You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
DocumentSearch should be capable to automatically determine document type based on the provided file.
This may be implemented with allowing additional type Source in async def ingest_document(self, document: Union[DocumentMeta, Document], document_processor: Optional[BaseProvider] = None) -> None: method inside DocumentSearch - then fetching source and determining document type
Motivation
Right now the main entrypoint to document ingestion pipeline requires DocumentMeta instance, which has required field document_type. It forces users to either know document type beforhand, or to detect it outsite of ragbits.
Additional context
No response
The text was updated successfully, but these errors were encountered:
Feature description
DocumentSearch should be capable to automatically determine document type based on the provided file.
This may be implemented with allowing additional type
Source
inasync def ingest_document(self, document: Union[DocumentMeta, Document], document_processor: Optional[BaseProvider] = None) -> None:
method insideDocumentSearch
- then fetching source and determining document typeMotivation
Right now the main entrypoint to document ingestion pipeline requires DocumentMeta instance, which has required field document_type. It forces users to either know document type beforhand, or to detect it outsite of ragbits.
Additional context
No response
The text was updated successfully, but these errors were encountered: