vectordb-patterns

Provides reusable AngularJS template code snippets for common use cases.

Updated Feb 25, 2026
One-click install
npx skills add https://github.com/HermeticOrmus/LibreMLOps-Claude-Code --skill vectordb-patterns
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: vectordb-patterns
Source: https://github.com/HermeticOrmus/LibreMLOps-Claude-Code/tree/main/plugins/vector-databases/skills/vectordb-patterns
Command: npx skills add https://github.com/HermeticOrmus/LibreMLOps-Claude-Code --skill vectordb-patterns

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides expert guidance and code examples for effectively implementing and optimizing vector databases, addressing common challenges in data storage, retrieval, and maintenance.

Core Features & Use Cases

  • Database Setup: Demonstrates best practices for setting up popular vector databases like pgvector, Pinecone, and Qdrant.
  • Indexing Strategies: Offers patterns for HNSW index tuning, metadata filtering, and handling multi-tenancy.
  • Drift Detection & Reindexing: Provides methods to monitor embedding drift and plan for reindexing.
  • Use Case: You need to implement a semantic search feature for your application. This Skill shows you how to set up a vector database, index your data efficiently, and query it with high accuracy, including strategies for managing embedding model updates.

Quick Start

Use the vectordb-patterns skill to set up a pgvector table with an HNSW index for storing document embeddings.

Frequently Asked Questions about vectordb-patterns

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

FAQPage Schema
How do I tune an HNSW index for vector database similarity search?

Implement pgvector or Pinecone for vector database similarity search by following setup scripts and code examples. This Skill demonstrates best practices for configuring tables, indexing data, and querying with high accuracy.

How do I detect embedding drift in a vector database?

Detect embedding drift in a vector database by monitoring vector distributions and tracking query accuracy degradation. This Skill outlines methods to identify drift and execute reindexing strategies to maintain search precision.

What is the best way to handle multi-tenancy in a vector database?

Implement multi-tenancy in a vector database by applying metadata filtering and partitioning patterns. This Skill provides architectural strategies to isolate tenant data securely within Qdrant, Pinecone, and pgvector.

Can I use metadata filtering with pgvector and Qdrant for similarity search?

Yes, you can use metadata filtering with pgvector and Qdrant to refine similarity search. This Skill provides code examples combining vector similarity queries with structured metadata constraints for precise retrieval.

When should I plan reindexing strategies for my vector database?

Plan reindexing strategies for your vector database when you update embedding models or detect significant embedding drift. This Skill outlines data maintenance workflows to restore search accuracy after representation changes.