feat: add Docling JSON ingestion #783
Conversation
Signed-off-by: Panos Vagenas <[email protected]>
Merge ProtectionsYour pull request matches the following merge protections and will not be merged until they are valid. 🟢 Enforce conventional commitWonderful, this rule succeeded.Make sure that we follow https://www.conventionalcommits.org/en/v1.0.0/
|
| def is_valid(self) -> bool: | ||
| return True |
There was a problem hiding this comment.
According to existing implementations, this method should only return True if the provided content from path_or_stream is supported by this backend.
I think that the logic in convert should be moved to the constructor and is_valid should just evaluate if the constructor was successful.
| elif mime == "application/json": | ||
| if ( | ||
| InputFormat.JSON_DOCLING in formats | ||
| and '"schema_name": "DoclingDocument"' in content_str | ||
| ): | ||
| input_format = InputFormat.JSON_DOCLING | ||
|
|
There was a problem hiding this comment.
I agree to keep the disambiguation here, like the XML pattern.
Just FYI, for a further PR, we thought of creating an abstract method in the DeclarativeDocumentBackend that would require the implementation of these types of disambiguation, given a fragment of a document content. We would then avoid having backend-specific logic in this method.
Resolves #781.