github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-05 13:06:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

improve docs for indexes (#1146)

Browse Source
This commit is contained in:
Harrison Chase
2023-02-19 23:14:50 -08:00
committed by GitHub
parent 28781a6213
commit 4f3fbd7267
41 changed files with 1590 additions and 904 deletions
Download Patch File Download Diff File Expand all files Collapse all files

178
docs/modules/indexes/chain_examples/analyze_document.ipynb Normal file
View File

@@ -0,0 +1,178 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "ad719b65",
"metadata": {},
"source": [
"# Analyze Document\n",
"\n",
"The AnalyzeDocumentChain is more of an end to chain. This chain takes in a single document, splits it up, and then runs it through a CombineDocumentsChain. This can be used as more of an end-to-end chain."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "15e1a8a2",
"metadata": {},
"outputs": [],
"source": [
"with open('../../state_of_the_union.txt') as f:\n",
" state_of_the_union = f.read()"
]
},
{
"cell_type": "markdown",
"id": "14da4012",
"metadata": {},
"source": [
"## Summarize\n",
"Let's take a look at it in action below, using it summarize a long document."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "765d6326",
"metadata": {},
"outputs": [],
"source": [
"from langchain import OpenAI\n",
"from langchain.chains.summarize import load_summarize_chain\n",
"\n",
"llm = OpenAI(temperature=0)\n",
"summary_chain = load_summarize_chain(llm, chain_type=\"map_reduce\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "3a3d3ebc",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chains import AnalyzeDocumentChain"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "97178aad",
"metadata": {},
"outputs": [],
"source": [
"summarize_document_chain = AnalyzeDocumentChain(combine_docs_chain=summary_chain)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "2e5a7bf7",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\" In this speech, President Biden addresses the American people and the world, discussing the recent aggression of Russia's Vladimir Putin in Ukraine and the US response. He outlines economic sanctions and other measures taken to hold Putin accountable, and announces the US Department of Justice's task force to go after the crimes of Russian oligarchs. He also announces plans to fight inflation and lower costs for families, invest in American manufacturing, and provide military, economic, and humanitarian assistance to Ukraine. He calls for immigration reform, protecting the rights of women, and advancing the rights of LGBTQ+ Americans, and pays tribute to military families. He concludes with optimism for the future of America.\""
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"summarize_document_chain.run(state_of_the_union)"
]
},
{
"cell_type": "markdown",
"id": "35739404",
"metadata": {},
"source": [
"## Question Answering\n",
"Let's take a look at this using a question answering chain."
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "8b9b7705",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chains.question_answering import load_qa_chain"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "60c309a8",
"metadata": {},
"outputs": [],
"source": [
"qa_chain = load_qa_chain(llm, chain_type=\"map_reduce\")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "ba1fc940",
"metadata": {},
"outputs": [],
"source": [
"qa_document_chain = AnalyzeDocumentChain(combine_docs_chain=qa_chain)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "9aa1fbde",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"' The president thanked Justice Breyer for his service.'"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"qa_document_chain.run(input_document=state_of_the_union, question=\"what did the president say about justice breyer?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7eb02f1e",
"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": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

514
docs/modules/indexes/chain_examples/chat_vector_db.ipynb Normal file
View File

@@ -0,0 +1,514 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "134a0785",
"metadata": {},
"source": [
"# Chat Vector DB\n",
"\n",
"This notebook goes over how to set up a chain to chat with a vector database. The only difference between this chain and the [VectorDBQAChain](./vector_db_qa.ipynb) is that this allows for passing in of a chat history which can be used to allow for follow up questions."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "70c4e529",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.vectorstores import Chroma\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.llms import OpenAI\n",
"from langchain.chains import ChatVectorDBChain"
]
},
{
"cell_type": "markdown",
"id": "cdff94be",
"metadata": {},
"source": [
"Load in documents. You can replace this with a loader for whatever type of data you want"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "01c46e92",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.document_loaders import TextLoader\n",
"loader = TextLoader('../../state_of_the_union.txt')\n",
"documents = loader.load()"
]
},
{
"cell_type": "markdown",
"id": "e9be4779",
"metadata": {},
"source": [
"If you had multiple loaders that you wanted to combine, you do something like:"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "433363a5",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"# loaders = [....]\n",
"# docs = []\n",
"# for loader in loaders:\n",
"# docs.extend(loader.load())"
]
},
{
"cell_type": "markdown",
"id": "239475d2",
"metadata": {},
"source": [
"We now split the documents, create embeddings for them, and put them in a vectorstore. This allows us to do semantic search over them."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "a8930cf7",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running Chroma using direct local API.\n",
"Using DuckDB in-memory for database. Data will be transient.\n"
]
}
],
"source": [
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"documents = text_splitter.split_documents(documents)\n",
"\n",
"embeddings = OpenAIEmbeddings()\n",
"vectorstore = Chroma.from_documents(documents, embeddings)"
]
},
{
"cell_type": "markdown",
"id": "3c96b118",
"metadata": {},
"source": [
"We now initialize the ChatVectorDBChain"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "7b4110f3",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"qa = ChatVectorDBChain.from_llm(OpenAI(temperature=0), vectorstore)"
]
},
{
"cell_type": "markdown",
"id": "3872432d",
"metadata": {},
"source": [
"Here's an example of asking a question with no chat history"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "7fe3e730",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"chat_history = []\n",
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"result = qa({\"question\": query, \"chat_history\": chat_history})"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "bfff9cc8",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, and from a family of public school educators and police officers. He also said that she is a consensus builder and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"result[\"answer\"]"
]
},
{
"cell_type": "markdown",
"id": "9e46edf7",
"metadata": {},
"source": [
"Here's an example of asking a question with some chat history"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "00b4cf00",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"chat_history = [(query, result[\"answer\"])]\n",
"query = \"Did he mention who she suceeded\"\n",
"result = qa({\"question\": query, \"chat_history\": chat_history})"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "f01828d1",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"' Justice Stephen Breyer'"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"result['answer']"
]
},
{
"cell_type": "markdown",
"id": "0eaadf0f",
"metadata": {},
"source": [
"## Return Source Documents\n",
"You can also easily return source documents from the ChatVectorDBChain. This is useful for when you want to inspect what documents were returned."
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "562769c6",
"metadata": {},
"outputs": [],
"source": [
"qa = ChatVectorDBChain.from_llm(OpenAI(temperature=0), vectorstore, return_source_documents=True)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "ea478300",
"metadata": {},
"outputs": [],
"source": [
"chat_history = []\n",
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"result = qa({\"question\": query, \"chat_history\": chat_history})"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "4cb75b4e",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Document(page_content='In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. \\n\\nWe cannot let this happen. \\n\\nTonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0)"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"result['source_documents'][0]"
]
},
{
"cell_type": "markdown",
"id": "7fb44daa",
"metadata": {},
"source": [
"## Chat Vector DB with `map_reduce`\n",
"We can also use different types of combine document chains with the Chat Vector DB chain."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e53a9d66",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chains import LLMChain\n",
"from langchain.chains.question_answering import load_qa_chain\n",
"from langchain.chains.chat_vector_db.prompts import CONDENSE_QUESTION_PROMPT"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "bf205e35",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)\n",
"question_generator = LLMChain(llm=llm, prompt=CONDENSE_QUESTION_PROMPT)\n",
"doc_chain = load_qa_chain(llm, chain_type=\"map_reduce\")\n",
"\n",
"chain = ChatVectorDBChain(\n",
" vectorstore=vectorstore,\n",
" question_generator=question_generator,\n",
" combine_docs_chain=doc_chain,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "78155887",
"metadata": {},
"outputs": [],
"source": [
"chat_history = []\n",
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"result = chain({\"question\": query, \"chat_history\": chat_history})"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "e54b5fa2",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, from a family of public school educators and police officers, a consensus builder, and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"result['answer']"
]
},
{
"cell_type": "markdown",
"id": "a2fe6b14",
"metadata": {},
"source": [
"## Chat Vector DB with Question Answering with sources\n",
"\n",
"You can also use this chain with the question answering with sources chain."
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "d1058fd2",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chains.qa_with_sources import load_qa_with_sources_chain"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "a6594482",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)\n",
"question_generator = LLMChain(llm=llm, prompt=CONDENSE_QUESTION_PROMPT)\n",
"doc_chain = load_qa_with_sources_chain(llm, chain_type=\"map_reduce\")\n",
"\n",
"chain = ChatVectorDBChain(\n",
" vectorstore=vectorstore,\n",
" question_generator=question_generator,\n",
" combine_docs_chain=doc_chain,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "e2badd21",
"metadata": {},
"outputs": [],
"source": [
"chat_history = []\n",
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"result = chain({\"question\": query, \"chat_history\": chat_history})"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "edb31fe5",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, from a family of public school educators and police officers, a consensus builder, and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \\nSOURCES: ../../state_of_the_union.txt\""
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"result['answer']"
]
},
{
"cell_type": "markdown",
"id": "2324cdc6-98bf-4708-b8cd-02a98b1e5b67",
"metadata": {},
"source": [
"## Chat Vector DB with streaming to `stdout`\n",
"\n",
"Output from the chain will be streamed to `stdout` token by token in this example."
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "2efacec3-2690-4b05-8de3-a32fd2ac3911",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.chains.llm import LLMChain\n",
"from langchain.callbacks.base import CallbackManager\n",
"from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
"from langchain.chains.chat_vector_db.prompts import CONDENSE_QUESTION_PROMPT, QA_PROMPT\n",
"from langchain.chains.question_answering import load_qa_chain\n",
"\n",
"# Construct a ChatVectorDBChain with a streaming llm for combine docs\n",
"# and a separate, non-streaming llm for question generation\n",
"llm = OpenAI(temperature=0)\n",
"streaming_llm = OpenAI(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)\n",
"\n",
"question_generator = LLMChain(llm=llm, prompt=CONDENSE_QUESTION_PROMPT)\n",
"doc_chain = load_qa_chain(streaming_llm, chain_type=\"stuff\", prompt=QA_PROMPT)\n",
"\n",
"qa = ChatVectorDBChain(vectorstore=vectorstore, combine_docs_chain=doc_chain, question_generator=question_generator)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "fd6d43f4-7428-44a4-81bc-26fe88a98762",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, and from a family of public school educators and police officers. He also said that she is a consensus builder and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans."
]
}
],
"source": [
"chat_history = []\n",
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"result = qa({\"question\": query, \"chat_history\": chat_history})"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "5ab38978-f3e8-4fa7-808c-c79dec48379a",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Justice Stephen Breyer"
]
}
],
"source": [
"chat_history = [(query, result[\"answer\"])]\n",
"query = \"Did he mention who she suceeded\"\n",
"result = qa({\"question\": query, \"chat_history\": chat_history})"
]
}
],
"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
}

238
docs/modules/indexes/chain_examples/graph_qa.ipynb Normal file
View File

@@ -0,0 +1,238 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "a6850189",
"metadata": {},
"source": [
"# Graph QA\n",
"\n",
"This notebook goes over how to do question answering over a graph data structure."
]
},
{
"cell_type": "markdown",
"id": "9e516e3e",
"metadata": {},
"source": [
"## Create the graph\n",
"\n",
"In this section, we construct an example graph. At the moment, this works best for small pieces of text."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "3849873d",
"metadata": {},
"outputs": [],
"source": [
"from langchain.indexes import GraphIndexCreator\n",
"from langchain.llms import OpenAI\n",
"from langchain.document_loaders import TextLoader"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "05d65c87",
"metadata": {},
"outputs": [],
"source": [
"index_creator = GraphIndexCreator(llm=OpenAI(temperature=0))"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "0a45a5b9",
"metadata": {},
"outputs": [],
"source": [
"with open(\"../../state_of_the_union.txt\") as f:\n",
" all_text = f.read()"
]
},
{
"cell_type": "markdown",
"id": "3fca3e1b",
"metadata": {},
"source": [
"We will use just a small snippet, because extracting the knowledge triplets is a bit intensive at the moment."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "80522bd6",
"metadata": {},
"outputs": [],
"source": [
"text = \"\\n\".join(all_text.split(\"\\n\\n\")[105:108])"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "da5aad5a",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'It won’t look like much, but if you stop and look closely, you’ll see a “Field of dreams,” the ground on which America’s future will be built. \\nThis is where Intel, the American company that helped build Silicon Valley, is going to build its $20 billion semiconductor “mega site”. \\nUp to eight state-of-the-art factories in one place. 10,000 new good-paying jobs. '"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"text"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "8dad7b59",
"metadata": {},
"outputs": [],
"source": [
"graph = index_creator.from_text(text)"
]
},
{
"cell_type": "markdown",
"id": "2118f363",
"metadata": {},
"source": [
"We can inspect the created graph."
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "32878c13",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[('Intel', '$20 billion semiconductor \"mega site\"', 'is going to build'),\n",
" ('Intel', 'state-of-the-art factories', 'is building'),\n",
" ('Intel', '10,000 new good-paying jobs', 'is creating'),\n",
" ('Intel', 'Silicon Valley', 'is helping build'),\n",
" ('Field of dreams',\n",
" \"America's future will be built\",\n",
" 'is the ground on which')]"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"graph.get_triples()"
]
},
{
"cell_type": "markdown",
"id": "e9737be1",
"metadata": {},
"source": [
"## Querying the graph\n",
"We can now use the graph QA chain to ask question of the graph"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "76edc854",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chains import GraphQAChain"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "8e7719b4",
"metadata": {},
"outputs": [],
"source": [
"chain = GraphQAChain.from_llm(OpenAI(temperature=0), graph=graph, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "f6511169",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new GraphQAChain chain...\u001b[0m\n",
"Entities Extracted:\n",
"\u001b[32;1m\u001b[1;3m Intel\u001b[0m\n",
"Full Context:\n",
"\u001b[32;1m\u001b[1;3mIntel is going to build $20 billion semiconductor \"mega site\"\n",
"Intel is building state-of-the-art factories\n",
"Intel is creating 10,000 new good-paying jobs\n",
"Intel is helping build Silicon Valley\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"' Intel is going to build a $20 billion semiconductor \"mega site\" with state-of-the-art factories, creating 10,000 new good-paying jobs and helping to build Silicon Valley.'"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain.run(\"what is Intel going to build?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f70b9ada",
"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
}

735
docs/modules/indexes/chain_examples/qa_with_sources.ipynb Normal file
View File

