Chroma DB
Open-source search and retrieval database for AI applications.
Cost / License
- Freemium (Pay once or Subscription)
- Open Source (Apache-2.0)
Platforms
- Online
- Software as a Service (SaaS)
- Python
Features
Properties
- Scalable
Features
- File Versioning
- Command line interface
- Full-Text Search
- Vector Database
- Serverless
- Search metadata
- Support for regular expressions
- A/B Testing
Tags
- Database
- information-retrieval
- vector-search
Chroma DB News & Activities
Recent activities
POX added Chroma DB as alternative to Meilisearch, Algolia, Elasticsearch and OpenSearch- POX added Chroma DB
Chroma DB information
Developed by
Chroma Inc. Licensing
Open Source (Apache-2.0) and Freemium product.Pricing
One time purchase ranging between $4 and $9827, and / or subscription that costs $250 per month + free version with limited functionality.Written in
Alternatives
52 alternatives listedSupported Languages
- English
AlternativeTo Categories
Business & Commerce, Development, OS & UtilitiesGitHub repository
- 25,597 Stars
- 2,006 Forks
- 482 Open Issues
- Updated
What is Chroma DB?
Build AI applications that know, learn, and search — intelligently.
Fast, serverless, and scalable search platform supporting vector, full-text, regex, and metadata search. Built on object storage and trusted by millions of developers. Open-source Apache 2.0.
- Vector search: Semantic similarity search
- Sparse vector search: Lexical search (BM25, SPLADE)
- Full-text Search: Trigram and regex search
- Metadata Search: Filtering and faceted search
- Forking: Dataset versioning, A/B testing, and roll-outs
- CLI: Command-line tools for development
Performance
Fast search over billions of multi-tenant indexes
Chroma's indexes are built and optimized for object-storage offering unparalleled cost and performance. State-of-the-art vector, full-text, and regex search.
Enterprise
Chroma brings the security, compliance, education and operational model enterprises need with our Apache 2.0 architecture.
BYOC in your VPC, multi-cloud/multi-region replication, point-in-time-recovery ensure a resilient and scalable search system with the same 0-ops story as Cloud.