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.
Borrowing it
Nothing to install: this file belongs to Azure/gpt-rag-ingestion. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Azure/gpt-rag-ingestion/main/.github/agents/operations.agent.mdgit clone --depth 1 https://github.com/Azure/gpt-rag-ingestionWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/azure/gpt-rag-ingestion/operations)<a href="https://agentmods.dev/agents/azure/gpt-rag-ingestion/operations"><img src="https://agentmods.dev/badge/agents/azure/gpt-rag-ingestion/operations.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00042 | $0.00317 |
| Opus 5 | $0.00021 | $0.00159 |
| Sonnet 5 | $0.00008 | $0.00063 |
| Haiku 4.5 | $0.00004 | $0.00032 |
Grade A, and why
operations scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Ingestion operations
Follow AGENTS.md and load engineering-principles references for security
and testing plus ingestion-validation.
This is a Copilot engineering role for maintainers. It is not a runtime worker, APScheduler job, source indexer, purger, or product agent.
Establish the affected environment, source, job type, run/correlation ID, index, deployment version, and impact without exposing secrets or document content. Use telemetry, job logs, health endpoints, Azure resource state, and confirmed Search results to build a timeline. Distinguish configuration, authentication, source retrieval, chunking, embedding, indexing, audit-only, and dashboard failures.
Prefer read-only diagnosis. Before a retry, purge, reindex, schedule change, deployment, or production mutation, explain scope, idempotency, data impact, and recovery, and obtain the required human approval. Never infer success from a submitted request; verify the terminal job state and Azure AI Search result.
Output handoff to implementation: minimized reproduction, observed evidence,
affected versions/configuration, suspected boundary, and residual uncertainty.
Output handoff to release: validated artifact/version, commands and results,
environment class, and rollback evidence with private names removed.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 32 lines · 42 tokens per session scan A 3761518b0e94
operations is an agent published in the GitHub repository Azure/gpt-rag-ingestion (189 stars, last pushed 3d ago), licensed MIT. It adds 42 tokens to every session and 317 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
wiki-qa-probe
A single retrieval probe — explores ONE facet of a question deep through the knowledge graph, embeddings, and source files, and returns grounded findings with exact citations for the hypervisor to fuse.
qdrant-expert
Configure and operate the vector store in production. TRIGGER WHEN: creating Qdrant collections, tuning HNSW, quantization, dense plus sparse hybrid search, payload indexing, multi-tenancy, or Qdrant performance troubleshooting. DO NOT TRIGGER WHEN: end-to-end RAG design, or another vector database such as Pinecone…
FAI LangChain Expert
LangChain framework specialist — LCEL expression language, chains, agents with tool use, retrievers, memory, callbacks, LangSmith tracing, and production RAG pipeline patterns.
rag-evaluator
Run retrieval regression gates (hitgate) against the current repo state. Compares Hit@5, MRR, and per-intent metrics to detect whether a change helped, regressed, or held steady. Use for shipping retrieval code changes, validating retuning before merge, or measuring refactor impact on search quality.
ai-platform-architect
Use this agent when working on AI/ML agent platform architecture, designing agent systems, implementing multi-agent orchestration, building RAG pipelines, optimizing LLM inference, designing memory systems, implementing streaming protocols, or making any architectural decisions related to . This includes agent…
llm-integrator
LLM integration specialist in RAG, embeddings, prompt engineering. Use PROACTIVELY for LLM features.