feat(rag): add RAG pipeline scaffold#2
Open
khb-git wants to merge 1 commit into
Open
Conversation
Adds the skeleton of the RAG pipeline with stubbed interfaces. Two collections (permits + reference) kept separate. Schema-aware chunking respects REVIEW_SCHEMA boundaries. All-local inference. 12 smoke tests pass; real implementations are TODOs marked in each module. See rag/README.md for the layout and suggested fill-in order.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds the skeleton of the RAG pipeline for Phase 2.
Design decisions baked in:
Two collections (permits + reference) kept strictly separate — see rag/types.py::Collection for rationale
Schema-aware chunking respects REVIEW_SCHEMA section boundaries
All-local inference (no cloud API calls — air-gapped requirement)
What's NOT in this PR: real loading, chunking, embedding, or retrieval logic. Every method is a stub that logs a warning. Phase 2 fills in the TODOs marked in each module.
Testing: pytest tests/ — 12 tests pass, covering interface contracts.
Review focus: interface shapes (renaming fields after Phase 2 starts is expensive) and the two-collection design (sanity check the rationale).