RAGatouille
Python library that simplifies training and using ColBERT for late-interaction retrieval in RAG.
About
RAGatouille is a Python library that makes ColBERT, a state-of-the-art late-interaction retrieval method, accessible for RAG pipelines. It exposes modular components for training and fine-tuning models, indexing documents, and retrieving results. ColBERT models tend to generalize well to new domains and remain data-efficient compared to dense embedding approaches.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- RAG & Document Retrieval
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- License
- Apache-2.0
- Added
- May 7, 2026
Related Tools
Self-hosted application layer for LLMs with chat, RAG, web search, code execution, and agents.
Open-source data extraction and indexing engine for RAG applications.
Open-source embedding database for AI applications
Web scraping API that turns websites into clean LLM-ready markdown.
Local RAG capabilities in GPT4All for chatting with documents privately.
Cloud-native vector database for scalable similarity search