Chroma For Code Part 1: Chunking a Codebase for Code Search
In the first video of a three part series on code search, we walk through chunking strategies using tree-sitter, a popular parsing library. Chunking is a critical first step in building fast and efficient code search for AI agents, enabling them to retrieve important context when responding to user prompts. We’ll also learn about how Chroma supports various features optimal for code search, like semantic search, full text search, regex search and metadata filtering.
0:00 - Intro
2:02 - Chunking overview
3:19 - Tree Sitter
4:38 - Chunk file function
5:22 - collectTreeNodes function
8:49 - split function
13:31 - Demo
15:02 - Example queries in Chroma Cloud
—
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
On this page of the site you can watch the video online Chroma For Code Part 1: Chunking a Codebase for Code Search with a duration of hours minute second in good quality, which was uploaded by the user Chroma 21 August 2025, share the link with friends and acquaintances, this video has already been watched 8,875 times on youtube and it was liked by 163 viewers. Enjoy your viewing!