@@ -0,0 +1,735 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "74148cee",
"metadata": {},
"source": [
"# Question Answering with Sources\n",
"\n",
"This notebook walks through how to use LangChain for question answering with sources over a list of documents. It covers four different chain types: `stuff`, `map_reduce`, `refine`,`map-rerank`. For a more in depth explanation of what these chain types are, see [here](../combine_docs.md)."
]
},
{
"cell_type": "markdown",
"id": "ca2f0efc",
"metadata": {},
"source": [
"## Prepare Data\n",
"First we prepare the data. For this example we do similarity search over a vector database, but these documents could be fetched in any manner (the point of this notebook to highlight what to do AFTER you fetch the documents)."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "78f28130",
"metadata": {},
"outputs": [],
"source": [
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.embeddings.cohere import CohereEmbeddings\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.vectorstores.elastic_vector_search import ElasticVectorSearch\n",
"from langchain.vectorstores import Chroma\n",
"from langchain.docstore.document import Document\n",
"from langchain.prompts import PromptTemplate"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "4da195a3",
"metadata": {},
"outputs": [],
"source": [
"with open('../../state_of_the_union.txt') as f:\n",
" state_of_the_union = f.read()\n",
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"texts = text_splitter.split_text(state_of_the_union)\n",
"\n",
"embeddings = OpenAIEmbeddings()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "5ec2b55b",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running Chroma using direct local API.\n",
"Using DuckDB in-memory for database. Data will be transient.\n"
]
}
],
"source": [
"docsearch = Chroma.from_texts(texts, embeddings, metadatas=[{\"source\": str(i)} for i in range(len(texts))])"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "5286f58f",
"metadata": {},
"outputs": [],
"source": [
"query = \"What did the president say about Justice Breyer\"\n",
"docs = docsearch.similarity_search(query)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "005a47e9",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chains.qa_with_sources import load_qa_with_sources_chain\n",
"from langchain.llms import OpenAI"
]
},
{
"cell_type": "markdown",
"id": "5b119026",
"metadata": {},
"source": [
"## Quickstart\n",
"If you just want to get started as quickly as possible, this is the recommended way to do it:"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "3722373b",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'output_text': ' The president thanked Justice Breyer for his service.\\nSOURCES: 30-pl'}"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain = load_qa_with_sources_chain(OpenAI(temperature=0), chain_type=\"stuff\")\n",
"query = \"What did the president say about Justice Breyer\"\n",
"chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
]
},
{
"cell_type": "markdown",
"id": "bdaf9268",
"metadata": {},
"source": [
"If you want more control and understanding over what is happening, please see the information below."
]
},
{
"cell_type": "markdown",
"id": "d82f899a",
"metadata": {},
"source": [
"## The `stuff` Chain\n",
"\n",
"This sections shows results of using the `stuff` Chain to do question answering with sources."
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "fc1a5ed6",
"metadata": {},
"outputs": [],
"source": [
"chain = load_qa_with_sources_chain(OpenAI(temperature=0), chain_type=\"stuff\")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "7d766417",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'output_text': ' The president thanked Justice Breyer for his service.\\nSOURCES: 30-pl'}"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"query = \"What did the president say about Justice Breyer\"\n",
"chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
]
},
{
"cell_type": "markdown",
"id": "e966aea8",
"metadata": {},
"source": [
"**Custom Prompts**\n",
"\n",
"You can also use your own prompts with this chain. In this example, we will respond in Italian."
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "426c570b",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'output_text': '\\nNon so cosa abbia detto il presidente riguardo a Justice Breyer.\\nSOURCES: 30, 31, 33'}"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"template = \"\"\"Given the following extracted parts of a long document and a question, create a final answer with references (\"SOURCES\"). \n",
"If you don't know the answer, just say that you don't know. Don't try to make up an answer.\n",
"ALWAYS return a \"SOURCES\" part in your answer.\n",
"Respond in Italian.\n",
"\n",
"QUESTION: {question}\n",
"=========\n",
"{summaries}\n",
"=========\n",
"FINAL ANSWER IN ITALIAN:\"\"\"\n",
"PROMPT = PromptTemplate(template=template, input_variables=[\"summaries\", \"question\"])\n",
"\n",
"chain = load_qa_with_sources_chain(OpenAI(temperature=0), chain_type=\"stuff\", prompt=PROMPT)\n",
"query = \"What did the president say about Justice Breyer\"\n",
"chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
]
},
{
"cell_type": "markdown",
"id": "c5dbb304",
"metadata": {},
"source": [
"## The `map_reduce` Chain\n",
"\n",
"This sections shows results of using the `map_reduce` Chain to do question answering with sources."
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "921db0a4",
"metadata": {},
"outputs": [],
"source": [
"chain = load_qa_with_sources_chain(OpenAI(temperature=0), chain_type=\"map_reduce\")"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "e417926a",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'output_text': ' The president thanked Justice Breyer for his service.\\nSOURCES: 30-pl'}"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"query = \"What did the president say about Justice Breyer\"\n",
"chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
]
},
{
"cell_type": "markdown",
"id": "ae2f6d97",
"metadata": {},
"source": [
"**Intermediate Steps**\n",
"\n",
"We can also return the intermediate steps for `map_reduce` chains, should we want to inspect them. This is done with the `return_map_steps` variable."
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "15af265f",
"metadata": {},
"outputs": [],
"source": [
"chain = load_qa_with_sources_chain(OpenAI(temperature=0), chain_type=\"map_reduce\", return_intermediate_steps=True)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "21b136e5",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'intermediate_steps': [' \"Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service.\"',\n",
" ' None',\n",
" ' None',\n",
" ' None'],\n",
" 'output_text': ' The president thanked Justice Breyer for his service.\\nSOURCES: 30-pl'}"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
]
},
{
"cell_type": "markdown",
"id": "d56e101a",
"metadata": {},
"source": [
"**Custom Prompts**\n",
"\n",
"You can also use your own prompts with this chain. In this example, we will respond in Italian."
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "47f0d517",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'intermediate_steps': [\"\\nStasera vorrei onorare qualcuno che ha dedicato la sua vita a servire questo paese: il giustizia Stephen Breyer - un veterano dell'esercito, uno studioso costituzionale e un giustizia in uscita della Corte Suprema degli Stati Uniti. Giustizia Breyer, grazie per il tuo servizio.\",\n",
" ' Non pertinente.',\n",
" ' Non rilevante.',\n",
" \" Non c'è testo pertinente.\"],\n",
" 'output_text': ' Non conosco la risposta. SOURCES: 30, 31, 33, 20.'}"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\n",
"question_prompt_template = \"\"\"Use the following portion of a long document to see if any of the text is relevant to answer the question. \n",
"Return any relevant text in Italian.\n",
"{context}\n",
"Question: {question}\n",
"Relevant text, if any, in Italian:\"\"\"\n",
"QUESTION_PROMPT = PromptTemplate(\n",
" template=question_prompt_template, input_variables=[\"context\", \"question\"]\n",
")\n",
"\n",
"combine_prompt_template = \"\"\"Given the following extracted parts of a long document and a question, create a final answer with references (\"SOURCES\"). \n",
"If you don't know the answer, just say that you don't know. Don't try to make up an answer.\n",
"ALWAYS return a \"SOURCES\" part in your answer.\n",
"Respond in Italian.\n",
"\n",
"QUESTION: {question}\n",
"=========\n",
"{summaries}\n",
"=========\n",
"FINAL ANSWER IN ITALIAN:\"\"\"\n",
"COMBINE_PROMPT = PromptTemplate(\n",
" template=combine_prompt_template, input_variables=[\"summaries\", \"question\"]\n",
")\n",
"\n",
"chain = load_qa_with_sources_chain(OpenAI(temperature=0), chain_type=\"map_reduce\", return_intermediate_steps=True, question_prompt=QUESTION_PROMPT, combine_prompt=COMBINE_PROMPT)\n",
"chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
]
},
{
"cell_type": "markdown",
"id": "d943c6c1",
"metadata": {},
"source": [
"**Batch Size**\n",
"\n",
"When using the `map_reduce` chain, one thing to keep in mind is the batch size you are using during the map step. If this is too high, it could cause rate limiting errors. You can control this by setting the batch size on the LLM used. Note that this only applies for LLMs with this parameter. Below is an example of doing so:\n",
"\n",
"```python\n",
"llm = OpenAI(batch_size=5, temperature=0)\n",
"```"
]
},
{
"cell_type": "markdown",
"id": "5bf0e1ab",
"metadata": {},
"source": [
"## The `refine` Chain\n",
"\n",
"This sections shows results of using the `refine` Chain to do question answering with sources."
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "904835c8",
"metadata": {},
"outputs": [],
"source": [
"chain = load_qa_with_sources_chain(OpenAI(temperature=0), chain_type=\"refine\")"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "f60875c6",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'output_text': \"\\n\\nThe president said that he was honoring Justice Breyer for his dedication to serving the country and that he was a retiring Justice of the United States Supreme Court. He also thanked him for his service and praised his career as a top litigator in private practice, a former federal public defender, and a family of public school educators and police officers. He noted Justice Breyer's reputation as a consensus builder and the broad range of support he has received from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. He also highlighted the importance of securing the border and fixing the immigration system in order to advance liberty and justice, and mentioned the new technology, joint patrols, dedicated immigration judges, and commitments to support partners in South and Central America that have been put in place. He also expressed his commitment to the LGBTQ+ community, noting the need for the bipartisan Equality Act and the importance of protecting transgender Americans from state laws targeting them. He also highlighted his commitment to bipartisanship, noting the 80 bipartisan bills he signed into law last year, and his plans to strengthen the Violence Against Women Act. Additionally, he announced that the Justice Department will name a chief prosecutor for pandemic fraud and his plan to lower the deficit by more than one trillion dollars in a\"}"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"query = \"What did the president say about Justice Breyer\"\n",
"chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
]
},
{
"cell_type": "markdown",
"id": "ac357530",
"metadata": {},
"source": [
"**Intermediate Steps**\n",
"\n",
"We can also return the intermediate steps for `refine` chains, should we want to inspect them. This is done with the `return_intermediate_steps` variable."
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "3396a773",
"metadata": {},
"outputs": [],
"source": [
"chain = load_qa_with_sources_chain(OpenAI(temperature=0), chain_type=\"refine\", return_intermediate_steps=True)"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "be5739ef",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'intermediate_steps': ['\\nThe president said that he was honoring Justice Breyer for his dedication to serving the country and that he was a retiring Justice of the United States Supreme Court. He also thanked Justice Breyer for his service.',\n",
" '\\n\\nThe president said that he was honoring Justice Breyer for his dedication to serving the country and that he was a retiring Justice of the United States Supreme Court. He also thanked Justice Breyer for his service, noting his background as a top litigator in private practice, a former federal public defender, and a family of public school educators and police officers. He praised Justice Breyer for being a consensus builder and for receiving a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. He also noted that in order to advance liberty and justice, it was necessary to secure the border and fix the immigration system, and that the government was taking steps to do both. \\n\\nSource: 31',\n",
" '\\n\\nThe president said that he was honoring Justice Breyer for his dedication to serving the country and that he was a retiring Justice of the United States Supreme Court. He also thanked Justice Breyer for his service, noting his background as a top litigator in private practice, a former federal public defender, and a family of public school educators and police officers. He praised Justice Breyer for being a consensus builder and for receiving a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. He also noted that in order to advance liberty and justice, it was necessary to secure the border and fix the immigration system, and that the government was taking steps to do both. He also mentioned the need to pass the bipartisan Equality Act to protect LGBTQ+ Americans, and to strengthen the Violence Against Women Act that he had written three decades ago. \\n\\nSource: 31, 33',\n",
" '\\n\\nThe president said that he was honoring Justice Breyer for his dedication to serving the country and that he was a retiring Justice of the United States Supreme Court. He also thanked Justice Breyer for his service, noting his background as a top litigator in private practice, a former federal public defender, and a family of public school educators and police officers. He praised Justice Breyer for being a consensus builder and for receiving a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. He also noted that in order to advance liberty and justice, it was necessary to secure the border and fix the immigration system, and that the government was taking steps to do both. He also mentioned the need to pass the bipartisan Equality Act to protect LGBTQ+ Americans, and to strengthen the Violence Against Women Act that he had written three decades ago. Additionally, he mentioned his plan to lower costs to give families a fair shot, lower the deficit, and go after criminals who stole billions in relief money meant for small businesses and millions of Americans. He also announced that the Justice Department will name a chief prosecutor for pandemic fraud. \\n\\nSource: 20, 31, 33'],\n",
" 'output_text': '\\n\\nThe president said that he was honoring Justice Breyer for his dedication to serving the country and that he was a retiring Justice of the United States Supreme Court. He also thanked Justice Breyer for his service, noting his background as a top litigator in private practice, a former federal public defender, and a family of public school educators and police officers. He praised Justice Breyer for being a consensus builder and for receiving a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. He also noted that in order to advance liberty and justice, it was necessary to secure the border and fix the immigration system, and that the government was taking steps to do both. He also mentioned the need to pass the bipartisan Equality Act to protect LGBTQ+ Americans, and to strengthen the Violence Against Women Act that he had written three decades ago. Additionally, he mentioned his plan to lower costs to give families a fair shot, lower the deficit, and go after criminals who stole billions in relief money meant for small businesses and millions of Americans. He also announced that the Justice Department will name a chief prosecutor for pandemic fraud. \\n\\nSource: 20, 31, 33'}"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
]
},
{
"cell_type": "markdown",
"id": "cf08c8a1",
"metadata": {},
"source": [
"**Custom Prompts**\n",
"\n",
"You can also use your own prompts with this chain. In this example, we will respond in Italian."
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "97e33bd9",
"metadata": {},
"outputs": [],
"source": [
"refine_template = (\n",
" \"The original question is as follows: {question}\\n\"\n",
" \"We have provided an existing answer, including sources: {existing_answer}\\n\"\n",
" \"We have the opportunity to refine the existing answer\"\n",
" \"(only if needed) with some more context below.\\n\"\n",
" \"------------\\n\"\n",
" \"{context_str}\\n\"\n",
" \"------------\\n\"\n",
" \"Given the new context, refine the original answer to better \"\n",
" \"answer the question (in Italian)\"\n",
" \"If you do update it, please update the sources as well. \"\n",
" \"If the context isn't useful, return the original answer.\"\n",
")\n",
"refine_prompt = PromptTemplate(\n",
" input_variables=[\"question\", \"existing_answer\", \"context_str\"],\n",
" template=refine_template,\n",
")\n",
"\n",
"\n",
"question_template = (\n",
" \"Context information is below. \\n\"\n",
" \"---------------------\\n\"\n",
" \"{context_str}\"\n",
" \"\\n---------------------\\n\"\n",
" \"Given the context information and not prior knowledge, \"\n",
" \"answer the question in Italian: {question}\\n\"\n",
")\n",
"question_prompt = PromptTemplate(\n",
" input_variables=[\"context_str\", \"question\"], template=question_template\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "41565992",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'intermediate_steps': ['\\nIl presidente ha detto che Justice Breyer ha dedicato la sua vita al servizio di questo paese e ha onorato la sua carriera.',\n",
" \"\\n\\nIl presidente ha detto che Justice Breyer ha dedicato la sua vita al servizio di questo paese, ha onorato la sua carriera e ha contribuito a costruire un consenso. Ha ricevuto un ampio sostegno, dall'Ordine Fraterno della Polizia a ex giudici nominati da democratici e repubblicani. Inoltre, ha sottolineato l'importanza di avanzare la libertà e la giustizia attraverso la sicurezza delle frontiere e la risoluzione del sistema di immigrazione. Ha anche menzionato le nuove tecnologie come scanner all'avanguardia per rilevare meglio il traffico di droga, le pattuglie congiunte con Messico e Guatemala per catturare più trafficanti di esseri umani, l'istituzione di giudici di immigrazione dedicati per far sì che le famiglie che fuggono da per\",\n",
" \"\\n\\nIl presidente ha detto che Justice Breyer ha dedicato la sua vita al servizio di questo paese, ha onorato la sua carriera e ha contribuito a costruire un consenso. Ha ricevuto un ampio sostegno, dall'Ordine Fraterno della Polizia a ex giudici nominati da democratici e repubblicani. Inoltre, ha sottolineato l'importanza di avanzare la libertà e la giustizia attraverso la sicurezza delle frontiere e la risoluzione del sistema di immigrazione. Ha anche menzionato le nuove tecnologie come scanner all'avanguardia per rilevare meglio il traffico di droga, le pattuglie congiunte con Messico e Guatemala per catturare più trafficanti di esseri umani, l'istituzione di giudici di immigrazione dedicati per far sì che le famiglie che fuggono da per\",\n",
" \"\\n\\nIl presidente ha detto che Justice Breyer ha dedicato la sua vita al servizio di questo paese, ha onorato la sua carriera e ha contribuito a costruire un consenso. Ha ricevuto un ampio sostegno, dall'Ordine Fraterno della Polizia a ex giudici nominati da democratici e repubblicani. Inoltre, ha sottolineato l'importanza di avanzare la libertà e la giustizia attraverso la sicurezza delle frontiere e la risoluzione del sistema di immigrazione. Ha anche menzionato le nuove tecnologie come scanner all'avanguardia per rilevare meglio il traffico di droga, le pattuglie congiunte con Messico e Guatemala per catturare più trafficanti di esseri umani, l'istituzione di giudici di immigrazione dedicati per far sì che le famiglie che fuggono da per\"],\n",
" 'output_text': \"\\n\\nIl presidente ha detto che Justice Breyer ha dedicato la sua vita al servizio di questo paese, ha onorato la sua carriera e ha contribuito a costruire un consenso. Ha ricevuto un ampio sostegno, dall'Ordine Fraterno della Polizia a ex giudici nominati da democratici e repubblicani. Inoltre, ha sottolineato l'importanza di avanzare la libertà e la giustizia attraverso la sicurezza delle frontiere e la risoluzione del sistema di immigrazione. Ha anche menzionato le nuove tecnologie come scanner all'avanguardia per rilevare meglio il traffico di droga, le pattuglie congiunte con Messico e Guatemala per catturare più trafficanti di esseri umani, l'istituzione di giudici di immigrazione dedicati per far sì che le famiglie che fuggono da per\"}"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain = load_qa_with_sources_chain(OpenAI(temperature=0), chain_type=\"refine\", return_intermediate_steps=True, question_prompt=question_prompt, refine_prompt=refine_prompt)\n",
"chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
]
},
{
"cell_type": "markdown",
"id": "07ff756e",
"metadata": {},
"source": [
"## The `map-rerank` Chain\n",
"\n",
"This sections shows results of using the `map-rerank` Chain to do question answering with sources."
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "46b52ef9",
"metadata": {},
"outputs": [],
"source": [
"chain = load_qa_with_sources_chain(OpenAI(temperature=0), chain_type=\"map_rerank\", metadata_keys=['source'], return_intermediate_steps=True)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "7ce2da04",
"metadata": {},
"outputs": [],
"source": [
"query = \"What did the president say about Justice Breyer\"\n",
"result = chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "cbdcd3c5",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"' The President thanked Justice Breyer for his service and honored him for dedicating his life to serve the country.'"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"result[\"output_text\"]"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "6f0b3d03",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[{'answer': ' The President thanked Justice Breyer for his service and honored him for dedicating his life to serve the country.',\n",
" 'score': '100'},\n",
" {'answer': ' This document does not answer the question', 'score': '0'},\n",
" {'answer': ' This document does not answer the question', 'score': '0'},\n",
" {'answer': ' This document does not answer the question', 'score': '0'}]"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"result[\"intermediate_steps\"]"
]
},
{
"cell_type": "markdown",
"id": "b94bfeb6",
"metadata": {},
"source": [
"**Custom Prompts**\n",
"\n",
"You can also use your own prompts with this chain. In this example, we will respond in Italian."
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "cb46ba3f",
"metadata": {},
"outputs": [],
"source": [
"from langchain.prompts.base import RegexParser\n",
"\n",
"output_parser = RegexParser(\n",
" regex=r\"(.*?)\\nScore: (.*)\",\n",
" output_keys=[\"answer\", \"score\"],\n",
")\n",
"\n",
"prompt_template = \"\"\"Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer.\n",
"\n",
"In addition to giving an answer, also return a score of how fully it answered the user's question. This should be in the following format:\n",
"\n",
"Question: [question here]\n",
"Helpful Answer In Italian: [answer here]\n",
"Score: [score between 0 and 100]\n",
"\n",
"Begin!\n",
"\n",
"Context:\n",
"---------\n",
"{context}\n",
"---------\n",
"Question: {question}\n",
"Helpful Answer In Italian:\"\"\"\n",
"PROMPT = PromptTemplate(\n",
" template=prompt_template,\n",
" input_variables=[\"context\", \"question\"],\n",
" output_parser=output_parser,\n",
")\n",
"chain = load_qa_with_sources_chain(OpenAI(temperature=0), chain_type=\"map_rerank\", metadata_keys=['source'], return_intermediate_steps=True, prompt=PROMPT)\n",
"query = \"What did the president say about Justice Breyer\"\n",
"result = chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "fee7b055",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'source': 30,\n",
" 'intermediate_steps': [{'answer': ' Il presidente ha detto che Justice Breyer ha dedicato la sua vita a servire questo paese e ha onorato la sua carriera.',\n",
" 'score': '100'},\n",
" {'answer': ' Il presidente non ha detto nulla sulla Giustizia Breyer.',\n",
" 'score': '100'},\n",
" {'answer': ' Non so.', 'score': '0'},\n",
" {'answer': ' Il presidente non ha detto nulla sulla giustizia Breyer.',\n",
" 'score': '100'}],\n",
" 'output_text': ' Il presidente ha detto che Justice Breyer ha dedicato la sua vita a servire questo paese e ha onorato la sua carriera.'}"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"result"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5a51c987",
"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"
},
"vscode": {
"interpreter": {
"hash": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}

710
docs/modules/indexes/chain_examples/question_answering.ipynb Normal file
View File

