skills.rest
DrLuggels
DrLuggelsCOMMUNITY
Explore all skills by this author →
GitHub

similarity-search-patterns

Provide patterns for similarity search with vector databases like Pinecone and Qdrant.

3|Updated Jan 8, 2026
Search Tags:#semantic search#vector database#RAG#similarity search#Weaviate#Qdrant#Pinecone
One-click install
npx skills add https://github.com/DrLuggels/my_dhbw --skill similarity-search-patterns-drluggels
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: similarity-search-patterns
Source: https://github.com/DrLuggels/my_dhbw/tree/main/.claude/plugins/llm-application-dev/skills/similarity-search-patterns
Command: npx skills add https://github.com/DrLuggels/my_dhbw --skill similarity-search-patterns-drluggels

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pinecone-client, qdrant-client, asyncpg, numpy, weaviate-client, sentence-transformers, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides patterns and templates for implementing efficient similarity search using vector databases, crucial for modern AI applications.

Core Features & Use Cases

  • Vector Database Integration: Implementations for Pinecone, Qdrant, pgvector, and Weaviate.
  • Similarity Metrics: Understand and apply Cosine, Euclidean, Dot Product, and Manhattan distances.
  • Index Types: Learn about Flat, HNSW, and IVF+PQ indexing strategies.
  • Use Case: Building a RAG system for a large document corpus where efficient retrieval of semantically similar chunks is paramount.

Quick Start

Use the similarity-search-patterns skill to implement a Pinecone vector store for semantic search.

Frequently Asked Questions about similarity-search-patterns

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

FAQPage Schema
How do I implement similarity search with Pinecone, Qdrant, or Weaviate for a RAG system?▼

You can implement similarity search for RAG using provided patterns and templates for vector databases like Pinecone, Qdrant, pgvector, and Weaviate to efficiently retrieve semantically similar document chunks.

What is the difference between Cosine, Euclidean, and Dot Product distance metrics for semantic search?▼

Distance metrics for semantic search like Cosine, Euclidean, Dot Product, and Manhattan dictate how vector similarity is calculated, directly impacting retrieval accuracy and ranking performance in your vector database.

When should I use HNSW versus IVF+PQ indexing strategies in a vector database?▼

HNSW and IVF+PQ are index types for vector databases. HNSW prioritizes query speed, while IVF+PQ optimizes memory compression, making your choice dependent on your specific latency and scale requirements.

Can I use pgvector with asyncpg to build a recommendation engine?▼

Yes, you can use pgvector with asyncpg to build recommendation engines, leveraging its similarity search patterns and distance metrics to efficiently retrieve matching items within a PostgreSQL environment.

Do I need to understand vector embeddings to use these similarity search patterns?▼

Yes, understanding vector embeddings and database configurations is required, as the similarity search patterns rely on properly formatted vector inputs and optimized database setups to function correctly.

What is the best way to perform hybrid search with Weaviate and sentence-transformers?▼

The best way to perform hybrid search with Weaviate involves combining keyword and vector search strategies using sentence-transformers embeddings to improve retrieval relevance over purely semantic approaches.

Related Skills

Explore More Software Engineering Skills→
lewisperez999lewisperez999

vector-embeddings

Generate text embeddings with OpenAI and search by cosine similarity in Upstash Vector or pg-vector.

Community
Intermediate
h4vzzh4vzz
33

context-optimization

Optimize raw context chunks for AI models within a token budget.

Community
Intermediate
SriRamkunamsettySriRamkunamsetty

pinecone

Create a serverless Pinecone index using the pinecone-client library.

Community
Intermediate
voidrotvoidrot

similarity-search-patterns

Implement efficient similarity search using vector databases.

Community
Advanced