How to beginner · 3 min read

How to use FAISS with LangChain

Q: How to use FAISS with LangChain

Use FAISS from langchain_community.vectorstores to create a vector store with embeddings generated by OpenAIEmbeddings. Load documents, embed them, and index with FAISS for efficient similarity search within LangChain.

Quick answer

Use FAISS from langchain_community.vectorstores to create a vector store with embeddings generated by OpenAIEmbeddings. Load documents, embed them, and index with FAISS for efficient similarity search within LangChain.

PREREQUISITES

Python 3.8+
OpenAI API key (free tier works)
pip install langchain_openai langchain_community faiss-cpu openai

Setup

Install the required packages and set your OpenAI API key as an environment variable.

bash

pip install langchain_openai langchain_community faiss-cpu openai

Step by step

This example loads text documents, creates embeddings with OpenAI, indexes them with FAISS, and performs a similarity search.

python

import os
from langchain_openai import OpenAIEmbeddings
from langchain_community.vectorstores import FAISS
from langchain_community.document_loaders import TextLoader

# Set your OpenAI API key in environment variable before running
# export OPENAI_API_KEY='your_api_key'

# Load documents from text files
loader = TextLoader("example_docs/doc1.txt")
docs = loader.load()

# Initialize OpenAI embeddings
embeddings = OpenAIEmbeddings(openai_api_key=os.environ["OPENAI_API_KEY"])

# Create FAISS vector store from documents
vectorstore = FAISS.from_documents(docs, embeddings)

# Query vector store
query = "What is LangChain?"
results = vectorstore.similarity_search(query, k=3)

for i, doc in enumerate(results, 1):
    print(f"Result {i}: {doc.page_content}")

output

Result 1: LangChain is a framework for developing applications powered by language models.
Result 2: LangChain helps you build chatbots, question answering systems, and more.
Result 3: It integrates with vector stores like FAISS for semantic search.

Common variations

Use different embedding models by swapping OpenAIEmbeddings with other LangChain embeddings.
Use FAISS.load_local() and save_local() to persist the index.
Integrate with async LangChain chains for asynchronous workflows.

python

from langchain_community.vectorstores import FAISS

# Save FAISS index locally
vectorstore.save_local("faiss_index")

# Load FAISS index later
loaded_vectorstore = FAISS.load_local("faiss_index", embeddings)

Troubleshooting

If you get import errors for faiss, ensure you installed faiss-cpu or faiss-gpu correctly.
Check your OpenAI API key is set in os.environ["OPENAI_API_KEY"].
For large document sets, increase FAISS index parameters or use approximate nearest neighbor settings.

✅

Key Takeaways

Use FAISS.from_documents() with OpenAIEmbeddings to build a vector store in LangChain.
Persist your FAISS index locally with save_local() and load_local() for reuse.
Ensure faiss-cpu is installed to avoid import errors.
Customize embeddings or indexing parameters for different use cases.
LangChain's modular design makes it easy to swap vector stores or embedding models.

Verified 2026-04 · gpt-4o, OpenAIEmbeddings

Verify ↗