tools_agents.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Search Engine With Tools And Agents"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Arxiv--Research\n",
    "## Tools creation\n",
    "from langchain_community.tools import ArxivQueryRun,WikipediaQueryRun\n",
    "from langchain_community.utilities import WikipediaAPIWrapper,ArxivAPIWrapper"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'wikipedia'"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "## Used the inbuilt tool of wikipedia\n",
    "api_wrapper_wiki=WikipediaAPIWrapper(top_k_results=1,doc_content_chars_max=250)\n",
    "wiki=WikipediaQueryRun(api_wrapper=api_wrapper_wiki)\n",
    "wiki.name"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "arxiv\n"
     ]
    }
   ],
   "source": [
    "api_wrapper_arxiv=ArxivAPIWrapper(top_k_results=1,doc_content_chars_max=250)\n",
    "arxiv=ArxivQueryRun(api_wrapper=api_wrapper_arxiv)\n",
    "print(arxiv.name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "tools=[wiki,arxiv]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[WikipediaQueryRun(api_wrapper=WikipediaAPIWrapper(wiki_client=<module 'wikipedia' from 'c:\\\\Users\\\\sujat\\\\Downloads\\\\Search-Engine-LLM\\\\venv\\\\Lib\\\\site-packages\\\\wikipedia\\\\__init__.py'>, top_k_results=1, lang='en', load_all_available_meta=False, doc_content_chars_max=250)),\n",
       " ArxivQueryRun(api_wrapper=ArxivAPIWrapper(arxiv_search=<class 'arxiv.Search'>, arxiv_exceptions=(<class 'arxiv.ArxivError'>, <class 'arxiv.UnexpectedEmptyPageError'>, <class 'arxiv.HTTPError'>), top_k_results=1, ARXIV_MAX_QUERY_LENGTH=300, continue_on_failure=False, load_max_docs=100, load_all_available_meta=False, doc_content_chars_max=250))]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tools"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "from dotenv import load_dotenv\n",
    "import os\n",
    "import openai\n",
    "\n",
    "load_dotenv()\n",
    "openai.api_key = os.getenv('OPENAI_API_KEY')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "USER_AGENT environment variable not set, consider setting it to identify your requests.\n"
     ]
    }
   ],
   "source": [
    "## Custom tools[RAG Tool]\n",
    "from langchain_community.document_loaders import WebBaseLoader\n",
    "from langchain_community.vectorstores import FAISS\n",
    "from langchain_openai import OpenAIEmbeddings\n",
    "from langchain_text_splitters import RecursiveCharacterTextSplitter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "VectorStoreRetriever(tags=['FAISS', 'OpenAIEmbeddings'], vectorstore=<langchain_community.vectorstores.faiss.FAISS object at 0x000001A33BFEE600>, search_kwargs={})"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "loader=WebBaseLoader(\"https://docs.smith.langchain.com/\")\n",
    "docs=loader.load()\n",
    "documents=RecursiveCharacterTextSplitter(chunk_size=1000,chunk_overlap=200).split_documents(docs)\n",
    "vectordb=FAISS.from_documents(documents,OpenAIEmbeddings())\n",
    "retriever=vectordb.as_retriever()\n",
    "retriever"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'langsmith-search'"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from langchain.tools.retriever import create_retriever_tool\n",
    "retriever_tool=create_retriever_tool(retriever,\"langsmith-search\",\"Search any information about Langsmith \")\n",
    "\n",
    "retriever_tool.name"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "tools=[wiki,arxiv,retriever_tool]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[WikipediaQueryRun(api_wrapper=WikipediaAPIWrapper(wiki_client=<module 'wikipedia' from 'c:\\\\Users\\\\sujat\\\\Downloads\\\\Search-Engine-LLM\\\\venv\\\\Lib\\\\site-packages\\\\wikipedia\\\\__init__.py'>, top_k_results=1, lang='en', load_all_available_meta=False, doc_content_chars_max=250)),\n",
