{"cells": [{"cell_type": "markdown", "id": "ba5f8741", "metadata": {}, "source": ["# 插拔式", "", "这个笔记本是基于[插件检索](./custom_agent_with_plugin_retrieval.html)的想法构建的，但是从`plugnplai`目录中提取所有工具 - 一组AI插件。"]}, {"cell_type": "markdown", "id": "fea4812c", "metadata": {}, "source": ["## 设置环境", "", "进行必要的导入等操作。"]}, {"cell_type": "markdown", "id": "aca08be8", "metadata": {}, "source": ["安装 plugnplai 库，从 https://plugplai.com 目录获取活动插件列表。"]}, {"cell_type": "code", "execution_count": 1, "id": "52e248c9", "metadata": {}, "outputs": [{"name": "stdout", "output_type": "stream", "text": ["\n", "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip available: \u001b[0m\u001b[31;49m22.3.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.1.1\u001b[0m\n", "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n", "Note: you may need to restart the kernel to use updated packages.\n"]}], "source": ["# 安装 plugnplai 包", "!pip install plugnplai -q"]}, {"cell_type": "code", "execution_count": 2, "id": "9af9734e", "metadata": {}, "outputs": [], "source": ["import re  # 导入正则表达式模块", "from typing import Union  # 导入Union类型", "", "import plugnplai  # 导入plugnplai模块", "from langchain.agents import (  # 导入langchain.agents模块中的以下类", "    AgentExecutor,  # AgentExecutor类", "    AgentOutputParser,  # AgentOutputParser类", "    LLMSingleActionAgent,  # LLMSingleActionAgent类", ")", "from langchain.chains import LLMChain  # 导入LLMChain类", "from langchain.prompts import StringPromptTemplate  # 导入StringPromptTemplate类", "from langchain_community.agent_toolkits import NLAToolkit  # 导入NLAToolkit类", "from langchain_community.tools.plugin import AIPlugin  # 导入AIPlugin类", "from langchain_core.agents import AgentAction, AgentFinish  # 导入AgentAction和AgentFinish类", "from langchain_openai import OpenAI  # 导入OpenAI类", "以上是给定的代码的翻译结果，已经在代码上方添加了注释。"]}, {"cell_type": "markdown", "id": "2f91d8b4", "metadata": {}, "source": ["## 设置LLM"]}, {"cell_type": "code", "execution_count": 4, "id": "a1a3b59c", "metadata": {}, "outputs": [], "source": ["# 导入OpenAI类", "from openai import OpenAI", "", "# 创建OpenAI对象并设置温度为0", "llm = OpenAI(temperature=0)"]}, {"cell_type": "markdown", "id": "6df0253f", "metadata": {}, "source": ["## 设置插件", "", "加载并索引插件"]}, {"cell_type": "code", "execution_count": 8, "id": "9e0f7882", "metadata": {}, "outputs": [], "source": ["# 从plugnplai.com获取所有插件", "urls = plugnplai.get_plugins()", "", "# 获取ChatGPT插件 - 仅获取ChatGPT验证的插件", "urls = plugnplai.get_plugins(filter=\"ChatGPT\")", "", "# 获取可用的插件 - 仅获取经过测试的插件（进行中）", "urls = plugnplai.get_plugins(filter=\"working\")", "", "# 从urls中的每个url获取AI插件的信息并创建AIPlugin对象", "AI_PLUGINS = [AIPlugin.from_url(url + \"/.well-known/ai-plugin.json\") for url in urls]"]}, {"cell_type": "markdown", "id": "17362717", "metadata": {}, "source": ["## 工具检索器", "", "我们将使用一个向量存储库为每个工具描述创建嵌入。然后，对于传入的查询，我们可以为该查询创建嵌入，并对相关工具进行相似性搜索。"]}, {"cell_type": "code", "execution_count": 4, "id": "77c4be4b", "metadata": {}, "outputs": [], "source": ["# 导入所需的模块", "from langchain_community.vectorstores import FAISS", "from langchain_core.documents import Document", "from langchain_openai import OpenAIEmbeddings"]}, {"cell_type": "code", "execution_count": 5, "id": "9092a158", "metadata": {}, "outputs": [{"name": "stderr", "output_type": "stream", "text": ["Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n", "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n", "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n", "Attempting to load an OpenAPI 3.0.2 