{ "cells": [ { "cell_type": "markdown", "id": "782ffcf1", "metadata": {}, "source": [ "# Router Chains: Selecting from multiple prompts with MultiRetrievalQAChain\n", "\n", "This notebook demonstrates how to use the `RouterChain` paradigm to create a chain that dynamically selects which Retrieval system to use. Specifically we show how to use the `MultiRetrievalQAChain` to create a question-answering chain that selects the retrieval QA chain which is most relevant for a given question, and then answers the question using it." ] }, { "cell_type": "code", "execution_count": 1, "id": "b6aeec07", "metadata": {}, "outputs": [], "source": [ "from langchain.chains.router import MultiRetrievalQAChain\n", "from langchain.llms import OpenAI" ] }, { "cell_type": "code", "execution_count": 2, "id": "3c42f051", "metadata": {}, "outputs": [], "source": [ "from langchain.embeddings import OpenAIEmbeddings\n", "from langchain.document_loaders import TextLoader\n", "from langchain.vectorstores import FAISS\n", "\n", "sou_docs = TextLoader('../../state_of_the_union.txt').load_and_split()\n", "sou_retriever = FAISS.from_documents(sou_docs, OpenAIEmbeddings()).as_retriever()\n", "\n", "pg_docs = TextLoader('../../paul_graham_essay.txt').load_and_split()\n", "pg_retriever = FAISS.from_documents(pg_docs, OpenAIEmbeddings()).as_retriever()\n", "\n", "personal_texts = [\n", " \"I love apple pie\",\n", " \"My favorite color is fuchsia\",\n", " \"My dream is to become a professional dancer\",\n", " \"I broke my arm when I was 12\",\n", " \"My parents are from Peru\",\n", "]\n", "personal_retriever = FAISS.from_texts(personal_texts, OpenAIEmbeddings()).as_retriever()\n" ] }, { "cell_type": "code", "execution_count": 3, "id": "5b671ac5", "metadata": {}, "outputs": [], "source": [ "retriever_infos = [\n", " (\"state of the union\", \"Good for answering questions about the 2023 State of the Union address\", sou_retriever),\n", " (\"pg essay\", \"Good for answer quesitons about Paul Graham's essay on his career\", pg_retriever),\n", " (\"personal\", \"Good for answering questions about me\", personal_retriever)\n", "]\n", "chain = MultiRetrievalQAChain.from_retrievers(OpenAI(), *zip(*retriever_infos), verbose=True)" ] }, { "cell_type": "code", "execution_count": 4, "id": "7db5814f", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "\n", "\u001b[1m> Entering new MultiRetrievalQAChain chain...\u001b[0m\n", "state of the union: {'query': 'What did the president say about the economy in the 2023 State of the Union Address?'}\n", "\u001b[1m> Finished chain.\u001b[0m\n", " The president said that the economy had created over 6.5 million jobs in the previous year, the strongest growth in nearly 40 years, and that his plan to fight inflation would lower costs and the deficit. He also announced the Bipartisan Infrastructure Law and said that investing in workers and building the economy from the bottom up and the middle out would build a better America.\n" ] } ], "source": [ "print(chain.run(\"What did the president say about the economy?\"))" ] }, { "cell_type": "code", "execution_count": 5, "id": "bbcdbe82", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "\n", "\u001b[1m> Entering new MultiRetrievalQAChain chain...\u001b[0m\n", "pg essay: {'query': 'What is something Paul Graham regrets about his work?'}\n", "\u001b[1m> Finished chain.\u001b[0m\n", " Paul Graham regrets that he was so consumed by running Y Combinator that it ended up eating away at his other projects, like writing essays and working on Arc.\n" ] } ], "source": [ "print(chain.run(\"What is something Paul Graham regrets about his work?\"))" ] }, { "cell_type": "code", "execution_count": 6, "id": "37c88a27", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "\n", "\u001b[1m> Entering new MultiRetrievalQAChain chain...\u001b[0m\n", "personal: {'query': 'What is my background?'}\n", "\u001b[1m> Finished chain.\u001b[0m\n", " Your background is Peruvian.\n" ] } ], "source": [ "print(chain.run(\"What is my background?\"))" ] }, { "cell_type": "code", "execution_count": 7, "id": "de8519b2", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "\n", "\u001b[1m> Entering new MultiRetrievalQAChain chain...\u001b[0m\n", "None: {'query': 'What year was the Internet created in?'}\n", "\u001b[1m> Finished chain.\u001b[0m\n", "The Internet was created in the late 1960s by the United States Department of Defense's Advanced Research Projects Agency (ARPA). It was originally called the ARPANET and was used to connect computers at different universities and research institutions. Over time, it evolved into the global network that we know today. So, to answer your question, the Internet was technically created in the late 1960s.\n" ] } ], "source": [ "print(chain.run(\"What year was the Internet created in?\"))" ] }, { "cell_type": "code", "execution_count": null, "id": "e50a0227", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "venv", "language": "python", "name": "venv" }, "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" } }, "nbformat": 4, "nbformat_minor": 5 }