Parse File

cURL

curl --request POST \
  --url https://api.contextual.ai/v1/parse \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form raw_file='@example-file' \
  --form parse_mode=standard \
  --form enable_document_hierarchy=true \
  --form enable_split_tables=true \
  --form max_split_table_cells=123 \
  --form 'page_range=<string>'

Response Codes:

• 200
• 422

Successful Response Example:

{
  "job_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a"
}

Documentation Index

Fetch the complete documentation index at: https://docs.contextual.ai/llms.txt

Authorizations

Authorization
Type: string
In header: required
Format: Bearer <token>, where <token> is your auth token.

Body

Multipart/form-data:

• raw_file:

  • Type: file
  • Required: Yes
  • Description: The file to be parsed. Supported types: PDF, DOC/DOCX, PPT/PPTX, PNG, JPG/JPEG.

• parse_mode:

  • Type: enum<string>
  • Default: standard
  • Options: basic, standard
  • Description: The settings for parsing.

• enable_document_hierarchy:

  • Type: boolean
  • Description: Adds a table of contents with the structure of the entire document. (Beta feature)

• enable_split_tables:

  • Type: boolean
  • Description: Splits large tables for improved LLM comprehension.

• max_split_table_cells:

  • Type: integer
  • Description: Threshold for splitting large tables.

• page_range:

  • Type: string
  • Description: Represents page ranges to be parsed.

Response

Successful Response:

• 200 application/json
  • Contains: /parse response object.

Fields:

• job_id:
  • Type: string<uuid>
  • Required: Yes
  • Description: Unique ID of the parse job.