langchain-chroma

What it is and what it does

langchain-chroma is a bridge package that integrates Chroma vector database with LangChain's ecosystem. It provides a LangChain-compatible vector store interface to Chroma, allowing you to store and retrieve embeddings within LangChain workflows. The package handles the plumbing between LangChain's embedding and retrieval abstractions and Chroma's vector storage engine.

You use it when building retrieval-augmented generation (RAG) systems, semantic search applications, or any LangChain pipeline that needs to persist and query embeddings. It depends on chromadb for the actual vector storage, langchain-core for the integration interface, and numpy for numerical operations. The package is lightweight and focused narrowly on this one integration point.

Use it for:

• Build a RAG chatbot that retrieves relevant documents from a Chroma vector store before generating responses.
• Implement semantic search over a corpus of documents by storing embeddings in Chroma and querying via LangChain.
• Create a memory system for LangChain agents that persists conversation context as embeddings in Chroma.
• Prototype multi-step LLM workflows where intermediate results are stored and retrieved from a vector database.
• Set up a document Q&A system that chunks documents, embeds them with LangChain, and stores them in Chroma for retrieval.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Connects LangChain applications to Chroma, a vector database, enabling semantic search and retrieval-augmented generation workflows.

Yes. This is a straightforward integration package with low install friction, active maintenance, no known vulnerabilities, and permissive licensing. Install it if you are already using LangChain and want to use Chroma as your vector store; it is the standard way to connect the two.

Install

langchain-chroma on PyPI

pip install langchain-chroma

uv add langchain-chroma

poetry add langchain-chroma

Installing langchain-chroma

Before you install

Low friction install with three direct runtime dependencies (chromadb, langchain-core, numpy). Actively maintained as of 2026-08-14 with recent release activity.

License in practice

MIT license permits commercial and private use with minimal restrictions; suitable for most projects.

Quickstart

pip install langchain-chroma

from langchain_chroma import Chroma
from langchain_core.embeddings import Embeddings

vector_store = Chroma(embedding_function=embeddings)

Requires Python 3.10 or later; chromadb must be installed and functional on your system.

Verify before relying

• Whether chromadb requires system-level dependencies or compilation on your target platform
• Specific version compatibility constraints between chromadb and langchain-core beyond what requires_python specifies

Package facts

Evidence: langchain_chroma-1.1.0-py3-none-any.whl

Tags

More Artificial Intelligence packages

Further reading