skills.rest
creepyblues
creepybluesCOMMUNITY
Explore all skills by this author →
GitHub

regenerate-embeddings

Regenerate OpenAI embeddings for titles to support vector-based similarity search.

Updated Jul 22, 2025
Search Tags:#embeddings#openai#vector-search#cost-estimation#titles#regeneration
One-click install
npx skills add https://github.com/creepyblues/kstorybridge-integrated --skill regenerate-embeddings
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: regenerate-embeddings
Source: https://github.com/creepyblues/kstorybridge-integrated/tree/main/.claude/skills/regenerate-embeddings
Command: npx skills add https://github.com/creepyblues/kstorybridge-integrated --skill regenerate-embeddings

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

The skill orchestrates the regeneration of OpenAI embeddings for titles to ensure accurate vector similarity search across the chat-orchestrator and mandate-matcher features, especially when new titles are added or existing content changes.

Core Features & Use Cases

  • Batch-regenerate embeddings for titles by popularity or priority, and update individual titles as needed.
  • Verify embedding coverage, estimate costs, and monitor regeneration outcomes.
  • Integrate with existing scripts (run-regeneration.js, regenerate-specific-title.js, count-valid-embeddings.js, verify-regeneration-success.js) to automate workflows.

Quick Start

Run the provided node scripts to begin regenerating embeddings for titles in your catalog.

Frequently Asked Questions about regenerate-embeddings

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

FAQPage Schema
How do I regenerate OpenAI embeddings for titles to update vector search?▼

You can regenerate OpenAI embeddings for titles by running provided node scripts that connect to your database and the OpenAI API to batch-process vectors, verify coverage, and estimate costs for similarity search.

When do I need to regenerate title embeddings for vector-based similarity search?▼

You need to regenerate title embeddings when new titles lacking vectors are added or when existing title content changes, ensuring accurate similarity search across chat orchestration and mandate matching.

How do I batch regenerate embeddings by popularity or priority?▼

Batch regeneration is handled by executing existing scripts like run-regeneration.js, which targets specific titles based on popularity or priority to systematically update OpenAI vectors.

Can I estimate the cost of regenerating OpenAI embeddings before running the process?▼

Yes, the skill includes cost estimation functionality that calculates expected expenses before connecting to the OpenAI API to perform the actual title vector regeneration.

How do I verify embedding coverage and regeneration outcomes?▼

You verify embedding coverage and outcomes by running scripts like count-valid-embeddings.js and verify-regeneration-success.js, which check that titles have valid updated vectors after processing.

Does this skill require specific dependencies to update title vectors?▼

No external dependencies are required; the skill leverages existing node scripts to interact directly with your database and the OpenAI API for embedding generation and verification.

Related Skills

Explore More Software Engineering Skills→
patricio0312revpatricio0312rev
5

vector-db-setup

Configure Pinecone, Chroma, pgvector, and Qdrant vector databases for semantic search.

Community
Advanced
MLAI-AUS-IncMLAI-AUS-Inc
4

connect-users

Search community members by expertise using vector embeddings and cosine similarity.

Official
Intermediate
jonnabiojonnabio
6

faiss

Index and search dense vectors using the Faiss library.

Community
Advanced
ihatesea69ihatesea69
3

sentence-transformers

Generate sentence, text, and image embeddings using pre-trained transformer models.

Community
Intermediate