# Split PDFs into chunks for RAG and vector databases

**Use case:** 

Converts documents to Markdown and splits them into overlapping chunks ready for embeddings and a vector database.

## Input

```json
{
  "urls": [
    "https://arxiv.org/pdf/2401.18059"
  ],
  "outputFormat": "markdown",
  "includeTables": true,
  "includePageMarkers": true,
  "includePageContents": false,
  "chunkSize": 1000,
  "chunkOverlap": 200,
  "ocrMode": "auto",
  "ocrLanguages": [
    "eng"
  ],
  "removeHeadersFooters": true,
  "maxPagesPerDocument": 200,
  "maxFileSizeMb": 50,
  "maxConcurrency": 5,
  "requestTimeoutSecs": 120
}
```

## Output

```json
{
  "url": {
    "label": "URL",
    "format": "string"
  },
  "fileName": {
    "label": "File",
    "format": "string"
  },
  "format": {
    "label": "Type",
    "format": "string"
  },
  "title": {
    "label": "Title",
    "format": "string"
  },
  "pages": {
    "label": "Pages",
    "format": "integer"
  },
  "pagesConverted": {
    "label": "Converted",
    "format": "integer"
  },
  "wordCount": {
    "label": "Words",
    "format": "integer"
  },
  "tableCount": {
    "label": "Tables",
    "format": "integer"
  },
  "ocrUsed": {
    "label": "OCR",
    "format": "boolean"
  },
  "error": {
    "label": "Error",
    "format": "string"
  }
}
```

## How it works

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

The PDF to Markdown API \[$2/1k\] - Word, PowerPoint, Excel & OCR Actor is ready to run with the inputs already set for "Split PDFs into chunks for RAG and vector databases". [Sign up or log in](https://console.apify.com/create-task-from-example/3xJ86vsB5Zjz5JsfK) and you'll land in Apify Console with a copy of this exact task.

### 2. Start the "Split PDFs into chunks for RAG and vector databases" task

The PDF to Markdown API \[$2/1k\] - Word, PowerPoint, Excel & OCR Actor will start running based on the input automatically. You can also change all the input fields, like document urls, output format, and more, to match your specific use case.

### 3. Receive the "Split PDFs into chunks for RAG and vector databases" 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 URL, file, type, 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 "Split PDFs into chunks for RAG and vector databases" task via API](https://apify.com/kadi_bence/document-to-markdown.md).

## FAQ

### What does this task return?

The "Split PDFs into chunks for RAG and vector databases" task returns one row per chunk with its text, position and source document.

### How much does it cost?

The "Split PDFs into chunks for RAG and vector databases" task costs $2 per 1,000 documents on the base plan, plus a tiny start fee. Higher Apify plans pay less.

### Can I run it on a schedule?

The "Split PDFs into chunks for RAG and vector databases" task can run on any Apify schedule, and the results can go to Google Sheets, Slack, a webhook or the API.

## About this Actor

This example demonstrates how to use [PDF to Markdown API [$2/1k] - Word, PowerPoint, Excel & OCR](https://apify.com/kadi_bence/document-to-markdown.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/kadi_bence/document-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/kadi_bence/document-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`).
