skills.rest
OrionArchitekton
OrionArchitektonCOMMUNITY
Explore all skills by this author →
Website𝕏@danmercedeGitHub

tbm-rag-index

Refresh RAG embeddings for new transcripts to update the Marie-voice chatbot vector index.

Updated Aug 27, 2026
Search Tags:#embeddings#rag#chatbot#transcripts#vector index#daily refresh
One-click install
npx skills add https://github.com/OrionArchitekton/cosmocrat-core --skill tbm-rag-index
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: tbm-rag-index
Source: https://github.com/OrionArchitekton/cosmocrat-core/tree/main/skills/tbm/tbm-rag-index
Command: npx skills add https://github.com/OrionArchitekton/cosmocrat-core --skill tbm-rag-index

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates the daily refresh of Retrieval Augmented Generation (RAG) embeddings, ensuring the Marie-voice chatbot has up-to-date information from new transcripts.

Core Features & Use Cases

  • Daily Embedding Refresh: Automatically updates the vector index with new transcript data.
  • Vector Index Maintenance: Keeps the knowledge base for the chatbot current.
  • Use Case: Ensures the Marie-voice chatbot can accurately answer questions about the latest conversations by regularly updating its underlying data.

Quick Start

Run the tbm-rag-index skill to refresh RAG embeddings for today's date.

Frequently Asked Questions about tbm-rag-index

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

FAQPage Schema
How do I automate daily RAG embedding refreshes for new transcripts?▼

Daily RAG embedding refreshes for new transcripts are performed by updating the vector index used by the Marie-voice chatbot. The skill uses read-only mode with service-only access for memory writes to ensure data integrity.

What is the best way to keep a chatbot vector index updated with new transcripts?▼

Keeping a chatbot vector index updated requires a daily refresh of RAG embeddings from new transcripts. This ensures the Marie-voice chatbot accurately answers questions about the latest conversations.

Do I need specific task definitions in cosmocrat_tasks.yaml to run the RAG index refresh?▼

Yes, specific task definitions in app/cosmocrat_tasks.yaml are required to execute the RAG index refresh. The skill relies on this configuration to process new transcripts and update the vector index.

How does the RAG embedding refresh process protect existing vector index data?▼

The RAG embedding refresh protects data by operating in read-only mode and using service-only access for memory writes. This ensures data integrity throughout the vector index update process.

Why does my chatbot need a daily refresh of RAG embeddings?▼

A daily refresh of RAG embeddings is needed to maintain an accurate vector index from new transcripts. Without regular updates, the chatbot cannot reliably answer questions about recent conversations.

Related Skills

Explore More Software Engineering Skills→
duyetduyet
5

orchestration

Coordinate multiple AI agents to execute parallel tasks and synthesize results.

Community
Advanced
imglyimgly
7

docs-node

Query local CE.SDK Node.js documentation for configuration and API references.

Official
Intermediate
markus41markus41
1

vectordb

Manage vector embeddings for semantic search across Pinecone, Weaviate, Chroma, and pgvector.

Community
Intermediate
ialamehialameh
2

semantic-codebase-search

Index codebases into LanceDB vector stores and retrieve relevant snippets via natural language queries.

Community
Intermediate