shubhprocoder / rag
pythonmainadb294f3.7K linessynced 3d ago
Code health
9.3out of 10Excellent
This codebase scores 9.3 out of 10 on defect risk, which we rate excellent. It also scores maintainability 9.6 and static performance risk 10.0 out of 10. The three are scored separately and never blended into one number.
- Lines of code
- 3.7K
Recent activity
All commitsCommits
No commits indexed yet.
Decisions
- Recursive chunking that preserves page numbers and chunk coherenceproposed · 3d ago
- Use lazy imports to avoid circular dependencies in document routesproposed · 3d ago
- Use a Singleton configuration/service pattern via importproposed · 3d ago
- Centralize configuration via Pydantic Settings and environment overridesproposed · 3d ago
Needs attention
15 open- medium severity. ProposedRecursive chunking that preserves page numbers and chunk coherenceAuto-proposed decision awaiting review
- medium severity. ProposedUse lazy imports to avoid circular dependencies in document routesAuto-proposed decision awaiting review
- medium severity. ProposedUse a Singleton configuration/service pattern via importAuto-proposed decision awaiting review
- medium severity. ProposedCentralize configuration via Pydantic Settings and environment overridesAuto-proposed decision awaiting review
- medium severity. Knowledge silobackend/app/__init__.py100% single-owner concentration
Composition
Open the graphpython 80%javascript 11%markdown 2%dockerfile 2%yaml 2%Other 2%
Explore this codebase
- Docs57 pages across 13 modules
- ChatAsk this codebase a question and get an answer with its sources
- Files46 files with per-file docs, health and history
- ArchitectureDependency graph, layers, and 3 entry points
- Code healthPer-file scores, 47 open findings, coverage and refactoring targets
- Knowledge graphEntities, communities, and the paths between them
- Change couplingFiles that keep changing together, mined from commit history
- CommitsChange-risk ranked history with agent provenance
- ContributorsBus factor, per-file maintainers, and the human/agent split
- StatsSize class, origin, lifetime churn, rhythm and records
- CostsWhat indexing this snapshot cost, by model and by run