How to beginner · 3 min read

How to use Chroma with LangChain

Q: How to use Chroma with LangChain

Use Chroma from langchain_community.vectorstores to create a vector store with document embeddings generated by OpenAIEmbeddings. Load documents, embed them, and query with LangChain's retrieval tools for semantic search.

Quick answer

Use Chroma from langchain_community.vectorstores to create a vector store with document embeddings generated by OpenAIEmbeddings. Load documents, embed them, and query with LangChain's retrieval tools for semantic search.

PREREQUISITES

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

Setup

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

Install packages: pip install langchain_openai langchain_community chromadb openai
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 chromadb openai

Step by step

This example loads text documents, creates embeddings with OpenAI, stores them in Chroma, and performs a semantic search query.

python

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

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

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

# Create Chroma vector store from documents
vectordb = Chroma.from_documents(documents=docs, embedding=embeddings, collection_name="example_collection")

# Query the vector store
query = "What is the main topic of the document?"
results = vectordb.similarity_search(query, k=3)

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

output

Result 1: <relevant text snippet from example_doc.txt>
Result 2: <relevant text snippet from example_doc.txt>
Result 3: <relevant text snippet from example_doc.txt>

Common variations

Use Chroma asynchronously with async methods if your environment supports it.
Switch embeddings to other providers like HuggingFaceEmbeddings by changing the embedding class.
Use different models for embeddings by configuring OpenAIEmbeddings with a specific model parameter.

Troubleshooting

If you get authentication errors, verify your OPENAI_API_KEY environment variable is set correctly.
If documents do not return relevant results, check that the documents are loaded properly and embeddings are generated without errors.
For connection issues with Chroma, ensure the chromadb package is installed and compatible with your Python version.

✅

Key Takeaways

Use Chroma.from_documents with OpenAIEmbeddings to create a vector store for semantic search.
Load documents with TextLoader or other LangChain loaders before embedding.
Set your OpenAI API key in os.environ to authenticate embedding requests.
Chroma supports fast similarity search and integrates seamlessly with LangChain's retrieval interface.
You can customize embeddings and vector store parameters for different use cases.

Verified 2026-04 · gpt-4o, OpenAIEmbeddings

Verify ↗