@@ -0,0 +1,710 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "05859721",
"metadata": {},
"source": [
"# Question Answering\n",
"\n",
"This notebook walks through how to use LangChain for question answering over a list of documents. It covers four different types of chaings: `stuff`, `map_reduce`, `refine`, `map-rerank`. For a more in depth explanation of what these chain types are, see [here](../combine_docs.md)."
]
},
{
"cell_type": "markdown",
"id": "726f4996",
"metadata": {},
"source": [
"## Prepare Data\n",
"First we prepare the data. For this example we do similarity search over a vector database, but these documents could be fetched in any manner (the point of this notebook to highlight what to do AFTER you fetch the documents)."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "17fcbc0f",
"metadata": {},
"outputs": [],
"source": [
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.vectorstores import Chroma\n",
"from langchain.docstore.document import Document\n",
"from langchain.prompts import PromptTemplate"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "291f0117",
"metadata": {},
"outputs": [],
"source": [
"from langchain.document_loaders import TextLoader\n",
"loader = TextLoader('../../state_of_the_union.txt')\n",
"documents = loader.load()\n",
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"texts = text_splitter.split_documents(documents)\n",
"\n",
"embeddings = OpenAIEmbeddings()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "fd9666a9",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running Chroma using direct local API.\n",
"Using DuckDB in-memory for database. Data will be transient.\n"
]
}
],
"source": [
"docsearch = Chroma.from_documents(texts, embeddings)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "d1eaf6e6",
"metadata": {},
"outputs": [],
"source": [
"query = \"What did the president say about Justice Breyer\"\n",
"docs = docsearch.similarity_search(query)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "a16e3453",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chains.question_answering import load_qa_chain\n",
"from langchain.llms import OpenAI"
]
},
{
"cell_type": "markdown",
"id": "2f64b7f8",
"metadata": {},
"source": [
"## Quickstart\n",
"If you just want to get started as quickly as possible, this is the recommended way to do it:"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "fd9e6190",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"' The president said that he was honoring Justice Breyer for his service to the country and that he was a Constitutional scholar, Army veteran, and retiring Justice of the United States Supreme Court.'"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain = load_qa_chain(OpenAI(temperature=0), chain_type=\"stuff\")\n",
"query = \"What did the president say about Justice Breyer\"\n",
"chain.run(input_documents=docs, question=query)"
]
},
{
"cell_type": "markdown",
"id": "eea01309",
"metadata": {},
"source": [
"If you want more control and understanding over what is happening, please see the information below."
]
},
{
"cell_type": "markdown",
"id": "f78787a0",
"metadata": {},
"source": [
"## The `stuff` Chain\n",
"\n",
"This sections shows results of using the `stuff` Chain to do question answering."
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "180fd4c1",
"metadata": {},
"outputs": [],
"source": [
"chain = load_qa_chain(OpenAI(temperature=0), chain_type=\"stuff\")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "77fdf1aa",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'output_text': ' The president said that he was honoring Justice Breyer for his service to the country and that he was a Constitutional scholar, Army veteran, and retiring Justice of the United States Supreme Court.'}"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"query = \"What did the president say about Justice Breyer\"\n",
"chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
]
},
{
"cell_type": "markdown",
"id": "84794d4c",
"metadata": {},
"source": [
"**Custom Prompts**\n",
"\n",
"You can also use your own prompts with this chain. In this example, we will respond in Italian."
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "5558c9e0",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'output_text': ' Il presidente ha detto che Justice Breyer ha dedicato la sua vita a servire questo paese e ha onorato la sua carriera come giudice della Corte Suprema degli Stati Uniti.'}"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"prompt_template = \"\"\"Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer.\n",
"\n",
"{context}\n",
"\n",
"Question: {question}\n",
"Answer in Italian:\"\"\"\n",
"PROMPT = PromptTemplate(\n",
" template=prompt_template, input_variables=[\"context\", \"question\"]\n",
")\n",
"chain = load_qa_chain(OpenAI(temperature=0), chain_type=\"stuff\", prompt=PROMPT)\n",
"chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
]
},
{
"cell_type": "markdown",
"id": "91522e29",
"metadata": {},
"source": [
"## The `map_reduce` Chain\n",
"\n",
"This sections shows results of using the `map_reduce` Chain to do question answering."
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "b0060f51",
"metadata": {},
"outputs": [],
"source": [
"chain = load_qa_chain(OpenAI(temperature=0), chain_type=\"map_reduce\")"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "fbdb9137",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'output_text': ' The president said, \"Justice Breyer, thank you for your service.\"'}"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"query = \"What did the president say about Justice Breyer\"\n",
"chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
]
},
{
"cell_type": "markdown",
"id": "31478d32",
"metadata": {},
"source": [
"**Intermediate Steps**\n",
"\n",
"We can also return the intermediate steps for `map_reduce` chains, should we want to inspect them. This is done with the `return_map_steps` variable."
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "452c8680",
"metadata": {},
"outputs": [],
"source": [
"chain = load_qa_chain(OpenAI(temperature=0), chain_type=\"map_reduce\", return_map_steps=True)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "90b47a75",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'intermediate_steps': [' \"Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service.\"',\n",
" ' None',\n",
" ' None',\n",
" ' None'],\n",
" 'output_text': ' The president said, \"Justice Breyer, thank you for your service.\"'}"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
]
},
{
"cell_type": "markdown",
"id": "93c51102",
"metadata": {},
"source": [
"**Custom Prompts**\n",
"\n",
"You can also use your own prompts with this chain. In this example, we will respond in Italian."
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "af03a578",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'intermediate_steps': [\"\\nStasera vorrei onorare qualcuno che ha dedicato la sua vita a servire questo paese: il giustizia Stephen Breyer - un veterano dell'esercito, uno studioso costituzionale e un giustizia in uscita della Corte Suprema degli Stati Uniti. Giustizia Breyer, grazie per il tuo servizio.\",\n",
" '\\nNessun testo pertinente.',\n",
" \"\\nCome ho detto l'anno scorso, soprattutto ai nostri giovani americani transgender, avrò sempre il tuo sostegno come tuo Presidente, in modo che tu possa essere te stesso e raggiungere il tuo potenziale donato da Dio.\",\n",
" '\\nNella mia amministrazione, i guardiani sono stati accolti di nuovo. Stiamo andando dietro ai criminali che hanno rubato miliardi di dollari di aiuti di emergenza destinati alle piccole imprese e a milioni di americani. E stasera, annuncio che il Dipartimento di Giustizia nominerà un procuratore capo per la frode pandemica.'],\n",
" 'output_text': ' Non conosco la risposta alla tua domanda su cosa abbia detto il Presidente riguardo al Giustizia Breyer.'}"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"question_prompt_template = \"\"\"Use the following portion of a long document to see if any of the text is relevant to answer the question. \n",
"Return any relevant text translated into italian.\n",
"{context}\n",
"Question: {question}\n",
"Relevant text, if any, in Italian:\"\"\"\n",
"QUESTION_PROMPT = PromptTemplate(\n",
" template=question_prompt_template, input_variables=[\"context\", \"question\"]\n",
")\n",
"\n",
"combine_prompt_template = \"\"\"Given the following extracted parts of a long document and a question, create a final answer italian. \n",
"If you don't know the answer, just say that you don't know. Don't try to make up an answer.\n",
"\n",
"QUESTION: {question}\n",
"=========\n",
"{summaries}\n",
"=========\n",
"Answer in Italian:\"\"\"\n",
"COMBINE_PROMPT = PromptTemplate(\n",
" template=combine_prompt_template, input_variables=[\"summaries\", \"question\"]\n",
")\n",
"chain = load_qa_chain(OpenAI(temperature=0), chain_type=\"map_reduce\", return_map_steps=True, question_prompt=QUESTION_PROMPT, combine_prompt=COMBINE_PROMPT)\n",
"chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
]
},
{
"cell_type": "markdown",
"id": "6391b7ab",
"metadata": {},
"source": [
"**Batch Size**\n",
"\n",
"When using the `map_reduce` chain, one thing to keep in mind is the batch size you are using during the map step. If this is too high, it could cause rate limiting errors. You can control this by setting the batch size on the LLM used. Note that this only applies for LLMs with this parameter. Below is an example of doing so:\n",
"\n",
"```python\n",
"llm = OpenAI(batch_size=5, temperature=0)\n",
"```"
]
},
{
"cell_type": "markdown",
"id": "6ea50ad0",
"metadata": {},
"source": [
"## The `refine` Chain\n",
"\n",
"This sections shows results of using the `refine` Chain to do question answering."
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "fb167057",
"metadata": {},
"outputs": [],
"source": [
"chain = load_qa_chain(OpenAI(temperature=0), chain_type=\"refine\")"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "d8b5286e",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'output_text': '\\n\\nThe president said that he wanted to honor Justice Breyer for his dedication to serving the country, his legacy of excellence, and his commitment to advancing liberty and justice, as well as for his commitment to protecting the rights of LGBTQ+ Americans and his support for the bipartisan Equality Act. He also mentioned his plan to lower costs to give families a fair shot, lower the deficit, and go after criminals who stole pandemic relief funds. He also announced that the Justice Department will name a chief prosecutor for pandemic fraud.'}"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"query = \"What did the president say about Justice Breyer\"\n",
"chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
]
},
{
"cell_type": "markdown",
"id": "f95dfb2e",
"metadata": {},
"source": [
"**Intermediate Steps**\n",
"\n",
"We can also return the intermediate steps for `refine` chains, should we want to inspect them. This is done with the `return_refine_steps` variable."
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "a5c64200",
"metadata": {},
"outputs": [],
"source": [
"chain = load_qa_chain(OpenAI(temperature=0), chain_type=\"refine\", return_refine_steps=True)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "817546ac",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'intermediate_steps': ['\\nThe president said that he wanted to honor Justice Breyer for his dedication to serving the country and his legacy of excellence.',\n",
" '\\n\\nThe president said that he wanted to honor Justice Breyer for his dedication to serving the country, his legacy of excellence, and his commitment to advancing liberty and justice.',\n",
" '\\n\\nThe president said that he wanted to honor Justice Breyer for his dedication to serving the country, his legacy of excellence, and his commitment to advancing liberty and justice, as well as for his commitment to protecting the rights of LGBTQ+ Americans and his support for the bipartisan Equality Act.',\n",
" '\\n\\nThe president said that he wanted to honor Justice Breyer for his dedication to serving the country, his legacy of excellence, and his commitment to advancing liberty and justice, as well as for his commitment to protecting the rights of LGBTQ+ Americans and his support for the bipartisan Equality Act. He also mentioned his plan to lower costs to give families a fair shot, lower the deficit, and go after criminals who stole pandemic relief funds. He also announced that the Justice Department will name a chief prosecutor for pandemic fraud.'],\n",
" 'output_text': '\\n\\nThe president said that he wanted to honor Justice Breyer for his dedication to serving the country, his legacy of excellence, and his commitment to advancing liberty and justice, as well as for his commitment to protecting the rights of LGBTQ+ Americans and his support for the bipartisan Equality Act. He also mentioned his plan to lower costs to give families a fair shot, lower the deficit, and go after criminals who stole pandemic relief funds. He also announced that the Justice Department will name a chief prosecutor for pandemic fraud.'}"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
]
},
{
"cell_type": "markdown",
"id": "4f0bcae4",
"metadata": {},
"source": [
"**Custom Prompts**\n",
"\n",
"You can also use your own prompts with this chain. In this example, we will respond in Italian."
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "6664bda7",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'intermediate_steps': ['\\nIl presidente ha detto che Justice Breyer ha dedicato la sua vita al servizio di questo paese e ha onorato la sua carriera. Ha anche detto che la sua nomina di Circuit Court of Appeals Judge Ketanji Brown Jackson continuerà il suo eccezionale lascito.',\n",
" \"\\nIl presidente ha detto che Justice Breyer ha dedicato la sua vita al servizio di questo paese e ha onorato la sua carriera. Ha anche detto che la sua nomina di Circuit Court of Appeals Judge Ketanji Brown Jackson continuerà il suo eccezionale lascito. Ha sottolineato che la sua esperienza come avvocato di alto livello in pratica privata, come ex difensore federale pubblico e come membro di una famiglia di educatori e agenti di polizia, la rende una costruttrice di consenso. Ha anche sottolineato che, dalla sua nomina, ha ricevuto un ampio sostegno, dall'Ordine Fraterno della Polizia a ex giudici nominati da democratici e repubblicani.\",\n",
" \"\\n\\nIl presidente ha detto che Justice Breyer ha dedicato la sua vita al servizio di questo paese e ha onorato la sua carriera. Ha anche detto che la sua nomina di Circuit Court of Appeals Judge Ketanji Brown Jackson continuerà il suo eccezionale lascito. Ha sottolineato che la sua esperienza come avvocato di alto livello in pratica privata, come ex difensore federale pubblico e come membro di una famiglia di educatori e agenti di polizia, la rende una costruttrice di consenso. Ha anche sottolineato che, dalla sua nomina, ha ricevuto un ampio sostegno, dall'Ordine Fraterno della Polizia a ex giudici nominati da democratici e repubblicani. Ha inoltre sottolineato che la nomina di Justice Breyer è un passo importante verso l'uguaglianza per tutti gli americani, in partic\",\n",
" \"\\n\\nIl presidente ha detto che Justice Breyer ha dedicato la sua vita al servizio di questo paese e ha onorato la sua carriera. Ha anche detto che la sua nomina di Circuit Court of Appeals Judge Ketanji Brown Jackson continuerà il suo eccezionale lascito. Ha sottolineato che la sua esperienza come avvocato di alto livello in pratica privata, come ex difensore federale pubblico e come membro di una famiglia di educatori e agenti di polizia, la rende una costruttrice di consenso. Ha anche sottolineato che, dalla sua nomina, ha ricevuto un ampio sostegno, dall'Ordine Fraterno della Polizia a ex giudici nominati da democratici e repubblicani. Ha inoltre sottolineato che la nomina di Justice Breyer è un passo importante verso l'uguaglianza per tutti gli americani, in partic\"],\n",
" 'output_text': \"\\n\\nIl presidente ha detto che Justice Breyer ha dedicato la sua vita al servizio di questo paese e ha onorato la sua carriera. Ha anche detto che la sua nomina di Circuit Court of Appeals Judge Ketanji Brown Jackson continuerà il suo eccezionale lascito. Ha sottolineato che la sua esperienza come avvocato di alto livello in pratica privata, come ex difensore federale pubblico e come membro di una famiglia di educatori e agenti di polizia, la rende una costruttrice di consenso. Ha anche sottolineato che, dalla sua nomina, ha ricevuto un ampio sostegno, dall'Ordine Fraterno della Polizia a ex giudici nominati da democratici e repubblicani. Ha inoltre sottolineato che la nomina di Justice Breyer è un passo importante verso l'uguaglianza per tutti gli americani, in partic\"}"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"refine_prompt_template = (\n",
" \"The original question is as follows: {question}\\n\"\n",
" \"We have provided an existing answer: {existing_answer}\\n\"\n",
" \"We have the opportunity to refine the existing answer\"\n",
" \"(only if needed) with some more context below.\\n\"\n",
" \"------------\\n\"\n",
" \"{context_str}\\n\"\n",
" \"------------\\n\"\n",
" \"Given the new context, refine the original answer to better \"\n",
" \"answer the question. \"\n",
" \"If the context isn't useful, return the original answer. Reply in Italian.\"\n",
")\n",
"refine_prompt = PromptTemplate(\n",
" input_variables=[\"question\", \"existing_answer\", \"context_str\"],\n",
" template=refine_prompt_template,\n",
")\n",
"\n",
"\n",
"initial_qa_template = (\n",
" \"Context information is below. \\n\"\n",
" \"---------------------\\n\"\n",
" \"{context_str}\"\n",
" \"\\n---------------------\\n\"\n",
" \"Given the context information and not prior knowledge, \"\n",
" \"answer the question: {question}\\nYour answer should be in Italian.\\n\"\n",
")\n",
"initial_qa_prompt = PromptTemplate(\n",
" input_variables=[\"context_str\", \"question\"], template=initial_qa_template\n",
")\n",
"chain = load_qa_chain(OpenAI(temperature=0), chain_type=\"refine\", return_refine_steps=True,\n",
" question_prompt=initial_qa_prompt, refine_prompt=refine_prompt)\n",
"chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
]
},
{
"cell_type": "markdown",
"id": "521a77cb",
"metadata": {},
"source": [
"## The `map-rerank` Chain\n",
"\n",
"This sections shows results of using the `map-rerank` Chain to do question answering with sources."
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "e2bfe203",
"metadata": {},
"outputs": [],
"source": [
"chain = load_qa_chain(OpenAI(temperature=0), chain_type=\"map_rerank\", return_intermediate_steps=True)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "5c28880c",
"metadata": {},
"outputs": [],
"source": [
"query = \"What did the president say about Justice Breyer\"\n",
"results = chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "80ac2db3",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"' The president thanked Justice Breyer for his service and honored him for dedicating his life to serving the country. '"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"results[\"output_text\"]"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "b428fcb9",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[{'answer': ' The president thanked Justice Breyer for his service and honored him for dedicating his life to serving the country. ',\n",
" 'score': '100'},\n",
" {'answer': \" The president said that Justice Breyer is a former top litigator in private practice, a former federal public defender, and from a family of public school educators and police officers. He also said that since she's been nominated, she's received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans, and that she is a consensus builder.\",\n",
" 'score': '100'},\n",
" {'answer': ' The president did not mention Justice Breyer in this context.',\n",
" 'score': '0'},\n",
" {'answer': ' The president did not mention Justice Breyer in the given context. ',\n",
" 'score': '0'}]"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"results[\"intermediate_steps\"]"
]
},
{
"cell_type": "markdown",
"id": "5e47a818",
"metadata": {},
"source": [
"**Custom Prompts**\n",
"\n",
"You can also use your own prompts with this chain. In this example, we will respond in Italian."
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "41b83cd8",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'intermediate_steps': [{'answer': ' Il presidente ha detto che Justice Breyer ha dedicato la sua vita a servire questo paese e ha onorato la sua carriera.',\n",
" 'score': '100'},\n",
" {'answer': ' Il presidente non ha detto nulla sulla Giustizia Breyer.',\n",
" 'score': '100'},\n",
" {'answer': ' Non so.', 'score': '0'},\n",
" {'answer': ' Il presidente non ha detto nulla sulla giustizia Breyer.',\n",
" 'score': '100'}],\n",
" 'output_text': ' Il presidente ha detto che Justice Breyer ha dedicato la sua vita a servire questo paese e ha onorato la sua carriera.'}"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain.prompts.base import RegexParser\n",
"\n",
"output_parser = RegexParser(\n",
" regex=r\"(.*?)\\nScore: (.*)\",\n",
" output_keys=[\"answer\", \"score\"],\n",
")\n",
"\n",
"prompt_template = \"\"\"Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer.\n",
"\n",
"In addition to giving an answer, also return a score of how fully it answered the user's question. This should be in the following format:\n",
"\n",
"Question: [question here]\n",
"Helpful Answer In Italian: [answer here]\n",
"Score: [score between 0 and 100]\n",
"\n",
"Begin!\n",
"\n",
"Context:\n",
"---------\n",
"{context}\n",
"---------\n",
"Question: {question}\n",
"Helpful Answer In Italian:\"\"\"\n",
"PROMPT = PromptTemplate(\n",
" template=prompt_template,\n",
" input_variables=[\"context\", \"question\"],\n",
" output_parser=output_parser,\n",
")\n",
"\n",
"chain = load_qa_chain(OpenAI(temperature=0), chain_type=\"map_rerank\", return_intermediate_steps=True, prompt=PROMPT)\n",
"query = \"What did the president say about Justice Breyer\"\n",
"chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e0f0bbdf",
"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"
},
"vscode": {
"interpreter": {
"hash": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}

