mirror of
https://github.com/hwchase17/langchain.git
synced 2025-11-12 23:15:42 +00:00
[docs]: vector store integration pages (#24858)
Co-authored-by: Erick Friis <erick@langchain.dev>
This commit is contained in:
Isaac Francisco
GitHub
@@ -7,11 +7,9 @@
|
||||
"source": [
|
||||
"# Faiss\n",
|
||||
"\n",
|
||||
">[Facebook AI Similarity Search (Faiss)](https://engineering.fb.com/2017/03/29/data-infrastructure/faiss-a-library-for-efficient-similarity-search/) is a library for efficient similarity search and clustering of dense vectors. It contains algorithms that search in sets of vectors of any size, up to ones that possibly do not fit in RAM. It also contains supporting code for evaluation and parameter tuning.\n",
|
||||
">[Facebook AI Similarity Search (FAISS)](https://engineering.fb.com/2017/03/29/data-infrastructure/faiss-a-library-for-efficient-similarity-search/) is a library for efficient similarity search and clustering of dense vectors. It contains algorithms that search in sets of vectors of any size, up to ones that possibly do not fit in RAM. It also contains supporting code for evaluation and parameter tuning.\n",
|
||||
"\n",
|
||||
"[Faiss documentation](https://faiss.ai/).\n",
|
||||
"\n",
|
||||
"You'll need to install `langchain-community` with `pip install -qU langchain-community` to use this integration\n",
|
||||
"You can find the FAISS documentation at [this page](https://faiss.ai/).\n",
|
||||
"\n",
|
||||
"This notebook shows how to use functionality related to the `FAISS` vector database. It will show functionality specific to this integration. After going through, it may be useful to explore [relevant use-case pages](/docs/how_to#qa-with-rag) to learn how to use this vectorstore as part of a larger chain."
|
||||
]
|
||||
@@ -25,28 +23,19 @@
|
||||
"source": [
|
||||
"## Setup\n",
|
||||
"\n",
|
||||
"The integration lives in the `langchain-community` package. We also need to install the `faiss` package itself. We will also be using OpenAI for embeddings, so we need to install those requirements. We can install these with:\n",
|
||||
"The integration lives in the `langchain-community` package. We also need to install the `faiss` package itself. We can install these with:\n",
|
||||
"\n",
|
||||
"```bash\n",
|
||||
"pip install -U langchain-community faiss-cpu langchain-openai tiktoken\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"Note that you can also install `faiss-gpu` if you want to use the GPU enabled version\n",
|
||||
"\n",
|
||||
"Since we are using OpenAI, you will need an OpenAI API Key."
|
||||
"Note that you can also install `faiss-gpu` if you want to use the GPU enabled version"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "23984e60-c29a-461a-be2b-219108ac37ee",
|
||||
"id": "08165d56",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import getpass\n",
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"OPENAI_API_KEY\"] = getpass.getpass()"
|
||||
"pip install -qU langchain-community faiss-cpu"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -54,7 +43,7 @@
|
||||
"id": "408be78f-7b0e-44d4-8d48-56a6cb9b3fb9",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"It's also helpful (but not needed) to set up [LangSmith](https://smith.langchain.com/) for best-in-class observability"
|
||||
"If you want to get best in-class automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -73,200 +62,366 @@
|
||||
"id": "78dde98a-584f-4f2a-98d5-e776fd9558fa",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Ingestion\n",
|
||||
"## Initialization\n",
|
||||
"\n",
|
||||
"Here, we ingest documents into the vectorstore"
|
||||
"```{=mdx}\n",
|
||||
"import EmbeddingTabs from \"@theme/EmbeddingTabs\";\n",
|
||||
"\n",
|
||||
"<EmbeddingTabs/>\n",
|
||||
"```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "dc37144c-208d-4ab3-9f3a-0407a69fe052",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"42"
|
||||
]
|
||||
},
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Uncomment the following line if you need to initialize FAISS with no AVX2 optimization\n",
|
||||
"# os.environ['FAISS_NO_AVX2'] = '1'\n",
|
||||
"\n",
|
||||
"from langchain_community.document_loaders import TextLoader\n",
|
||||
"from langchain_community.vectorstores import FAISS\n",
|
||||
"from langchain_openai import OpenAIEmbeddings\n",
|
||||
"from langchain_text_splitters import CharacterTextSplitter\n",
|
||||
"\n",
|
||||
"loader = TextLoader(\"../../how_to/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",
|
||||
"embeddings = OpenAIEmbeddings()\n",
|
||||
"db = FAISS.from_documents(docs, embeddings)\n",
|
||||
"print(db.index.ntotal)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "ecdd7a65-f310-4b36-bc1e-2a39dfd58d5f",
|
||||
"id": "5b394da3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"## Querying\n",
|
||||
"# | output: false\n",
|
||||
"# | echo: false\n",
|
||||
"from langchain_openai import OpenAIEmbeddings\n",
|
||||
"\n",
|
||||
"Now, we can query the vectorstore. There a few methods to do this. The most standard is to use `similarity_search`."
