← Latest products

LettuceDetect

Lightweight hallucination detector for RAG pipelines. Span-level grounding verification for RAG, code, and tool-grounded AI outputs. Hallucinations are still a major blocker for deploying reliable retrieval-augmented generation (RAG) systems, especially in complex domains like medical or legal.

Open source

619 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. Open-source model and scorecard for measuring hallucinations in LLMs

    vectara.com

    This morning, we released a new Apache 2.0 licensed model on HuggingFace for detecting hallucinations in retrieval augmented generation (RAG) systems.

    Hacker News65 pts

  2. Nomadic

    news.ycombinator.com

    Minimize RAG Hallucinations with 1 Hyperparameter Experiment

    Hacker News95 pts

  3. Demystifying Advanced RAG Pipelines

    github.com

    An LLM-powered advanced RAG pipeline built from scratch

    Hacker News131 pts

  4. dreamGPT

    github.com

    What if LLM hallucinations were a feature and not a bug?

    Hacker News34 pts

  5. RAGatouille

    github.com

    a simple lib to use&train top retrieval models in RAG apps

    Hacker News15 pts