skills.rest
lewisperez999
lewisperez999COMMUNITY
Explore all skills by this author →
GitHub

vector-embeddings

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

1|Updated Sep 1, 2025
Search Tags:#openai#semantic-search#cosine-similarity#upstash#vector-embeddings#pg-vector
One-click install
npx skills add https://github.com/lewisperez999/v0-lewis-perez-portfolio-twin --skill vector-embeddings
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: vector-embeddings
Source: https://github.com/lewisperez999/v0-lewis-perez-portfolio-twin/tree/main/.skills/vector-embeddings
Command: npx skills add https://github.com/lewisperez999/v0-lewis-perez-portfolio-twin --skill vector-embeddings

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Vector embeddings enable semantic search, similarity matching, and scalable retrieval by converting text into numerical representations that machines can compare efficiently.

Core Features & Use Cases

  • Generate embeddings from text using OpenAI models.
  • Store embeddings in Upstash Vector or PostgreSQL pg-vector with optional metadata.
  • Search by cosine similarity and filter results by metadata to refine relevance.
  • Use cases include knowledge bases, document search, and product content discovery.

Quick Start

Index a sample text and run a vector search using the provided embedding and search utilities.

Frequently Asked Questions about vector-embeddings

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

FAQPage Schema
How do I generate vector embeddings from text for semantic search?▼

Vector embeddings are generated by passing input text to an OpenAI model, which converts it into numerical representations that machines can compare efficiently for semantic search and similarity matching.

Can I attach metadata to vector embeddings for filtering search results?▼

Yes, you can attach optional metadata to vector embeddings when storing them in Upstash Vector or pg-vector, and apply those metadata filters during cosine similarity search to refine and return top_k results.

Does this approach work with both Upstash Vector and PostgreSQL pg-vector?▼

Yes, the semantic search approach supports both Upstash Vector and PostgreSQL pg-vector as storage backends, allowing you to store embeddings with metadata and query them using cosine similarity.

How do I search stored embeddings using cosine similarity?▼

To search stored embeddings using cosine similarity, generate a query embedding from your search text, compare it against the database, apply optional metadata filters, and return the top_k most relevant results.

What is the best way to build a scalable knowledge base with semantic search?▼

Building a scalable knowledge base with semantic search involves generating OpenAI embeddings from documents, storing them in Upstash Vector or pg-vector with metadata, and querying by cosine similarity to retrieve relevant content.

Related Skills

Explore More Software Engineering Skills→
ricablericable
1

@ruvector/postgres-cli

Manage PostgreSQL instances with RuVector for AI vector operations.

Community
Advanced
wesichainwesichain

wesichain-rag

Build RAG pipelines for document Q&A and semantic search.

Official
Advanced
ivanshamaevivanshamaev
14

rag-data-pipeline

Build RAG ingestion and query pipelines with hybrid retrieval and reranking.

Community
Advanced
SignmanalSignmanal
1

chroma

Store and query vector embeddings with metadata filtering for RAG applications.

Community
Intermediate