Add Real-World Project: RAG Over a GitHub Repo - #271
Open
abderrahim-lectures wants to merge 1 commit into
Open
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds a new Real-World Projects lesson: Build a RAG App Over a GitHub Repo (backlog idea #16).
What's included
docs/projects/github-repo-rag/index.md— full lesson in the house skeleton, building directly on the notes-based RAG project. Core upgrades over that sibling: chunking code at function/class boundaries vs. prose at paragraph boundaries, per-chunk line-range metadata, and a generation prompt that demands[path.py:start-end]citations you can open and verify.docs/projects/github-repo-rag/_category_.jsonexamples/github-repo-rag/— runnable 4-script tool (prepare_repo.py,build_index.py,retrieve.py,query.py), 6-provider LLM support inquery.py, plusnotebook.ipynb, README, pyproject/uv.lock/env template.src/data/projects.ts,docs/projects/index.mdx,src/pages/index.tsx(English only — i18n in a follow-up PR).Verification
docs/projects/→ 3233 chunks embedded locally, retrieval returns scores in [-1,1] with correct file/line citations.npm run typecheckpasses;npm run buildpasses all 4 locales (the only github-repo-rag warnings are the pre-existing translated ai-agent anchor pattern shared with rag-notes).Closes #270