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n", "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n", "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n", "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n", "Attempting to load an OpenAPI 3.0.1 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n", "Attempting to load a Swagger 2.0 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n"]}], "source": ["# 导入OpenAIEmbeddings模块", "embeddings = OpenAIEmbeddings()", "", "# 创建一个包含多个Document对象的列表", "docs = [", "    Document(", "        page_content=plugin.description_for_model,", "        metadata={\"plugin_name\": plugin.name_for_model},", "    )", "    for plugin in AI_PLUGINS", "]", "", "# 使用docs和embeddings创建一个vector_store对象", "vector_store = FAISS.from_documents(docs, embeddings)", "", "# 创建一个包含多个NLAToolkit对象的字典", "toolkits_dict = {", "    plugin.name_for_model: NLAToolkit.from_llm_and_ai_plugin(llm, plugin)", "    for plugin in AI_PLUGINS", "}"]}, {"cell_type": "code", "execution_count": 6, "id": "735a7566", "metadata": {}, "outputs": [], "source": ["retriever = vector_store.as_retriever()  # 将vector_store转换为检索器", "", "def get_tools(query):", "    # 获取包含要使用的插件的文档", "    docs = retriever.invoke(query)", "    # 获取每个插件的工具包", "    tool_kits = [toolkits_dict[d.metadata[\"plugin_name\"]] for d in docs]", "    # 获取每个端点的单独NLAChain工具", "    tools = []", "    for tk in tool_kits:", "        tools.extend(tk.nla_tools)", "    return tools  # 返回工具列表"]}, {"cell_type": "markdown", "id": "7699afd7", "metadata": {}, "source": ["我们现在可以测试这个检索器，看看它是否能正常工作。"]}, {"cell_type": "code", "execution_count": 7, "id": "425f2886", "metadata": {}, "outputs": [{"data": {"text/plain": ["['Milo.askMilo',\n", " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.search_all_actions',\n", " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.preview_a_zap',\n", " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.get_configuration_link',\n", " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.list_exposed_actions',\n", " 'SchoolDigger_API_V2.0.Autocomplete_GetSchools',\n", " 'SchoolDigger_API_V2.0.Districts_GetAllDistricts2',\n", " 'SchoolDigger_API_V2.0.Districts_GetDistrict2',\n", " 'SchoolDigger_API_V2.0.Rankings_GetSchoolRank2',\n", " 'SchoolDigger_API_V2.0.Rankings_GetRank_District',\n", " 'SchoolDigger_API_V2.0.Schools_GetAllSchools20',\n", " 'SchoolDigger_API_V2.0.Schools_GetSchool20',\n", " 'Speak.translate',\n", " 'Speak.explainPhrase',\n", " 'Speak.explainTask']"]}, "execution_count": 7, "metadata": {}, "output_type": "execute_result"}], "source": ["# 导入get_tools函数", "from some_module import get_tools", "", "# 调用get_tools函数，并传入\"What could I do today with my kiddo\"作为参数", "tools = get_tools(\"What could I do today with my kiddo\")", "", "# 使用列表推导式，获取tools列表中每个元素的name属性，并将结果存储在新的列表中", "[name for t in tools]"]}, {"cell_type": "code", "execution_count": 8, "id": "3aa88768", "metadata": {}, "outputs": [{"data": {"text/plain": ["['Open_AI_Klarna_product_Api.productsUsingGET',\n", " 'Milo.askMilo',\n", " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.search_all_actions',\n", " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.preview_a_zap',\n", " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.get_configuration_link',\n", " 'Zapier_Natural_Language_Actions_(NLA)_API_(Dynamic)_-_Beta.list_exposed_actions',\n", " 'SchoolDigger_API_V2.0.Autocomplete_GetSchools',\n", " 'SchoolDigger_API_V2.0.Districts_GetAllDistricts2',\n", " 'SchoolDigger_API_V2.0.Districts_GetDistrict2',\n", " 'SchoolDigger_API_V2.0.Rankings_GetSchoolRank2',\n", " 'SchoolDigger_API_V2.0.Rankings_GetRank_District',\n", " 'SchoolDigger_API_V2.0.Schools_GetAllSchools20',\n", " 'SchoolDigger_API_V2.0.Schools_GetSchool20']"]}, "execution_count": 8, "metadata": {}, "output_type": "execute_result"}], "source": ["# 获取工具函数，参数为用户输入的问题", "tools = get_tools(\"我可以买什么样的衬衫？