Raw Extraction

Extract everything from a given Document

In this example, we have the following PDF page:

Page 8 of the Paper Point-e

By calling our raw-extract endpoint we can extract all content from this PDF document. Here is an example of calling it:

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:

⚠️ To use this endpoint, book a meeting to discuss how you would like the result formatted⚠️