How to beginner · 3 min read

How to create vector store in LangChain

Q: How to create vector store in LangChain

Use OpenAIEmbeddings to generate vector embeddings and FAISS from langchain_community.vectorstores to create a vector store. Load your documents, embed them, and then build the vector store for semantic search.

Quick answer

Use OpenAIEmbeddings to generate vector embeddings and FAISS from langchain_community.vectorstores to create a vector store. Load your documents, embed them, and then build the vector store for semantic search.

PREREQUISITES

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

Setup

Install the required packages and set your OpenAI API key in the environment variables.

Install packages: pip install langchain_openai langchain_community faiss-cpu
Set environment variable: export OPENAI_API_KEY='your_api_key' (Linux/macOS) or setx OPENAI_API_KEY "your_api_key" (Windows)

bash

pip install langchain_openai langchain_community faiss-cpu

Step by step

This example loads text documents, creates OpenAI embeddings, and builds a FAISS vector store for semantic search.

python

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

# Load documents from local text files
loader = TextLoader("example.txt")
docs = loader.load()

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

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

# Save the vector store locally
vector_store.save_local("faiss_index")

# Example query: search top 3 relevant docs
query = "What is LangChain?"
results = vector_store.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 building applications with LLMs.
Result 2: LangChain supports vector stores for semantic search.
Result 3: You can create vector stores using FAISS and OpenAI embeddings.

Common variations

Use other vector stores like Chroma or Weaviate instead of FAISS.
Use different embedding models by swapping OpenAIEmbeddings with other providers.
Load documents from PDFs or other formats using PyPDFLoader or custom loaders.
Use async methods if your environment supports it.

Troubleshooting

If you get ModuleNotFoundError, ensure faiss-cpu is installed correctly.
If embeddings fail, verify your OPENAI_API_KEY is set and valid.
For large document sets, consider batching embeddings to avoid rate limits.
If similarity search returns empty, check document loading and embedding steps.

✅

Key Takeaways

Use OpenAIEmbeddings with FAISS to create efficient vector stores in LangChain.
Load documents with LangChain loaders like TextLoader or PyPDFLoader before embedding.
Save and reuse vector stores locally to optimize performance and avoid recomputing embeddings.
Swap vector stores or embedding models easily to fit your use case.
Ensure environment variables and dependencies are correctly set to avoid common errors.

Verified 2026-04 · gpt-4o, OpenAIEmbeddings

Verify ↗