Converts files uploaded in "agent_only" ingest mode to PDF and parses them.

String id of the collection to add the ingested documents into.

String id of the document to be parsed.

Whether to auto-generate document summaries (uses LLM).

Whether to auto-generate sample questions for each document (uses LLM).

Language of audio files.

Which method to use to extract text from images using AI-enabled optical character recognition (OCR) models. docTR is best for Latin text, PaddleOCR is best for certain non-Latin languages, Tesseract covers a wide range of languages. Mississippi works well on handwriting. - auto - Automatic will auto-select the best OCR model for every page. - off - Disable OCR for speed, but all images will then be skipped (also no image captions will be made).

Whether the document should be restricted only to certain users.

The list of usernames having permissions to the document.

Which language to use when using ocr_model="tesseract".

When tables are identified by the table parser the table tokens will be kept in a single chunk.

Each page will be a chunk. keep_tables_as_one_chunk will be ignored if this is true.

Check pages for handwriting. Will use specialized models if handwriting is found.

Timeout in seconds