44 lines
1.8 KiB
Markdown
44 lines
1.8 KiB
Markdown
# RAG Agent (Postgres)
|
|
|
|
Custom RAG agent that indexes text files from a git repository into Postgres
|
|
and answers queries using retrieval + LLM generation. Commits are tied to
|
|
**stories**; indexing and retrieval can be scoped by story.
|
|
|
|
## Quick start
|
|
|
|
1. Configure environment variables:
|
|
- `RAG_REPO_PATH` — path to git repo with text files
|
|
- `RAG_DB_DSN` — Postgres DSN (e.g. `postgresql://user:pass@localhost:5432/rag`)
|
|
- `RAG_EMBEDDINGS_DIM` — embedding vector dimension (e.g. `1536`)
|
|
2. Create DB schema:
|
|
- `python scripts/create_db.py` (or `psql "$RAG_DB_DSN" -f scripts/schema.sql`)
|
|
3. Index files for a story (e.g. branch name as story slug):
|
|
- `rag-agent index --story my-branch --changed --base-ref HEAD~1 --head-ref HEAD`
|
|
4. Ask a question (optionally scoped to a story):
|
|
- `rag-agent ask "What is covered?"`
|
|
- `rag-agent ask "What is covered?" --story my-branch`
|
|
|
|
## Git hook (index on commit)
|
|
|
|
Install the post-commit hook so changed files are indexed after each commit:
|
|
|
|
```bash
|
|
cp scripts/post-commit .git/hooks/post-commit && chmod +x .git/hooks/post-commit
|
|
```
|
|
|
|
Story for the commit is taken from (in order): env `RAG_STORY`, file `.rag-story` in repo root (one line = slug), or current branch name.
|
|
|
|
## DB structure
|
|
|
|
- **stories** — story slug (e.g. branch name); documents and chunks are tied to a story.
|
|
- **documents** — path + version per story; unique `(story_id, path)`.
|
|
- **chunks** — text chunks with embeddings (pgvector); updated when documents are re-indexed.
|
|
|
|
Scripts: `scripts/create_db.py` (Python, uses `ensure_schema` and `RAG_*` env), `scripts/schema.sql` (raw SQL).
|
|
|
|
## Notes
|
|
|
|
- The default embedding/LLM clients are stubs. Replace them in
|
|
`src/rag_agent/index/embeddings.py` and `src/rag_agent/agent/pipeline.py`.
|
|
- This project requires Postgres with the `pgvector` extension.
|