       " ArxivQueryRun(api_wrapper=ArxivAPIWrapper(arxiv_search=<class 'arxiv.Search'>, arxiv_exceptions=(<class 'arxiv.ArxivError'>, <class 'arxiv.UnexpectedEmptyPageError'>, <class 'arxiv.HTTPError'>), top_k_results=1, ARXIV_MAX_QUERY_LENGTH=300, continue_on_failure=False, load_max_docs=100, load_all_available_meta=False, doc_content_chars_max=250)),\n",
       " Tool(name='langsmith-search', description='Search any information about Langsmith ', args_schema=<class 'langchain_core.tools.retriever.RetrieverInput'>, func=functools.partial(<function _get_relevant_documents at 0x000001A32A7F1F80>, retriever=VectorStoreRetriever(tags=['FAISS', 'OpenAIEmbeddings'], vectorstore=<langchain_community.vectorstores.faiss.FAISS object at 0x000001A33BFEE600>, search_kwargs={}), document_prompt=PromptTemplate(input_variables=['page_content'], input_types={}, partial_variables={}, template='{page_content}'), document_separator='\\n\\n'), coroutine=functools.partial(<function _aget_relevant_documents at 0x000001A32BB49120>, retriever=VectorStoreRetriever(tags=['FAISS', 'OpenAIEmbeddings'], vectorstore=<langchain_community.vectorstores.faiss.FAISS object at 0x000001A33BFEE600>, search_kwargs={}), document_prompt=PromptTemplate(input_variables=['page_content'], input_types={}, partial_variables={}, template='{page_content}'), document_separator='\\n\\n'))]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tools"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Run all this tools with Agents and LLM Models\n",
    "\n",
    "## Tools, LLM-->AgentExecutor\n",
    "from langchain_groq import ChatGroq\n",
    "from dotenv import load_dotenv\n",
    "import openai\n",
    "load_dotenv()\n",
    "import os\n",
    "\n",
    "groq_api_key=os.getenv(\"GROQ_API_KEY\")\n",
    "openai.api_key=os.getenv(\"OPENAI_API_KEY\")\n",
    "\n",
    "llm=ChatGroq(groq_api_key=groq_api_key,model_name=\"Llama3-8b-8192\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "#%pip install langchain-community"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "from dotenv import load_dotenv\n",
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "#from langchain_community import LangSmithClient\n",
    "#from langchain_community import LangSmithAPI\n",
    "#load_dotenv()\n",
    "#langsmith_api_key = os.getenv('LANGSMITH_API_KEY')\n",
    "#client = LangSmithClient(api_key=langsmith_api_key)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[SystemMessagePromptTemplate(prompt=PromptTemplate(input_variables=[], input_types={}, partial_variables={}, template='You are a helpful assistant'), additional_kwargs={}),\n",
       " MessagesPlaceholder(variable_name='chat_history', optional=True),\n",
       " HumanMessagePromptTemplate(prompt=PromptTemplate(input_variables=['input'], input_types={}, partial_variables={}, template='{input}'), additional_kwargs={}),\n",
       " MessagesPlaceholder(variable_name='agent_scratchpad')]"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "## Prompt Template\n",
    "from langchain import hub\n",
    "prompt=hub.pull(\"hwchase17/openai-functions-agent\")\n",
    "prompt.messages"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RunnableAssign(mapper={\n",
       "  agent_scratchpad: RunnableLambda(lambda x: format_to_openai_tool_messages(x['intermediate_steps']))\n",
       "})\n",
       "| ChatPromptTemplate(input_variables=['agent_scratchpad', 'input'], optional_variables=['chat_history'], input_types={'chat_history': list[typing.Annotated[typing.Union[typing.Annotated[langchain_core.messages.ai.AIMessage, Tag(tag='ai')], typing.Annotated[langchain_core.messages.human.HumanMessage, Tag(tag='human')], typing.Annotated[langchain_core.messages.chat.ChatMessage, Tag(tag='chat')], typing.Annotated[langchain_core.messages.system.SystemMessage, Tag(tag='system')], typing.Annotated[langchain_core.messages.function.FunctionMessage, Tag(tag='function')], typing.Annotated[langchain_core.messages.tool.ToolMessage, Tag(tag='tool')], typing.Annotated[langchain_core.messages.ai.AIMessageChunk, Tag(tag='AIMessageChunk')], typing.Annotated[langchain_core.messages.human.HumanMessageChunk, Tag(tag='HumanMessageChunk')], typing.Annotated[langchain_core.messages.chat.ChatMessageChunk, Tag(tag='ChatMessageChunk')], typing.Annotated[langchain_core.messages.system.SystemMessageChunk, Tag(tag='SystemMessageChunk')], typing.Annotated[langchain_core.messages.function.FunctionMessageChunk, Tag(tag='FunctionMessageChunk')], typing.Annotated[langchain_core.messages.tool.ToolMessageChunk, Tag(tag='ToolMessageChunk')]], FieldInfo(annotation=NoneType, required=True, discriminator=Discriminator(discriminator=<function _get_type at 0x000001A329F93E20>, custom_error_type=None, custom_error_message=None, custom_error_context=None))]], 'agent_scratchpad': list[typing.Annotated[typing.Union[typing.Annotated[langchain_core.messages.ai.AIMessage, Tag(tag='ai')], typing.Annotated[langchain_core.messages.human.HumanMessage, Tag(tag='human')], typing.Annotated[langchain_core.messages.chat.ChatMessage, Tag(tag='chat')], typing.Annotated[langchain_core.messages.system.SystemMessage, Tag(tag='system')], typing.Annotated[langchain_core.messages.function.FunctionMessage, Tag(tag='function')], typing.Annotated[langchain_core.messages.tool.ToolMessage, Tag(tag='tool')], typing.Annotated[langchain_core.messages.ai.AIMessageChunk, Tag(tag='AIMessageChunk')], typing.Annotated[langchain_core.messages.human.HumanMessageChunk, Tag(tag='HumanMessageChunk')], typing.Annotated[langchain_core.messages.chat.ChatMessageChunk, Tag(tag='ChatMessageChunk')], typing.Annotated[langchain_core.messages.system.SystemMessageChunk, Tag(tag='SystemMessageChunk')], typing.Annotated[langchain_core.messages.function.FunctionMessageChunk, Tag(tag='FunctionMessageChunk')], typing.Annotated[langchain_core.messages.tool.ToolMessageChunk, Tag(tag='ToolMessageChunk')]], FieldInfo(annotation=NoneType, required=True, discriminator=Discriminator(discriminator=<function _get_type at 0x000001A329F93E20>, custom_error_type=None, custom_error_message=None, custom_error_context=None))]]}, partial_variables={'chat_history': []}, metadata={'lc_hub_owner': 'hwchase17', 'lc_hub_repo': 'openai-functions-agent', 'lc_hub_commit_hash': 'a1655024b06afbd95d17449f21316291e0726f13dcfaf990cc0d18087ad689a5'}, messages=[SystemMessagePromptTemplate(prompt=PromptTemplate(input_variables=[], input_types={}, partial_variables={}, template='You are a helpful assistant'), additional_kwargs={}), MessagesPlaceholder(variable_name='chat_history', optional=True), HumanMessagePromptTemplate(prompt=PromptTemplate(input_variables=['input'], input_types={}, partial_variables={}, template='{input}'), additional_kwargs={}), MessagesPlaceholder(variable_name='agent_scratchpad')])\n",
       "| RunnableBinding(bound=ChatGroq(client=<groq.resources.chat.completions.Completions object at 0x000001A33ADD5970>, async_client=<groq.resources.chat.completions.AsyncCompletions object at 0x000001A33ADD4D70>, model_name='Llama3-8b-8192', model_kwargs={}, groq_api_key=SecretStr('**********')), kwargs={'tools': [{'type': 'function', 'function': {'name': 'wikipedia', 'description': 'A wrapper around Wikipedia. Useful for when you need to answer general questions about people, places, companies, facts, historical events, or other subjects. Input should be a search query.', 'parameters': {'properties': {'query': {'description': 'query to look up on wikipedia', 'type': 'string'}}, 'required': ['query'], 'type': 'object'}}}, {'type': 'function', 'function': {'name': 'arxiv', 'description': 'A wrapper around Arxiv.org Useful for when you need to answer questions about Physics, Mathematics, Computer Science, Quantitative Biology, Quantitative Finance, Statistics, Electrical Engineering, and Economics from scientific articles on arxiv.org. Input should be a search query.', 'parameters': {'properties': {'query': {'description': 'search query to look up', 'type': 'string'}}, 'required': ['query'], 'type': 'object'}}}, {'type': 'function', 'function': {'name': 'langsmith-search', 'description': 'Search any information about Langsmith ', 'parameters': {'properties': {'query': {'description': 'query to look up in retriever', 'type': 'string'}}, 'required': ['query'], 'type': 'object'}}}]}, config={}, config_factories=[])\n",