\")", "# 打印工具列表中每个工具的名称", "[t.name for t in tools]"]}, {"cell_type": "markdown", "id": "2e7a075c", "metadata": {}, "source": ["## 提示模板", "", "提示模板相当标准，因为我们实际上并没有在实际提示模板中改变太多逻辑，而是改变了检索的方式。"]}, {"cell_type": "code", "execution_count": 9, "id": "339b1bb8", "metadata": {}, "outputs": [], "source": ["# 设置基本模板", "template = \"\"\"以海盗的口吻回答以下问题，尽力而为。你可以使用以下工具：", "", "{tools}", "", "使用以下格式：", "", "问题：你必须回答的输入问题", "思考：你应该始终考虑该做什么", "行动：要采取的行动，应该是[{tool_names}]中的一个", "行动输入：行动的"]}, {"cell_type": "markdown", "id": "1583acdc", "metadata": {}, "source": ["自定义提示模板现在具有一个名为tools_getter的概念，我们在输入上调用它来选择要使用的工具。"]}, {"cell_type": "code", "execution_count": 10, "id": "fd969d31", "metadata": {}, "outputs": [], "source": ["从typing模块导入Callable", "", "", "# 设置一个提示模板", "class CustomPromptTemplate(StringPromptTemplate):", "    # 要使用的模板", "    template: str", "    ############## 新增 ######################", "    # 可用工具的列表", "    tools_getter: Callable", "", "    def format(self, **kwargs) -> str:", "        # 获取中间步骤（AgentAction，Observation元组）", "        # 以特定方式格式化它们", "        intermediate_steps = kwargs.pop(\"intermediate_steps\")", "        thoughts = \"\"", "        for action, observation in intermediate_steps:", "            thoughts += action.log", "            thoughts += f\"\\nObservation: {observation}\\nThought: \"", "        # 将agent_scratchpad变量设置为该值", "        kwargs[\"agent_scratchpad\"] = thoughts", "        ############## 新增 ######################", "        tools = self.tools_getter(kwargs[\"input\"])", "        # 从提供的工具列表创建一个tools变量", "        kwargs[\"tools\"] = \"\\n\".join(", "            [f\"{tool.name}: {tool.description}\" for tool in tools]", "        )", "        # 为提供的工具创建一个工具名称列表", "        kwargs[\"tool_names\"] = \", \".join([tool.name for tool in tools])", "        return self.template.format(**kwargs)"]}, {"cell_type": "code", "execution_count": 11, "id": "798ef9fb", "metadata": {}, "outputs": [], "source": ["prompt = CustomPromptTemplate(", "    template=template,", "    tools_getter=get_tools,", "    # 这里省略了`agent_scratchpad`、`tools`和`tool_names`变量，因为它们是动态生成的", "    # 这里包括`intermediate_steps`变量，因为它是必需的", "    input_variables=[\"input\", \"intermediate_steps\"],", ")"]}, {"cell_type": "markdown", "id": "ef3a1af3", "metadata": {}, "source": ["## 输出解析器", "", "输出解析器与之前的笔记本保持不变，因为我们不会改变输出格式的任何内容。"]}, {"cell_type": "code", "execution_count": 12, "id": "7c6fe0d3", "metadata": {}, "outputs": [], "source": ["class CustomOutputParser(AgentOutputParser):", "    def parse(self, llm_output: str) -> Union[AgentAction, AgentFinish]:", "        # 检查代理是否应该完成", "        if \"Final Answer:\" in llm_output:", "            return AgentFinish(", "                # 返回值通常始终是一个带有单个 `output` 键的字典", "                # 目前不建议尝试其他操作 :)", "                return_values={\"output\": llm_output.split(\"Final Answer:\")[-1].strip()},", "                log=llm_output,", "            )", "        # 解析动作和动作输入", "        regex = r\"Action\\s*\\d*\\s*:(.*?)\\nAction\\s*\\d*\\s*Input\\s*\\d*\\s*:[\\s]*(.