|
||||
"embeddings = OpenAIEmbeddings(model=\"text-embedding-3-large\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "5eabdb75",
|
||||
"id": "dc37144c-208d-4ab3-9f3a-0407a69fe052",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
|
||||
"docs = db.similarity_search(query)"
|
||||
"import faiss\n",
|
||||
"from langchain_community.docstore.in_memory import InMemoryDocstore\n",
|
||||
"from langchain_community.vectorstores import FAISS\n",
|
||||
"\n",
|
||||
"index = faiss.IndexFlatL2(len(embeddings.embed_query(\"hello world\")))\n",
|
||||
"\n",
|
||||
"vector_store = FAISS(\n",
|
||||
" embedding_function=embeddings,\n",
|
||||
" index=index,\n",
|
||||
" docstore=InMemoryDocstore(),\n",
|
||||
" index_to_docstore_id={},\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "d8761614",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Manage vector store\n",
|
||||
"\n",
|
||||
"### Add items to vector store"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "4b172de8",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"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": "6d9286c2-0802-4f02-8f9a-9f7fae7c79b0",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## As a Retriever\n",
|
||||
"\n",
|
||||
"We can also convert the vectorstore into a [Retriever](/docs/how_to#retrievers) class. This allows us to easily use it in other LangChain methods, which largely work with retrievers"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "6e91b475-3878-44e0-8720-98d903754b46",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"retriever = db.as_retriever()\n",
|
||||
"docs = retriever.invoke(query)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "046739d2-91fe-4101-8b72-c0bcdd9e02b9",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"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 distance score of the query to them. The returned distance score is L2 distance. Therefore, a lower score is better."
|
||||
]
|
||||
},
|
||||
{
|
||||
"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",
|
||||
"id": "3867e154",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"(Document(page_content='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\\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.', metadata={'source': '../../how_to/state_of_the_union.txt'}),\n",
|
||||
" 0.36913747)"
|
||||
"['22f5ce99-cd6f-4e0c-8dab-664128307c72',\n",
|
||||
" 'dc3f061b-5f88-4fa1-a966-413550c51891',\n",
|
||||
" 'd33d890b-baad-47f7-b7c1-175f5f7b4e59',\n",
|
||||
" '6e6c01d2-6020-4a7b-95da-ef43d43f01b5',\n",
|
||||
" 'e677223d-ad75-4c1a-bef6-b5912bd1de03',\n",
|
||||
" '47e2a168-6462-4ed2-b1d9-d9edfd7391d6',\n",
|
||||
" '1e4d66d6-e155-4891-9212-f7be97f36c6a',\n",
|
||||
" 'c0663096-e1a5-4665-b245-1c2e6c4fb653',\n",
|
||||
" '8297474a-7f7c-4006-9865-398c1781b1bc',\n",
|
||||
" '44e4be03-0a8d-4316-b3c4-f35f4bb2b532']"
|
||||
]
|
||||
},
|
||||
"execution_count": 8,
