jina-colbert-v2 is an open-source multilingual ColBERT-style embedding model supporting 8192 sequence length.

This model produces vectors of size 64 for tokens in input documents.

ColBERT (Contextualized Late Interaction over BERT) leverages the deep language understanding of BERT while introducing a novel interaction mechanism. This mechanism, known as late interaction, allows for efficient and precise retrieval by processing queries and documents separately until the final stages of the retrieval process.

This state-of-the-art AI embedding model enables many applications, such as document clustering, classification, content personalization, vector search, or retrieval augmented generation.