The GPT-RAG Data Ingestion service automates processing of diverse documents—PDFs, images, spreadsheets, transcripts, and SharePoint—readying them for Azure AI Search. It applies smart chunking, generates text and image embeddings, and enables rich, multimodal retrieval.
GPT-RAG Data Ingestion is a service that processes documents such as PDFs, images, spreadsheets, transcripts, and SharePoint files so they can be searched through Azure AI Search. It prepares data with format-specific chunking and text or image embeddings for multimodal retrieval in agent-based applications.
Agent ✓ vendor
Analyzes ingestion boundaries, chunk/index contracts, source integrations, security, and operational trade-offs. Use for structural or hard-to-reverse changes; do not use for local implementation with settled requirements.
Agent ✓ vendor
Implements, tests, and documents scoped gpt-rag-ingestion changes after requirements are clear. Do not use to decide broad architecture, diagnose live incidents, or publish releases.
Agent ✓ vendor
Diagnoses and safely operates deployed ingestion services, jobs, source connectors, indexing, telemetry, and release validation. Use for operational investigation and recovery; do not use for feature design or autonomous production changes.
Agent ✓ vendor
Prepares and validates gpt-rag-ingestion releases, including VERSION, changelog, compatibility evidence, tags, and release notes. Do not use for feature work or publish without explicit human approval.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: