Metadata Arrays

Chroma now supports regular expression filtering via $regex and $not_regex operators in the where_document field, allowing users to search and filter collection documents by pattern — such as finding function definitions, email addresses, or URLs. Available through the Python API and the Chroma Cloud UI.

Jun 24, 2025

Chroma Sync is a new Chroma Cloud feature that automatically handles chunking, embedding, and indexing of external data sources. The initial launch supports GitHub, using collection forking to process only diffs between commits rather than entire repositories. Enables version-aware retrieval at specific commits or branches, designed to support background agents and automated CI/CD workflows. More data sources to follow.

Oct 22, 2025

Chroma Cloud can now automatically crawl and index websites. Users supply a starting URL and Chroma handles scraping, converting pages to markdown, chunking via Tree-sitter, and generating embeddings — no custom ingestion pipeline required. The resulting collections support hybrid search blending dense embeddings for semantic matching with BM25 sparse vectors for keyword precision. Designed for product docs, blogs, and support pages.

Nov 4, 2025

Chroma Sync, Chroma Cloud's serverless ingestion service, now supports Amazon S3, GitHub repositories, and web crawling as data sources. The service handles parsing, chunking, and embedding automatically with queue-based retries and rate-limit awareness. Amazon S3 supports PDFs, images, and code with optional auto-sync; GitHub uses collection forking for efficient incremental updates; web uses a JavaScript-capable crawler with configurable depth. Pricing starts at $0.04/GiB processed.

Mar 3, 2026