       "| OpenAIToolsAgentOutputParser()"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "## Agents\n",
    "from langchain.agents import create_openai_tools_agent\n",
    "agent=create_openai_tools_agent(llm,tools,prompt)\n",
    "agent"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "AgentExecutor(verbose=True, agent=RunnableMultiActionAgent(runnable=RunnableAssign(mapper={\n",
       "  agent_scratchpad: RunnableLambda(lambda x: format_to_openai_tool_messages(x['intermediate_steps']))\n",
       "})\n",
       "| ChatPromptTemplate(input_variables=['agent_scratchpad', 'input'], optional_variables=['chat_history'], input_types={'chat_history': list[typing.Annotated[typing.Union[typing.Annotated[langchain_core.messages.ai.AIMessage, Tag(tag='ai')], typing.Annotated[langchain_core.messages.human.HumanMessage, Tag(tag='human')], typing.Annotated[langchain_core.messages.chat.ChatMessage, Tag(tag='chat')], typing.Annotated[langchain_core.messages.system.SystemMessage, Tag(tag='system')], typing.Annotated[langchain_core.messages.function.FunctionMessage, Tag(tag='function')], typing.Annotated[langchain_core.messages.tool.ToolMessage, Tag(tag='tool')], typing.Annotated[langchain_core.messages.ai.AIMessageChunk, Tag(tag='AIMessageChunk')], typing.Annotated[langchain_core.messages.human.HumanMessageChunk, Tag(tag='HumanMessageChunk')], typing.Annotated[langchain_core.messages.chat.ChatMessageChunk, Tag(tag='ChatMessageChunk')], typing.Annotated[langchain_core.messages.system.SystemMessageChunk, Tag(tag='SystemMessageChunk')], typing.Annotated[langchain_core.messages.function.FunctionMessageChunk, Tag(tag='FunctionMessageChunk')], typing.Annotated[langchain_core.messages.tool.ToolMessageChunk, Tag(tag='ToolMessageChunk')]], FieldInfo(annotation=NoneType, required=True, discriminator=Discriminator(discriminator=<function _get_type at 0x000001A329F93E20>, custom_error_type=None, custom_error_message=None, custom_error_context=None))]], 'agent_scratchpad': list[typing.Annotated[typing.Union[typing.Annotated[langchain_core.messages.ai.AIMessage, Tag(tag='ai')], typing.Annotated[langchain_core.messages.human.HumanMessage, Tag(tag='human')], typing.Annotated[langchain_core.messages.chat.ChatMessage, Tag(tag='chat')], typing.Annotated[langchain_core.messages.system.SystemMessage, Tag(tag='system')], typing.Annotated[langchain_core.messages.function.FunctionMessage, Tag(tag='function')], typing.Annotated[langchain_core.messages.tool.ToolMessage, Tag(tag='tool')], typing.Annotated[langchain_core.messages.ai.AIMessageChunk, Tag(tag='AIMessageChunk')], typing.Annotated[langchain_core.messages.human.HumanMessageChunk, Tag(tag='HumanMessageChunk')], typing.Annotated[langchain_core.messages.chat.ChatMessageChunk, Tag(tag='ChatMessageChunk')], typing.Annotated[langchain_core.messages.system.SystemMessageChunk, Tag(tag='SystemMessageChunk')], typing.Annotated[langchain_core.messages.function.FunctionMessageChunk, Tag(tag='FunctionMessageChunk')], typing.Annotated[langchain_core.messages.tool.ToolMessageChunk, Tag(tag='ToolMessageChunk')]], FieldInfo(annotation=NoneType, required=True, discriminator=Discriminator(discriminator=<function _get_type at 0x000001A329F93E20>, custom_error_type=None, custom_error_message=None, custom_error_context=None))]]}, partial_variables={'chat_history': []}, metadata={'lc_hub_owner': 'hwchase17', 'lc_hub_repo': 'openai-functions-agent', 'lc_hub_commit_hash': 'a1655024b06afbd95d17449f21316291e0726f13dcfaf990cc0d18087ad689a5'}, messages=[SystemMessagePromptTemplate(prompt=PromptTemplate(input_variables=[], input_types={}, partial_variables={}, template='You are a helpful assistant'), additional_kwargs={}), MessagesPlaceholder(variable_name='chat_history', optional=True), HumanMessagePromptTemplate(prompt=PromptTemplate(input_variables=['input'], input_types={}, partial_variables={}, template='{input}'), additional_kwargs={}), MessagesPlaceholder(variable_name='agent_scratchpad')])\n",
