RAGatouille

Open-source RAG engine for LLM apps with deep document parsing, multi-granularity chunking, hybrid retrieval integrating vector stores (e.g., Elasticsearch), and visual workflow builder.

Advanced multi-vector retrieval model creating token-level embeddings with late interaction mechanism, featuring denoised supervision and improved memory efficiency over original ColBERT.

The first workshop dedicated to late interaction and multi-vector retrieval methods at ECIR 2026, featuring keynote speaker Omar Khattab (ColBERT creator) and focusing on advances in token-level representations, multi-modal retrieval, and long-context search.

Community workshop dedicated to late interaction techniques in information retrieval, a retrieval approach where fine-grained similarity is computed between query and document token-level representations rather than single global embeddings. Addresses research in ColBERT, ColPali, MUVERA, and related methods.

Library built on Sentence Transformers for flexible training, inference, and retrieval with state-of-the-art ColBERT models. Features FastPLAID index for efficient multi-vector late interaction retrieval with 10x storage compression and sub-200ms latency.

Late interaction retrieval model that applies the ColBERT token-level embedding approach using the Qwen language model as the base encoder. Provides high-quality semantic search with detailed token-level matching for improved retrieval accuracy.