> ## Documentation Index
> Fetch the complete documentation index at: https://docs.apowerb.com/llms.txt
> Use this file to discover all available pages before exploring further.

# RAG

> Index documents, URLs, SQL results and S3 buckets into per-agent knowledge bases.

RAG lets an agent answer from documents you provide. Indexing is delegated to the RAG
service ([th2rag](/ecosystem/th2rag)), reachable at `RAG_BASE_URL`.

```
Upload documents → indexed by th2rag → the agent searches them when answering
```

## Sources

| Source                     | Endpoint                    | Notes                                   |
| -------------------------- | --------------------------- | --------------------------------------- |
| Files                      | `POST /api/rag/index-files` | PDF, CSV, TXT, DOCX… max 50 MB per file |
| URL                        | `POST /api/rag/index-url`   | Crawls and indexes a web page           |
| Database, SQL              | `POST /api/rag/index-db`    | Indexes the result of a SQL query       |
| Database, natural language | `POST /api/rag/index-db-nl` | Same, from a question                   |
| S3                         | `POST /api/rag/index-s3`    | Indexes files from a bucket             |

## Following progress

* Poll `GET /api/rag/status/{knowledge_id}`
* Or stream `GET /api/rag/stream/{agent_id}?session_id=xxx` — events `connected`,
  `status`, `complete`

`GET /api/rag/knowledge/{agent_id}` lists what an agent currently has indexed.

## Security

* Path traversal is blocked on session and agent identifiers
* URL indexing refuses localhost and private address ranges (SSRF protection)
* Session ownership is validated on every call
* Completion callbacks from th2rag are verified with an HMAC-SHA256 signature
  (`RAG_WEBHOOK_SECRET`)


## Related topics

- [Rag Webhook](/api-reference/rag/rag-webhook.md)
- [Rag Stream](/api-reference/rag/rag-stream.md)
- [Configuration](/configuration.md)
- [Secrets](/self-hosting/secrets.md)
- [th2rag](/ecosystem/th2rag.md)