       "| RunnableBinding(bound=ChatGroq(client=<groq.resources.chat.completions.Completions object at 0x000001A33ADD5970>, async_client=<groq.resources.chat.completions.AsyncCompletions object at 0x000001A33ADD4D70>, model_name='Llama3-8b-8192', model_kwargs={}, groq_api_key=SecretStr('**********')), kwargs={'tools': [{'type': 'function', 'function': {'name': 'wikipedia', 'description': 'A wrapper around Wikipedia. Useful for when you need to answer general questions about people, places, companies, facts, historical events, or other subjects. Input should be a search query.', 'parameters': {'properties': {'query': {'description': 'query to look up on wikipedia', 'type': 'string'}}, 'required': ['query'], 'type': 'object'}}}, {'type': 'function', 'function': {'name': 'arxiv', 'description': 'A wrapper around Arxiv.org Useful for when you need to answer questions about Physics, Mathematics, Computer Science, Quantitative Biology, Quantitative Finance, Statistics, Electrical Engineering, and Economics from scientific articles on arxiv.org. Input should be a search query.', 'parameters': {'properties': {'query': {'description': 'search query to look up', 'type': 'string'}}, 'required': ['query'], 'type': 'object'}}}, {'type': 'function', 'function': {'name': 'langsmith-search', 'description': 'Search any information about Langsmith ', 'parameters': {'properties': {'query': {'description': 'query to look up in retriever', 'type': 'string'}}, 'required': ['query'], 'type': 'object'}}}]}, config={}, config_factories=[])\n",
       "| OpenAIToolsAgentOutputParser(), input_keys_arg=[], return_keys_arg=[], stream_runnable=True), tools=[WikipediaQueryRun(api_wrapper=WikipediaAPIWrapper(wiki_client=<module 'wikipedia' from 'c:\\\\Users\\\\sujat\\\\Downloads\\\\Search-Engine-LLM\\\\venv\\\\Lib\\\\site-packages\\\\wikipedia\\\\__init__.py'>, top_k_results=1, lang='en', load_all_available_meta=False, doc_content_chars_max=250)), ArxivQueryRun(api_wrapper=ArxivAPIWrapper(arxiv_search=<class 'arxiv.Search'>, arxiv_exceptions=(<class 'arxiv.ArxivError'>, <class 'arxiv.UnexpectedEmptyPageError'>, <class 'arxiv.HTTPError'>), top_k_results=1, ARXIV_MAX_QUERY_LENGTH=300, continue_on_failure=False, load_max_docs=100, load_all_available_meta=False, doc_content_chars_max=250)), Tool(name='langsmith-search', description='Search any information about Langsmith ', args_schema=<class 'langchain_core.tools.retriever.RetrieverInput'>, func=functools.partial(<function _get_relevant_documents at 0x000001A32A7F1F80>, retriever=VectorStoreRetriever(tags=['FAISS', 'OpenAIEmbeddings'], vectorstore=<langchain_community.vectorstores.faiss.FAISS object at 0x000001A33BFEE600>, search_kwargs={}), document_prompt=PromptTemplate(input_variables=['page_content'], input_types={}, partial_variables={}, template='{page_content}'), document_separator='\\n\\n'), coroutine=functools.partial(<function _aget_relevant_documents at 0x000001A32BB49120>, retriever=VectorStoreRetriever(tags=['FAISS', 'OpenAIEmbeddings'], vectorstore=<langchain_community.vectorstores.faiss.FAISS object at 0x000001A33BFEE600>, search_kwargs={}), document_prompt=PromptTemplate(input_variables=['page_content'], input_types={}, partial_variables={}, template='{page_content}'), document_separator='\\n\\n'))])"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "## Agent Executer\n",
    "from langchain.agents import AgentExecutor\n",
    "agent_executor=AgentExecutor(agent=agent,tools=tools,verbose=True)\n",
    "agent_executor"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3m\n",
      "Invoking: `langsmith-search` with `{'query': 'Langsmith'}`\n",
      "\n",
      "\n",
      "\u001b[0m\u001b[38;5;200m\u001b[1;3mGet started with LangSmith | ü¶úÔ∏èüõ†Ô∏è LangSmith\n",
      "\n",
      "\n",
      "\n",
      "\n",
      "\n",
      "\n",