483
docs/modules/indexes/chain_examples/summarize.ipynb Normal file
View File

@@ -0,0 +1,483 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "d9a0131f",
"metadata": {},
"source": [
"# Summarization\n",
"\n",
"This notebook walks through how to use LangChain for summarization over a list of documents. It covers three different chain types: `stuff`, `map_reduce`, and `refine`. For a more in depth explanation of what these chain types are, see [here](../combine_docs.md)."
]
},
{
"cell_type": "markdown",
"id": "0b5660bf",
"metadata": {},
"source": [
"## Prepare Data\n",
"First we prepare the data. For this example we create multiple documents from one long one, but these documents could be fetched in any manner (the point of this notebook to highlight what to do AFTER you fetch the documents)."
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "e9db25f3",
"metadata": {},
"outputs": [],
"source": [
"from langchain import OpenAI, PromptTemplate, LLMChain\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.chains.mapreduce import MapReduceChain\n",
"from langchain.prompts import PromptTemplate\n",
"\n",
"llm = OpenAI(temperature=0)\n",
"\n",
"text_splitter = CharacterTextSplitter()"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "99bbe19b",
"metadata": {},
"outputs": [],
"source": [
"with open('../../state_of_the_union.txt') as f:\n",
" state_of_the_union = f.read()\n",
"texts = text_splitter.split_text(state_of_the_union)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "baa6e808",
"metadata": {},
"outputs": [],
"source": [
"from langchain.docstore.document import Document\n",
"\n",
"docs = [Document(page_content=t) for t in texts[:3]]"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "27989fc4",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chains.summarize import load_summarize_chain"
]
},
{
"cell_type": "markdown",
"id": "21284c47",
"metadata": {},
"source": [
"## Quickstart\n",
"If you just want to get started as quickly as possible, this is the recommended way to do it:"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "5cfa89b2",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\" In response to Russia's aggression in Ukraine, the United States and its allies have imposed economic sanctions and are taking other measures to hold Putin accountable. The US is also providing economic and military assistance to Ukraine, protecting NATO countries, and investing in American products to create jobs. President Biden and Vice President Harris have passed the American Rescue Plan and the Bipartisan Infrastructure Law to help working people and rebuild America.\""
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain = load_summarize_chain(llm, chain_type=\"map_reduce\")\n",
"chain.run(docs)"
]
},
{
"cell_type": "markdown",
"id": "1bc784bd",
"metadata": {},
"source": [
"If you want more control and understanding over what is happening, please see the information below."
]
},
{
"cell_type": "markdown",
"id": "ea2d5c99",
"metadata": {},
"source": [
"## The `stuff` Chain\n",
"\n",
"This sections shows results of using the `stuff` Chain to do summarization."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "f01f3196",
"metadata": {},
"outputs": [],
"source": [
"chain = load_summarize_chain(llm, chain_type=\"stuff\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "da4d9801",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"' In his speech, President Biden addressed the crisis in Ukraine, the American Rescue Plan, and the Bipartisan Infrastructure Law. He discussed the need to invest in America, educate Americans, and build the economy from the bottom up. He also announced the release of 60 million barrels of oil from reserves around the world, and the creation of a dedicated task force to go after the crimes of Russian oligarchs. He concluded by emphasizing the need to Buy American and use taxpayer dollars to rebuild America.'"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain.run(docs)"
]
},
{
"cell_type": "markdown",
"id": "42b6d8ae",
"metadata": {},
"source": [
"**Custom Prompts**\n",
"\n",
"You can also use your own prompts with this chain. In this example, we will respond in Italian."
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "71dc4212",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\"\\n\\nIn questa serata, il Presidente degli Stati Uniti ha annunciato una serie di misure per affrontare la crisi in Ucraina, causata dall'aggressione di Putin. Ha anche annunciato l'invio di aiuti economici, militari e umanitari all'Ucraina. Ha anche annunciato che gli Stati Uniti e i loro alleati stanno imponendo sanzioni economiche a Putin e stanno rilasciando 60 milioni di barili di petrolio dalle riserve di tutto il mondo. Inoltre, ha annunciato che il Dipartimento di Giustizia degli Stati Uniti sta creando una task force dedicata ai crimini degli oligarchi russi. Il Presidente ha anche annunciato l'approvazione della legge bipartitica sull'infrastruttura, che prevede investimenti per la ricostruzione dell'America. Questo porterà a creare posti\""
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"prompt_template = \"\"\"Write a concise summary of the following:\n",
"\n",
"\n",
"{text}\n",
"\n",
"\n",
"CONCISE SUMMARY IN ITALIAN:\"\"\"\n",
"PROMPT = PromptTemplate(template=prompt_template, input_variables=[\"text\"])\n",
"chain = load_summarize_chain(llm, chain_type=\"stuff\", prompt=PROMPT)\n",
"chain.run(docs)"
]
},
{
"cell_type": "markdown",
"id": "9c868e86",
"metadata": {},
"source": [
"## The `map_reduce` Chain\n",
"\n",
"This sections shows results of using the `map_reduce` Chain to do summarization."
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "ef28e1d4",
"metadata": {},
"outputs": [],
"source": [
"chain = load_summarize_chain(llm, chain_type=\"map_reduce\")"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "f82c5f9f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\" In response to Russia's aggression in Ukraine, the United States and its allies have imposed economic sanctions and are taking other measures to hold Putin accountable. The US is also providing economic and military assistance to Ukraine, protecting NATO countries, and releasing oil from its Strategic Petroleum Reserve. President Biden and Vice President Harris have passed legislation to help struggling families and rebuild America's infrastructure.\""
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain.run(docs)"
]
},
{
"cell_type": "markdown",
"id": "d0c2a6d3",
"metadata": {},
"source": [
"**Intermediate Steps**\n",
"\n",
"We can also return the intermediate steps for `map_reduce` chains, should we want to inspect them. This is done with the `return_map_steps` variable."
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "d9cfc24e",
"metadata": {},
"outputs": [],
"source": [
"chain = load_summarize_chain(OpenAI(temperature=0), chain_type=\"map_reduce\", return_intermediate_steps=True)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "c7dff5e8",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'map_steps': [\" In response to Russia's aggression in Ukraine, the United States has united with other freedom-loving nations to impose economic sanctions and hold Putin accountable. The U.S. Department of Justice is also assembling a task force to go after the crimes of Russian oligarchs and seize their ill-gotten gains.\",\n",
" ' The United States and its European allies are taking action to punish Russia for its invasion of Ukraine, including seizing assets, closing off airspace, and providing economic and military assistance to Ukraine. The US is also mobilizing forces to protect NATO countries and has released 30 million barrels of oil from its Strategic Petroleum Reserve to help blunt gas prices. The world is uniting in support of Ukraine and democracy, and the US stands with its Ukrainian-American citizens.',\n",
" \" President Biden and Vice President Harris ran for office with a new economic vision for America, and have since passed the American Rescue Plan and the Bipartisan Infrastructure Law to help struggling families and rebuild America's infrastructure. This includes creating jobs, modernizing roads, airports, ports, and waterways, replacing lead pipes, providing affordable high-speed internet, and investing in American products to support American jobs.\"],\n",
" 'output_text': \" In response to Russia's aggression in Ukraine, the United States and its allies have imposed economic sanctions and are taking other measures to hold Putin accountable. The US is also providing economic and military assistance to Ukraine, protecting NATO countries, and passing legislation to help struggling families and rebuild America's infrastructure. The world is uniting in support of Ukraine and democracy, and the US stands with its Ukrainian-American citizens.\"}"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain({\"input_documents\": docs}, return_only_outputs=True)"
]
},
{
"cell_type": "markdown",
"id": "255c8993",
"metadata": {},
"source": [
"**Custom Prompts**\n",
"\n",
"You can also use your own prompts with this chain. In this example, we will respond in Italian."
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "b65d5069",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'intermediate_steps': [\"\\n\\nQuesta sera, ci incontriamo come democratici, repubblicani e indipendenti, ma soprattutto come americani. La Russia di Putin ha cercato di scuotere le fondamenta del mondo libero, ma ha sottovalutato la forza della gente ucraina. Gli Stati Uniti e i loro alleati stanno ora imponendo sanzioni economiche a Putin e stanno tagliando l'accesso della Russia alla tecnologia. Il Dipartimento di Giustizia degli Stati Uniti sta anche creando una task force dedicata per andare dopo i crimini degli oligarchi russi.\",\n",
" \"\\n\\nStiamo unendo le nostre forze con quelle dei nostri alleati europei per sequestrare yacht, appartamenti di lusso e jet privati di Putin. Abbiamo chiuso lo spazio aereo americano ai voli russi e stiamo fornendo più di un miliardo di dollari in assistenza all'Ucraina. Abbiamo anche mobilitato le nostre forze terrestri, aeree e navali per proteggere i paesi della NATO. Abbiamo anche rilasciato 60 milioni di barili di petrolio dalle riserve di tutto il mondo, di cui 30 milioni dalla nostra riserva strategica di petrolio. Stiamo affrontando una prova reale e ci vorrà del tempo, ma alla fine Putin non riuscirà a spegnere l'amore dei popoli per la libertà.\",\n",
" \"\\n\\nIl Presidente Biden ha lottato per passare l'American Rescue Plan per aiutare le persone che soffrivano a causa della pandemia. Il piano ha fornito sollievo economico immediato a milioni di americani, ha aiutato a mettere cibo sulla loro tavola, a mantenere un tetto sopra le loro teste e a ridurre il costo dell'assicurazione sanitaria. Il piano ha anche creato più di 6,5 milioni di nuovi posti di lavoro, il più alto numero di posti di lavoro creati in un anno nella storia degli Stati Uniti. Il Presidente Biden ha anche firmato la legge bipartitica sull'infrastruttura, la più ampia iniziativa di ricostruzione della storia degli Stati Uniti. Il piano prevede di modernizzare le strade, gli aeroporti, i porti e le vie navigabili in\"],\n",
" 'output_text': \"\\n\\nIl Presidente Biden sta lavorando per aiutare le persone che soffrono a causa della pandemia attraverso l'American Rescue Plan e la legge bipartitica sull'infrastruttura. Gli Stati Uniti e i loro alleati stanno anche imponendo sanzioni economiche a Putin e tagliando l'accesso della Russia alla tecnologia. Stanno anche sequestrando yacht, appartamenti di lusso e jet privati di Putin e fornendo più di un miliardo di dollari in assistenza all'Ucraina. Alla fine, Putin non riuscirà a spegnere l'amore dei popoli per la libertà.\"}"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"prompt_template = \"\"\"Write a concise summary of the following:\n",
"\n",
"\n",
"{text}\n",
"\n",
"\n",
"CONCISE SUMMARY IN ITALIAN:\"\"\"\n",
"PROMPT = PromptTemplate(template=prompt_template, input_variables=[\"text\"])\n",
"chain = load_summarize_chain(OpenAI(temperature=0), chain_type=\"map_reduce\", return_intermediate_steps=True, map_prompt=PROMPT, combine_prompt=PROMPT)\n",
"chain({\"input_documents\": docs}, return_only_outputs=True)"
]
},
{
"cell_type": "markdown",
"id": "f61350f9",
"metadata": {},
"source": [
"## The `refine` Chain\n",
"\n",
"This sections shows results of using the `refine` Chain to do summarization."
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "3bcbe31e",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\"\\n\\nIn response to Russia's aggression in Ukraine, the United States has united with other freedom-loving nations to impose economic sanctions and hold Putin accountable. The U.S. Department of Justice is also assembling a task force to go after the crimes of Russian oligarchs and seize their ill-gotten gains. We are joining with our European allies to find and seize the assets of Russian oligarchs, including yachts, luxury apartments, and private jets. The U.S. is also closing off American airspace to all Russian flights, further isolating Russia and adding an additional squeeze on their economy. The U.S. and its allies are providing support to the Ukrainians in their fight for freedom, including military, economic, and humanitarian assistance. The U.S. is also mobilizing ground forces, air squadrons, and ship deployments to protect NATO countries. The U.S. and its allies are also releasing 60 million barrels of oil from reserves around the world, with the U.S. contributing 30 million barrels from its own Strategic Petroleum Reserve. In addition, the U.S. has passed the American Rescue Plan to provide immediate economic relief for tens of millions of Americans, and the Bipartisan Infrastructure Law to rebuild America and create jobs. This investment will\""
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain = load_summarize_chain(llm, chain_type=\"refine\")\n",
"\n",
"chain.run(docs)"
]
},
{
"cell_type": "markdown",
"id": "84e9567e",
"metadata": {},
"source": [
"**Intermediate Steps**\n",
"\n",
"We can also return the intermediate steps for `refine` chains, should we want to inspect them. This is done with the `return_refine_steps` variable."
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "cd49ac4d",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'refine_steps': [\" In response to Russia's aggression in Ukraine, the United States has united with other freedom-loving nations to impose economic sanctions and hold Putin accountable. The U.S. Department of Justice is also assembling a task force to go after the crimes of Russian oligarchs and seize their ill-gotten gains.\",\n",
" \"\\n\\nIn response to Russia's aggression in Ukraine, the United States has united with other freedom-loving nations to impose economic sanctions and hold Putin accountable. The U.S. Department of Justice is also assembling a task force to go after the crimes of Russian oligarchs and seize their ill-gotten gains. We are joining with our European allies to find and seize the assets of Russian oligarchs, including yachts, luxury apartments, and private jets. The U.S. is also closing off American airspace to all Russian flights, further isolating Russia and adding an additional squeeze on their economy. The U.S. and its allies are providing support to the Ukrainians in their fight for freedom, including military, economic, and humanitarian assistance. The U.S. is also mobilizing ground forces, air squadrons, and ship deployments to protect NATO countries. The U.S. and its allies are also releasing 60 million barrels of oil from reserves around the world, with the U.S. contributing 30 million barrels from its own Strategic Petroleum Reserve. Putin's war on Ukraine has left Russia weaker and the rest of the world stronger, with the world uniting in support of democracy and peace.\",\n",
" \"\\n\\nIn response to Russia's aggression in Ukraine, the United States has united with other freedom-loving nations to impose economic sanctions and hold Putin accountable. The U.S. Department of Justice is also assembling a task force to go after the crimes of Russian oligarchs and seize their ill-gotten gains. We are joining with our European allies to find and seize the assets of Russian oligarchs, including yachts, luxury apartments, and private jets. The U.S. is also closing off American airspace to all Russian flights, further isolating Russia and adding an additional squeeze on their economy. The U.S. and its allies are providing support to the Ukrainians in their fight for freedom, including military, economic, and humanitarian assistance. The U.S. is also mobilizing ground forces, air squadrons, and ship deployments to protect NATO countries. The U.S. and its allies are also releasing 60 million barrels of oil from reserves around the world, with the U.S. contributing 30 million barrels from its own Strategic Petroleum Reserve. In addition, the U.S. has passed the American Rescue Plan to provide immediate economic relief for tens of millions of Americans, and the Bipartisan Infrastructure Law to rebuild America and create jobs. This includes investing\"],\n",
" 'output_text': \"\\n\\nIn response to Russia's aggression in Ukraine, the United States has united with other freedom-loving nations to impose economic sanctions and hold Putin accountable. The U.S. Department of Justice is also assembling a task force to go after the crimes of Russian oligarchs and seize their ill-gotten gains. We are joining with our European allies to find and seize the assets of Russian oligarchs, including yachts, luxury apartments, and private jets. The U.S. is also closing off American airspace to all Russian flights, further isolating Russia and adding an additional squeeze on their economy. The U.S. and its allies are providing support to the Ukrainians in their fight for freedom, including military, economic, and humanitarian assistance. The U.S. is also mobilizing ground forces, air squadrons, and ship deployments to protect NATO countries. The U.S. and its allies are also releasing 60 million barrels of oil from reserves around the world, with the U.S. contributing 30 million barrels from its own Strategic Petroleum Reserve. In addition, the U.S. has passed the American Rescue Plan to provide immediate economic relief for tens of millions of Americans, and the Bipartisan Infrastructure Law to rebuild America and create jobs. This includes investing\"}"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain = load_summarize_chain(OpenAI(temperature=0), chain_type=\"refine\", return_intermediate_steps=True)\n",
"\n",
"chain({\"input_documents\": docs}, return_only_outputs=True)"
]
},
{
"cell_type": "markdown",
"id": "822be0d2",
"metadata": {},
"source": [
"**Custom Prompts**\n",
"\n",
"You can also use your own prompts with this chain. In this example, we will respond in Italian."
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "ffe37bec",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'intermediate_steps': [\"\\n\\nQuesta sera, ci incontriamo come democratici, repubblicani e indipendenti, ma soprattutto come americani. La Russia di Putin ha cercato di scuotere le fondamenta del mondo libero, ma ha sottovalutato la forza della gente ucraina. Insieme ai nostri alleati, stiamo imponendo sanzioni economiche, tagliando l'accesso della Russia alla tecnologia e bloccando i suoi più grandi istituti bancari dal sistema finanziario internazionale. Il Dipartimento di Giustizia degli Stati Uniti sta anche assemblando una task force dedicata per andare dopo i crimini degli oligarchi russi.\",\n",
" \"\\n\\nQuesta sera, ci incontriamo come democratici, repubblicani e indipendenti, ma soprattutto come americani. La Russia di Putin ha cercato di scuotere le fondamenta del mondo libero, ma ha sottovalutato la forza della gente ucraina. Insieme ai nostri alleati, stiamo imponendo sanzioni economiche, tagliando l'accesso della Russia alla tecnologia, bloccando i suoi più grandi istituti bancari dal sistema finanziario internazionale e chiudendo lo spazio aereo americano a tutti i voli russi. Il Dipartimento di Giustizia degli Stati Uniti sta anche assemblando una task force dedicata per andare dopo i crimini degli oligarchi russi. Stiamo fornendo più di un miliardo di dollari in assistenza diretta all'Ucraina e fornendo assistenza militare,\",\n",
" \"\\n\\nQuesta sera, ci incontriamo come democratici, repubblicani e indipendenti, ma soprattutto come americani. La Russia di Putin ha cercato di scuotere le fondamenta del mondo libero, ma ha sottovalutato la forza della gente ucraina. Insieme ai nostri alleati, stiamo imponendo sanzioni economiche, tagliando l'accesso della Russia alla tecnologia, bloccando i suoi più grandi istituti bancari dal sistema finanziario internazionale e chiudendo lo spazio aereo americano a tutti i voli russi. Il Dipartimento di Giustizia degli Stati Uniti sta anche assemblando una task force dedicata per andare dopo i crimini degli oligarchi russi. Stiamo fornendo più di un miliardo di dollari in assistenza diretta all'Ucraina e fornendo assistenza militare.\"],\n",
" 'output_text': \"\\n\\nQuesta sera, ci incontriamo come democratici, repubblicani e indipendenti, ma soprattutto come americani. La Russia di Putin ha cercato di scuotere le fondamenta del mondo libero, ma ha sottovalutato la forza della gente ucraina. Insieme ai nostri alleati, stiamo imponendo sanzioni economiche, tagliando l'accesso della Russia alla tecnologia, bloccando i suoi più grandi istituti bancari dal sistema finanziario internazionale e chiudendo lo spazio aereo americano a tutti i voli russi. Il Dipartimento di Giustizia degli Stati Uniti sta anche assemblando una task force dedicata per andare dopo i crimini degli oligarchi russi. Stiamo fornendo più di un miliardo di dollari in assistenza diretta all'Ucraina e fornendo assistenza militare.\"}"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"prompt_template = \"\"\"Write a concise summary of the following:\n",
"\n",
"\n",
"{text}\n",
"\n",
"\n",
"CONCISE SUMMARY IN ITALIAN:\"\"\"\n",
"PROMPT = PromptTemplate(template=prompt_template, input_variables=[\"text\"])\n",
"refine_template = (\n",
" \"Your job is to produce a final summary\\n\"\n",
" \"We have provided an existing summary up to a certain point: {existing_answer}\\n\"\n",
" \"We have the opportunity to refine the existing summary\"\n",
" \"(only if needed) with some more context below.\\n\"\n",
" \"------------\\n\"\n",
" \"{text}\\n\"\n",
" \"------------\\n\"\n",
" \"Given the new context, refine the original summary in Italian\"\n",
" \"If the context isn't useful, return the original summary.\"\n",
")\n",
"refine_prompt = PromptTemplate(\n",
" input_variables=[\"existing_answer\", \"text\"],\n",
" template=refine_template,\n",
")\n",
"chain = load_summarize_chain(OpenAI(temperature=0), chain_type=\"refine\", return_intermediate_steps=True, question_prompt=PROMPT, refine_prompt=refine_prompt)\n",
"chain({\"input_documents\": docs}, return_only_outputs=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5175b1d4",
"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": "3.10.9"
},
"vscode": {
"interpreter": {
"hash": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}

