/raw-extract
Convert documents (PDFs, Images, ...) to plain text
Creates a Raw Extraction Job
POST
https://waveline.ai/api/v1/raw-extract
Creates a new job that converts documents into plain text.
Headers
Name | Type | Description |
---|---|---|
Content-Type | String | Should be |
Authorization* | String |
|
Request Body
Name | Type | Description |
---|---|---|
contentUrl* | String | A URL pointing to your data. (e.g. https://example.com/invoice.pdf) |
⚠️To use this endpoint, book a meeting to discuss how you would like the result formatted⚠️
With this endpoint, you can extract everything from PDFs: Text, Titles, Tables, Images etc. To give you a better intuition have a look at our Example.
If you already have an account, you can get an API key here.
Last updated