      "Skip to main contentLearn the essentials of LangSmith in the new Introduction to LangSmith course!  Enroll for free. API ReferenceRESTPythonSearchRegionUSEUGo to AppQuick StartObservabilityEvaluationPrompt EngineeringDeployment (LangGraph Platform)AdministrationSelf-hostingPricingReferenceCloud architecture and scalabilityAuthz and AuthnAuthentication methodsdata_formatsEvaluationDataset transformationsRegions FAQsdk_referenceQuick StartOn this pageGet started with LangSmith\n",
      "LangSmith is a platform for building production-grade LLM applications.\n",
      "It allows you to closely monitor and evaluate your application, so you can ship quickly and with confidence.\n",
      "With LangSmith you can:\n",
      "\n",
      "LangSmith + LangChain OSSLangSmith integrates seamlessly with LangChain's open source frameworks langchain and langgraph, with no extra instrumentation needed.If you're already using either of these, see the how-to guide for setting up LangSmith with LangChain or setting up LangSmith with LangGraph.\n",
      "LangSmith is a standalone platform that can be used on it's own no matter how you're creating your LLM applicatons.\n",
      "In this tutorial, we'll walk you though logging your first trace in LangSmith using the LangSmith SDK and running an evaluation to measure the performance of your application. This example uses the OpenAI API, however you can use your provider of choice.\n",
      "1. Install LangSmith‚Äã\n",
      "PythonTypeScriptpip install -U langsmith openaiyarn add langsmith openai\n",
      "2. Create an API key‚Äã\n",
      "To create an API key head to the Settings page. Then click Create API Key.\n",
      "3. Set up your environment‚Äã\n",
      "\n",
      "Click the link printed out by your evaluation run to access the LangSmith experiments UI,\n",
      "and explore the results of your evaluation.\n",
      "Learn more about evaluation in the tutorials, conceptual guide, and how-to guides.\n",
      "Was this page helpful?You can leave detailed feedback on GitHub.NextObservability tutorials1. Install LangSmith2. Create an API key3. Set up your environment4. Log your first trace5. View your trace6. Run your first evaluationCommunityDiscordTwitterGitHubDocs CodeLangSmith SDKPythonJS/TSMoreHomepageBlogLangChain Python DocsLangChain JS/TS DocsCopyright ¬© 2024 LangChain, Inc.\n",
      "\n",
      "2. Create an API key‚Äã\n",
      "To create an API key head to the Settings page. Then click Create API Key.\n",
      "3. Set up your environment‚Äã\n",
      "Shellexport LANGCHAIN_TRACING_V2=trueexport LANGCHAIN_API_KEY=<your-api-key>export OPENAI_API_KEY=<your-openai-api-key>\n",
      "4. Log your first trace‚Äã\n",
      "We provide multiple ways to log traces to LangSmith. Below, we'll highlight\n",
      "how to use traceable(). See more on the Annotate code for tracing page.\u001b[0m\u001b[32;1m\u001b[1;3mIt seems that the tool call yielded a webpage content about Langsmith. Since you asked about Langsmith, I will summarize the key points from the webpage:\n",
      "\n",
      "Langsmith is a platform for building production-grade LLM (Large Language Model) applications. It allows developers to closely monitor and evaluate their applications, making it easier to ship quickly and with confidence.\n",
      "\n",
      "Some of the key features of Langsmith include:\n",
      "\n",
      "* Integration with LangChain's open-source frameworks, langchain and langgraph\n",
      "* Ability to log traces and evaluate performance\n",
      "* Support for multiple programming languages, including Python and JavaScript\n",
      "* API key creation and management\n",
      "* Observability tutorials and guides for setup and use\n",
      "\n",
      "Langsmith seems to be a comprehensive platform for building and managing LLM applications, with a focus on ease of use and scalability.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'input': 'Tell me about Langsmith',\n",
