# Raw Extraction

In this example, we have the following PDF page:

<figure><img src="/files/gF6c0TKTKjzZniMqk48k" alt=""><figcaption><p>Page 8 of the Paper Point-e</p></figcaption></figure>

By calling our [raw-extract endpoint ](/extract/endpoints/raw-extract.md)we can extract all content from this PDF document. Here is an example of calling it:

```bash
curl -X POST "https://waveline.ai/api/v1/raw-extract" \
     -H "Content-Type: application/pdf" \
     -H "Authorization: Bearer YOUR_API_KEY" \
     -d '{
          "fileName": "pointe_8-8.pdf",
          "contentType": "application/pdf",
          "contentUrl": "https://vwxzjwxlflvltwsntpsb.supabase.co/storage/v1/object/public/documentation/pointe_8-8.pdf",
        }'
```

The Waveline Pipeline then extracts all parts of the PDF and returns the content along with some metadata. Here is the result of what parts were detected:

<figure><img src="/files/TDiwrGaUNpEHsPnbZsyP" alt=""><figcaption></figcaption></figure>

:warning: To use this endpoint, book a [meeting](https://calendly.com/waveline/30min-landing) to discuss how you would like the result formatted:warning:&#x20;


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.waveline.ai/extract/examples/raw-extraction.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.