跳转到主要内容
此内容尚未提供您的语言版本,正在以英文显示。

Qdrant Vector Search

技能 已验证 活跃

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

目的

To enable users to build production-ready RAG systems by providing a high-performance, scalable vector similarity search engine.

功能

  • High-performance vector similarity search
  • Integration for RAG and semantic search
  • Scalable vector storage with Rust-powered performance
  • Hybrid search with metadata filtering
  • Examples for common RAG frameworks (LangChain, LlamaIndex)

使用场景

  • Building production RAG systems requiring low latency
  • Implementing hybrid search (vectors + metadata filtering)
  • Deploying scalable vector storage with full data control
  • Developing real-time recommendation systems

非目标

  • Simpler setup for embedded use cases (use Chroma instead)
  • Maximum raw speed for research/batch processing (use FAISS instead)
  • Fully managed zero-ops solutions (use Pinecone instead)

工作流

  1. Connect to Qdrant instance
  2. Create a collection with vector parameters
  3. Upsert points (vectors + payload)
  4. Perform search or filtered search operations
  5. Integrate results into RAG pipeline

先决条件

  • Qdrant client library
  • Qdrant server instance (local, Docker, or cloud)

安装

请先添加 Marketplace

/plugin marketplace add Orchestra-Research/AI-Research-SKILLs
/plugin install AI-Research-SKILLs@ai-research-skills

质量评分

已验证
95 /100
1 day ago 分析

信任信号

最近提交17 days ago
星标8.3k
许可证MIT
状态
查看源代码