# Build a RAG corpus from the Hono docs with heading chunks

**Use case:** 

Converts the Hono web framework docs into Markdown and splits each page into heading-scoped chunks with stable IDs and heading paths, ready to embed into a vector database. Re-run it later and unchanged sections keep their IDs. Point it at any docs site to build your own corpus.

## Input

```json
{
  "inputs": [
    {
      "url": "https://hono.dev/docs/",
      "maxPages": 10
    }
  ],
  "chunk": true,
  "concurrency": 2
}
```

## Output

```json
{
  "status": {
    "label": "Status",
    "format": "string"
  },
  "url": {
    "label": "URL",
    "format": "string"
  },
  "title": {
    "label": "Title",
    "format": "string"
  },
  "markdown": {
    "label": "Markdown",
    "format": "string"
  },
  "source": {
    "label": "Source",
    "format": "string"
  },
  "lastModified": {
    "label": "Last modified",
    "format": "string"
  },
  "error": {
    "label": "Error",
    "format": "object"
  }
}
```

## How it works

### 1. Sign up on Apify or log in

The Docs to Markdown Crawler Actor is ready to run with the inputs already set for "Build a RAG corpus from the Hono docs with heading chunks". [Sign up or log in](https://console.apify.com/create-task-from-example/zMmZOv2WFF6NdGPYC) and you'll land in Apify Console with a copy of this exact task.

### 2. Start the "Build a RAG corpus from the Hono docs with heading chunks" task

The Docs to Markdown Crawler Actor will start running based on the input automatically. You can also change all the input fields, like docs roots or page urls, include sections, and more, to match your specific use case.

### 3. Receive the "Build a RAG corpus from the Hono docs with heading chunks" output

Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as status, URL, title, and more.

### 4. Integrate into your workflow

The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow. You can also [run the "Build a RAG corpus from the Hono docs with heading chunks" task via API](https://apify.com/miacx/docs-to-markdown.md).

## FAQ

### What does the Hono docs RAG task return?

The Hono docs RAG task returns one row per page with its Markdown and a chunks array. Each chunk has an id, its headingPath and its Markdown.

### Do chunk IDs change between runs of the Hono docs RAG task?

Chunk IDs in the Hono docs RAG task stay the same while a section's URL, heading path and text stay the same, so you can update embeddings incrementally.

### Does the Hono docs RAG task call an LLM?

No. The Hono docs RAG task splits pages deterministically by headings. No LLM runs.

## About this Actor

This example demonstrates how to use [Docs to Markdown Crawler](https://apify.com/miacx/docs-to-markdown.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/miacx/docs-to-markdown.md) to learn more, explore other use cases, and run it yourself.


## How to integrate an Actor?

This Task's input is already configured above. Use it as-is rather than inventing a new one.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

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

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).