["当我们在使用大型语言模型进行聊天对话时，**大型语言模型本身实际上是无状态的。语言模型本身并不记得到目前为止的历史对话**。每次调用API结点都是独立的。\n","\n","聊天机器人似乎有记忆，只是因为通常有快速的代码可以向LLM提供迄今为止的完整对话以及上下文。因此，Memory可以明确地存储到目前为止的所有术语或对话。这个Memory存储器被用作输入或附加上下文到LLM中，以便它可以生成一个输出，就好像它只有在进行下一轮对话的时候，才知道之前说过什么。\n"]},{"cell_type":"markdown","id":"cf98e9ff","metadata":{},"source":["## 三、对话缓存窗口储存\n"," \n","随着对话变得越来越长，所需的内存量也变得非常长。将大量的tokens发送到LLM的成本，也会变得更加昂贵,这也就是为什么API的调用费用，通常是基于它需要处理的tokens数量而收费的。\n"," \n","针对以上问题，LangChain也提供了几种方便的memory来保存历史对话。\n","其中，对话缓存窗口记忆只保留一个窗口大小的对话缓存区窗口记忆。它只使用最近的n次交互。这可以用于保持最近交互的滑动窗口，以便缓冲区不会过大"]},{"cell_type":"code","execution_count":52,"id":"66eeccc3","metadata":{"height":47},"outputs":[],"source":["from langchain.memory import ConversationBufferWindowMemory"]},{"cell_type":"markdown","id":"641477a4","metadata":{},"source":["### 3.1 向memory添加两轮对话，并查看记忆变量当前的记录"]},{"cell_type":"code","execution_count":53,"id":"3ea6233e","metadata":{"height":47},"outputs":[],"source":["memory = ConversationBufferWindowMemory(k=1) # k=1表明只保留一个对话记忆 "]},{"cell_type":"code","execution_count":54,"id":"dc4553fb","metadata":{"height":115},"outputs":[],"source":["memory.save_context({\"input\": \"Hi\"},\n"," {\"output\": \"What's up\"})\n","memory.save_context({\"input\": \"Not much, just hanging\"},\n"," {\"output\": \"Cool\"})\n"]},{"cell_type":"code","execution_count":55,"id":"6a788403","metadata":{"height":31},"outputs":[{"data":{"text/plain":["{'history': 'Human: Not much, just hanging\\nAI: Cool'}"]},"execution_count":55,"metadata":{},"output_type":"execute_result"}],"source":["memory.load_memory_variables({})"]},{"cell_type":"markdown","id":"9b401f0b","metadata":{},"source":["### 3.2 在看一个例子，发现和上面的结果一样，只保留了一轮对话记忆"]},{"cell_type":"code","execution_count":56,"id":"68a2907c","metadata":{},"outputs":[{"data":{"text/plain":["{'history': 'Human: 很高兴和你成为朋友！\\nAI: 是的，让我们一起去冒险吧！'}"]},"execution_count":56,"metadata":{},"output_type":"execute_result"}],"source":["#中文\n","memory = ConversationBufferWindowMemory(k=1) # k=1表明只保留一个对话记忆 \n","memory.save_context({\"input\": \"你好，我叫皮皮鲁\"}, \n"," {\"output\": \"你好啊，我叫鲁西西\"})\n","memory.save_context({\"input\": \"很高兴和你成为朋友！\"}, \n"," {\"output\": \"是的，让我们一起去冒险吧！\"})\n","memory.load_memory_variables({})"]},{"cell_type":"markdown","id":"63bda148","metadata":{},"source":["### 3.3 将对话缓存窗口记忆应用到对话链中"]},{"cell_type":"code","execution_count":57,"id":"4087bc87","metadata":{"height":133},"outputs":[],"source":["llm = ChatOpenAI(temperature=0.0)\n","memory = ConversationBufferWindowMemory(k=1)\n","conversation = ConversationChain( \n"," llm=llm, \n"," memory = memory,\n"," verbose=False #这里改为FALSE不显示提示，你可以尝试修改为TRUE后的结果\n",")"]},{"cell_type":"code","execution_count":61,"id":"0c737101","metadata":{},"outputs":[],"source":["# 中文版\n","llm = ChatOpenAI(temperature=0.0)\n","memory_zh = ConversationBufferWindowMemory(k=1)\n","conversation_zh = ConversationChain( \n"," llm=llm, \n"," memory = memory_zh,\n"," verbose=False #这里改为FALSE不显示提示，你可以尝试修改为TRUE后的结果\n",")"]},{"cell_type":"markdown","id":"b6d661e3","metadata":{},"source":["注意此处！