Documents Extract | Prediction Guard

This endpoint allows you to parse text from documents using OCR.

AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

This endpoint expects a multipart form containing a file.

filefileRequired

The document file to upload.

embedImagesbooleanOptional

Whether to embed images from the document.

outputFormatstringOptional

The output format for the content of the document.

chunkDocumentbooleanOptional

Whether to separate the document into chunks.

chunkSizeintegerOptional

The size of chunks for the documents.

enableOCRbooleanOptional

Whether to enable OCR for document parsing.

Successful response.

titlestring

The parsed document title.

contentsstring

The parsed document contents.

countinteger

The word count for the document.

400

Bad Request Error

403

Forbidden Error

1	curl -X POST https://{your-pg.api-domain}.com/documents/extract \
2	-H "Toxicity: true" \
3	-H "Pii: replace" \
4	-H "Replace-Method: category" \
5	-H "Entity-List: ["ADDRESS"]" \
6	-H "Injection: true" \
7	-H "Authorization: Bearer <token>" \
8	-H "Content-Type: multipart/form-data" \
9	-F [email protected] \
10	-F embedImages='false' \
11	-F outputFormat="markdown" \
12	-F chunkDocument='true' \
13	-F chunkSize='1000' \
14	-F enableOCR='true'

1	{
2	"title": "sample.pdf",
3	"contents": "## Sample PDF\n\n## This is a simple PDF file. Fun fun fun.\n\nLorem ipsum dolor sit amet, consectetuer adipiscing elit. Phasellus facilisis odio sed mi. Curabitur suscipit...",
4	"count": 3041
5	}