How do I choose between different distance metrics?

The skill provides a guide: Cosine is best for normalized embeddings, Euclidean (L2) for raw distances, and Dot Product when magnitude is a critical factor.

What indexing methods are covered?

The skill includes patterns for Flat, HNSW (graph-based), and IVF+PQ (quantized) indexing to help you balance search speed versus accuracy.

Does it support hybrid search?

Yes, it includes patterns for combining semantic vector search with traditional keyword filtering and metadata constraints for more precise results.

What is similarity search used for?

It is primarily used for semantic search, recommendation systems, and RAG, where finding similar context matters more than exact keyword matching.

Which vector databases does this skill support?

It provides ready-to-use implementation patterns for Pinecone (managed), Qdrant (high-performance), and PostgreSQL with the pgvector extension.

Vector Similarity Search Patterns

Name: Vector Similarity Search Patterns
Author: drgaciw

bydrgaciw

0•

数据科学与机器学习

Implement high-performance similarity search and vector retrieval patterns across multiple database providers.

This skill provides standardized patterns for implementing efficient similarity search within production systems, focusing on vector databases and Retrieval-Augmented Generation (RAG). It equips developers with optimized implementations for popular vector stores like Pinecone, Qdrant, and pgvector, while offering deep insights into distance metrics and indexing strategies like HNSW and IVF+PQ. Whether you're building a semantic search engine, a recommendation system, or scaling an AI application to millions of vectors, this skill ensures best practices for low-latency retrieval, high recall, and advanced reranking workflows.

主要功能

01Comprehensive distance metric selection guide (Cosine, L2, Dot Product)

02Advanced reranking and cross-encoder implementation patterns

03Optimized HNSW and IVF+PQ indexing configurations

04Hybrid search and complex metadata filtering workflows

05Multi-provider support for Pinecone, Qdrant, and pgvector

060 GitHub stars

使用场景

01Developing high-scale semantic search and recommendation engines

02Optimizing vector retrieval latency and recall for production AI apps

03Building robust Retrieval-Augmented Generation (RAG) pipelines

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add drgaciw/academic-compliance-hub-glm similarity-search-patterns

For use in Claude.ai and ChatGPT

Download Skill