340
docs/modules/indexes/chain_examples/vector_db_qa.ipynb Normal file
View File

@@ -0,0 +1,340 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "07c1e3b9",
"metadata": {},
"source": [
"# Vector DB Question/Answering\n",
"\n",
"This example showcases question answering over a vector database."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "82525493",
"metadata": {},
"outputs": [],
"source": [
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.vectorstores import Chroma\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain import OpenAI, VectorDBQA"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "5c7049db",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running Chroma using direct local API.\n",
"Using DuckDB in-memory for database. Data will be transient.\n"
]
}
],
"source": [
"from langchain.document_loaders import TextLoader\n",
"loader = TextLoader('../../state_of_the_union.txt')\n",
"documents = loader.load()\n",
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"texts = text_splitter.split_documents(documents)\n",
"\n",
"embeddings = OpenAIEmbeddings()\n",
"docsearch = Chroma.from_documents(texts, embeddings)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "3018f865",
"metadata": {},
"outputs": [],
"source": [
"qa = VectorDBQA.from_chain_type(llm=OpenAI(), chain_type=\"stuff\", vectorstore=docsearch)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "032a47f8",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice and federal public defender, from a family of public school educators and police officers, a consensus builder, and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"qa.run(query)"
]
},
{
"cell_type": "markdown",
"id": "c28f1f64",
"metadata": {},
"source": [
"## Chain Type\n",
"You can easily specify different chain types to load and use in the VectorDBQA chain. For a more detailed walkthrough of these types, please see [this notebook](question_answering.ipynb).\n",
"\n",
"There are two ways to load different chain types. First, you can specify the chain type argument in the `from_chain_type` method. This allows you to pass in the name of the chain type you want to use. For example, in the below we change the chain type to `map_reduce`."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "22d2417d",
"metadata": {},
"outputs": [],
"source": [
"qa = VectorDBQA.from_chain_type(llm=OpenAI(), chain_type=\"map_reduce\", vectorstore=docsearch)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "43204ad1",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, from a family of public school educators and police officers, a consensus builder, and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"qa.run(query)"
]
},
{
"cell_type": "markdown",
"id": "60368f38",
"metadata": {},
"source": [
"The above way allows you to really simply change the chain_type, but it does provide a ton of flexibility over parameters to that chain type. If you want to control those parameters, you can load the chain directly (as you did in [this notebook](question_answering.ipynb)) and then pass that directly to the the VectorDBQA chain with the `combine_documents_chain` parameter. For example:"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "7b403f0d",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chains.question_answering import load_qa_chain\n",
"qa_chain = load_qa_chain(OpenAI(temperature=0), chain_type=\"stuff\")\n",
"qa = VectorDBQA(combine_documents_chain=qa_chain, vectorstore=docsearch)"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "9e04a9ac",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, and from a family of public school educators and police officers. He also said that she is a consensus builder and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"qa.run(query)"
]
},
{
"cell_type": "markdown",
"id": "90c7899a",
"metadata": {},
"source": [
"## Custom Prompts\n",
"You can pass in custom prompts to do question answering. These prompts are the same prompts as you can pass into the [base question answering chain](./question_answering.ipynb)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "a45232a2",
"metadata": {},
"outputs": [],
"source": [
"from langchain.prompts import PromptTemplate\n",
"prompt_template = \"\"\"Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer.\n",
"\n",
"{context}\n",
"\n",
"Question: {question}\n",
"Answer in Italian:\"\"\"\n",
"PROMPT = PromptTemplate(\n",
" template=prompt_template, input_variables=[\"context\", \"question\"]\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "9b5c8d1d",
"metadata": {},
"outputs": [],
"source": [
"chain_type_kwargs = {\"prompt\": PROMPT}\n",
"qa = VectorDBQA.from_chain_type(llm=OpenAI(), chain_type=\"stuff\", vectorstore=docsearch, chain_type_kwargs=chain_type_kwargs)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "26ee7671",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\" Il Presidente ha detto che Ketanji Brown Jackson è uno dei pensatori legali più importanti del nostro Paese, che continuerà l'eccellente eredità di giustizia Breyer. È un ex principale litigante in pratica privata, un ex difensore federale pubblico e appartiene a una famiglia di insegnanti e poliziotti delle scuole pubbliche. È un costruttore di consenso che ha ricevuto un ampio supporto da parte di Fraternal Order of Police e giudici designati da democratici e repubblicani.\""
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"qa.run(query)"
]
},
{
"cell_type": "markdown",
"id": "0b8c37f7",
"metadata": {},
"source": [
"## Return Source Documents\n",
"Additionally, we can return the source documents used to answer the question by specifying an optional parameter when constructing the chain."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "af093aba",
"metadata": {},
"outputs": [],
"source": [
"qa = VectorDBQA.from_chain_type(llm=OpenAI(), chain_type=\"stuff\", vectorstore=docsearch, return_source_documents=True)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "eac11321",
"metadata": {},
"outputs": [],
"source": [
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"result = qa({\"query\": query})"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "7d75945a",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\" The president said that Ketanji Brown Jackson is one of our nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\""
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"result[\"result\"]"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "35b4f31f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[Document(page_content='In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. \\n\\nWe cannot let this happen. \\n\\nTonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', lookup_str='', metadata={}, lookup_index=0),\n",
" Document(page_content='A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \\n\\nAnd if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \\n\\nWe can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling. \\n\\nWe’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers. \\n\\nWe’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \\n\\nWe’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.', lookup_str='', metadata={}, lookup_index=0),\n",
" Document(page_content='And for our LGBTQ+ Americans, let’s finally get the bipartisan Equality Act to my desk. The onslaught of state laws targeting transgender Americans and their families is wrong. \\n\\nAs I said last year, especially to our younger transgender Americans, I will always have your back as your President, so you can be yourself and reach your God-given potential. \\n\\nWhile it often appears that we never agree, that isn’t true. I signed 80 bipartisan bills into law last year. From preventing government shutdowns to protecting Asian-Americans from still-too-common hate crimes to reforming military justice. \\n\\nAnd soon, we’ll strengthen the Violence Against Women Act that I first wrote three decades ago. It is important for us to show the nation that we can come together and do big things. \\n\\nSo tonight I’m offering a Unity Agenda for the Nation. Four big things we can do together. \\n\\nFirst, beat the opioid epidemic.', lookup_str='', metadata={}, lookup_index=0),\n",
" Document(page_content='As I’ve told Xi Jinping, it is never a good bet to bet against the American people. \\n\\nWe’ll create good jobs for millions of Americans, modernizing roads, airports, ports, and waterways all across America. \\n\\nAnd we’ll do it all to withstand the devastating effects of the climate crisis and promote environmental justice. \\n\\nWe’ll build a national network of 500,000 electric vehicle charging stations, begin to replace poisonous lead pipes—so every child—and every American—has clean water to drink at home and at school, provide affordable high-speed internet for every American—urban, suburban, rural, and tribal communities. \\n\\n4,000 projects have already been announced. \\n\\nAnd tonight, I’m announcing that this year we will start fixing over 65,000 miles of highway and 1,500 bridges in disrepair. \\n\\nWhen we use taxpayer dollars to rebuild America – we are going to Buy American: buy American products to support American jobs.', lookup_str='', metadata={}, lookup_index=0)]"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"result[\"source_documents\"]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8b403637",
"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"
},
"vscode": {
"interpreter": {
"hash": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}

218
docs/modules/indexes/chain_examples/vector_db_qa_with_sources.ipynb Normal file
View File

@@ -0,0 +1,218 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "efc5be67",
"metadata": {},
"source": [
"# VectorDB Question Answering with Sources\n",
"\n",
"This notebook goes over how to do question-answering with sources over a vector database. It does this by using the `VectorDBQAWithSourcesChain`, which does the lookup of the documents from a vector database. "
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "1c613960",
"metadata": {},
"outputs": [],
"source": [
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.embeddings.cohere import CohereEmbeddings\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.vectorstores.elastic_vector_search import ElasticVectorSearch\n",
"from langchain.vectorstores import Chromaoma"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "17d1306e",
"metadata": {},
"outputs": [],
"source": [
"with open('../../state_of_the_union.txt') as f:\n",
" state_of_the_union = f.read()\n",
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"texts = text_splitter.split_text(state_of_the_union)\n",
"\n",
"embeddings = OpenAIEmbeddings()"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "0e745d99",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running Chroma using direct local API.\n",
"Using DuckDB in-memory for database. Data will be transient.\n",
"Exiting: Cleaning up .chroma directory\n"
]
}
],
"source": [
"docsearch = Chroma.from_texts(texts, embeddings, metadatas=[{\"source\": f\"{i}-pl\"} for i in range(len(texts))])"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "8aa571ae",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chains import VectorDBQAWithSourcesChain"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "aa859d4c",
"metadata": {},
"outputs": [],
"source": [
"from langchain import OpenAI\n",
"\n",
"chain = VectorDBQAWithSourcesChain.from_chain_type(OpenAI(temperature=0), chain_type=\"stuff\", vectorstore=docsearch)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "8ba36fa7",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'answer': ' The president thanked Justice Breyer for his service and mentioned his legacy of excellence.\\n',\n",
" 'sources': '30-pl'}"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain({\"question\": \"What did the president say about Justice Breyer\"}, return_only_outputs=True)"
]
},
{
"cell_type": "markdown",
"id": "718ecbda",
"metadata": {},
"source": [
"## Chain Type\n",
"You can easily specify different chain types to load and use in the VectorDBQAWithSourcesChain chain. For a more detailed walkthrough of these types, please see [this notebook](qa_with_sources.ipynb).\n",
"\n",
"There are two ways to load different chain types. First, you can specify the chain type argument in the `from_chain_type` method. This allows you to pass in the name of the chain type you want to use. For example, in the below we change the chain type to `map_reduce`."
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "8b35b30a",
"metadata": {},
"outputs": [],
"source": [
"chain = VectorDBQAWithSourcesChain.from_chain_type(OpenAI(temperature=0), chain_type=\"map_reduce\", vectorstore=docsearch)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "58bd424f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'answer': ' The president honored Justice Stephen Breyer for his service.\\n',\n",
" 'sources': '30-pl'}"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain({\"question\": \"What did the president say about Justice Breyer\"}, return_only_outputs=True)"
]
},
{
"cell_type": "markdown",
"id": "21e14eed",
"metadata": {},
"source": [
"The above way allows you to really simply change the chain_type, but it does provide a ton of flexibility over parameters to that chain type. If you want to control those parameters, you can load the chain directly (as you did in [this notebook](qa_with_sources.ipynb)) and then pass that directly to the the VectorDBQA chain with the `combine_documents_chain` parameter. For example:"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "af35f0c6",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chains.qa_with_sources import load_qa_with_sources_chain\n",
"qa_chain = load_qa_with_sources_chain(OpenAI(temperature=0), chain_type=\"stuff\")\n",
"qa = VectorDBQAWithSourcesChain(combine_documents_chain=qa_chain, vectorstore=docsearch)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "c91fdc8a",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'answer': ' The president honored Justice Stephen Breyer for his service.\\n',\n",
" 'sources': '30-pl'}"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"qa({\"question\": \"What did the president say about Justice Breyer\"}, return_only_outputs=True)"
]
}
],
"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"
},
"vscode": {
"interpreter": {
"hash": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}

199
docs/modules/indexes/chain_examples/vector_db_text_generation.ipynb Normal file
View File

@@ -0,0 +1,199 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Vector DB Text Generation\n",
"\n",
"This notebook walks through how to use LangChain for text generation over a vector index. This is useful if we want to generate text that is able to draw from a large body of custom text, for example, generating blog posts that have an understanding of previous blog posts written, or product tutorials that can refer to product documentation."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Prepare Data\n",
"\n",
"First, we prepare the data. For this example, we fetch a documentation site that consists of markdown files hosted on Github and split them into small enough Documents."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from langchain.llms import OpenAI\n",
"from langchain.docstore.document import Document\n",
"import requests\n",
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.vectorstores import Chromama\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.prompts import PromptTemplate\n",
"import pathlib\n",
"import subprocess\n",
"import tempfile"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Cloning into '.'...\n"
]
}
],
"source": [
"def get_github_docs(repo_owner, repo_name):\n",
" with tempfile.TemporaryDirectory() as d:\n",
" subprocess.check_call(\n",
" f\"git clone --depth 1 https://github.com/{repo_owner}/{repo_name}.git .\",\n",
" cwd=d,\n",
" shell=True,\n",
" )\n",
" git_sha = (\n",
" subprocess.check_output(\"git rev-parse HEAD\", shell=True, cwd=d)\n",
" .decode(\"utf-8\")\n",
" .strip()\n",
" )\n",
" repo_path = pathlib.Path(d)\n",
" markdown_files = list(repo_path.glob(\"*/*.md\")) + list(\n",
" repo_path.glob(\"*/*.mdx\")\n",
" )\n",
" for markdown_file in markdown_files:\n",
" with open(markdown_file, \"r\") as f:\n",
" relative_path = markdown_file.relative_to(repo_path)\n",
" github_url = f\"https://github.com/{repo_owner}/{repo_name}/blob/{git_sha}/{relative_path}\"\n",
" yield Document(page_content=f.read(), metadata={\"source\": github_url})\n",
"\n",
"sources = get_github_docs(\"yirenlu92\", \"deno-manual-forked\")\n",
"\n",
"source_chunks = []\n",
"splitter = CharacterTextSplitter(separator=\" \", chunk_size=1024, chunk_overlap=0)\n",
"for source in sources:\n",
" for chunk in splitter.split_text(source.page_content):\n",
" source_chunks.append(Document(page_content=chunk, metadata=source.metadata))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Set Up Vector DB\n",
"\n",
"Now that we have the documentation content in chunks, let's put all this information in a vector index for easy retrieval."
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"search_index = Chroma.from_documents(source_chunks, OpenAIEmbeddings())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Set Up LLM Chain with Custom Prompt\n",
"\n",
"Next, let's set up a simple LLM chain but give it a custom prompt for blog post generation. Note that the custom prompt is parameterized and takes two inputs: `context`, which will be the documents fetched from the vector search, and `topic`, which is given by the user."
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"from langchain.chains import LLMChain\n",
"prompt_template = \"\"\"Use the context below to write a 400 word blog post about the topic below:\n",
" Context: {context}\n",
" Topic: {topic}\n",
" Blog post:\"\"\"\n",
"\n",
"PROMPT = PromptTemplate(\n",
" template=prompt_template, input_variables=[\"context\", \"topic\"]\n",
")\n",
"\n",
"llm = OpenAI(temperature=0)\n",
"\n",
"chain = LLMChain(llm=llm, prompt=PROMPT)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Generate Text\n",
"\n",
"Finally, we write a function to apply our inputs to the chain. The function takes an input parameter `topic`. We find the documents in the vector index that correspond to that `topic`, and use them as additional context in our simple LLM chain."
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"def generate_blog_post(topic):\n",
" docs = search_index.similarity_search(topic, k=4)\n",
" inputs = [{\"context\": doc.page_content, \"topic\": topic} for doc in docs]\n",
" print(chain.apply(inputs))"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[{'text': '\\n\\nEnvironment variables are a great way to store and access sensitive information in your Deno applications. Deno offers built-in support for environment variables with `Deno.env`, and you can also use a `.env` file to store and access environment variables.\\n\\nUsing `Deno.env` is simple. It has getter and setter methods, so you can easily set and retrieve environment variables. For example, you can set the `FIREBASE_API_KEY` and `FIREBASE_AUTH_DOMAIN` environment variables like this:\\n\\n```ts\\nDeno.env.set(\"FIREBASE_API_KEY\", \"examplekey123\");\\nDeno.env.set(\"FIREBASE_AUTH_DOMAIN\", \"firebasedomain.com\");\\n\\nconsole.log(Deno.env.get(\"FIREBASE_API_KEY\")); // examplekey123\\nconsole.log(Deno.env.get(\"FIREBASE_AUTH_DOMAIN\")); // firebasedomain.com\\n```\\n\\nYou can also store environment variables in a `.env` file. This is a great'}, {'text': '\\n\\nEnvironment variables are a powerful tool for managing configuration settings in a program. They allow us to set values that can be used by the program, without having to hard-code them into the code. This makes it easier to change settings without having to modify the code.\\n\\nIn Deno, environment variables can be set in a few different ways. The most common way is to use the `VAR=value` syntax. This will set the environment variable `VAR` to the value `value`. This can be used to set any number of environment variables before running a command. For example, if we wanted to set the environment variable `VAR` to `hello` before running a Deno command, we could do so like this:\\n\\n```\\nVAR=hello deno run main.ts\\n```\\n\\nThis will set the environment variable `VAR` to `hello` before running the command. We can then access this variable in our code using the `Deno.env.get()` function. For example, if we ran the following command:\\n\\n```\\nVAR=hello && deno eval \"console.log(\\'Deno: \\' + Deno.env.get(\\'VAR'}, {'text': '\\n\\nEnvironment variables are a powerful tool for developers, allowing them to store and access data without having to hard-code it into their applications. In Deno, you can access environment variables using the `Deno.env.get()` function.\\n\\nFor example, if you wanted to access the `HOME` environment variable, you could do so like this:\\n\\n```js\\n// env.js\\nDeno.env.get(\"HOME\");\\n```\\n\\nWhen running this code, you\\'ll need to grant the Deno process access to environment variables. This can be done by passing the `--allow-env` flag to the `deno run` command. You can also specify which environment variables you want to grant access to, like this:\\n\\n```shell\\n# Allow access to only the HOME env var\\ndeno run --allow-env=HOME env.js\\n```\\n\\nIt\\'s important to note that environment variables are case insensitive on Windows, so Deno also matches them case insensitively (on Windows only).\\n\\nAnother thing to be aware of when using environment variables is subprocess permissions. Subprocesses are powerful and can access system resources regardless of the permissions you granted to the Den'}, {'text': '\\n\\nEnvironment variables are an important part of any programming language, and Deno is no exception. Deno is a secure JavaScript and TypeScript runtime built on the V8 JavaScript engine, and it recently added support for environment variables. This feature was added in Deno version 1.6.0, and it is now available for use in Deno applications.\\n\\nEnvironment variables are used to store information that can be used by programs. They are typically used to store configuration information, such as the location of a database or the name of a user. In Deno, environment variables are stored in the `Deno.env` object. This object is similar to the `process.env` object in Node.js, and it allows you to access and set environment variables.\\n\\nThe `Deno.env` object is a read-only object, meaning that you cannot directly modify the environment variables. Instead, you must use the `Deno.env.set()` function to set environment variables. This function takes two arguments: the name of the environment variable and the value to set it to. For example, if you wanted to set the `FOO` environment variable to `bar`, you would use the following code:\\n\\n```'}]\n"
]
}
],
"source": [
"generate_blog_post(\"environment variables\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"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": 2
}

