Chroma (vector database)

From Wikipedia the free encyclopedia

Chroma
Developer(s)Chroma
Initial releaseOctober 22, 2022; 2 years ago (2022-10-22)
Stable release
v1.0.12 / May 30, 2025; 18 days ago (2025-05-30).:[1]
Repositorygithub.com/chroma-core/chroma
Written inRust, Python, TypeScript, Go
Operating systemLinux, macOS, Windows
Platformx86
TypeVector database
LicenseApache License 2.0
Websitetrychroma.com

Chroma or ChromaDB is an open-source vector database tailored to applications with large language models.[2]

Its headquarters are in San Francisco. In April 2023, it raised 18 million US dollars as seed funding.[3]

ChromaDB has been used in academic studies on artificial intelligence, particularly as part of the tech stack for retrieval-augmented generation.[4][5]

References

[edit]
  1. ^ "Release notes for Chroma v1.0.12". GitHub.
  2. ^ MSV, Janakiram (July 28, 2023). "Exploring Chroma: The Open Source Vector Database for LLMs". The New Stack. Retrieved July 31, 2024.
  3. ^ "Chroma funding: Database provider raises $18M for AI-Powered Database". SiliconANGLE. April 6, 2023. Retrieved July 31, 2024.
  4. ^ Toro, Sabrina; Anagnostopoulos, Anna V.; Bello, Sue; Blumberg, Kai; Cameron, Rhiannon; Carmody, Leigh; Diehl, Alexander D.; Dooley, Damion; Duncan, William (June 12, 2024), "Dynamic Retrieval Augmented Generation of Ontologies using Artificial Intelligence (DRAGON-AI)", Journal of Biomedical Semantics, 15 (1): 19, arXiv:2312.10904, doi:10.1186/s13326-024-00320-3, PMC 11484368, PMID 39415214
  5. ^ Caspari, Laura; Dastidar, Kanishka Ghosh; Zerhoudi, Saber; Mitrovic, Jelena; Granitzer, Michael (July 11, 2024), Beyond Benchmarks: Evaluating Embedding Model Similarity for Retrieval Augmented Generation Systems, arXiv:2407.08275
[edit]