skills.rest
Clay-HHK
Clay-HHKCOMMUNITY
Explore all skills by this author →
GitHub

qdrant-vector-search

Implements vector similarity search and hybrid retrieval for RAG systems using Qdrant.

1|Updated Mar 5, 2026
Search Tags:#semantic search#embeddings#rag#vector database#vector search#hybrid search#qdrant
One-click install
npx skills add https://github.com/Clay-HHK/claude-skills --skill qdrant-vector-search-clay-hhk
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: qdrant-vector-search
Source: https://github.com/Clay-HHK/claude-skills/tree/main/qdrant
Command: npx skills add https://github.com/Clay-HHK/claude-skills --skill qdrant-vector-search-clay-hhk

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Building production RAG and semantic search systems requires fast nearest neighbor search, metadata filtering, and scalable vector storage, which is difficult to implement from scratch. ## Core Features & Use Cases - Vector Search with Filtering: Perform nearest neighbor search combined with payload filters, geo queries, and full-text conditions using the qdrant-client Python API. - Hybrid and Multi-Vector Search: Combine dense and sparse vectors with Reciprocal Rank Fusion, named vectors, and multi-stage retrieval pipelines. - Production Scaling: Configure HNSW parameters, scalar/product/binary quantization, sharding, replication, snapshots, and collection aliases for large-scale deployments. - Use Case: Build a knowledge base by encoding documents with sentence-transformers, upserting them into a Qdrant collection, and retrieving top-k context chunks to feed into an LLM prompt. ## Quick Start Set up a Qdrant collection, insert my document embeddings, and show me how to run a filtered similarity search for my RAG pipeline.

Frequently Asked Questions about qdrant-vector-search

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

FAQPage Schema
How do I build a RAG system with Qdrant and sentence-transformers?▼

Encode documents with a SentenceTransformer model, create a Qdrant collection matching the embedding dimension, upsert points with text payloads, then search with the encoded query vector. Return the top-k payloads as context for your LLM prompt.

Qdrant vs FAISS vs Pinecone for vector search?▼

Qdrant suits production systems needing filtering, hybrid search, and distributed deployment. FAISS offers maximum raw speed for research and batch processing, while Pinecone is fully managed for teams preferring zero operations.

Does Qdrant support hybrid search with sparse vectors?▼

Yes, Qdrant supports collections with both dense and sparse vector configurations. You can prefetch results from each vector type and fuse them using Reciprocal Rank Fusion via the query_points API.

Why is my Qdrant filtered search slow?▼

Slow filtered search usually means missing payload indexes on filtered fields. Create a payload index with client.create_payload_index for fields like category or timestamp, and consider enabling quantization for large collections.

How do I reduce Qdrant memory usage for large collections?▼

Enable scalar quantization for roughly 4x memory reduction, product quantization for 16x, or binary quantization for 32x. Also set on_disk_payload=True and configure HNSW on-disk storage for very large datasets.

How do I fix vector dimension mismatch errors in Qdrant?▼

The error occurs when your embedding dimension differs from the collection's configured vector size. Check the collection config with get_collection, then recreate the collection with the correct size matching your embedding model.

Related Skills

Explore More Software Engineering Skills→
qcmuuqcmuu

sentence-transformers

Generate semantic embeddings from text using sentence-transformers models.

Community
Intermediate
JCETools-PetraJCETools-Petra
16

ai-llm-engineering

Design RAG pipelines with chunking, embedding, retrieval, and evaluation metrics.

Community
Advanced
patornpatorn

langchain-rag

Build end-to-end RAG pipelines with LangChain document loaders, embeddings, and vector stores.

Community
Advanced
infantesromeroadrianinfantesromeroadrian

langchain-rag

Build RAG workflows with LangChain for document loading, chunking, and vector stores.

Community
Intermediate