由于这里用的是一个窗口的记忆，因此只能保存一轮的历史消息，因此AI并不能知道你第一轮对话中提到的名字，他最多只能记住上一轮（第二轮）的对话信息"]},{"cell_type":"code","execution_count":58,"id":"4faaa952","metadata":{"height":47},"outputs":[{"data":{"text/plain":["\"Hello Andrew! It's nice to meet you. How can I assist you today?\""]},"execution_count":58,"metadata":{},"output_type":"execute_result"}],"source":["conversation.predict(input=\"Hi, my name is Andrew\")"]},{"cell_type":"code","execution_count":63,"id":"b3a941b5","metadata":{},"outputs":[{"data":{"text/plain":["'你好，皮皮鲁！很高兴认识你。我是一个AI助手，可以回答你的问题和提供帮助。有什么我可以帮你的吗？'"]},"execution_count":63,"metadata":{},"output_type":"execute_result"}],"source":["conversation_zh.predict(input=\"你好，我是皮皮鲁\")"]},{"cell_type":"code","execution_count":64,"id":"bb20ddaa","metadata":{"height":31},"outputs":[{"data":{"text/plain":["'1+1 is equal to 2.'"]},"execution_count":64,"metadata":{},"output_type":"execute_result"}],"source":["conversation.predict(input=\"What is 1+1?\")"]},{"cell_type":"code","execution_count":65,"id":"90bf6403","metadata":{},"outputs":[{"data":{"text/plain":["'1+1等于2。'"]},"execution_count":65,"metadata":{},"output_type":"execute_result"}],"source":["conversation_zh.predict(input=\"1+1等于几\")"]},{"cell_type":"code","execution_count":66,"id":"489b2194","metadata":{"height":31},"outputs":[{"data":{"text/plain":["\"I'm sorry, but I don't have access to personal information.\""]},"execution_count":66,"metadata":{},"output_type":"execute_result"}],"source":["conversation.predict(input=\"What is my name?\")"]},{"cell_type":"code","execution_count":67,"id":"932ace4f","metadata":{},"outputs":[{"data":{"text/plain":["'很抱歉，我无法知道您的名字。'"]},"execution_count":67,"metadata":{},"output_type":"execute_result"}],"source":["conversation_zh.predict(input=\"我叫什么名字\")"]},{"cell_type":"markdown","id":"d2931b92","metadata":{},"source":["## 四、对话token缓存储存"]},{"cell_type":"markdown","id":"dff5b4c7","metadata":{},"source":["使用对话token缓存记忆，内存将限制保存的token数量。如果token数量超出指定数目，它会切掉这个对话的早期部分\n","以保留与最近的交流相对应的token数量，但不超过token限制。"]