Chroma is the open-source embedding database. It makes it easy to build AI applications with embeddings — store, search, and retrieve in 4 lines of code.
What You Get for Free
- Simple API — 4 lines to store and search
- Built-in embeddings — auto-embed with sentence-transformers
- Metadata filtering — filter results by metadata
- Persistent storage — SQLite + Parquet backend
- Client/Server mode — embed or run as service
- LangChain/LlamaIndex — first-class integrations
Quick Start
pip install chromadb
Store and Search
import chromadb
client = chromadb.Client()
collection = client.create_collection('docs')
collection.add(
documents=['AI is transforming healthcare', 'Python is great for ML'],
ids=['doc1', 'doc2']
)
results = collection.query(query_texts=['machine learning'], n_results=2)
Chroma auto-embeds your text — no need for external embedding calls.
Chroma vs Pinecone
| Feature | Chroma | Pinecone |
|---|---|---|
| Price | Free (OSS) | Freemium |
| Setup | pip install | Cloud signup |
| Embeddings | Built-in | BYOV |
| Best for | Prototyping + prod | Production cloud |
Need AI app development? Check my work on GitHub or email spinov001@gmail.com for consulting.
Top comments (0)