51
docs/modules/indexes/combine_docs.md Normal file
View File

@@ -0,0 +1,51 @@
# CombineDocuments Chains
CombineDocuments chains are useful for when you need to run a language over multiple documents.
Common use cases for this include question answering, question answering with sources, summarization, and more.
For more information on specific use cases as well as different methods for **fetching** these documents, please see
[this overview](/use_cases/combine_docs.md).
This documentation now picks up from after you've fetched your documents - now what?
How do you pass them to the language model in a format it can understand?
There are a few different methods, or chains, for doing so. LangChain supports four of the more common ones - and
we are actively looking to include more, so if you have any ideas please reach out! Note that there is not
one best method - the decision of which one to use is often very context specific. In order from simplest to
most complex:
## Stuffing
Stuffing is the simplest method, whereby you simply stuff all the related data into the prompt as context
to pass to the language model. This is implemented in LangChain as the `StuffDocumentsChain`.
**Pros:** Only makes a single call to the LLM. When generating text, the LLM has access to all the data at once.
**Cons:** Most LLMs have a context length, and for large documents (or many documents) this will not work as it will result in a prompt larger than the context length.
The main downside of this method is that it only works one smaller pieces of data. Once you are working
with many pieces of data, this approach is no longer feasible. The next two approaches are designed to help deal with that.
## Map Reduce
This method involves an initial prompt on each chunk of data (for summarization tasks, this
could be a summary of that chunk; for question-answering tasks, it could be an answer based solely on that chunk).
Then a different prompt is run to combine all the initial outputs. This is implemented in the LangChain as the `MapReduceDocumentsChain`.
**Pros:** Can scale to larger documents (and more documents) than `StuffDocumentsChain`. The calls to the LLM on individual documents are independent and can therefore be parallelized.
**Cons:** Requires many more calls to the LLM than `StuffDocumentsChain`. Loses some information during the final combining call.
## Refine
This method involves an initial prompt on the first chunk of data, generating some output.
For the remaining documents, that output is passed in, along with the next document,
asking the LLM to refine the output based on the new document.
**Pros:** Can pull in more relevant context, and may be less lossy than `MapReduceDocumentsChain`.
**Cons:** Requires many more calls to the LLM than `StuffDocumentsChain`. The calls are also NOT independent, meaning they cannot be paralleled like `MapReduceDocumentsChain`. There is also some potential dependencies on the ordering of the documents.
## Map-Rerank
This method involves running an initial prompt on each chunk of data, that not only tries to complete a
task but also gives a score for how certain it is in its answer. The responses are then
ranked according to this score, and the highest score is returned.
**Pros:** Similar pros as `MapReduceDocumentsChain`. Compared to `MapReduceDocumentsChain`, it requires fewer calls.
**Cons:** Cannot combine information between documents. This means it is most useful when you expect there to be a single simple answer in a single document.

494
docs/modules/indexes/examples/embeddings.ipynb Normal file
View File

@@ -0,0 +1,494 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "249b4058",
"metadata": {},
"source": [
"# Embeddings\n",
"\n",
"This notebook goes over how to use the Embedding class in LangChain.\n",
"\n",
"The Embedding class is a class designed for interfacing with embeddings. There are lots of Embedding providers (OpenAI, Cohere, Hugging Face, etc) - this class is designed to provide a standard interface for all of them.\n",
"\n",
"Embeddings create a vector representation of a piece of text. This is useful because it means we can think about text in the vector space, and do things like semantic search where we look for pieces of text that are most similar in the vector space.\n",
"\n",
"The base Embedding class in LangChain exposes two methods: `embed_documents` and `embed_query`. The largest difference is that these two methods have different interfaces: one works over multiple documents, while the other works over a single document. Besides this, another reason for having these as two separate methods is that some embedding providers have different embedding methods for documents (to be searched over) vs queries (the search query itself)."
]
},
{
"cell_type": "markdown",
"id": "278b6c63",
"metadata": {},
"source": [
"## OpenAI\n",
"\n",
"Let's load the OpenAI Embedding class."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "0be1af71",
"metadata": {},
"outputs": [],
"source": [
"from langchain.embeddings import OpenAIEmbeddings"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "2c66e5da",
"metadata": {},
"outputs": [],
"source": [
"embeddings = OpenAIEmbeddings()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "01370375",
"metadata": {},
"outputs": [],
"source": [
"text = \"This is a test document.\""
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "bfb6142c",
"metadata": {},
"outputs": [],
"source": [
"query_result = embeddings.embed_query(text)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "0356c3b7",
"metadata": {},
"outputs": [],
"source": [
"doc_result = embeddings.embed_documents([text])"
]
},
{
"cell_type": "markdown",
"id": "42f76e43",
"metadata": {},
"source": [
"## Cohere\n",
"\n",
"Let's load the Cohere Embedding class."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "6b82f59f",
"metadata": {},
"outputs": [],
"source": [
"from langchain.embeddings import CohereEmbeddings"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "26895c60",
"metadata": {},
"outputs": [],
"source": [
"embeddings = CohereEmbeddings(cohere_api_key= cohere_api_key)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "eea52814",
"metadata": {},
"outputs": [],
"source": [
"text = \"This is a test document.\""
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "fbe167bf",
"metadata": {},
"outputs": [],
"source": [
"query_result = embeddings.embed_query(text)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "38ad3b20",
"metadata": {},
"outputs": [],
"source": [
"doc_result = embeddings.embed_documents([text])"
]
},
{
"cell_type": "markdown",
"id": "ed47bb62",
"metadata": {},
"source": [
"## Hugging Face Hub\n",
"Let's load the Hugging Face Embedding class."
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "861521a9",
"metadata": {},
"outputs": [],
"source": [
"from langchain.embeddings import HuggingFaceEmbeddings"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "ff9be586",
"metadata": {},
"outputs": [],
"source": [
"embeddings = HuggingFaceEmbeddings()"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "d0a98ae9",
"metadata": {},
"outputs": [],
"source": [
"text = \"This is a test document.\""
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "5d6c682b",
"metadata": {},
"outputs": [],
"source": [
"query_result = embeddings.embed_query(text)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "bb5e74c0",
"metadata": {},
"outputs": [],
"source": [
"doc_result = embeddings.embed_documents([text])"
]
},
{
"cell_type": "markdown",
"id": "fff4734f",
"metadata": {},
"source": [
"## TensorflowHub\n",
"Let's load the TensorflowHub Embedding class."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "f822104b",
"metadata": {},
"outputs": [],
"source": [
"from langchain.embeddings import TensorflowHubEmbeddings"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "bac84e46",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"2023-01-30 23:53:01.652176: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA\n",
"To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
"2023-01-30 23:53:34.362802: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA\n",
"To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
]
}
],
"source": [
"embeddings = TensorflowHubEmbeddings()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "4790d770",
"metadata": {},
"outputs": [],
"source": [
"text = \"This is a test document.\""
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "f556dcdb",
"metadata": {},
"outputs": [],
"source": [
"query_result = embeddings.embed_query(text)"
]
},
{
"cell_type": "markdown",
"id": "59428e05",
"metadata": {},
"source": [
"## InstructEmbeddings\n",
"Let's load the HuggingFace instruct Embeddings class."
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "92c5b61e",
"metadata": {},
"outputs": [],
"source": [
"from langchain.embeddings import HuggingFaceInstructEmbeddings"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "062547b9",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"load INSTRUCTOR_Transformer\n",
"max_seq_length 512\n"
]
}
],
"source": [
"embeddings = HuggingFaceInstructEmbeddings(query_instruction=\"Represent the query for retrieval: \")"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "e1dcc4bd",
"metadata": {},
"outputs": [],
"source": [
"text = \"This is a test document.\""
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "90f0db94",
"metadata": {},
"outputs": [],
"source": [
"query_result = embeddings.embed_query(text)"
]
},
{
"cell_type": "markdown",
"id": "eec4efda",
"metadata": {},
"source": [
"## Self Hosted Embeddings\n",
"Let's load the SelfHostedEmbeddings, SelfHostedHuggingFaceEmbeddings, and SelfHostedHuggingFaceInstructEmbeddings classes."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d338722a",
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"from langchain.embeddings import (\n",
" SelfHostedEmbeddings, \n",
" SelfHostedHuggingFaceEmbeddings, \n",
" SelfHostedHuggingFaceInstructEmbeddings\n",
")\n",
"import runhouse as rh"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "146559e8",
"metadata": {},
"outputs": [],
"source": [
"# For an on-demand A100 with GCP, Azure, or Lambda\n",
"gpu = rh.cluster(name=\"rh-a10x\", instance_type=\"A100:1\", use_spot=False)\n",
"\n",
"# For an on-demand A10G with AWS (no single A100s on AWS)\n",
"# gpu = rh.cluster(name='rh-a10x', instance_type='g5.2xlarge', provider='aws')\n",
"\n",
"# For an existing cluster\n",
"# gpu = rh.cluster(ips=['<ip of the cluster>'], \n",
"# ssh_creds={'ssh_user': '...', 'ssh_private_key':'<path_to_key>'},\n",
"# name='my-cluster')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1230f7df",
"metadata": {},
"outputs": [],
"source": [
"embeddings = SelfHostedHuggingFaceEmbeddings(hardware=gpu)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "2684e928",
"metadata": {},
"outputs": [],
"source": [
"text = \"This is a test document.\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1dc5e606",
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"query_result = embeddings.embed_query(text)"
]
},
{
"cell_type": "markdown",
"id": "cef9cc54",
"metadata": {},
"source": [
"And similarly for SelfHostedHuggingFaceInstructEmbeddings:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "81a17ca3",
"metadata": {},
"outputs": [],
"source": [
"embeddings = SelfHostedHuggingFaceInstructEmbeddings(hardware=gpu)"
]
},
{
"cell_type": "markdown",
"id": "5a33d1c8",
"metadata": {},
"source": [
"Now let's load an embedding model with a custom load function:"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "c4af5679",
"metadata": {},
"outputs": [],
"source": [
"def get_pipeline():\n",
" from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline # Must be inside the function in notebooks\n",
" model_id = \"facebook/bart-base\"\n",
" tokenizer = AutoTokenizer.from_pretrained(model_id)\n",
" model = AutoModelForCausalLM.from_pretrained(model_id)\n",
" return pipeline(\"feature-extraction\", model=model, tokenizer=tokenizer)\n",
"\n",
"def inference_fn(pipeline, prompt):\n",
" # Return last hidden state of the model\n",
" if isinstance(prompt, list):\n",
" return [emb[0][-1] for emb in pipeline(prompt)] \n",
" return pipeline(prompt)[0][-1]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8654334b",
"metadata": {},
"outputs": [],
"source": [
"embeddings = SelfHostedEmbeddings(\n",
" model_load_fn=get_pipeline, \n",
" hardware=gpu,\n",
" model_reqs=[\"./\", \"torch\", \"transformers\"],\n",
" inference_fn=inference_fn\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "fc1bfd0f",
"metadata": {
"scrolled": false
},
"outputs": [],
"source": [
"query_result = embeddings.embed_query(text)"
]
}
],
"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": "3.10.9"
},
"vscode": {
"interpreter": {
"hash": "ce6f9b0d7cdac41515b0e0c38d0e6e153a2edce81d579281cb1ab99da6e8ea6d"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}

263
docs/modules/indexes/examples/hyde.ipynb Normal file
View File

@@ -0,0 +1,263 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "ccb74c9b",
"metadata": {},
"source": [
"# Hypothetical Document Embeddings\n",
"This notebook goes over how to use Hypothetical Document Embeddings (HyDE), as described in [this paper](https://arxiv.org/abs/2212.10496). \n",
"\n",
"At a high level, HyDE is an embedding technique that takes queries, generates a hypothetical answer, and then embeds that generated document and uses that as the final example. \n",
"\n",
"In order to use HyDE, we therefore need to provide a base embedding model, as well as an LLMChain that can be used to generate those documents. By default, the HyDE class comes with some default prompts to use (see the paper for more details on them), but we can also create our own."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "546e87ee",
"metadata": {},
"outputs": [],
"source": [
"from langchain.llms import OpenAI\n",
"from langchain.embeddings import OpenAIEmbeddings\n",
"from langchain.chains import LLMChain, HypotheticalDocumentEmbedder\n",
"from langchain.prompts import PromptTemplate"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "c0ea895f",
"metadata": {},
"outputs": [],
"source": [
"base_embeddings = OpenAIEmbeddings()\n",
"llm = OpenAI()"
]
},
{
"cell_type": "markdown",
"id": "33bd6905",
"metadata": {},
"source": []
},
{
"cell_type": "code",
"execution_count": 3,
"id": "50729989",
"metadata": {},
"outputs": [],
"source": [
"# Load with `web_search` prompt\n",
"embeddings = HypotheticalDocumentEmbedder.from_llm(llm, base_embeddings, \"web_search\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "3aa573d6",
"metadata": {},
"outputs": [],
"source": [
"# Now we can use it as any embedding class!\n",
"result = embeddings.embed_query(\"Where is the Taj Mahal?\")"
]
},
{
"cell_type": "markdown",
"id": "c7a0b556",
"metadata": {},
"source": [
"## Multiple generations\n",
"We can also generate multiple documents and then combine the embeddings for those. By default, we combine those by taking the average. We can do this by changing the LLM we use to generate documents to return multiple things."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "05da7060",
"metadata": {},
"outputs": [],
"source": [
"multi_llm = OpenAI(n=4, best_of=4)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "9b1e12bd",
"metadata": {},
"outputs": [],
"source": [
"embeddings = HypotheticalDocumentEmbedder.from_llm(multi_llm, base_embeddings, \"web_search\")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "a60cd343",
"metadata": {},
"outputs": [],
"source": [
"result = embeddings.embed_query(\"Where is the Taj Mahal?\")"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "1da90437",
"metadata": {},
"source": [
"## Using our own prompts\n",
"Besides using preconfigured prompts, we can also easily construct our own prompts and use those in the LLMChain that is generating the documents. This can be useful if we know the domain our queries will be in, as we can condition the prompt to generate text more similar to that.\n",
"\n",
"In the example below, let's condition it to generate text about a state of the union address (because we will use that in the next example)."
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "0b4a650f",
"metadata": {},
"outputs": [],
"source": [
"prompt_template = \"\"\"Please answer the user's question about the most recent state of the union address\n",
"Question: {question}\n",
"Answer:\"\"\"\n",
"prompt = PromptTemplate(input_variables=[\"question\"], template=prompt_template)\n",
"llm_chain = LLMChain(llm=llm, prompt=prompt)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "7f7e2b86",
"metadata": {},
"outputs": [],
"source": [
"embeddings = HypotheticalDocumentEmbedder(llm_chain=llm_chain, base_embeddings=base_embeddings)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "6dd83424",
"metadata": {},
"outputs": [],
"source": [
"result = embeddings.embed_query(\"What did the president say about Ketanji Brown Jackson\")"
]
},
{
"cell_type": "markdown",
"id": "31388123",
"metadata": {},
"source": [
"## Using HyDE\n",
"Now that we have HyDE, we can use it as we would any other embedding class! Here is using it to find similar passages in the state of the union example."
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "97719b29",
"metadata": {},
"outputs": [],
"source": [
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.vectorstores import Chroma\n",
"\n",
"with open('../../state_of_the_union.txt') as f:\n",
" state_of_the_union = f.read()\n",
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"texts = text_splitter.split_text(state_of_the_union)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "bfcfc039",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running Chroma using direct local API.\n",
"Using DuckDB in-memory for database. Data will be transient.\n"
]
}
],
"source": [
"docsearch = Chroma.from_texts(texts, embeddings)\n",
"\n",
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"docs = docsearch.similarity_search(query)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "632af7f2",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. \n",
"\n",
"We cannot let this happen. \n",
"\n",
"Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
"\n",
"Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
"\n",
"One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
"\n",
"And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n"
]
}
],
"source": [
"print(docs[0].page_content)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b9e57b93",
"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": "3.9.12 (main, Mar 26 2022, 15:51:15) \n[Clang 13.1.6 (clang-1316.0.21.2)]"
},
"vscode": {
"interpreter": {
"hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}

