In the second part of our three-part series on code search, we extend the chunking logic from part one to index an entire repository. We’ll create a workflow that chunks files and stores them in Chroma Collections for each commit, ensuring coding agents can search code relevant to the repository’s current state. We’ll also demonstrate how to use Chroma Cloud’s forking feature to avoid duplicate work and reduce storage overhead during indexing.
—
Chroma is the open-source AI application database. Batteries included.
Embeddings, vector search, document storage, full-text search, metadata filtering, and multi-modal. All in one place. Retrieval that just works. As it should be.
Try it today:
https://trychroma.com/cloud
