code for training & evaluating Contextual Document Embedding models

Late Interaction Models Training & Retrieval

Official software repository of S. Bruch, F. M. Nardini, C. Rulli, and R. Venturini, "Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations". Long Paper @ ACM SIG…

web search done right

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

Lightweight Pytorch framework developed by NAVER LABS Europe for training and running text generation models (machine translation, speech translation, language modeling and dialogue)

IR module for experimaestro

Unified Learned Sparse Retrieval Framework

CoSPLADE: Contextualizing SPLADE for Conversational Information Retrieval

A Fine-Grained Analysis of Distribution Shifts in MSMARCO (MS-Shift). Evaluation benchmark on three types of distribution shifts, all conditioned on MSMARCO queries.

SPLADE: sparse neural search (SIGIR21, SIGIR22)

A Python nearest neighbor descent for approximate nearest neighbors

Approximate Nearest Neighbors in C /Python optimized for memory usage and loading/saving to disk

Linux/OSX/FreeBSD resource monitor