Code aware chunking in RAG strategies#967
Merged
dgageot merged 1 commit intodocker:mainfrom Nov 28, 2025
Merged
Conversation
b132740 to
87d9f29
Compare
Contributor
Author
|
needs some extra work to prepare for using CGO in CI |
Signed-off-by: Christopher Petito <chrisjpetito@gmail.com>
97b6e92 to
bc2b832
Compare
dgageot
approved these changes
Nov 28, 2025
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The goal of this change is to allow RAG strategy chunking configurations to define they are
code_aware.When
code_aware: true, the rag system will use treesitter bindings to parse the AST of the code for the chunking, in order to not spit up logical blocks of code like functions.Only Go code is supported in this initial implementation, but we can add support for more languages fairly easily in followup PRs.
Example:
The treesitter AST parsing will also be used in follow up rag strategies to gather the semantic meaning of the analyzed code before generating embeddings 😏