# Build Source-Linked RAG Chunks from a Sitemap

**Use case:** 

Convert an authorized public sitemap into bounded text chunks with stable IDs, source evidence, confidence, crawl gaps, and reconciliation.

## Input

```json
{
  "items": [
    "docs.apify.com"
  ],
  "maxConcurrency": 1
}
```

## Output

```json
{
  "entityId": {
    "label": "Stable chunk ID",
    "format": "text"
  },
  "input": {
    "label": "Site",
    "format": "text"
  },
  "sourceUrl": {
    "label": "Source page",
    "format": "link"
  },
  "text": {
    "label": "Knowledge text",
    "format": "text"
  },
  "contentHash": {
    "label": "Content SHA-256",
    "format": "text"
  },
  "chunkIndex": {
    "label": "Chunk #",
    "format": "number"
  },
  "charCount": {
    "label": "Chars",
    "format": "number"
  },
  "tokensApprox": {
    "label": "Approx. tokens",
    "format": "number"
  },
  "summary": {
    "label": "Summary",
    "format": "text"
  },
  "confidenceBasis": {
    "label": "Confidence basis",
    "format": "text"
  },
  "confidenceScore": {
    "label": "Confidence",
    "format": "number"
  },
  "confidenceBand": {
    "label": "Confidence band",
    "format": "text"
  },
  "confidenceRisks": {
    "label": "Confidence risks",
    "format": "array"
  },
  "recommendedAction": {
    "label": "Recommended action",
    "format": "text"
  },
  "actionPriority": {
    "label": "Priority",
    "format": "text"
  },
  "observedAt": {
    "label": "Observed at",
    "format": "date"
  },
  "freshness": {
    "label": "Evidence freshness",
    "format": "object"
  },
  "dataGaps": {
    "label": "Data gaps",
    "format": "array"
  },
  "negativeSignals": {
    "label": "Negative signals",
    "format": "array"
  },
  "partial": {
    "label": "Partial",
    "format": "boolean"
  },
  "partialReasons": {
    "label": "Partial reasons",
    "format": "array"
  },
  "crawlStats": {
    "label": "Crawl completeness",
    "format": "object"
  },
  "sourceEvidence": {
    "label": "Source evidence",
    "format": "array"
  },
  "failureType": {
    "label": "Failure type",
    "format": "text"
  },
  "retryable": {
    "label": "Retryable",
    "format": "boolean"
  },
  "failureDiagnostics": {
    "label": "Failure diagnostics",
    "format": "object"
  },
  "billing": {
    "label": "Delivery and billing",
    "format": "object"
  },
  "safeToAutomate": {
    "label": "Automation safe",
    "format": "boolean"
  }
}
```

## About this Actor

This example demonstrates how to use [RAG Dataset Builder](https://apify.com/zinin/sitemap-to-knowledge) with a specific input configuration. Visit the [Actor detail page](https://apify.com/zinin/sitemap-to-knowledge) to learn more, explore other use cases, and run it yourself.


## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
This Task's input is already configured above — use it as-is rather than inventing a new one.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For full API examples (JavaScript, Python, CLI, MCP, OpenAPI), see this Task's Actor page: https://apify.com/zinin/sitemap-to-knowledge.md

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).