*)\"", "        match = re.search(regex, llm_output, re.DOTALL)", "        if not match:", "            raise ValueError(f\"无法解析LLM输出：`{llm_output}`\")", "        action = match.group(1).strip()", "        action_input = match.group(2)", "        # 返回动作和动作输入", "        return AgentAction(", "            tool=action, tool_input=action_input.strip(\" \").strip('\"'), log=llm_output", "        )"]}, {"cell_type": "code", "execution_count": 13, "id": "d278706a", "metadata": {}, "outputs": [], "source": ["# 创建一个名为output_parser的对象，类型为CustomOutputParser()", "output_parser = CustomOutputParser()"]}, {"cell_type": "markdown", "id": "170587b1", "metadata": {}, "source": ["## 设置LLM、停止序列和代理", "", "与之前的笔记本相同。"]}, {"cell_type": "code", "execution_count": 14, "id": "f9d4c374", "metadata": {}, "outputs": [], "source": ["# 创建一个OpenAI对象，设置温度参数为0", "llm = OpenAI(temperature=0)"]}, {"cell_type": "code", "execution_count": 15, "id": "9b1cc2a2", "metadata": {}, "outputs": [], "source": ["# 创建一个LLM链，包括LLM模型和一个提示", "llm_chain = LLMChain(llm=llm, prompt=prompt)"]}, {"cell_type": "code", "execution_count": 16, "id": "e4f5092f", "metadata": {}, "outputs": [], "source": ["# 创建一个列表，包含了所有工具的名称", "tool_names = [tool.name for tool in tools]", "", "# 创建一个LLMSingleActionAgent对象", "# 参数：", "# llm_chain: LLM链", "# output_parser: 输出解析器", "# stop: 停止标志，当遇到\"\\nObservation:\"时停止", "# allowed_tools: 允许使用的工具名称列表", "agent = LLMSingleActionAgent(", "    llm_chain=llm_chain,", "    output_parser=output_parser,", "    stop=[\"\\nObservation:\"],", "    allowed_tools=tool_names,", ")"]}, {"cell_type": "markdown", "id": "aa8a5326", "metadata": {}, "source": ["## 使用代理", "", "现在我们可以使用它了！"]}, {"cell_type": "code", "execution_count": 17, "id": "490604e9", "metadata": {}, "outputs": [], "source": ["# 导入AgentExecutor类", "from rasa.core.agent import AgentExecutor", "", "# 创建AgentExecutor对象，并传入agent和tools参数，verbose设置为True", "agent_executor = AgentExecutor.from_agent_and_tools(", "    agent=agent, tools=tools, verbose=True", ")"]}, {"cell_type": "code", "execution_count": 18, "id": "653b1617", "metadata": {}, "outputs": [{"name": "stdout", "output_type": "stream", "text": ["\n", "\n", "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n", "\u001b[32;1m\u001b[1;3mThought: I need to find a product API\n", "Action: Open_AI_Klarna_product_Api.productsUsingGET\n", "Action Input: shirts\u001b[0m\n", "\n", "Observation:\u001b[36;1m\u001b[1;3mI found 10 shirts from the API response. They range in price from $9.99 to $450.00 and come in a variety of materials, colors, and patterns.\u001b[0m\u001b[32;1m\u001b[1;3m I now know what shirts I can buy\n", "Final Answer: Arg, I found 10 shirts from the API response. They range in price from $9.99 to $450.00 and come in a variety of materials, colors, and patterns.\u001b[0m\n", "\n", "\u001b[1m> Finished chain.\u001b[0m\n"]}, {"data": {"text/plain": ["'Arg, I found 10 shirts from the API response. They range in price from $9.99 to $450.00 and come in a variety of materials, colors, and patterns.'"]}, "execution_count": 18, "metadata": {}, "output_type": "execute_result"}], "source": ["# 导入所需的库", "import agent_executor", "", "# 调用agent_executor的run函数，并传入参数\"what shirts can i buy?\"", "agent_executor.run(\"what shirts can i buy?\")"]}, {"cell_type": "code", "execution_count": null, "id": "2481ee76", "metadata": {}, "outputs": [], "source": []}], "metadata": {"kernelspec": {"display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3"}, "language_info": {"codemirror_mode": {"name": "ipython", "version": 3}, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.11.3"}, "vscode": {"interpreter": {"hash": "3ccef4e08d87aa1eeb90f63e0f071292ccb2e9c42e70f74ab2bf6f5493ca7bbc"}}}, "nbformat": 4, "nbformat_minor": 5}