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"docs_and_scores[0]"
|
||||
"from uuid import uuid4\n",
|
||||
"\n",
|
||||
"from langchain_core.documents import Document\n",
|
||||
"\n",
|
||||
"document_1 = Document(\n",
|
||||
" page_content=\"I had chocalate chip pancakes and scrambled eggs for breakfast this morning.\",\n",
|
||||
" metadata={\"source\": \"tweet\"},\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"document_2 = Document(\n",
|
||||
" page_content=\"The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees.\",\n",
|
||||
" metadata={\"source\": \"news\"},\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"document_3 = Document(\n",
|
||||
" page_content=\"Building an exciting new project with LangChain - come check it out!\",\n",
|
||||
" metadata={\"source\": \"tweet\"},\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"document_4 = Document(\n",
|
||||
" page_content=\"Robbers broke into the city bank and stole $1 million in cash.\",\n",
|
||||
" metadata={\"source\": \"news\"},\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"document_5 = Document(\n",
|
||||
" page_content=\"Wow! That was an amazing movie. I can't wait to see it again.\",\n",
|
||||
" metadata={\"source\": \"tweet\"},\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"document_6 = Document(\n",
|
||||
" page_content=\"Is the new iPhone worth the price? Read this review to find out.\",\n",
|
||||
" metadata={\"source\": \"website\"},\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"document_7 = Document(\n",
|
||||
" page_content=\"The top 10 soccer players in the world right now.\",\n",
|
||||
" metadata={\"source\": \"website\"},\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"document_8 = Document(\n",
|
||||
" page_content=\"LangGraph is the best framework for building stateful, agentic applications!\",\n",
|
||||
" metadata={\"source\": \"tweet\"},\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"document_9 = Document(\n",
|
||||
" page_content=\"The stock market is down 500 points today due to fears of a recession.\",\n",
|
||||
" metadata={\"source\": \"news\"},\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"document_10 = Document(\n",
|
||||
" page_content=\"I have a bad feeling I am going to get deleted :(\",\n",
|
||||
" metadata={\"source\": \"tweet\"},\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"documents = [\n",
|
||||
" document_1,\n",
|
||||
" document_2,\n",
|
||||
" document_3,\n",
|
||||
" document_4,\n",
|
||||
" document_5,\n",
|
||||
" document_6,\n",
|
||||
" document_7,\n",
|
||||
" document_8,\n",
|
||||
" document_9,\n",
|
||||
" document_10,\n",
|
||||
"]\n",
|
||||
"uuids = [str(uuid4()) for _ in range(len(documents))]\n",
|
||||
"\n",
|
||||
"vector_store.add_documents(documents=documents, ids=uuids)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f34420cf",
|
||||
"id": "a410a2dc",
|
||||
"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."
