qdrant-hybrid-search-prefetches

Official

Optimize hybrid search performance in Qdrant.

Authorqdrant
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill addresses the need for constructing effective prefetch queries for hybrid retrieval in Qdrant, enhancing both performance and accuracy for specific query types.

Core Features & Use Cases

  • Hybrid Search Query Construction: Guidance on combining dense and sparse vector search and multi-field retrieval scenarios.
  • Sparse Vector Choice: Recommendations for the best sparse vector models for text search based on the context of the use case.
  • Combining Multiple Representations: Strategies for when the same item has multiple embeddings across various fields or languages.

Quick Start

Use this skill to create a hybrid search query by combining a sparse BM25 model with a dense model for 'keyword_and_semantic_search' in your project.

Dependency Matrix

Required Modules

FastEmbed

Components

scriptsreferencesassets

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: qdrant-hybrid-search-prefetches
Download link: https://github.com/qdrant/skills/archive/main.zip#qdrant-hybrid-search-prefetches

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.