LettuceDetect
Span-level grounding verification for RAG, code, and tool-grounded AI outputs.
- 627
- Python
- MIT
- 1 d ago
KRLabsOrg
Built from KRLabsOrg's public GitHub profile, Austria. Not on Take My Repo yet, so there are no posts or updates here.
Span-level grounding verification for RAG, code, and tool-grounded AI outputs.
Provenance-first extractive RAG: return verbatim source spans with citations using local ModernBERT or optional LLM-assisted extraction.
Learn rule-based models from examples using LLM-powered synthesis. Replace expensive LLM calls with fast, deterministic, inspectable regex, code, or spaCy rules.
Squeeze verbose LLM agent tool output down to only the relevant lines
Q&A system based on papers in the ACL Anthology and the VerbatimRAG system
Python SDK and CLI for the Verbatim platform — grounded, verbatim answers from curated document collections.