{ "opencollection": "1.0.0", "info": { "name": "LLMWhisperer Extraction API", "version": "2.0" }, "request": { "auth": { "type": "apikey", "key": "unstract-key", "value": "{{unstract-key}}", "placement": "header" } }, "items": [ { "info": { "name": "Extraction", "type": "folder" }, "items": [ { "info": { "name": "Submit a document for text extraction", "type": "http" }, "http": { "method": "POST", "url": "https://llmwhisperer-api.us-central.unstract.com/api/v2/whisper", "params": [ { "name": "mode", "value": "", "type": "query", "description": "Extraction mode." }, { "name": "output_mode", "value": "", "type": "query", "description": "Output formatting mode." }, { "name": "page_seperator", "value": "", "type": "query", "description": "Page delimiter string inserted between pages." }, { "name": "pages_to_extract", "value": "", "type": "query", "description": "Pages to extract, e.g. \"1-5,7,21-\"." }, { "name": "median_filter_size", "value": "", "type": "query", "description": "Median filter size for low_cost mode noise removal." }, { "name": "gaussian_blur_radius", "value": "", "type": "query", "description": "Gaussian blur radius for low_cost mode noise removal." }, { "name": "line_splitter_tolerance", "value": "", "type": "query", "description": "Baseline factor for line splitting (fraction of line height)." }, { "name": "line_splitter_strategy", "value": "", "type": "query", "description": "Line splitting strategy." }, { "name": "horizontal_stretch_factor", "value": "", "type": "query", "description": "Horizontal stretch factor for multi-column layout adjustment." }, { "name": "url_in_post", "value": "", "type": "query", "description": "When true, the request body is a document URL instead of binary data." }, { "name": "mark_vertical_lines", "value": "", "type": "query", "description": "Reproduce vertical layout lines in the output." }, { "name": "mark_horizontal_lines", "value": "", "type": "query", "description": "Reproduce horizontal layout lines in the output." }, { "name": "lang", "value": "", "type": "query", "description": "Language hint for OCR (ISO 639-2/B, e.g. eng)." }, { "name": "tag", "value": "", "type": "query", "description": "Auditing label associated with the request." }, { "name": "file_name", "value": "", "type": "query", "description": "Auditing reference file name." }, { "name": "use_webhook", "value": "", "type": "query", "description": "Name of a registered webhook to deliver the result to." }, { "name": "webhook_metadata", "value": "", "type": "query", "description": "Metadata echoed back to the webhook with the result." }, { "name": "add_line_nos", "value": "", "type": "query", "description": "Enable line numbering and persist line metadata for highlights." }, { "name": "allow_rotated_text", "value": "", "type": "query", "description": "Include rotated/angled text in extraction." }, { "name": "word_confidence_threshold", "value": "", "type": "query", "description": "OCR word confidence filter (0-1)." } ] }, "docs": "Converts a document to text. Accepts the raw document as binary (application/octet-stream) or, when url_in_post is true, a URL in the request body. Processing is asynchronous; a whisper_hash is returned to track and retrieve the job." } ] } ], "bundled": true }