ggozad/haiku.rag

Description and use

A lightweight, opinionated Retrieval‑Augmented Generation (RAG) framework that combines LanceDB for scalable vector storage, Pydantic‑AI for structured prompt handling, and Docling for seamless document ingestion. Designed for developers building agentic AI applications, it offers a clean, backend‑focused API that streamlines indexing, querying, and response generation. The project is open‑source and targets AI/ML, backend, and dev‑tools use cases.

Use in a workflow

ggozad/haiku.rag helps connect AI assistants to real tools and data through a standard protocol.

• connect AI agents to tools
• ship Model Context Protocol servers
• standardize integrations

Limitations and review notes

Medium: useful for prototypes or internal workflows, with dependency and maintenance checks before production.