},{"cell_type":"code","execution_count":null,"id":"9f6d063c","metadata":{"height":31},"outputs":[],"source":["#!pip install tiktoken #需要用到tiktoken包，没有的可以先安装一下"]},{"cell_type":"markdown","id":"2187cfe6","metadata":{},"source":["### 4.1 导入相关包和API密钥"]},{"cell_type":"code","execution_count":68,"id":"fb9020ed","metadata":{"height":81},"outputs":[],"source":["from langchain.memory import ConversationTokenBufferMemory\n","from langchain.llms import OpenAI\n","\n","llm = ChatOpenAI(temperature=0.0)"]},{"cell_type":"markdown","id":"f3a84112","metadata":{},"source":["### 4.2 限制token数量，进行测试"]},{"cell_type":"code","execution_count":69,"id":"43582ee6","metadata":{"height":149},"outputs":[],"source":["memory = ConversationTokenBufferMemory(llm=llm, max_token_limit=30)\n","memory.save_context({\"input\": \"AI is what?!\"},\n"," {\"output\": \"Amazing!\"})\n","memory.save_context({\"input\": \"Backpropagation is what?\"},\n"," {\"output\": \"Beautiful!\"})\n","memory.save_context({\"input\": \"Chatbots are what?\"}, \n"," {\"output\": \"Charming!\"})"]},{"cell_type":"markdown","id":"7b62b2e1","metadata":{},"source":["可以看到前面超出的的token已经被舍弃了！！！"]},{"cell_type":"code","execution_count":70,"id":"284288e1","metadata":{"height":31},"outputs":[{"data":{"text/plain":["{'history': 'AI: Beautiful!\\nHuman: Chatbots are what?\\nAI: Charming!'}"]},"execution_count":70,"metadata":{},"output_type":"execute_result"}],"source":["memory.load_memory_variables({})"]},{"cell_type":"markdown","id":"f7f6be43","metadata":{},"source":["### 4.3 中文例子"]},{"cell_type":"code","execution_count":71,"id":"e9191020","metadata":{},"outputs":[{"data":{"text/plain":["{'history': 'AI: 轻舟已过万重山。'}"]},"execution_count":71,"metadata":{},"output_type":"execute_result"}],"source":["memory = ConversationTokenBufferMemory(llm=llm, max_token_limit=30)\n","memory.save_context({\"input\": \"朝辞白帝彩云间，\"}, \n"," {\"output\": \"千里江陵一日还。\"})\n","memory.save_context({\"input\": \"两岸猿声啼不住，\"},\n"," {\"output\": \"轻舟已过万重山。\"})\n","memory.load_memory_variables({})"]},{"cell_type":"markdown","id":"5e4d918b","metadata":{},"source":["补充： \n","\n","ChatGPT使用一种基于字节对编码（Byte Pair Encoding，BPE）的方法来进行tokenization（将输入文本拆分为token）。 \n","BPE是一种常见的tokenization技术，它将输入文本分割成较小的子词单元。 \n","\n","OpenAI在其官方GitHub上公开了一个最新的开源Python库：tiktoken，这个库主要是用来计算tokens数量的。相比较Hugging Face的tokenizer，其速度提升了好几倍\n", " OPENAI_API_KEY=\"your_api_key\" \n", "
\n", " \n", " \u66ff\u6362\"your_api_key\"\u4e3a\u4f60\u81ea\u5df1\u7684 API Key"]}, {"cell_type": "code", "execution_count": 1, "id": "cc33ceb1-535f-454d-988c-347a8b14fd72", "metadata": {}, "outputs": [], "source": ["# \u4e0b\u8f7d\u9700\u8981\u7684\u5305python-dotenv\u548copenai\n", "# \u5982\u679c\u4f60\u9700\u8981\u67e5\u770b\u5b89\u88c5\u8fc7\u7a0b\u65e5\u5fd7\uff0c\u53ef\u5220\u9664 -q \n", "!pip install -q python-dotenv\n", "!pip install -q openai"]}, {"cell_type": "code", "execution_count": 2, "id": "e3c97235-f101-47f2-92db-1c37f4bf9845", "metadata": {"tags": []}, "outputs": [], "source": ["import os\n", "import