Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The backend supports PDFs (https://github.com/psychic-api/psychic/blob/main/server/connectors/google_drive_connector/google_drive_connector.py). Docx can be exported from Google API into PDF as well.
The current view, "DOCS" allows users to select any files that are MIME-types supported by Gdrive -- Could be Drawings, SpreadSheets, iPynb etc. Even if the handling for random files is fine on the backend, the users would probably expect the files they selected to be successfully uploaded. Better to handle "DOCUMENTS" (Google Drive Documents -- google docs)
or "PDFS" view to show exclusively the kind of docs we can process for now.
Also, should be fairly straightforward to support Most types from Google Drive (Sheets, Docx, PDFs) mainly using Unstructured loader // Random files with textual data can also be read using UnstructuredFileLoader.