# Turn a 10-K into RAG-ready chunks by section

**Use case:** 

Get the text of a company’s 10-K annual report split by Item (Business, Risk Factors, MD&A and more), cut into paragraph chunks of about 2,000 characters, ready for a vector database or a language model. Enter a ticker and how many reports. No SEC API key needed.

## Input

```json
{
  "mode": "fulltext",
  "ticker": "AAPL",
  "formTypes": [
    "10-K"
  ],
  "chunking": "paragraph",
  "includeExhibits": false,
  "dedupeFacts": true,
  "maxItems": 2
}
```

## Output

```json
{
  "itemType": {
    "label": "Type",
    "format": "string"
  },
  "title": {
    "label": "Title",
    "format": "string"
  },
  "formType": {
    "label": "Form",
    "format": "string"
  },
  "date": {
    "label": "Date",
    "format": "string"
  },
  "url": {
    "label": "URL",
    "format": "string"
  }
}
```

## How it works

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

The SEC EDGAR Scraper — Filings, Full-Text RAG & XBRL Financials Actor is ready to run with the inputs already set for "Turn a 10-K into RAG-ready chunks by section". [Sign up or log in](https://console.apify.com/create-task-from-example/bfH4hgs0wh2oeyUdy) and you'll land in Apify Console with a copy of this exact task.

### 2. Start the "Turn a 10-K into RAG-ready chunks by section" task

The SEC EDGAR Scraper — Filings, Full-Text RAG & XBRL Financials Actor will start running based on the input automatically. You can also change all the input fields, like mode, ticker, and more, to match your specific use case.

### 3. Receive the "Turn a 10-K into RAG-ready chunks by section" 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 type, title, form, 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 "Turn a 10-K into RAG-ready chunks by section" task via API](https://apify.com/autofacts/sec-edgar-scraper.md).

## FAQ

### Do I need an SEC API key?

No. EDGAR is public data. The Actor follows the SEC’s request-rate rules for you.

### What does each result contain?

One record per filing, with its sections and their sizes and the text cut into chunks. Each chunk is tagged with the section it came from.

### Can I choose how the text is chunked?

Yes: one chunk per section, paragraph chunks of about 2,000 characters, or the whole document with no chunking.

### Does it work for other forms?

It works for filings whose main document is HTML. Forms that are XML only, such as Form 4, are skipped and not charged.

### How much does it cost?

You pay per item returned: about $0.001 per filing or search hit, $0.005 per full-text document and $0.0002 per XBRL fact. See the Pricing tab for current rates.

## About this Actor

This example demonstrates how to use [SEC EDGAR Scraper — Filings, Full-Text RAG & XBRL Financials](https://apify.com/autofacts/sec-edgar-scraper.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/autofacts/sec-edgar-scraper.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/autofacts/sec-edgar-scraper.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`).
