fix(rag): use full kodit enrichment content instead of 300-char preview#2015
Closed
philwinder wants to merge 1 commit into
Closed
fix(rag): use full kodit enrichment content instead of 300-char preview#2015philwinder wants to merge 1 commit into
philwinder wants to merge 1 commit into
Conversation
Previously the RAG query returned only the first 300 characters of the enriched chunk (via r.Preview), ignoring the chunk_size setting. Now we store both the full content and a truncated preview: the RAG pipeline uses full content for better context, while the UI/API handlers continue to use the preview for display efficiency. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Previously the RAG query returned only the first 300 characters of enriched chunks (via
r.Preview), ignoring the configured chunk_size setting entirely. This meant that even if you set chunk_size to 5000, the LLM would only ever see ~200 tokens.Now we:
Fixes the issue where RAG chunks were hard-capped at 300 characters regardless of configuration.
Changes
kodit_servicer.go: AddContentfield toKoditFileResultkodit_service.go: Populate full content and truncated preview separatelyrag_kodit.go: Use fullr.Contentinstead ofr.Preview