H2h2o
Document Ingestion

Adds files from the local system into a collection.

Adds files from the local system into a collection.

post/ingest/file_system

Request

Query parameters

collection_idstring required

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

gen_doc_summariesboolean

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

gen_doc_questionsboolean

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

audio_input_languagestring

Language of audio files.

ocr_modelstring

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).

tesseract_langstring

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

keep_tables_as_one_chunkboolean

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

chunk_by_pageboolean

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

handwriting_checkboolean

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

ingest_mode'standard' | 'agent_only'

Ingest mode to use. - standard - Files will be ingested for use with RAG - agent_only - Bypasses standard ingestion. Files can only be used with agents.

timeoutnumber double

Timeout in seconds

Request body

root_dirstring required

String path of where to look for files.

globstring required

String of the glob pattern used to match files in the root directory.

Response

Successful operation

Changes

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