KRLabsOrg / verbatim-rag
Provenance-first extractive RAG: return verbatim source spans with citations using local ModernBERT or optional LLM-assisted extraction.
Why this job: says: rag; topics: rag, retrieval-augmented-generation
What it does
Provenance-first extractive RAG: retrieve documents, select answer-relevant passages, and return source excerpts with citations instead of freely rewriting the evidence.
Get started
# Install the package
pip install verbatim-ragYou need: Docker with Docker Compose v2.24+; An OpenAI-compatible API key (Groq by default, see api/dependencies.py)
- Maintenance
- Active
- Last commit 4 days ago
- Stars
- 208
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.2.8
- Released 5 months ago
- Built with
- Python
- 94% of the code
Is it looked after?
- Contributors
- 6
- Last 90 days
- Issues
- 39% closed
- 36 still open
- Pull requests
- 56 merged
- 5 waiting
- Releases
- 19
- 12 in the last year
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| NovaSearch-Team / RAG-Retrieval | 1,137 | 2 months ago | MIT | No downloads |
| hhy-huang / HiRAG | 555 | 4 months ago | MIT | No downloads |
More: languages, topics, project record and preview image
Languages
- Python 94%
- JavaScript 6%
- Dockerfile <1%
- CSS <1%
Topics
- citation
- hallucination-prevention
- llm
- modernbert
- nlp
- openai
- python
- rag
- retrieval-augmented-generation
- span-extraction
Project record
- JobRAG and search
- StatusListed
- Commits200
- Forks40
- Watching0
- Stars in 28 days+2
- CreatedJan 31, 2025
- First seen by usNov 7, 2026
- CheckedNov 7, 2026