ggozad/haiku.rag
Opinionated agentic RAG powered by LanceDB, Pydantic AI, and Docling
This tool helps researchers, analysts, and knowledge workers rapidly understand large collections of documents like PDFs and web pages. You feed it your documents, and it allows you to ask complex questions, get summarized answers with page-level citations, conduct multi-step research, or even perform data analysis using code. It's designed for anyone who needs to extract deep insights from unstructured text without getting lost in manual reading.
494 stars.
Use this if you need to quickly and accurately find answers, synthesize information, or analyze data across many documents, complete with source citations.
Not ideal if you only need simple keyword searches or are working with highly structured data like spreadsheets.
Stars
494
Forks
29
Language
Python
License
MIT
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/ggozad/haiku.rag"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
vitali87/code-graph-rag
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with...
stevereiner/flexible-graphrag
Flexible GraphRAG: Python, LlamaIndex, Docker Compose: 8 Graph dbs, 10 Vector dbs, OpenSearch,...
dmayboroda/minima
On-premises conversational RAG with configurable containers
christopherkarani/Wax
Lightening fast RAG on Apple Silicon. On-Device. No Server. No API. One File. Pure Swift
shredEngineer/Archive-Agent
Find your files with natural language and ask questions.