|
||||
"### Delete items from vector store"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "b558ebb7",
|
||||
"execution_count": 4,
|
||||
"id": "c3db04bd",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"True"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"vector_store.delete(ids=[uuids[-1]])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "77de24ff",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Query vector store\n",
|
||||
"\n",
|
||||
"Once your vector store has been created and the relevant documents have been added you will most likely wish to query it during the running of your chain or agent. \n",
|
||||
"\n",
|
||||
"### Query directly\n",
|
||||
"\n",
|
||||
"#### Similarity search\n",
|
||||
"\n",
|
||||
"Performing a simple similarity search with filtering on metadata can be done as follows:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "53d95d3f",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"* Building an exciting new project with LangChain - come check it out! [{'source': 'tweet'}]\n",
|
||||
"* LangGraph is the best framework for building stateful, agentic applications! [{'source': 'tweet'}]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"results = vector_store.similarity_search(\n",
|
||||
" \"LangChain provides abstractions to make working with LLMs easy\",\n",
|
||||
" k=2,\n",
|
||||
" filter={\"source\": \"tweet\"},\n",
|
||||
")\n",
|
||||
"for res in results:\n",
|
||||
" print(f\"* {res.page_content} [{res.metadata}]\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5ae35069",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Similarity search with score\n",
|
||||
"\n",
|
||||
"You can also search with score:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "a9078ce9",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"* [SIM=0.893688] The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees. [{'source': 'news'}]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"results = vector_store.similarity_search_with_score(\n",
|
||||
" \"Will it be hot tomorrow?\", k=1, filter={\"source\": \"news\"}\n",
|
||||
")\n",
|
||||
"for res, score in results:\n",
|
||||
" print(f\"* [SIM={score:3f}] {res.page_content} [{res.metadata}]\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "e9091b1f",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Other search methods\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"There are a variety of other ways to search a FAISS vector store. For a complete list of those methods, please refer to the [API Reference](https://api.python.langchain.com/en/latest/vectorstores/langchain_community.vectorstores.faiss.FAISS.html)\n",
|
||||
"\n",
|
||||
"### Query by turning into retriever\n",
|
||||
"\n",
|
||||
"You can also transform the vector store into a retriever for easier usage in your chains. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "10da64fa",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(metadata={'source': 'news'}, page_content='Robbers broke into the city bank and stole $1 million in cash.')]"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"retriever = vector_store.as_retriever(search_type=\"mmr\", search_kwargs={\"k\": 1})\n",
|
||||
"retriever.invoke(\"Stealing from the bank is a crime\", filter={\"source\": \"news\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5edd1909",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Chain usage\n",
|
||||
"\n",
|
||||
"The code below shows how to use the vector store as a retriever in a simple RAG chain:\n",
|
||||
"\n",
|
||||
"```{=mdx}\n",
|
||||
"import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
|
||||
"\n",
|
||||
"<ChatModelTabs customVarName=\"llm\" />\n",
|
||||
"```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "6b792eaa",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embedding_vector = embeddings.embed_query(query)\n",
|
||||
"docs_and_scores = db.similarity_search_by_vector(embedding_vector)"
|
||||
"# | output: false\n",
|
||||
"# | echo: false\n",
|
||||
"from langchain_openai import ChatOpenAI\n",
|
||||
"\n",
|
||||
"llm = ChatOpenAI(model=\"gpt-4o-mini\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "1aca9435",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'LangGraph is used for building stateful, agentic applications. It provides a framework that facilitates the development of these types of applications.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain import hub\n",
|
||||
"from langchain_core.output_parsers import StrOutputParser\n",
|
||||
"from langchain_core.runnables import RunnablePassthrough\n",
|
||||
"\n",
|
||||
"prompt = hub.pull(\"rlm/rag-prompt\")\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def format_docs(docs):\n",
|
||||
" return \"\\n\\n\".join(doc.page_content for doc in docs)\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"rag_chain = (\n",
|
||||
" {\"context\": retriever | format_docs, \"question\": RunnablePassthrough()}\n",
|
||||
" | prompt\n",
|
||||
" | llm\n",
|
||||
" | StrOutputParser()\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"rag_chain.invoke(\"What is LangGraph used for?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -280,31 +435,33 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 11,
|
||||
"id": "1b31fe27-e0b3-42c6-b17c-8270b517ee1f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"db.save_local(\"faiss_index\")\n",
|
||||
"vector_store.save_local(\"faiss_index\")\n",
|
||||
"\n",
|
||||
"new_db = FAISS.load_local(\"faiss_index\", embeddings)\n",
|
||||
"new_vector_store = FAISS.load_local(\n",
|
||||
" \"faiss_index\", embeddings, allow_dangerous_deserialization=True\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"docs = new_db.similarity_search(query)"
|
||||
"docs = new_vector_store.similarity_search(\"qux\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"execution_count": 12,
|
||||
"id": "98378c4e",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"Document(page_content='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\\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.', metadata={'source': '../../../state_of_the_union.txt'})"
|
||||
"Document(metadata={'source': 'tweet'}, page_content='Building an exciting new project with LangChain - come check it out!')"
