[WIP]: Add multimodal support via lance #39
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This commit introduces multimodal parsing capabilities to the `ingest` command, allowing the extraction of both text and associated image data from various document formats.
Key changes include:
- A new `--multimodal` flag for the `ingest` command in `synthetic_data_kit/cli.py`.
- Updates to `synthetic_data_kit/core/ingest.py` to manage the multimodal workflow.
- Modifications to the following parsers in `synthetic_data_kit/parsers/` (DOCX, PDF, PPTX, HTML) to:
- Extract images when `--multimodal` is enabled.
- Implement initial image-text association logic:
- DOCX: First image in document associated with all text blocks.
- PDF: First image on a page associated with all text from that page.
- PPTX: First image on a slide associated with all text from that slide.
- HTML: Text from content tags and `alt`-text from `<img>` tags are extracted, with images linked to their `alt`-text entries.
- Their `save` methods now create Lance datasets with 'text' (string) and 'image' (binary, or None) columns when in multimodal mode.
- Unit tests for parser `parse()` methods have been added. HTML and TXT tests are functional. DOCX tests use mocking. PDF and PPTX `parse()` tests have ongoing mocking challenges. All `save()` method tests are currently blocked by an external `lance` library environment issue.
- `README.md` has been updated to document the new feature, usage, and association heuristics.
This feature provides a foundational capability for processing documents with embedded images. Future enhancements may include more sophisticated image-text association techniques.
facebook-github-bot
added
the
CLA Signed
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Uh oh!
There was an error while loading. Please reload this page.