multi-vector-retrieval

Python library for MUVERA multi-vector retrieval via Fixed Dimensional Encodings. ColBERT / ColQwen2 / ColQwen3.5 compatible.

MVR-Data defines how multi-vector retrieval data is organized at runtime and packaged for interchange using Apache Arrow.

AI agent that intercepts SaaS subscription cancellations and autonomously determines personalized retention offers using LangGraph multi-agent loops, ChromaDB multi-vector RAG, and DeepSeek LLM with policy guardrails.

State-of-the-art privacy for multi-vector VLM retrievers (ColPali/ColQwen2): a field-level PII linkage attack, the holographic leakage mechanism, an adaptive break of naive defenses, and Cataract — the first adaptively-evaluated, tunable, index-time real-privacy defense for this class.

Exhaustive Scanning Method for Multi-Vector Retrieval Tasks. (This tool can be used to generate embeddingp-level groundtruth for MVR datasets)

Budgeted multi-vector visual retrieval and Visual RAG for PCB engineering documents — a pilot-scale study (101 pages, 30 queries) comparing OCR BM25, dense text, CLIP and ColPali v1.3 late-interaction retrieval.

TopK is a search engine for accuracy-critical AI applications, delivering hybrid search, multi-vector (late-interaction) retrieval, dense and sparse vector search, BM25 keyword search, custom ranking, document parsing, and grounded question answering through a single API.