714
docs/modules/indexes/examples/textsplitter.ipynb Normal file
View File

@@ -0,0 +1,714 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "b118c9dc",
"metadata": {},
"source": [
"# Text Splitter\n",
"\n",
"When you want to deal with long pieces of text, it is necessary to split up that text into chunks.\n",
"This notebook showcases several ways to do that.\n",
"\n",
"At a high level, text splitters work as following:\n",
"\n",
"1. Split the text up into small, semantically meaningful chunks (often sentences).\n",
"2. Start combining these small chunks into a larger chunk until you reach a certain size (as measured by some function).\n",
"3. Once you reach that size, make that chunk its own piece of text and then start creating a new chunk of text with some overlap (to keep context between chunks)."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "e82c4685",
"metadata": {},
"outputs": [],
"source": [
"from langchain.text_splitter import CharacterTextSplitter, NLTKTextSplitter, SpacyTextSplitter\n",
"# This is a long document we can split up.\n",
"with open('../../state_of_the_union.txt') as f:\n",
" state_of_the_union = f.read()"
]
},
{
"cell_type": "markdown",
"id": "5c461b26",
"metadata": {},
"source": [
"## Character Text Splitting\n",
"\n",
"Let's start with the most simple method: let's split based on characters (by default \"\\n\\n\") and measure chunk length by number of characters."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "79ff6737",
"metadata": {},
"outputs": [],
"source": [
"text_splitter = CharacterTextSplitter( \n",
" separator = \"\\n\\n\",\n",
" chunk_size = 1000,\n",
" chunk_overlap = 200,\n",
" length_function = len,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "38547666",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans. \n",
"\n",
"Last year COVID-19 kept us apart. This year we are finally together again. \n",
"\n",
"Tonight, we meet as Democrats Republicans and Independents. But most importantly as Americans. \n",
"\n",
"With a duty to one another to the American people to the Constitution. \n",
"\n",
"And with an unwavering resolve that freedom will always triumph over tyranny. \n",
"\n",
"Six days ago, Russia’s Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways. But he badly miscalculated. \n",
"\n",
"He thought he could roll into Ukraine and the world would roll over. Instead he met a wall of strength he never imagined. \n",
"\n",
"He met the Ukrainian people. \n",
"\n",
"From President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world. \n"
]
}
],
"source": [
"texts = text_splitter.split_text(state_of_the_union)\n",
"print(texts[0])"
]
},
{
"cell_type": "markdown",
"id": "1be00b73",
"metadata": {},
"source": [
"## Recursive Character Text Splitting\n",
"Sometimes, it's not enough to split on just one character. This text splitter uses a whole list of characters and recursive splits them down until they are under the limit."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "1ac6376d",
"metadata": {},
"outputs": [],
"source": [
"from langchain.text_splitter import RecursiveCharacterTextSplitter"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "6787b13b",
"metadata": {},
"outputs": [],
"source": [
"text_splitter = RecursiveCharacterTextSplitter(\n",
" # Set a really small chunk size, just to show.\n",
" chunk_size = 100,\n",
" chunk_overlap = 20,\n",
" length_function = len,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "4f0e7d9b",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet.\n",
"and the Cabinet. Justices of the Supreme Court. My fellow Americans. \n"
]
}
],
"source": [
"texts = text_splitter.split_text(state_of_the_union)\n",
"print(texts[0])\n",
"print(texts[1])"
]
},
{
"cell_type": "markdown",
"id": "87a71115",
"metadata": {},
"source": [
"## Document creation\n",
"We can also use the text splitter to create \"Documents\" directly. Documents are a way of bundling pieces of text with associated metadata so that chains can interact with them. We can also create documents with empty metadata though!\n",
"\n",
"In the below example, we pass two pieces of text to get split up (we pass two just to show off the interface of splitting multiple pieces of text)."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "4cd16222",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"page_content='Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans. \\n\\nLast year COVID-19 kept us apart. This year we are finally together again. \\n\\nTonight, we meet as Democrats Republicans and Independents. But most importantly as Americans. \\n\\nWith a duty to one another to the American people to the Constitution. \\n\\nAnd with an unwavering resolve that freedom will always triumph over tyranny. \\n\\nSix days ago, Russia’s Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways. But he badly miscalculated. \\n\\nHe thought he could roll into Ukraine and the world would roll over. Instead he met a wall of strength he never imagined. \\n\\nHe met the Ukrainian people. \\n\\nFrom President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world. ' lookup_str='' metadata={} lookup_index=0\n"
]
}
],
"source": [
"documents = text_splitter.create_documents([state_of_the_union, state_of_the_union])\n",
"print(documents[0])"
]
},
{
"cell_type": "markdown",
"id": "2cede1b1",
"metadata": {},
"source": [
"Here's an example of passing metadata along with the documents, notice that it is split along with the documents."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "4a47515a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"page_content='Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans. \\n\\nLast year COVID-19 kept us apart. This year we are finally together again. \\n\\nTonight, we meet as Democrats Republicans and Independents. But most importantly as Americans. \\n\\nWith a duty to one another to the American people to the Constitution. \\n\\nAnd with an unwavering resolve that freedom will always triumph over tyranny. \\n\\nSix days ago, Russia’s Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways. But he badly miscalculated. \\n\\nHe thought he could roll into Ukraine and the world would roll over. Instead he met a wall of strength he never imagined. \\n\\nHe met the Ukrainian people. \\n\\nFrom President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world. ' lookup_str='' metadata={'document': 1} lookup_index=0\n"
]
}
],
"source": [
"metadatas = [{\"document\": 1}, {\"document\": 2}]\n",
"documents = text_splitter.create_documents([state_of_the_union, state_of_the_union], metadatas=metadatas)\n",
"print(documents[0])"
]
},
{
"cell_type": "markdown",
"id": "13dc0983",
"metadata": {},
"source": [
"## HuggingFace Length Function\n",
"Most LLMs are constrained by the number of tokens that you can pass in, which is not the same as the number of characters. In order to get a more accurate estimate, we can use HuggingFace tokenizers to count the text length."
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "a8ce51d5",
"metadata": {},
"outputs": [],
"source": [
"from transformers import GPT2TokenizerFast\n",
"\n",
"tokenizer = GPT2TokenizerFast.from_pretrained(\"gpt2\")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "ca5e72c0",
"metadata": {},
"outputs": [],
"source": [
"text_splitter = CharacterTextSplitter.from_huggingface_tokenizer(tokenizer, chunk_size=100, chunk_overlap=0)\n",
"texts = text_splitter.split_text(state_of_the_union)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "37cdfbeb",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans. \n",
"\n",
"Last year COVID-19 kept us apart. This year we are finally together again. \n",
"\n",
"Tonight, we meet as Democrats Republicans and Independents. But most importantly as Americans. \n",
"\n",
"With a duty to one another to the American people to the Constitution. \n"
]
}
],
"source": [
"print(texts[0])"
]
},
{
"cell_type": "markdown",
"id": "7683b36a",
"metadata": {},
"source": [
"## tiktoken (OpenAI) Length Function\n",
"You can also use tiktoken, a open source tokenizer package from OpenAI to estimate tokens used. Will probably be more accurate for their models."
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "825f7c0a",
"metadata": {},
"outputs": [],
"source": [
"text_splitter = CharacterTextSplitter.from_tiktoken_encoder(chunk_size=100, chunk_overlap=0)\n",
"texts = text_splitter.split_text(state_of_the_union)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "ae35d165",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans. \n",
"\n",
"Last year COVID-19 kept us apart. This year we are finally together again. \n",
"\n",
"Tonight, we meet as Democrats Republicans and Independents. But most importantly as Americans. \n",
"\n",
"With a duty to one another to the American people to the Constitution. \n"
]
}
],
"source": [
"print(texts[0])"
]
},
{
"cell_type": "markdown",
"id": "ea2973ac",
"metadata": {},
"source": [
"## NLTK Text Splitter\n",
"Rather than just splitting on \"\\n\\n\", we can use NLTK to split based on tokenizers."
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "20fa9c23",
"metadata": {},
"outputs": [],
"source": [
"text_splitter = NLTKTextSplitter(chunk_size=1000)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "5ea10835",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Madam Speaker, Madam Vice President, our First Lady and Second Gentleman.\n",
"\n",
"Members of Congress and the Cabinet.\n",
"\n",
"Justices of the Supreme Court.\n",
"\n",
"My fellow Americans.\n",
"\n",
"Last year COVID-19 kept us apart.\n",
"\n",
"This year we are finally together again.\n",
"\n",
"Tonight, we meet as Democrats Republicans and Independents.\n",
"\n",
"But most importantly as Americans.\n",
"\n",
"With a duty to one another to the American people to the Constitution.\n",
"\n",
"And with an unwavering resolve that freedom will always triumph over tyranny.\n",
"\n",
"Six days ago, Russia’s Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways.\n",
"\n",
"But he badly miscalculated.\n",
"\n",
"He thought he could roll into Ukraine and the world would roll over.\n",
"\n",
"Instead he met a wall of strength he never imagined.\n",
"\n",
"He met the Ukrainian people.\n",
"\n",
"From President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world.\n",
"\n",
"Groups of citizens blocking tanks with their bodies.\n"
]
}
],
"source": [
"texts = text_splitter.split_text(state_of_the_union)\n",
"print(texts[0])"
]
},
{
"cell_type": "markdown",
"id": "dab86b60",
"metadata": {},
"source": [
"## Spacy Text Splitter\n",
"Another alternative to NLTK is to use Spacy."
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "f9cc9dfc",
"metadata": {},
"outputs": [],
"source": [
"text_splitter = SpacyTextSplitter(chunk_size=1000)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "cef2b29e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Madam Speaker, Madam Vice President, our First Lady and Second Gentleman.\n",
"\n",
"Members of Congress and the Cabinet.\n",
"\n",
"Justices of the Supreme Court.\n",
"\n",
"My fellow Americans. \n",
"\n",
"\n",
"\n",
"Last year COVID-19 kept us apart.\n",
"\n",
"This year we are finally together again.\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"Tonight, we meet as Democrats Republicans and Independents.\n",
"\n",
"But most importantly as Americans.\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"With a duty to one another to the American people to the Constitution. \n",
"\n",
"\n",
"\n",
"And with an unwavering resolve that freedom will always triumph over tyranny.\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"Six days ago, Russia’s Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways.\n",
"\n",
"But he badly miscalculated.\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"He thought he could roll into Ukraine and the world would roll over.\n",
"\n",
"Instead he met a wall of strength he never imagined.\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"He met the Ukrainian people.\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"From President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world.\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"Groups of citizens blocking tanks with their bodies.\n"
]
}
],
"source": [
"texts = text_splitter.split_text(state_of_the_union)\n",
"print(texts[0])"
]
},
{
"cell_type": "markdown",
"id": "53049ff5",
"metadata": {},
"source": [
"## Token Text Splitter"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "a1a118b1",
"metadata": {},
"outputs": [],
"source": [
"from langchain.text_splitter import TokenTextSplitter"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "ef37c5d3",
"metadata": {},
"outputs": [],
"source": [
"text_splitter = TokenTextSplitter(chunk_size=10, chunk_overlap=0)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "5750228a",
"metadata": {
"scrolled": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Madam Speaker, Madam Vice President, our\n"
]
}
],
"source": [
"texts = text_splitter.split_text(state_of_the_union)\n",
"print(texts[0])"
]
},
{
"cell_type": "markdown",
"id": "c24dbbb7",
"metadata": {},
"source": [
"# Markdown Text Splitter\n",
"\n",
"MarkdownTextSplitter splits text along Markdown headings, code blocks, or horizontal rules. It's implemented as a simple subclass of RecursiveCharacterSplitter with Markdown-specific separators. See the source code to see the Markdown syntax expected by default."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "593e490c",
"metadata": {},
"outputs": [],
"source": [
"from langchain.text_splitter import MarkdownTextSplitter"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "89a9a3ea",
"metadata": {},
"outputs": [],
"source": [
"markdown_text = \"\"\"\n",
"# 🦜️🔗 LangChain\n",
"\n",
"⚡ Building applications with LLMs through composability ⚡\n",
"\n",
"## Quick Install\n",
"\n",
"```bash\n",
"# Hopefully this code block isn't split\n",
"pip install langchain\n",
"```\n",
"\n",
"As an open source project in a rapidly developing field, we are extremely open to contributions.\n",
"\"\"\"\n",
"markdown_splitter = MarkdownTextSplitter(chunk_size=100, chunk_overlap=0)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "241f0719",
"metadata": {},
"outputs": [],
"source": [
"docs = markdown_splitter.create_documents([markdown_text])"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "7789e643",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[Document(page_content='# 🦜️🔗 LangChain\\n\\n⚡ Building applications with LLMs through composability ⚡', lookup_str='', metadata={}, lookup_index=0),\n",
" Document(page_content=\"Quick Install\\n\\n```bash\\n# Hopefully this code block isn't split\\npip install langchain\", lookup_str='', metadata={}, lookup_index=0),\n",
" Document(page_content='As an open source project in a rapidly developing field, we are extremely open to contributions.', lookup_str='', metadata={}, lookup_index=0)]"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"docs"
]
},
{
"cell_type": "markdown",
"id": "04a6392a",
"metadata": {},
"source": [
"# Python Code Text Splitter\n",
"\n",
"PythonCodeTextSplitter splits text along python class and method definitions. It's implemented as a simple subclass of RecursiveCharacterSplitter with Python-specific separators. See the source code to see the Python syntax expected by default."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "8fb36bc7",
"metadata": {},
"outputs": [],
"source": [
"from langchain.text_splitter import PythonCodeTextSplitter"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "d359f3dc",
"metadata": {},
"outputs": [],
"source": [
"python_text = \"\"\"\n",
"class Foo:\n",
"\n",
" def bar():\n",
" \n",
" \n",
"def foo():\n",
"\n",
"def testing_func():\n",
"\n",
"def bar():\n",
"\"\"\"\n",
"python_splitter = PythonCodeTextSplitter(chunk_size=30, chunk_overlap=0)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "26b79cd9",
"metadata": {},
"outputs": [],
"source": [
"docs = python_splitter.create_documents([python_text])"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "b1749579",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[Document(page_content='Foo:\\n\\n def bar():', lookup_str='', metadata={}, lookup_index=0),\n",
" Document(page_content='foo():\\n\\ndef testing_func():', lookup_str='', metadata={}, lookup_index=0),\n",
" Document(page_content='bar():', lookup_str='', metadata={}, lookup_index=0)]"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"docs"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6e6c8cc7",
"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"
},
"vscode": {
"interpreter": {
"hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}

273
docs/modules/indexes/examples/vectorstores.ipynb Normal file
View File

@@ -0,0 +1,273 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "7ef4d402-6662-4a26-b612-35b542066487",
"metadata": {
"pycharm": {
"name": "#%% md\n"
}
},
"source": [
"# VectorStores\n",
"\n",
"This notebook showcases basic functionality related to VectorStores. A key part of working with vectorstores is creating the vector to put in them, which is usually created via embeddings. Therefor, it is recommended that you familiarize yourself with the [embedding notebook](embeddings.ipynb) before diving into this.\n",
"\n",
"This covers generic high level functionality related to all vector stores. For guides on specific vectorstores, please see the how-to guides [here](../how_to_guides.rst)"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "965eecee",
"metadata": {
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [],
"source": [
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.vectorstores import Chroma"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "68481687",
"metadata": {
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [],
"source": [
"with open('../../state_of_the_union.txt') as f:\n",
" state_of_the_union = f.read()\n",
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"texts = text_splitter.split_text(state_of_the_union)\n",
"\n",
"embeddings = OpenAIEmbeddings()"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "015f4ff5",
"metadata": {
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running Chroma using direct local API.\n",
"Using DuckDB in-memory for database. Data will be transient.\n"
]
}
],
"source": [
"docsearch = Chroma.from_texts(texts, embeddings)\n",
"\n",
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"docs = docsearch.similarity_search(query)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "67baf32e",
"metadata": {
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. \n",
"\n",
"We cannot let this happen. \n",
"\n",
"Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
"\n",
"Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
"\n",
"One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
"\n",
"And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n"
]
}
],
"source": [
"print(docs[0].page_content)"
]
},
{
"cell_type": "markdown",
"id": "fb6baaf8",
"metadata": {},
"source": [
"## Add texts\n",
"You can easily add text to a vectorstore with the `add_texts` method. It will return a list of document IDs (in case you need to use them downstream)."
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "70758e4f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['a05e3d0c-ab40-11ed-a853-e65801318981']"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"docsearch.add_texts([\"Ankush went to Princeton\"])"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "4edeb88f",
"metadata": {},
"outputs": [],
"source": [
"query = \"Where did Ankush go to college?\"\n",
"docs = docsearch.similarity_search(query)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "1cba64a2",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Document(page_content='Ankush went to Princeton', lookup_str='', metadata={}, lookup_index=0)"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"docs[0]"
]
},
{
"cell_type": "markdown",
"id": "bbf5ec44",
"metadata": {},
"source": [
"## From Documents\n",
"We can also initialize a vectorstore from documents directly. This is useful when we use the method on the text splitter to get documents directly (handy when the original documents have associated metadata)."
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "df4a459c",
"metadata": {},
"outputs": [],
"source": [
"documents = text_splitter.create_documents([state_of_the_union], metadatas=[{\"source\": \"State of the Union\"}])"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "4b480245",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running Chroma using direct local API.\n",
"Using DuckDB in-memory for database. Data will be transient.\n"
]
}
],
"source": [
"docsearch = Chroma.from_documents(documents, embeddings)\n",
"\n",
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"docs = docsearch.similarity_search(query)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "86aa4cda",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. \n",
"\n",
"We cannot let this happen. \n",
"\n",
"Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
"\n",
"Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
"\n",
"One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
"\n",
"And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n"
]
}
],
"source": [
"print(docs[0].page_content)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4af5a071",
"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
}

186
docs/modules/indexes/getting_started.ipynb Normal file
View File

@@ -0,0 +1,186 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "07c1e3b9",
"metadata": {},
"source": [
"# Getting Started\n",
"\n",
"This example showcases question answering over a vector database.\n",
"We have chosen this as the example for getting started because it nicely combines a lot of different elements (Text splitters, embeddings, vectorstores) and then also shows how to use them in a chain."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "82525493",
"metadata": {},
"outputs": [],
"source": [
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.vectorstores import Chroma\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain import OpenAI, VectorDBQA"
]
},
{
"cell_type": "markdown",
"id": "0b7adc54",
"metadata": {},
"source": [
"Here we load in the documents we want to use to create our index."
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "611e0c19",
"metadata": {},
"outputs": [],
"source": [
"from langchain.document_loaders import TextLoader\n",
"loader = TextLoader('../state_of_the_union.txt')\n",
"documents = loader.load()"
]
},
{
"cell_type": "markdown",
"id": "9fdc0fc2",
"metadata": {},
"source": [
"Next, we will split the documents into chunks."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "afecb8cf",
"metadata": {},
"outputs": [],
"source": [
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"texts = text_splitter.split_documents(documents)"
]
},
{
"cell_type": "markdown",
"id": "4bebc041",
"metadata": {},
"source": [
"We will then select which embeddings we want to use."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "9eaaa735",
"metadata": {},
"outputs": [],
"source": [
"embeddings = OpenAIEmbeddings()"
]
},
{
"cell_type": "markdown",
"id": "24612905",
"metadata": {},
"source": [
"We now create the vectorstore to use as the index."
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "5c7049db",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running Chroma using direct local API.\n",
"Using DuckDB in-memory for database. Data will be transient.\n"
]
}
],
"source": [
"db = Chroma.from_documents(texts, embeddings)"
]
},
{
"cell_type": "markdown",
"id": "30c4e5c6",
"metadata": {},
"source": [
"Finally, we create a chain and use it to answer questions!"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "3018f865",
"metadata": {},
"outputs": [],
"source": [
"qa = VectorDBQA.from_chain_type(llm=OpenAI(), chain_type=\"stuff\", vectorstore=db)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "032a47f8",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\" The President said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, and from a family of public school educators and police officers. He said that she is a consensus builder and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"qa.run(query)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8b403637",
"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"
},
"vscode": {
"interpreter": {
"hash": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}

93
docs/modules/indexes/how_to_guides.rst Normal file
View File

@@ -0,0 +1,93 @@
How To Guides
====================================
Utils
-----
There are a lot of different utilities that LangChain provides integrations for
These guides go over how to use them.
The utilities here are all utilities that make it easier to work with documents.
`Text Splitters <./examples/textsplitter.html>`_: A walkthrough of how to split large documents up into smaller, more manageable pieces of text.
`VectorStores <./examples/vectorstores.html>`_: A walkthrough of the vectorstore abstraction that LangChain supports.
`Embeddings <./examples/embeddings.html>`_: A walkthrough of embedding functionalities, and different types of embeddings, that LangChain supports.
`HyDE <./examples/hyde.html>`_: How to use Hypothetical Document Embeddings, a novel way of constructing embeddings for document retrieval systems.
.. toctree::
:maxdepth: 1
:glob:
:caption: Utils
:name: utils
:hidden:
examples/*
Vectorstores
------------
Vectorstores are one of the most important components of building indexes.
In the below guides, we cover different types of vectorstores and how to use them.
`Chroma <./vectorstore_examples/chroma.html>`_: A walkthrough of how to use the Chroma vectorstore wrapper.
`FAISS <./vectorstore_examples/faiss.html>`_: A walkthrough of how to use the FAISS vectorstore wrapper.
`Elastic Search <./vectorstore_examples/elasticsearch.html>`_: A walkthrough of how to use the ElasticSearch wrapper.
`Milvus <./vectorstore_examples/milvus.html>`_: A walkthrough of how to use the Milvus vectorstore wrapper.
`Pinecone <./vectorstore_examples/pinecone.html>`_: A walkthrough of how to use the Pinecone vectorstore wrapper.
`Qdrant <./vectorstore_examples/qdrant.html>`_: A walkthrough of how to use the Qdrant vectorstore wrapper.
`Weaviate <./vectorstore_examples/weaviate.html>`_: A walkthrough of how to use the Weaviate vectorstore wrapper.
.. toctree::
:maxdepth: 1
:glob:
:caption: Vectorstores
:name: vectorstores
:hidden:
vectorstore_examples/*
Chains
------
The examples here are all end-to-end chains that use indexes or utils covered above.
`Question Answering <./chain_examples/question_answering.html>`_: A walkthrough of how to use LangChain for question answering over specific documents.
`Question Answering with Sources <./chain_examples/qa_with_sources.html>`_: A walkthrough of how to use LangChain for question answering (with sources) over specific documents.
`Summarization <./chain_examples/summarize.html>`_: A walkthrough of how to use LangChain for summarization over specific documents.
`Vector DB Text Generation <./chain_examples/vector_db_text_generation.html>`_: A walkthrough of how to use LangChain for text generation over a vector database.
`Vector DB Question Answering <./chain_examples/vector_db_qa.html>`_: A walkthrough of how to use LangChain for question answering over a vector database.
`Vector DB Question Answering with Sources <./chain_examples/vector_db_qa_with_sources.html>`_: A walkthrough of how to use LangChain for question answering (with sources) over a vector database.
`Graph Question Answering <./chain_examples/graph_qa.html>`_: A walkthrough of how to use LangChain for question answering (with sources) over a graph database.
`Chat Vector DB <./chain_examples/chat_vector_db.html>`_: A walkthrough of how to use LangChain as a chatbot over a vector database.
`Analyze Document <./chain_examples/analyze_document.html>`_: A walkthrough of how to use LangChain to analyze long documents.
.. toctree::
:maxdepth: 1
:glob:
:caption: With Chains
:name: chains
:hidden:
./chain_examples/*

27
docs/modules/indexes/key_concepts.md Normal file
View File

@@ -0,0 +1,27 @@
# Key Concepts
## Text Splitter
This class is responsible for splitting long pieces of text into smaller components.
It contains different ways for splitting text (on characters, using Spacy, etc)
as well as different ways for measuring length (token based, character based, etc).
## Embeddings
These classes are very similar to the LLM classes in that they are wrappers around models,
but rather than return a string they return an embedding (list of floats). These are particularly useful when
implementing semantic search functionality. They expose separate methods for embedding queries versus embedding documents.
## Vectorstores
These are datastores that store embeddings of documents in vector form.
They expose a method for passing in a string and finding similar documents.
## CombineDocuments Chains
These are a subset of chains designed to work with documents. There are two pieces to consider:
1. The underlying chain method (eg, how the documents are combined)
2. Use cases for these types of chains.
For the first, please see [this documentation](combine_docs.md) for more detailed information on the types of chains LangChain supports.
For the second, please see the Use Cases section for more information on [question answering](/use_cases/question_answering.md),
[question answering with sources](/use_cases/qa_with_sources.md), and [summarization](/use_cases/summarization.md).

122
docs/modules/indexes/vectorstore_examples/chroma.ipynb Normal file
View File

@@ -0,0 +1,122 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "683953b3",
"metadata": {},
"source": [
"# Chroma\n",
"\n",
"This notebook shows how to use functionality related to the Chroma vector database."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "aac9563e",
"metadata": {},
"outputs": [],
"source": [
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.vectorstores import Chroma\n",
"from langchain.document_loaders import TextLoader"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "a3c3999a",
"metadata": {},
"outputs": [],
"source": [
"from langchain.document_loaders import TextLoader\n",
"loader = TextLoader('../../state_of_the_union.txt')\n",
"documents = loader.load()\n",
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"docs = text_splitter.split_documents(documents)\n",
"\n",
"embeddings = OpenAIEmbeddings()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "5eabdb75",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running Chroma using direct local API.\n",
"Using DuckDB in-memory for database. Data will be transient.\n"
]
}
],
"source": [
"db = Chroma.from_documents(docs, embeddings)\n",
"\n",
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"docs = db.similarity_search(query)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "4b172de8",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. \n",
"\n",
"We cannot let this happen. \n",
"\n",
"Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
"\n",
"Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
"\n",
"One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
"\n",
"And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n"
]
}
],
"source": [
"print(docs[0].page_content)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a359ed74",
"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
}

113
docs/modules/indexes/vectorstore_examples/elasticsearch.ipynb Normal file
View File

@@ -0,0 +1,113 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "683953b3",
"metadata": {},
"source": [
"# ElasticSearch\n",
"\n",
"This notebook shows how to use functionality related to the ElasticSearch database."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "aac9563e",
"metadata": {},
"outputs": [],
"source": [
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.vectorstores import ElasticVectorSearch\n",
"from langchain.document_loaders import TextLoader"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "a3c3999a",
"metadata": {},
"outputs": [],
"source": [
"from langchain.document_loaders import TextLoader\n",
"loader = TextLoader('../../state_of_the_union.txt')\n",
"documents = loader.load()\n",
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"docs = text_splitter.split_documents(documents)\n",
"\n",
"embeddings = OpenAIEmbeddings()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "12eb86d8",
"metadata": {},
"outputs": [],
"source": [
"db = ElasticVectorSearch.from_documents(docs, embeddings, elasticsearch_url=\"http://localhost:9200\"\n",
"\n",
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"docs = db.similarity_search(query)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "4b172de8",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. \n",
"\n",
"We cannot let this happen. \n",
"\n",
"Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
"\n",
"Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
"\n",
"One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
"\n",
"And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n"
]
}
],
"source": [
"print(docs[0].page_content)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a359ed74",
"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
}

233
docs/modules/indexes/vectorstore_examples/faiss.ipynb Normal file
View File

@@ -0,0 +1,233 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "683953b3",
"metadata": {},
"source": [
"# FAISS\n",
"\n",
"This notebook shows how to use functionality related to the FAISS vector database."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "aac9563e",
"metadata": {},
"outputs": [],
"source": [
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.vectorstores import FAISS\n",
"from langchain.document_loaders import TextLoader"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "a3c3999a",
"metadata": {},
"outputs": [],
"source": [
"from langchain.document_loaders import TextLoader\n",
"loader = TextLoader('../../state_of_the_union.txt')\n",
"documents = loader.load()\n",
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"docs = text_splitter.split_documents(documents)\n",
"\n",
"embeddings = OpenAIEmbeddings()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "5eabdb75",
"metadata": {},
"outputs": [],
"source": [
"db = FAISS.from_documents(docs, embeddings)\n",
"\n",
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"docs = db.similarity_search(query)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "4b172de8",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. \n",
"\n",
"We cannot let this happen. \n",
"\n",
"Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
"\n",
"Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
"\n",
"One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
"\n",
"And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n"
]
}
],
"source": [
"print(docs[0].page_content)"
]
},
{
"cell_type": "markdown",
"id": "f13473b5",
"metadata": {},
"source": [
"## Similarity Search with score\n",
"There are some FAISS specific methods. One of them is `similarity_search_with_score`, which allows you to return not only the documents but also the similarity score of the query to them."
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "186ee1d8",
"metadata": {},
"outputs": [],
"source": [
"docs_and_scores = db.similarity_search_with_score(query)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "284e04b5",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(Document(page_content='In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. \\n\\nWe cannot let this happen. \\n\\nTonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0),\n",
" 0.3914415)"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"docs_and_scores[0]"
]
},
{
"cell_type": "markdown",
"id": "f34420cf",
"metadata": {},
"source": [
"It is also possible to do a search for documents similar to a given embedding vector using `similarity_search_by_vector` which accepts an embedding vector as a parameter instead of a string."
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "b558ebb7",
"metadata": {},
"outputs": [],
"source": [
"embedding_vector = embeddings.embed_query(query)\n",
"docs_and_scores = db.similarity_search_by_vector(embedding_vector)"
]
},
{
"cell_type": "markdown",
"id": "31bda7fd",
"metadata": {},
"source": [
"## Saving and loading\n",
"You can also save and load a FAISS index. This is useful so you don't have to recreate it everytime you use it."
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "428a6816",
"metadata": {},
"outputs": [],
"source": [
"db.save_local(\"faiss_index\")"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "56d1841c",
"metadata": {},
"outputs": [],
"source": [
"new_db = FAISS.load_local(\"faiss_index\", embeddings)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "39055525",
"metadata": {},
"outputs": [],
"source": [
"docs = new_db.similarity_search(query)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "98378c4e",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Document(page_content='In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. \\n\\nWe cannot let this happen. \\n\\nTonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0)"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"docs[0]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "bc8b71f7",
"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
}

108
docs/modules/indexes/vectorstore_examples/milvus.ipynb Normal file
View File

@@ -0,0 +1,108 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "683953b3",
"metadata": {},
"source": [
"# Milvus\n",
"\n",
"This notebook shows how to use functionality related to the Milvus vector database.\n",
"\n",
"To run, you should have a Milvus instance up and running: https://milvus.io/docs/install_standalone-docker.md"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "aac9563e",
"metadata": {},
"outputs": [],
"source": [
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.vectorstores import Milvus\n",
"from langchain.document_loaders import TextLoader"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "a3c3999a",
"metadata": {},
"outputs": [],
"source": [
"from langchain.document_loaders import TextLoader\n",
"loader = TextLoader('../../state_of_the_union.txt')\n",
"documents = loader.load()\n",
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"docs = text_splitter.split_documents(documents)\n",
"\n",
"embeddings = OpenAIEmbeddings()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "dcf88bdf",
"metadata": {},
"outputs": [],
"source": [
"vector_db = Milvus.from_documents(\n",
" docs,\n",
" embeddings,\n",
" connection_args={\"host\": \"127.0.0.1\", \"port\": \"19530\"},\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a8c513ab",
"metadata": {},
"outputs": [],
"source": [
"docs = vector_db.similarity_search(query)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "fc516993",
"metadata": {},
"outputs": [],
"source": [
"docs[0]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a359ed74",
"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
}

105
docs/modules/indexes/vectorstore_examples/pinecone.ipynb Normal file
View File

@@ -0,0 +1,105 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "683953b3",
"metadata": {},
"source": [
"# Pinecone\n",
"\n",
"This notebook shows how to use functionality related to the Pinecone vector database."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "aac9563e",
"metadata": {},
"outputs": [],
"source": [
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.vectorstores import Pinecone\n",
"from langchain.document_loaders import TextLoader"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "a3c3999a",
"metadata": {},
"outputs": [],
"source": [
"from langchain.document_loaders import TextLoader\n",
"loader = TextLoader('../../state_of_the_union.txt')\n",
"documents = loader.load()\n",
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"docs = text_splitter.split_documents(documents)\n",
"\n",
"embeddings = OpenAIEmbeddings()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6e104aee",
"metadata": {},
"outputs": [],
"source": [
"import pinecone \n",
"\n",
"# initialize pinecone\n",
"pinecone.init(\n",
" api_key=\"YOUR_API_KEY\", # find at app.pinecone.io\n",
" environment=\"YOUR_ENV\" # next to api key in console\n",
")\n",
"\n",
"index_name = \"langchain-demo\"\n",
"\n",
"docsearch = Pinecone.from_documents(docs, embeddings, index_name=index_name)\n",
"\n",
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"docs = docsearch.similarity_search(query)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9c608226",
"metadata": {},
"outputs": [],
"source": [
"print(docs[0].page_content)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a359ed74",
"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
}

105
docs/modules/indexes/vectorstore_examples/qdrant.ipynb Normal file
View File

@@ -0,0 +1,105 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "683953b3",
"metadata": {},
"source": [
"# Qdrant\n",
"\n",
"This notebook shows how to use functionality related to the Qdrant vector database."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "aac9563e",
"metadata": {},
"outputs": [],
"source": [
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.vectorstores import Qdrant\n",
"from langchain.document_loaders import TextLoader"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "a3c3999a",
"metadata": {},
"outputs": [],
"source": [
"from langchain.document_loaders import TextLoader\n",
"loader = TextLoader('../../state_of_the_union.txt')\n",
"documents = loader.load()\n",
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"docs = text_splitter.split_documents(documents)\n",
"\n",
"embeddings = OpenAIEmbeddings()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "dcf88bdf",
"metadata": {},
"outputs": [],
"source": [
"host = \"<---host name here --->\"\n",
"api_key = \"<---api key here--->\"\n",
"qdrant = Qdrant.from_documents(docs, embeddings, host=host, prefer_grpc=True, api_key=api_key)\n",
"query = \"What did the president say about Ketanji Brown Jackson\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a8c513ab",
"metadata": {},
"outputs": [],
"source": [
"docs = qdrant.similarity_search(query)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "fc516993",
"metadata": {},
"outputs": [],
"source": [
"docs[0]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a359ed74",
"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
}

163
docs/modules/indexes/vectorstore_examples/weaviate.ipynb Normal file
View File

@@ -0,0 +1,163 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "683953b3",
"metadata": {},
"source": [
"# Weaviate\n",
"\n",
"This notebook shows how to use functionality related to the Weaviate vector database."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "aac9563e",
"metadata": {},
"outputs": [],
"source": [
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.vectorstores import Weaviate\n",
"from langchain.document_loaders import TextLoader"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "a3c3999a",
"metadata": {},
"outputs": [],
"source": [
"from langchain.document_loaders import TextLoader\n",
"loader = TextLoader('../../state_of_the_union.txt')\n",
"documents = loader.load()\n",
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"docs = text_splitter.split_documents(documents)\n",
"\n",
"embeddings = OpenAIEmbeddings()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5888dcc7",
"metadata": {},
"outputs": [],
"source": [
"import weaviate\n",
"import os\n",
"\n",
"WEAVIATE_URL = \"\"\n",
"client = weaviate.Client(\n",
" url=WEAVIATE_URL,\n",
" additional_headers={\n",
" 'X-OpenAI-Api-Key': os.environ[\"OPENAI_API_KEY\"]\n",
" }\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f004e8ee",
"metadata": {},
"outputs": [],
"source": [
"client.schema.delete_all()\n",
"client.schema.get()\n",
"schema = {\n",
" \"classes\": [\n",
" {\n",
" \"class\": \"Paragraph\",\n",
" \"description\": \"A written paragraph\",\n",
" \"vectorizer\": \"text2vec-openai\",\n",
" \"moduleConfig\": {\n",
" \"text2vec-openai\": {\n",
" \"model\": \"babbage\",\n",
" \"type\": \"text\"\n",
" }\n",
" },\n",
" \"properties\": [\n",
" {\n",
" \"dataType\": [\"text\"],\n",
" \"description\": \"The content of the paragraph\",\n",
" \"moduleConfig\": {\n",
" \"text2vec-openai\": {\n",
" \"skip\": False,\n",
" \"vectorizePropertyName\": False\n",
" }\n",
" },\n",
" \"name\": \"content\",\n",
" },\n",
" ],\n",
" },\n",
" ]\n",
"}\n",
"\n",
"client.schema.create(schema)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ef6d5d04",
"metadata": {},
"outputs": [],
"source": [
"vectorstore = Weaviate(client, \"Paragraph\", \"content\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "06e8c1ed",
"metadata": {},
"outputs": [],
"source": [
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"docs = vectorstore.similarity_search(query)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "38b86be6",
"metadata": {},
"outputs": [],
"source": [
"print(docs[0].page_content)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a359ed74",
"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
}