Quanta: A Self-Contained Python Library for Hybrid Retrieval over Quantised Embeddings, Lexical Indexes, and Knowledge Graphs

2026-09-16

AI Summary

本文介绍了一个名为Quanta的Python库，通过融合量化嵌入、词法索引和知识图谱的方法解决了混合检索系统集成复杂的问题。

Abstract

An advanced retrieval-augmented generation pipeline is typically assembled from three or four independently operated systems: an approximate nearest-neighbour index, a full-text search engine, a graph database, and a relational document store. Each contributes its own deployment surface, configuration model, and failure modes, and the integration logic that binds them is written anew in every project. In this work, we present \textsc{Quanta}, an open-source Python library, which unifies dense vector search over 4-bit quantised embeddings, BM25 full-text retrieval, and knowledge-graph traversal behind a single retrieval API. Quanta makes two design commitments, which distinguish it from existing hybrid retrieval stacks. First, signals are combined by \emph{weighted reciprocal rank fusion} rather than by normalising heterogeneous scores onto a shared range, which we argue is ill-posed because such normalisations are query-dependent. Second, the graph is a \emph{candidate expander and not a relevance scorer}: traversal widens the candidate pool, and the newly admitted documents are re-scored by the dense indexes under an identifier allowlist, so structural adjacency determines what is considered while content evidence determines how it ranks.

Problem

• retrieval-augmented generation
• independently operated systems
• integration logic
• deployment surface
• failure modes

Innovation

• weighted reciprocal rank fusion
• quantised embeddings
• knowledge graph traversal