skills.rest
MichaelYagi
MichaelYagiCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

media_ingestion

Ingest Plex media items into a RAG system with subtitles and metadata.

Updated Aug 27, 2026
Search Tags:#RAG#subtitles#ingest#parallel-processing#batch-ingestion#Plex
One-click install
npx skills add https://github.com/MichaelYagi/mcp_a2a --skill media-ingestion
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: media_ingestion
Source: https://github.com/MichaelYagi/mcp_a2a/tree/main/servers/plex/skills/media_ingestion
Command: npx skills add https://github.com/MichaelYagi/mcp_a2a --skill media-ingestion

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables seamless ingestion of Plex media items into a RAG system, turning media libraries into searchable, context-aware data sources.

Core Features & Use Cases

  • Granular, batch, and parallel ingestion: Ingest items by single ID, batch of IDs, or parallel processing to populate the RAG index.
  • Subtitle and metadata extraction: Retrieve subtitles and enriched metadata during ingestion to enhance context.
  • End-to-end ingestion pipelines: Trigger complete ingestion workflows for new or unprocessed media across multiple titles.

Quick Start

Use this skill to ingest 5 new movies from Plex, or ingest a list of specific item IDs and extract subtitles for richer context.

Frequently Asked Questions about media_ingestion

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

FAQPage Schema
How do I ingest Plex media into a RAG system?▼

You can ingest Plex media into a RAG system by processing items via granular single ID ingestion, batch ID processing, or parallel workflows to populate the searchable index with your media library data.

Can I extract subtitles during Plex media ingestion for RAG?▼

Yes, subtitle extraction is supported during Plex media ingestion. The pipeline retrieves subtitles and enriched metadata alongside the media items to provide deeper context for RAG queries.

What is the best way to run batch ingestion for multiple Plex titles?▼

The best way to run batch ingestion for multiple Plex titles is using the end-to-end parallel processing pipeline. It ingests new or unprocessed media across multiple titles by specifying a count or a list of item IDs.

Do I need specific item IDs to ingest media from Plex into my RAG pipeline?▼

No, you do not strictly need specific item IDs to ingest media. The system supports ingestion by count, allowing you to process a specified number of new movies or items automatically without manually providing IDs.

Does parallel processing work for ingesting large Plex libraries into RAG?▼

Yes, parallel processing works for ingesting large Plex libraries. It allows you to trigger complete ingestion workflows across multiple titles simultaneously, efficiently turning large media collections into searchable data sources.

Related Skills

Explore More Software Engineering Skills→
mindmorassmindmorass
2

knowledge-ingestion-patterns

Ingest PDFs, websites, code repos, and notes into vector databases with chunking and metadata schemas.

Community
Basic
icyzhicyzh
1

chroma

Manage vector embeddings for retrieval-augmented generation and semantic search.

Community
Intermediate
gatovillanogatovillano

onlyoffice-rag-pipeline

Extract, chunk, embed, and index OnlyOffice documents for RAG systems.

Community
Advanced
ddnettersddnetters
2

plex-media-server

Manage Plex Media Server libraries, searches, playback sessions, and maintenance via API.

Community
Intermediate