POST
/
documents
/
v1
/
parse
curl --request POST \
  --url https://api.tensorlake.ai/documents/v1/parse \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "file": "<string>",
  "pages": "<string>",
  "settings": {
    "chunkStrategy": null,
    "deliverWebhook": "false",
    "detectSignature": "false",
    "detectStrikethrough": "false",
    "disableLayoutDetection": "false",
    "figureSummarization": true,
    "figureSummarizationPrompt": "none",
    "formDetectionMode": "vlm",
    "jsonSchema": "<any>",
    "modelProvider": null,
    "skewCorrection": "false",
    "structuredExtractionPrompt": "none",
    "structuredExtractionSkipOcr": "false",
    "tableOutputMode": "json",
    "tableParsingMode": "tsr",
    "tableSummarization": true,
    "tableSummarizationPrompt": "none"
  }
}'
{
  "fileId": "<string>",
  "jobId": "<string>",
  "status": "<string>"
}

Submit a file for document parsing. If you have configured a webhook, we will notify you when the job is complete.

For structured extraction, you can provide a schema to guide the extraction process. The schema can be in the form of a JSON Schema object.

The API call returns a job_id, which you can use to retrieve the results of the job with your API key.

You can either use a managed file, tensorlake-<file_id>, or provide a pre-signed URL or any HTTP URL, that can be used to download the file.

Your data is NOT sent to a third party service(OpenAI, Anthropic, etc), and uses our own models to parse the document.

Authorizations

​
Authorization
string
header
required

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

Body

application/json

Response

200
application/json
Parse pages from a file

The response is of type object.