openai\n", "from dotenv import load_dotenv, find_dotenv\n", "\n", "# \u8bfb\u53d6\u672c\u5730/\u9879\u76ee\u7684\u73af\u5883\u53d8\u91cf\u3002\n", "\n", "# find_dotenv()\u5bfb\u627e\u5e76\u5b9a\u4f4d.env\u6587\u4ef6\u7684\u8def\u5f84\n", "# load_dotenv()\u8bfb\u53d6\u8be5.env\u6587\u4ef6\uff0c\u5e76\u5c06\u5176\u4e2d\u7684\u73af\u5883\u53d8\u91cf\u52a0\u8f7d\u5230\u5f53\u524d\u7684\u8fd0\u884c\u73af\u5883\u4e2d \n", "# \u5982\u679c\u4f60\u8bbe\u7f6e\u7684\u662f\u5168\u5c40\u7684\u73af\u5883\u53d8\u91cf\uff0c\u8fd9\u884c\u4ee3\u7801\u5219\u6ca1\u6709\u4efb\u4f55\u4f5c\u7528\u3002\n", "_ = load_dotenv(find_dotenv())\n", "\n", "# \u83b7\u53d6\u73af\u5883\u53d8\u91cf OPENAI_API_KEY\n", "openai.api_key = os.environ['OPENAI_API_KEY'] "]}, {"cell_type": "code", "execution_count": 52, "id": "af8c3c96", "metadata": {}, "outputs": [{"data": {"text/plain": ["'\\n\\n\u4eba\u5de5\u667a\u80fd\u662f\u4e00\u9879\u6781\u5177\u524d\u666f\u7684\u6280\u672f\uff0c\u5b83\u7684\u53d1\u5c55\u6b63\u5728\u6539\u53d8\u4eba\u7c7b\u7684\u751f\u6d3b\u65b9\u5f0f\uff0c\u5e26\u6765\u4e86\u65e0\u6570\u7684\u4fbf\u5229\uff0c\u4e5f\u88ab\u8ba4\u4e3a\u662f\u672a\u6765\u53d1\u5c55\u7684\u91cd\u8981\u6807\u5fd7\u3002\u4eba\u5de5\u667a\u80fd\u7684\u53d1\u5c55\u8ba9\u8bb8\u591a\u590d\u6742\u7684\u4efb\u52a1\u53d8\u5f97\u66f4\u52a0\u5bb9\u6613\uff0c\u66f4\u9ad8\u6548\u7684\u5b8c\u6210\uff0c\u8282\u7701\u4e86\u5927\u91cf\u7684\u65f6\u95f4\u548c\u7cbe\u529b\uff0c\u4e3a\u4eba\u7c7b\u53d1\u5c55\u5e26\u6765\u4e86\u6781\u5927\u7684\u5e2e\u52a9\u3002'"]}, "execution_count": 52, "metadata": {}, "output_type": "execute_result"}], "source": ["from langchain.llms import OpenAI\n", "\n", "llm = OpenAI(model_name=\"text-davinci-003\",max_tokens=1024)\n", "llm(\"\u600e\u4e48\u8bc4\u4ef7\u4eba\u5de5\u667a\u80fd\")"]}, {"cell_type": "markdown", "id": "8cb7a7ec", "metadata": {"height": 30}, "source": ["## \u4e00\u3001\u5bfc\u5165embedding\u6a21\u578b\u548c\u5411\u91cf\u5b58\u50a8\u7ec4\u4ef6\n", "\u4f7f\u7528Dock Array\u5185\u5b58\u641c\u7d22\u5411\u91cf\u5b58\u50a8\uff0c\u4f5c\u4e3a\u4e00\u4e2a\u5185\u5b58\u5411\u91cf\u5b58\u50a8\uff0c\u4e0d\u9700\u8981\u8fde\u63a5\u5916\u90e8\u6570\u636e\u5e93"]}, {"cell_type": "code", "execution_count": 3, "id": "974acf8e-8f88-42de-88f8-40a82cb58e8b", "metadata": {"height": 98}, "outputs": [], "source": ["from langchain.chains import RetrievalQA #\u68c0\u7d22QA\u94fe\uff0c\u5728\u6587\u6863\u4e0a\u8fdb\u884c\u68c0\u7d22\n", "from langchain.chat_models import ChatOpenAI #openai\u6a21\u578b\n", "from langchain.document_loaders import CSVLoader #\u6587\u6863\u52a0\u8f7d\u5668\uff0c\u91c7\u7528csv\u683c\u5f0f\u5b58\u50a8\n", "from langchain.vectorstores