Repository navigation
colbert
- Website
- Wikipedia
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
Efficient Retrieval Augmentation and Generation Framework
🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL
Use late-interaction multi-modal models such as ColPali in just a few lines of code.
Late Interaction Models Training & Retrieval
High-Performance Engine for Multi-Vector Search
ColBERT humor dataset for the task of humor detection, containing 200,000 jokes/news
PyLate efficient inference engine
An easy-to-use python toolkit for flexibly adapting various neural ranking models to target domain.
Vector Database with support for late interaction and token level embeddings.
Tree-based indexes for neural-search
A demonstration of hybrid search with reranking using Qdrant and BGE-M3 model. A showcase of dense and sparse retrieval combined with ColBERT reranking for optimal search results
Official codebase for the ACL 2025 Findings paper: Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrieval.
Efficient late-interaction retrieval systems in Julia!
An overview of popular reranking models and architectures for 2 stage RAG pipelines
A list of multi-vector retrieval resources
Open source ColBERT based document database
A Powerful Python Library to Build AI Applications with the RAG