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

arXiv:2609.18248v1 Announce Type: cross 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 extsc{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 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 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.

Related

• Query-Aware Spreading Activation for Multi-Hop Retrieval over Knowledge Graphs
• Noesis: Bidirectional Graph-RAG with Adaptive Parallelism and Cross-Knowledge-Base Semantic Discovery
• Beyond Vector Similarity: A Structural Analysis of Graph-Augmented Retrieval for Industrial Knowledge Graphs
• Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guarantees

Source: arXiv cs.AI | 2026-09-17