import DocArrayInMemorySearch #\u5411\u91cf\u5b58\u50a8\n", "from IPython.display import display, Markdown #\u5728jupyter\u663e\u793a\u4fe1\u606f\u7684\u5de5\u5177"]}, {"cell_type": "code", "execution_count": 4, "id": "7249846e", "metadata": {"height": 75}, "outputs": [], "source": ["#\u8bfb\u53d6\u6587\u4ef6\n", "file = 'OutdoorClothingCatalog_1000.csv'\n", "loader = CSVLoader(file_path=file)"]}, {"cell_type": "code", "execution_count": 24, "id": "7724f00e", "metadata": {"height": 30}, "outputs": [{"data": {"text/html": ["| \n", " | 0 | \n", "1 | \n", "2 | \n", "
|---|---|---|---|
| 0 | \n", "NaN | \n", "name | \n", "description | \n", "
| 1 | \n", "0.0 | \n", "Women's Campside Oxfords | \n", "This ultracomfortable lace-to-toe Oxford boast... | \n", "
| 2 | \n", "1.0 | \n", "Recycled Waterhog Dog Mat, Chevron Weave | \n", "Protect your floors from spills and splashing ... | \n", "
| 3 | \n", "2.0 | \n", "Infant and Toddler Girls' Coastal Chill Swimsu... | \n", "She'll love the bright colors, ruffles and exc... | \n", "
| 4 | \n", "3.0 | \n", "Refresh Swimwear, V-Neck Tankini Contrasts | \n", "Whether you're going for a swim or heading out... | \n", "
| ... | \n", "... | \n", "... | \n", "... | \n", "
| 996 | \n", "995.0 | \n", "Men's Classic Denim, Standard Fit | \n", "Crafted from premium denim that will last wash... | \n", "
| 997 | \n", "996.0 | \n", "CozyPrint Sweater Fleece Pullover | \n", "The ultimate sweater fleece - made from superi... | \n", "
| 998 | \n", "997.0 | \n", "Women's NRS Endurance Spray Paddling Pants | \n", "These comfortable and affordable splash paddli... | \n", "
| 999 | \n", "998.0 | \n", "Women's Stop Flies Hoodie | \n", "This great-looking hoodie uses No Fly Zone Tec... | \n", "
| 1000 | \n", "999.0 | \n", "Modern Utility Bag | \n", "This US-made crossbody bag is built with the s... | \n", "
1001 rows \u00d7 3 columns
\n", "\n"," OPENAI_API_KEY=\"your_api_key\" \n","
\n"," \n"," 替换\"your_api_key\"为你自己的 API Key"]},{"cell_type":"code","execution_count":1,"id":"cc33ceb1-535f-454d-988c-347a8b14fd72","metadata":{},"outputs":[],"source":["# 下载需要的包python-dotenv和openai\n","# 如果你需要查看安装过程日志，可删除 -q \n","!pip install -q python-dotenv\n","!pip install -q openai"]},{"cell_type":"code","execution_count":2,"id":"e3c97235-f101-47f2-92db-1c37f4bf9845","metadata":{"tags":[]},"outputs":[],"source":["import os\n","import openai\n","from dotenv import load_dotenv, find_dotenv\n","\n","# 读取本地/项目的环境变量。\n","\n","# find_dotenv()寻找并定位.env文件的路径\n","# load_dotenv()读取该.env文件，并将其中的环境变量加载到当前的运行环境中 \n","# 如果你设置的是全局的环境变量，这行代码则没有任何作用。