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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" 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 5.5 | $0.00017 | $0.00127 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 (188 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 317 once invoked, about $0.0002 per session on Opus 5.5. 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.
operations compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| operationsAzure/gpt-rag-ingestion | Agent | 188 | 1mo ago | MIT | A | 42 | Claude Code |
| langchain4j-ai-development-expertgiuseppe-trisciuoglio/developer-kit | Agent | 367 | 1mo ago | MIT | A | 65 | Claude Code |
| wiki-qa-probebearlike/Assistant | Agent | 43 | 7d ago | MIT | A | 43 | Claude Code |
| qdrant-expertacaprino/daodan | Agent | 9 | 4d ago | MIT | A | 91 | Claude Code |
| tokentonone-ai/tonone | Agent | 77 | 23d ago | MIT | A | 21 | Claude Code |
| FAI LangChain Expertfrootai/frootai | Agent | 7 | 4d ago | MIT | A | 41 | Claude Code |
| rag-evaluatorLucasSantana-Dev/sharekit | Agent | 2 | 4d ago | MIT | A | 68 | Claude Code |