|
||||
]
|
||||
},
|
||||
"execution_count": 9,
|
||||
"execution_count": 12,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -313,33 +470,6 @@
|
||||
"docs[0]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "30c8f57b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Serializing and De-Serializing to bytes\n",
|
||||
"\n",
|
||||
"you can pickle the FAISS Index by these functions. If you use embeddings model which is of 90 mb (sentence-transformers/all-MiniLM-L6-v2 or any other model), the resultant pickle size would be more than 90 mb. the size of the model is also included in the overall size. To overcome this, use the below functions. These functions only serializes FAISS index and size would be much lesser. this can be helpful if you wish to store the index in database like sql."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "d8faead5",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_huggingface import HuggingFaceEmbeddings\n",
|
||||
"\n",
|
||||
"pkl = db.serialize_to_bytes() # serializes the faiss\n",
|
||||
"embeddings = HuggingFaceEmbeddings(model_name=\"all-MiniLM-L6-v2\")\n",
|
||||
"\n",
|
||||
"db = FAISS.deserialize_from_bytes(\n",
|
||||
" embeddings=embeddings, serialized=pkl\n",
|
||||
") # Load the index"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "57da60d4",
|
||||
@@ -351,10 +481,21 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 13,
|
||||
"id": "9b8f5e31-3f40-4e94-8d97-5883125efba7",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'b752e805-350e-4cf5-ba54-0883d46a3a44': Document(page_content='foo')}"
|
||||
]
|
||||
},
|
||||
"execution_count": 13,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"db1 = FAISS.from_texts([\"foo\"], embeddings)\n",
|
||||
"db2 = FAISS.from_texts([\"bar\"], embeddings)\n",
|
||||
@@ -364,17 +505,17 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"execution_count": 14,
|
||||
"id": "83392605",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'807e0c63-13f6-4070-9774-5c6f0fbb9866': Document(page_content='bar', metadata={})}"
|
||||
"{'08192d92-746d-4cd1-b681-bdfba411f459': Document(page_content='bar')}"
|
||||
]
|
||||
},
|
||||
"execution_count": 10,
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -385,7 +526,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"execution_count": 15,
|
||||
"id": "a3fcc1c7",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@@ -395,18 +536,18 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"execution_count": 16,
|
||||
"id": "41c51f89",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'068c473b-d420-487a-806b-fb0ccea7f711': Document(page_content='foo', metadata={}),\n",
|
||||
" '807e0c63-13f6-4070-9774-5c6f0fbb9866': Document(page_content='bar', metadata={})}"
|
||||
"{'b752e805-350e-4cf5-ba54-0883d46a3a44': Document(page_content='foo'),\n",
|
||||
" '08192d92-746d-4cd1-b681-bdfba411f459': Document(page_content='bar')}"
|
||||
]
|
||||
},
|
||||
"execution_count": 13,
|
||||
"execution_count": 16,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -417,169 +558,12 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f4294b96",
|
||||
"id": "65654d80",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Similarity Search with filtering\n",
|
||||
"FAISS vectorstore can also support filtering, since the FAISS does not natively support filtering we have to do it manually. This is done by first fetching more results than `k` and then filtering them. This filter is either a callble that takes as input a metadata dict and returns a bool, or a metadata dict where each missing key is ignored and each present k must be in a list of values. You can also set the `fetch_k` parameter when calling any search method to set how many documents you want to fetch before filtering. Here is a small example:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"id": "d5bf812c",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Content: foo, Metadata: {'page': 1}, Score: 5.159960813797904e-15\n",
|
||||
"Content: foo, Metadata: {'page': 2}, Score: 5.159960813797904e-15\n",
|
||||
"Content: foo, Metadata: {'page': 3}, Score: 5.159960813797904e-15\n",
|
||||
"Content: foo, Metadata: {'page': 4}, Score: 5.159960813797904e-15\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain_core.documents import Document\n",
|
||||
"## API reference\n",
|
||||
"\n",
|
||||
"list_of_documents = [\n",
|
||||
