https://github.com/chroma-core/chroma
the AI-native open-source embedding database
https://github.com/chroma-core/chroma
document-retrieval embeddings llms
Last synced: 8 days ago
JSON representation
the AI-native open-source embedding database
- Host: GitHub
- URL: https://github.com/chroma-core/chroma
- Owner: chroma-core
- License: apache-2.0
- Created: 2022-10-05T17:58:44.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2025-05-12T14:42:18.000Z (11 months ago)
- Last Synced: 2025-05-12T15:54:11.409Z (11 months ago)
- Topics: document-retrieval, embeddings, llms
- Language: Rust
- Homepage: https://www.trychroma.com/
- Size: 515 MB
- Stars: 19,793
- Watchers: 110
- Forks: 1,610
- Open Issues: 492
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- Awesome-LLM-Productization - ChromaDB - open-source embedding database (Python based - in-memory only at the moment) (Models and Tools / Vector Store)
- best-of-ai-open-source - GitHub - 32% open ยท โฑ๏ธ 06.01.2025): (Vector Databases & Search)
- awesome-python - chromadb - An open-source embedding database for building AI applications with embeddings and semantic search. (Database)
- Awesome-RAG-Production - Chroma - scale | Developer-friendly, open-source embedding database. | (๐๏ธ Vector Databases / 3. The Enterprise / High-Scale Stack (The 1%))
- awesome-mlops - Chroma
- awesome-vector-database - Chroma - AI memory with semantic, full-text, & regex search (Multidimensional data / Vectors)
- awesome-llmops - Chroma - core/chroma.svg?style=flat-square) | (Search / Vector search)
- awesome-chatgpt - chroma - native open-source embedding database (Embeddings/Vector Databases / Emacs)
- StarryDivineSky - chroma-core/chroma
- awesome-generative-ai-data-scientist - ChromaDB - core/chroma) | (Vector Databases (RAG))
- awesome-production-machine-learning - Chroma - core/chroma.svg?style=social) - Chroma is an open-source embedding database. (Data Storage Optimisation)
- awesomeLibrary - chroma - the AI-native open-source embedding database (่ฏญ่จ่ตๆบๅบ / rust)
- awesome-multimodal-search - GitHub
- awesome-vector-databases - Chroma - Chroma is an open-source AI-native vector database that provides semantic, full-text, and regex search as a memory layer for LLM and RAG applications. ([Read more](/details/chroma.md)) (Curated Resource Lists)
- awesome-ai-agents - chroma-core/chroma - Chroma is an open-source search and retrieval database specifically engineered for AI applications, supporting embeddings, vector storage, and RAG. (Corporate and Analytical Applications / RAG and Business Analytics)
- Awesome-RAG - Chroma DB - native open-source embedding database. (๐พ Databases / Vector Databases:)
- awesome-ai-agents-2026 - Chroma
- awesome-local-ai - Chroma - Open-source embedding database (Advanced Topics / RAG & Document Search)
- awesome-vector-database - Chroma - ็ฎๅๆ็จ็ๅผๆบๅ้ๆฐๆฎๅบ๏ผ้ๅๅฟซ้ๅผๅๅๅฐ่งๆจกๅบ็จใ (๐ ๅ้ๆ็ดขๅบ & ๅผๆ)
- AiTreasureBox - chroma-core/chroma - 11-03_24198_1](https://img.shields.io/github/stars/chroma-core/chroma.svg) |the AI-native open-source embedding database| (Repos)
- my-awesome - chroma-core/chroma - agents,database,rust,rust-lang pushed_at:2026-04 star:27.1k fork:2.2k Data infrastructure for AI (Rust)
- Awesome-LLM-VLM-Foundation-Models - Chroma
- awesome-ai - ๐
- awesome-rust-python - chroma - Search and retrieval database for AI applications. (Machine Learning & AI)
- awesome-ai-agents - ChromaDB - core/chroma) | Vector DB for memory/context | (โ๏ธ Agent Operations / ๐ง Memory)
- Awesome-RAG - Chroma - native open-source embedding database. | [](https://github.com/chroma-core/chroma/stargazers) | (Vector Stores / GraphRAG Tutorials)
- llmops - Chroma - native embedding database |  | (Vector Search & RAG / Resources)
- fucking-awesome-python - chromadb - An open-source embedding database for building AI applications with embeddings and semantic search. (Database)
- awesome-rag-study - Chroma
- awesome-ai-agents - ChromaDB
- awesome-ai - Chroma - source embedding database. Chroma makes it easy to build LLM apps by making knowledge, facts, and skills pluggable for LLMs. |  | (Vector Database)
- awesome-rag - Chroma - Open-source embedding database for LLM applications (Vector DBs & Search Engines / Other Tools)
- awesome-vector-search - Chroma - The open-source embedding database for building LLM apps in Python or JavaScript with memory
- Awesome-LLMOps - chroma - native open-source embedding database.    (Runtime / Database)
- awesome-ccamel - chroma-core/chroma - Data infrastructure for AI (Rust)
README
Chroma - the open-source data infrastructure for AI.
```bash
pip install chromadb # python client
# for javascript, npm install chromadb!
# for client-server mode, chroma run --path /chroma_db_path
```
## Chroma Cloud
Our hosted service, Chroma Cloud, powers serverless vector, hybrid, and full-text search. It's extremely fast, cost-effective, scalable and painless. Create a DB and try it out in under 30 seconds with $5 of free credits.
[Get started with Chroma Cloud](https://trychroma.com/signup)
## API
The core API is only 4 functions (run our [๐ก Google Colab](https://colab.research.google.com/drive/1QEzFyqnoFxq7LUGyP1vzR4iLt9PpCDXv?usp=sharing)):
```python
import chromadb
# setup Chroma in-memory, for easy prototyping. Can add persistence easily!
client = chromadb.Client()
# Create collection. get_collection, get_or_create_collection, delete_collection also available!
collection = client.create_collection("all-my-documents")
# Add docs to the collection. Can also update and delete. Row-based API coming soon!
collection.add(
documents=["This is document1", "This is document2"], # we handle tokenization, embedding, and indexing automatically. You can skip that and add your own embeddings as well
metadatas=[{"source": "notion"}, {"source": "google-docs"}], # filter on these!
ids=["doc1", "doc2"], # unique for each doc
)
# Query/search 2 most similar results. You can also .get by id
results = collection.query(
query_texts=["This is a query document"],
n_results=2,
# where={"metadata_field": "is_equal_to_this"}, # optional filter
# where_document={"$contains":"search_string"} # optional filter
)
```
Learn about all features on our [Docs](https://docs.trychroma.com)
## Get involved
Chroma is a rapidly developing project. We welcome PR contributors and ideas for how to improve the project.
- [Join the conversation on Discord](https://discord.com/invite/chromadb) - `#contributing` channel
- [Review the ๐ฃ๏ธ Roadmap and contribute your ideas](https://docs.trychroma.com/docs/overview/oss#roadmap)
- [Grab an issue and open a PR](https://github.com/chroma-core/chroma/issues) - [`Good first issue tag`](https://github.com/chroma-core/chroma/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22)
- [Read our contributing guide](https://docs.trychroma.com/docs/overview/oss#contributing)
**Release Cadence**
We currently release new tagged versions of the `pypi` and `npm` packages on Mondays. Hotfixes go out at any time during the week.
## License
[Apache 2.0](./LICENSE)
