# Chroma — Open-Source Vector Database for AI

> Chroma is the open-source vector database and data infrastructure for AI applications. 27.1K+ GitHub stars. Simple 4-function API for embedding, storing, and querying documents. Supports Python, JavaS

## Install

Save in your project root:

## Quick Use

```bash
# Install Python client
pip install chromadb

# Or JavaScript
npm install chromadb

# Quick start
python -c "
import chromadb
client = chromadb.Client()
collection = client.create_collection('docs')
collection.add(documents=['AI is amazing', 'Vector search is fast'], ids=['1', '2'])
results = collection.query(query_texts=['artificial intelligence'], n_results=1)
print(results)
"
```

---

## Intro

Chroma is the open-source data infrastructure for AI — a vector database designed to make it easy to build AI applications with embeddings. With 27,100+ GitHub stars and Apache 2.0 license, Chroma provides a simple 4-function API: create a collection, add documents, query by similarity, and retrieve by ID. It handles tokenization, embedding, and indexing automatically. Chroma supports Python, JavaScript/TypeScript, Go, and Rust clients, and offers both local and cloud deployment options.

**Best for**: Developers building RAG pipelines, semantic search, or any AI app that needs vector similarity search
**Works with**: Claude Code, OpenAI Codex, Cursor, Gemini CLI, Windsurf
**Clients**: Python, JavaScript/TypeScript, Go, Rust

---

## Key Features

- **Simple 4-function API**: create_collection, add, query, get — no complex setup
- **Automatic embedding**: Built-in tokenization and embedding, or bring your own
- **Metadata filtering**: Filter queries by document metadata and content
- **Multi-language clients**: Python, JavaScript/TypeScript, Go, Rust
- **Local or cloud**: Run embedded in your app or deploy as a server
- **Chroma Cloud**: Serverless vector, hybrid, and full-text search

---

### FAQ

**Q: What is Chroma?**
A: Chroma is an open-source vector database with 27.1K+ stars for building AI applications. It provides automatic embedding, similarity search, and metadata filtering through a simple 4-function API. Apache 2.0 licensed.

**Q: How do I install Chroma?**
A: Run `pip install chromadb` for Python or `npm install chromadb` for JavaScript. No external dependencies required for local use.

**Q: How does Chroma compare to Pinecone or Weaviate?**
A: Chroma is fully open-source (Apache 2.0) and can run embedded in your application with zero infrastructure. Pinecone is cloud-only and proprietary. Weaviate is also open-source but heavier to deploy.

---

## Source & Thanks

> Created by [Chroma](https://github.com/chroma-core). Licensed under Apache 2.0.
> [chroma-core/chroma](https://github.com/chroma-core/chroma) — 27,100+ GitHub stars

---
Source: https://tokrepo.com/en/workflows/04367306-be4a-4f46-854d-dd2b4d0d429e
Author: AI Open Source