H2h2o
Document Ingestion

Creates a job to add plain text to a collection.

Creates a job to add plain text to a collection.

post/ingest/plain_text/job

Request

Query parameters

collection_idstring required

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

file_namestring required

String of the file name to use for the document.

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).

metadatastring

String with json-encoded metadata for the document.

timeoutnumber double

Timeout in seconds

Request body text/plain

string required

Response

Successful operation

idstring required
namestring required
overall_status'in progress' | 'completed' | 'failed' | 'canceled' required
statusstring
passed_percentagenumber double required
failed_percentagenumber double required
progressnumber double required
created_atstring date-time required
updated_atstring date-time required
kindstring required
errorsstring[] required
durationstring required
duration_secondsnumber double required
canceled_bystring
cancel_reasonstring
timeoutnumber double
start_timenumber double
files_totalinteger
files_failedinteger

Changes

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