\n","_ = load_dotenv(find_dotenv())\n","\n","# 获取环境变量 OPENAI_API_KEY\n","openai.api_key = os.environ['OPENAI_API_KEY'] "]},{"cell_type":"code","execution_count":52,"id":"af8c3c96","metadata":{},"outputs":[{"data":{"text/plain":["'\\n\\n人工智能是一项极具前景的技术，它的发展正在改变人类的生活方式，带来了无数的便利，也被认为是未来发展的重要标志。人工智能的发展让许多复杂的任务变得更加容易，更高效的完成，节省了大量的时间和精力，为人类发展带来了极大的帮助。'"]},"execution_count":52,"metadata":{},"output_type":"execute_result"}],"source":["from langchain.llms import OpenAI\n","\n","llm = OpenAI(model_name=\"text-davinci-003\",max_tokens=1024)\n","llm(\"怎么评价人工智能\")"]},{"cell_type":"markdown","id":"8cb7a7ec","metadata":{"height":30},"source":["## 一、导入embedding模型和向量存储组件\n","使用Dock Array内存搜索向量存储，作为一个内存向量存储，不需要连接外部数据库"]},{"cell_type":"code","execution_count":3,"id":"974acf8e-8f88-42de-88f8-40a82cb58e8b","metadata":{"height":98},"outputs":[],"source":["from langchain.chains import RetrievalQA #检索QA链，在文档上进行检索\n","from langchain.chat_models import ChatOpenAI #openai模型\n","from langchain.document_loaders import CSVLoader #文档加载器，采用csv格式存储\n","from langchain.vectorstores import DocArrayInMemorySearch #向量存储\n","from IPython.display import display, Markdown #在jupyter显示信息的工具"]},{"cell_type":"code","execution_count":4,"id":"7249846e","metadata":{"height":75},"outputs":[],"source":["#读取文件\n","file = 'OutdoorClothingCatalog_1000.csv'\n","loader = CSVLoader(file_path=file)"]},{"cell_type":"code","execution_count":24,"id":"7724f00e","metadata":{"height":30},"outputs":[{"data":{"text/html":["| \n"," | 0 | \n","1 | \n","2 | \n","
|---|---|---|---|
| 0 | \n","NaN | \n","name | \n","description | \n","
| 1 | \n","0.0 | \n","Women's Campside Oxfords | \n","This ultracomfortable lace-to-toe Oxford boast... | \n","
| 2 | \n","1.0 | \n","Recycled Waterhog Dog Mat, Chevron Weave | \n","Protect your floors from spills and splashing ... | \n","
| 3 | \n","2.0 | \n","Infant and Toddler Girls' Coastal Chill Swimsu... | \n","She'll love the bright colors, ruffles and exc... | \n","
| 4 | \n","3.0 | \n","Refresh Swimwear, V-Neck Tankini Contrasts | \n","Whether you're going for a swim or heading out... | \n","
| ... | \n","... | \n","... | \n","... | \n","
| 996 | \n","995.0 | \n","Men's Classic Denim, Standard Fit | \n","Crafted from premium denim that will last wash... | \n","
| 997 | \n","996.0 | \n","CozyPrint Sweater Fleece Pullover | \n","The ultimate sweater fleece - made from superi... | \n","
| 998 | \n","997.0 | \n","Women's NRS Endurance Spray Paddling Pants | \n","These comfortable and affordable splash paddli... | \n","
| 999 | \n","998.0 | \n","Women's Stop Flies Hoodie | \n","This great-looking hoodie uses No Fly Zone Tec... | \n","
| 1000 | \n","999.0 | \n","Modern Utility Bag | \n","This US-made crossbody bag is built with the s... | \n","
1001 rows × 3 columns
\n","