| Document extraction (asynchronous) |
- Extract doc at a Sensible URL
- Extract doc at your URL | Takes a document file, such as a PDF, and returns extracted data asynchronously. Use the asynchronous endpoints in production. You have two options for asynchronously extracting from your document:
- extract a doc at a URL you provide
- upload and extract the doc at a Sensible URL. You can then call the Retrieve extraction endpoint to get the results, or specify a webhook for Sensible to push the results to as soon as they’re ready. |
| Document extraction (synchronous) | Extract data from a document | Returns extracted document data synchronously. Use this endpoint for testing. |
| Get Excel from PDFs | Get Excel extraction | Get well-structured Excel files converted from PDF documents. This endpoint also supports documents formatted as images, for example, PNG or JPEG. |
| Portfolio extraction (asynchronous) |
- Extract portfolio at a Sensible URL
- Extract portfolio at your URL | Use these endpoints with multiple documents that are packaged into one PDF file (a PDF “portfolio”). |
| Document type classification | Classify document by type | Classifies a document by its similarity to document types you define in your Sensible account. |
