skills.rest
haxlys
haxlysCOMMUNITY
Explore all skills by this author →
GitHub

similarity-search-patterns

Perform top-k similarity search over vector embeddings across Pinecone, Qdrant, pgvector, and Weaviate.

1|Updated Apr 27, 2026
Search Tags:#qdrant#weaviate#pinecone#vector-search#semantic-retrieval#nearest-neighbor#multibackend
One-click install
npx skills add https://github.com/haxlys/skills --skill similarity-search-patterns-haxlys
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: similarity-search-patterns
Source: https://github.com/haxlys/skills/tree/main/vendored/wshobson-agents/plugins/llm-application-dev/skills/similarity-search-patterns
Command: npx skills add https://github.com/haxlys/skills --skill similarity-search-patterns-haxlys

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Implement efficient similarity search for vector embeddings across multiple backends, enabling scalable retrieval in semantic search and RAG systems.

Core Features & Use Cases

  • Support for document upsertion and vector indexing across Pinecone, Qdrant, pgvector, and Weaviate.
  • Fast top-k similarity search with configurable distance metrics and optional filtering.
  • Hybrid and combined search capabilities to blend vector similarity with keyword results for richer results.

Quick Start

Provide a sample query vector and retrieve the top-k most similar items from your chosen backend.

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 semantic search across multiple vector databases for RAG retrieval?▼

Semantic search for RAG retrieval is implemented by upserting document embeddings into a vector database and querying with top-k similarity. This pattern supports backends like Pinecone, Qdrant, pgvector, and Weaviate for scalable document indexing and retrieval.

Can I combine keyword search with vector similarity to improve retrieval results?▼

Yes, hybrid search combines vector similarity with keyword results to deliver richer retrieval outcomes. This blends semantic nearest-neighbor matching with traditional filtering, enhancing search accuracy across large vector datasets.

Does this approach support upserting and indexing vectors across Pinecone and Weaviate?▼

Yes, vector upsertion and indexing are supported across multiple backends including Pinecone, Weaviate, Qdrant, and pgvector. This allows flexible document ingestion and vector management within your chosen vector search infrastructure.

What is the best way to perform top-k nearest-neighbor search with metadata filtering?▼

Top-k nearest-neighbor search with filtering is performed by providing a query vector and applying configurable distance metrics. This retrieves the most similar items while restricting results to specific metadata constraints.

When do I need a dedicated vector database for semantic retrieval instead of standard search?▼

A dedicated vector database is needed for semantic retrieval when matching meaning rather than exact keywords. It enables fast similarity search over high-dimensional vector embeddings for applications like recommendation systems and RAG.

Related Skills

Explore More Data & Analytics Skills→
lewisperez999lewisperez999

vector-embeddings

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

Community
Intermediate
Mathews-TomMathews-Tom
310

rag-auditor

Evaluate RAG pipeline retrieval and generation quality with metrics.

Community
Advanced
Maheen-ZubairMaheen-Zubair

rag-ingestion-pipeline

Automate document ingestion and indexing for RAG systems.

Community
Advanced
Division6066Division6066

hybrid-search-implementation

Combine vector similarity with keyword matching for hybrid search retrieval.

Community
Advanced