Which vector databases does this skill support?

It includes implementation templates and best practices for popular vector databases including Pinecone, Qdrant, and pgvector for PostgreSQL.

What search patterns are covered in this skill?

The skill covers semantic search, hybrid search (combining dense and sparse vectors), and retrieval-augmented generation (RAG) workflows.

Can this skill help optimize search performance?

Yes, it provides technical guidance on choosing and configuring index types like HNSW and IVF to balance search latency, memory usage, and recall accuracy.

How does the skill handle result accuracy?

It includes patterns for using distance metrics correctly and implementing cross-encoder reranking to improve the relevance of the retrieved results.

Similarity Search Patterns

Name: Similarity Search Patterns
Author: goodnight000

bygoodnight000

数据科学与机器学习

Implement efficient vector-based similarity search, semantic retrieval, and RAG patterns across major vector databases.

关于

This skill provides standardized patterns for implementing high-performance similarity search in production systems using vector databases like Pinecone, Qdrant, and pgvector. It equips developers with optimized templates for semantic search, hybrid retrieval, and RAG (Retrieval-Augmented Generation) workflows. By covering essential concepts such as distance metrics, HNSW indexing, and cross-encoder reranking, it helps ensure that search systems are scalable, accurate, and optimized for low-latency AI-driven applications.

主要功能

Guidance on distance metrics including Cosine, Euclidean, and Dot Product
Integrated reranking patterns using cross-encoders for higher precision
Implementation patterns for semantic and hybrid (dense + sparse) search
Optimized templates for Pinecone, Qdrant, and pgvector
Index optimization strategies for HNSW and IVF configurations
0 GitHub stars

使用场景

Building RAG-based systems for high-accuracy LLM context retrieval
Developing real-time recommendation engines using vector embeddings
Creating semantic search engines for large-scale unstructured text data

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add goodnight000/kittycourt similarity-search-patterns

For use in Claude.ai and ChatGPT

Download Skill

GitHub

关于