" Document(page_content=\"foo\", metadata=dict(page=1)),\n",
|
||||
" Document(page_content=\"bar\", metadata=dict(page=1)),\n",
|
||||
" Document(page_content=\"foo\", metadata=dict(page=2)),\n",
|
||||
" Document(page_content=\"barbar\", metadata=dict(page=2)),\n",
|
||||
" Document(page_content=\"foo\", metadata=dict(page=3)),\n",
|
||||
" Document(page_content=\"bar burr\", metadata=dict(page=3)),\n",
|
||||
" Document(page_content=\"foo\", metadata=dict(page=4)),\n",
|
||||
" Document(page_content=\"bar bruh\", metadata=dict(page=4)),\n",
|
||||
"]\n",
|
||||
"db = FAISS.from_documents(list_of_documents, embeddings)\n",
|
||||
"results_with_scores = db.similarity_search_with_score(\"foo\")\n",
|
||||
"for doc, score in results_with_scores:\n",
|
||||
" print(f\"Content: {doc.page_content}, Metadata: {doc.metadata}, Score: {score}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "3d33c126",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Now we make the same query call but we filter for only `page = 1` "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"id": "83159330",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Content: foo, Metadata: {'page': 1}, Score: 5.159960813797904e-15\n",
|
||||
"Content: bar, Metadata: {'page': 1}, Score: 0.3131446838378906\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"results_with_scores = db.similarity_search_with_score(\"foo\", filter=dict(page=1))\n",
|
||||
"# Or with a callable:\n",
|
||||
"# results_with_scores = db.similarity_search_with_score(\"foo\", filter=lambda d: d[\"page\"] == 1)\n",
|
||||
"for doc, score in results_with_scores:\n",
|
||||
" print(f\"Content: {doc.page_content}, Metadata: {doc.metadata}, Score: {score}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "0be136e0",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Same thing can be done with the `max_marginal_relevance_search` as well."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 16,
|
||||
"id": "432c6980",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Content: foo, Metadata: {'page': 1}\n",
|
||||
"Content: bar, Metadata: {'page': 1}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"results = db.max_marginal_relevance_search(\"foo\", filter=dict(page=1))\n",
|
||||
"for doc in results:\n",
|
||||
" print(f\"Content: {doc.page_content}, Metadata: {doc.metadata}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1b4ecd86",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Here is an example of how to set `fetch_k` parameter when calling `similarity_search`. Usually you would want the `fetch_k` parameter >> `k` parameter. This is because the `fetch_k` parameter is the number of documents that will be fetched before filtering. If you set `fetch_k` to a low number, you might not get enough documents to filter from."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 17,
|
||||
"id": "1fd60fd1",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Content: foo, Metadata: {'page': 1}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"results = db.similarity_search(\"foo\", filter=dict(page=1), k=1, fetch_k=4)\n",
|
||||
"for doc in results:\n",
|
||||
" print(f\"Content: {doc.page_content}, Metadata: {doc.metadata}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1becca53",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Delete\n",
|
||||
"\n",
|
||||
"You can also delete records from vectorstore. In the example below `db.index_to_docstore_id` represents a dictionary with elements of the FAISS index."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 18,
|
||||
"id": "1408b870",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"count before: 8\n",
|
||||
"count after: 7"
|
||||
]
|
||||
},
|
||||
"execution_count": 18,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(\"count before:\", db.index.ntotal)\n",
|
||||
"db.delete([db.index_to_docstore_id[0]])\n",
|
||||
"print(\"count after:\", db.index.ntotal)"
|
||||
"For detailed documentation of all `FAISS` vector store features and configurations head to the API reference: https://api.python.langchain.com/en/latest/vectorstores/langchain_community.vectorstores.faiss.FAISS.html"
|
||||
]
|
||||
}
|
||||
],
|
||||
@@ -599,7 +583,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.1"
|
||||
"version": "3.11.9"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
Reference in New Issue
Block a user