qdrant-vector-search

Name: qdrant-vector-search
Availability: InStock
Author: eddielueng

Create Qdrant collections, upsert vectors, and run filtered similarity searches.

1|Updated Apr 14, 2026

Search Tags:#semantic search #embeddings #rag #vector search #qdrant #hnsw #payload filtering

Ready to run

npx skills add https://github.com/eddielueng/hermes-agent-zh --skill qdrant-vector-search-eddielueng

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: qdrant-vector-search
Source: https://github.com/eddielueng/hermes-agent-zh/tree/main/optional-skills/mlops/qdrant
Command: npx skills add https://github.com/eddielueng/hermes-agent-zh --skill qdrant-vector-search-eddielueng

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires qdrant-client>=1.12.0, and includes references (resource) components.

What problem does it solve?

This Skill helps you build production-ready vector similarity search so you can retrieve relevant context quickly for RAG and semantic search workflows.

Core Features & Use Cases

Low-latency vector retrieval: Perform nearest-neighbor search over embeddings with configurable distance metrics (e.g., cosine).
Metadata-aware filtering: Combine vector similarity with payload-based filters for precise results.
Scalable RAG storage patterns: Support production deployment needs such as quantization, on-disk payloads, sharding, and distributed clusters.
Hybrid and multi-vector approaches: Store and query dense and sparse vectors, including multi-vector per record for advanced retrieval strategies.

Quick Start

Connect to your Qdrant instance, create a collection with the right embedding dimension, upsert your document vectors with payload metadata, then run a filtered vector search to fetch the top matching contexts.

Frequently Asked Questions about qdrant-vector-search

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I perform vector similarity search with payload filtering for RAG?▼

Vector similarity search with payload filtering combines nearest-neighbor queries over embeddings with JSON metadata filters. You create a collection, upsert document vectors with payload metadata, then execute filtered search to retrieve top matching contexts for RAG workflows.

What is the best way to scale semantic search across large embedding collections in production?▼

Scaling semantic search across large embedding collections requires production features like sharding, replication, and quantization. This approach supports on-disk payload storage and distributed clusters to maintain low-latency vector retrieval under heavy workloads.

Does qdrant-client support multi-vector storage and hybrid search queries?▼

Yes, qdrant-client supports multi-vector storage and hybrid search queries. It enables storing and querying both dense and sparse vectors per record, allowing advanced retrieval strategies like hybrid query flows for semantic search workloads.

Can I configure custom distance metrics for nearest-neighbor search?▼

Yes, you can configure custom distance metrics like cosine for nearest-neighbor search. When creating collections, you specify configurable distance metrics to perform low-latency vector similarity retrieval tailored to your embedding patterns.

Why use Qdrant for semantic retrieval instead of other vector databases?▼

Qdrant targets production-ready vector similarity search with payload-based filtering, optional multi-vector storage, and built-in scaling features like quantization and sharding. It provides high-performance nearest-neighbor queries specifically optimized for RAG and semantic retrieval workloads.