       " 'output': \"It seems that the tool call yielded a webpage content about Langsmith. Since you asked about Langsmith, I will summarize the key points from the webpage:\\n\\nLangsmith is a platform for building production-grade LLM (Large Language Model) applications. It allows developers to closely monitor and evaluate their applications, making it easier to ship quickly and with confidence.\\n\\nSome of the key features of Langsmith include:\\n\\n* Integration with LangChain's open-source frameworks, langchain and langgraph\\n* Ability to log traces and evaluate performance\\n* Support for multiple programming languages, including Python and JavaScript\\n* API key creation and management\\n* Observability tutorials and guides for setup and use\\n\\nLangsmith seems to be a comprehensive platform for building and managing LLM applications, with a focus on ease of use and scalability.\"}"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent_executor.invoke({\"input\":\"Tell me about Langsmith\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3m\n",
      "Invoking: `wikipedia` with `{'query': 'machine learning'}`\n",
      "\n",
      "\n",
      "\u001b[0m\u001b[36;1m\u001b[1;3mPage: Machine learning\n",
      "Summary: Machine learning (ML) is a field of study in artificial intelligence concerned with the development and study of statistical algorithms that can learn from data and generalize to unseen data, and thus perform tasks wit\u001b[0m\u001b[32;1m\u001b[1;3m\n",
      "Invoking: `wikipedia` with `{'query': 'machine learning'}`\n",
      "\n",
      "\n",
      "\u001b[0m\u001b[36;1m\u001b[1;3mPage: Machine learning\n",
      "Summary: Machine learning (ML) is a field of study in artificial intelligence concerned with the development and study of statistical algorithms that can learn from data and generalize to unseen data, and thus perform tasks wit\u001b[0m\u001b[32;1m\u001b[1;3mThe Wikipedia summary didn't provide any new information. Let me summarize the information in my own words.\n",
      "\n",
      "Machine learning is a type of artificial intelligence that enables computers to learn from data and make decisions without being explicitly programmed. It involves developing and studying statistical algorithms that can analyze data, identify patterns, and make predictions or classify new data based on what they've learned.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'input': 'What is machine learning',\n",
       " 'output': \"The Wikipedia summary didn't provide any new information. Let me summarize the information in my own words.\\n\\nMachine learning is a type of artificial intelligence that enables computers to learn from data and make decisions without being explicitly programmed. It involves developing and studying statistical algorithms that can analyze data, identify patterns, and make predictions or classify new data based on what they've learned.\"}"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent_executor.invoke({\"input\":\"What is machine learning\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3m\n",
      "Invoking: `arxiv` with `{'query': '1706.03762'}`\n",
      "\n",
      "\n",
      "\u001b[0m\u001b[33;1m\u001b[1;3mPublished: 2023-08-02\n",
      "Title: Attention Is All You Need\n",
      "Authors: Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin\n",
      "Summary: The dominant sequence transduction models are based on c\u001b[0m\u001b[32;1m\u001b[1;3mBased on the result from tool call id \"call_gr03\", I can tell you that the paper 1706.03762 is \"Attention Is All You Need\" by Ashish Vaswani et al., published on August 2, 2023.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'input': \"What's the paper 1706.03762 about?\",\n",
       " 'output': 'Based on the result from tool call id \"call_gr03\", I can tell you that the paper 1706.03762 is \"Attention Is All You Need\" by Ashish Vaswani et al., published on August 2, 2023.'}"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent_executor.invoke({\"input\":\"What's the paper 1706.03762 about?\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.12.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}