{ "cells": [ { "cell_type": "markdown", "id": "991b1cc1", "metadata": {}, "source": [ "# Loading from LangChainHub\n", "\n", "This notebook covers how to load agents from [LangChainHub](https://github.com/hwchase17/langchain-hub)." ] }, { "cell_type": "code", "execution_count": 1, "id": "bd4450a2", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "No `_type` key found, defaulting to `prompt`.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\n", "\n", "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n", "\u001B[32;1m\u001B[1;3m Yes.\n", "Follow up: Who is the reigning men's U.S. Open champion?\u001B[0m\n", "Intermediate answer: \u001B[36;1m\u001B[1;3m2016 · SUI · Stan Wawrinka ; 2017 · ESP · Rafael Nadal ; 2018 · SRB · Novak Djokovic ; 2019 · ESP · Rafael Nadal.\u001B[0m\n", "\u001B[32;1m\u001B[1;3mSo the reigning men's U.S. Open champion is Rafael Nadal.\n", "Follow up: What is Rafael Nadal's hometown?\u001B[0m\n", "Intermediate answer: \u001B[36;1m\u001B[1;3mIn 2016, he once again showed his deep ties to Mallorca and opened the Rafa Nadal Academy in his hometown of Manacor.\u001B[0m\n", "\u001B[32;1m\u001B[1;3mSo the final answer is: Manacor, Mallorca, Spain.\u001B[0m\n", "\n", "\u001B[1m> Finished chain.\u001B[0m\n" ] }, { "data": { "text/plain": [ "'Manacor, Mallorca, Spain.'" ] }, "execution_count": 1, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from langchain import OpenAI, SerpAPIWrapper\n", "from langchain.agents import initialize_agent, Tool\n", "\n", "llm = OpenAI(temperature=0)\n", "search = SerpAPIWrapper()\n", "tools = [\n", " Tool(\n", " name=\"Intermediate Answer\",\n", " func=search.run,\n", " description=\"useful for when you need to ask with search\"\n", " )\n", "]\n", "\n", "self_ask_with_search = initialize_agent(tools, llm, agent_path=\"lc://agents/self-ask-with-search/agent.json\", verbose=True)\n", "self_ask_with_search.run(\"What is the hometown of the reigning men's U.S. Open champion?\")" ] }, { "cell_type": "markdown", "id": "3aede965", "metadata": {}, "source": [ "# Pinning Dependencies\n", "\n", "Specific versions of LangChainHub agents can be pinned with the `lc@://` syntax." ] }, { "cell_type": "code", "execution_count": 2, "id": "e679f7b6", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "No `_type` key found, defaulting to `prompt`.\n" ] } ], "source": [ "self_ask_with_search = initialize_agent(tools, llm, agent_path=\"lc@2826ef9e8acdf88465e1e5fc8a7bf59e0f9d0a85://agents/self-ask-with-search/agent.json\", verbose=True)" ] }, { "cell_type": "code", "execution_count": null, "id": "9d3d6697", "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": "3.9.1" } }, "nbformat": 4, "nbformat_minor": 5 }