Tools

Extract tables from a PDF

Find the tables in a PDF (ruled, shaded and borderless, plus charts drawn as vectors, as tables of their values) and write them as Excel (.xlsx, one sheet per table), CSV, JSON or Markdown. The output name must end in the format's extension (.xlsx, .csv, .json, .md).

Same tool as the MCP server's pdf_extract_tables. Runs before responding; for long work, POST /v1/jobs instead.

post/v1/tools/pdf_extract_tables

Request

  • Base URL: http://127.0.0.1:7341
  • URL: http://127.0.0.1:7341/v1/tools/pdf_extract_tables
  • Auth: HTTP bearer

Request body

inputstring required

Path to a PDF inside an allowed folder (absolute, or relative to the first allowed folder).

pagesstring

Page numbers or ranges, such as "1, 3-5". Omit for every page.

format'xlsx' | 'csv' | 'json' | 'markdown'
outputstring required

Path for the new file, ending in .xlsx, .csv, .json or .md to match the format, inside an allowed folder. Must not exist yet.

Response

The result. Any new files are written inside the allowed folders.

outputstring required
bytesinteger required
formatstring required
tablesinteger required

Changes

No recorded changes to this operation across all 1 revision of this API.