Update Unstructured Provider, Fix Type Error in SDK #2103
Merged
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
There was a problem hiding this comment.
❌ Changes requested. Reviewed everything up to dbc0495 in 2 minutes and 49 seconds
More details
- Looked at
122lines of code in7files - Skipped
0files when reviewing. - Skipped posting
15drafted comments based on config settings.
1. docker/compose.full.swarm.yaml:388
- Draft comment:
Image updated to 1.0.3. Verify that the new version is backwards compatible. - Reason this comment was not posted:
Confidence changes required:0%<= threshold50%
None
2. docker/compose.full.yaml:196
- Draft comment:
Image updated to 1.0.3; ensure environment consistency with other compose files. - Reason this comment was not posted:
Confidence changes required:0%<= threshold50%
None
3. docker/compose.yaml:52
- Draft comment:
r2r-dashboard image updated to 1.0.3. This should align with other configs. - Reason this comment was not posted:
Confidence changes required:0%<= threshold50%
None
4. py/core/providers/ingestion/r2r/base.py:259
- Draft comment:
Remove commented-out hardcoded parser override code if no longer needed. - Reason this comment was not posted:
Comment looked like it was already resolved.
5. py/pyproject.toml:7
- Draft comment:
Version bumped from 3.5.7 to 3.5.8; ensure changelog is updated accordingly. - Reason this comment was not posted:
Confidence changes required:0%<= threshold50%
None
6. py/sdk/sync_methods/documents.py:65
- Draft comment:
Updated type hint for ingestion_mode to allow IngestionMode | str. Verify associated documentation matches this change. - Reason this comment was not posted:
Comment did not seem useful. Confidence is useful =0%<= threshold50%
The comment is asking the PR author to verify that the documentation matches the code change. This falls under the rule of not asking the author to ensure or verify things. The comment does not provide a specific suggestion or point out a potential issue with the code itself.
7. docker/compose.full.swarm.yaml:388
- Draft comment:
Updated r2r-dashboard image to version 1.0.3. Confirm that the new version is compatible with dependent services. - Reason this comment was not posted:
Confidence changes required:33%<= threshold50%
None
8. docker/compose.full.yaml:193
- Draft comment:
Ensure consistent update of r2r-dashboard image to version 1.0.3 across all compose configurations. - Reason this comment was not posted:
Confidence changes required:33%<= threshold50%
None
9. docker/compose.yaml:50
- Draft comment:
r2r-dashboard image updated to version 1.0.3 here as well. Verify consistency across environments. - Reason this comment was not posted:
Confidence changes required:33%<= threshold50%
None
10. py/core/providers/ingestion/r2r/base.py:259
- Draft comment:
Removed hardcoded parser override check. Ensure that fallback processing for 'zerox' PDF override is intentionally relaxed and consistent with other providers. - Reason this comment was not posted:
Confidence changes required:33%<= threshold50%
None
11. py/core/providers/ingestion/unstructured/base.py:293
- Draft comment:
Added explicit handling for parser_override values 'zerox' and 'ocr'. Consider adding an 'else' branch to log or handle unexpected override values. - Reason this comment was not posted:
Confidence changes required:33%<= threshold50%
None
12. py/pyproject.toml:7
- Draft comment:
Version bumped to 3.5.8. Ensure that the changelog and release notes are updated appropriately. - Reason this comment was not posted:
Confidence changes required:33%<= threshold50%
None
13. py/sdk/sync_methods/documents.py:65
- Draft comment:
Updated 'ingestion_mode' type annotation to accept both IngestionMode and str to fix type errors. Verify that downstream usage correctly handles both types. - Reason this comment was not posted:
Confidence changes required:33%<= threshold50%
None
14. py/core/providers/ingestion/r2r/base.py:222
- Draft comment:
Typographical error: Consider renaming 'text_spliiter' to 'text_splitter' for clarity and consistency. - Reason this comment was not posted:
Comment was not on a location in the diff, so it can't be submitted as a review comment.
15. py/core/providers/ingestion/unstructured/base.py:416
- Draft comment:
Typographical error: The word 'inadvertedly' in the TODO comment should be corrected to 'inadvertently'. - Reason this comment was not posted:
Comment was not on a location in the diff, so it can't be submitted as a review comment.
Workflow ID: wflow_ZsHvBUDRFqYo7csL
Want Ellipsis to fix these issues? Tag @ellipsis-dev in a comment. You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet mode, and more.
8000
| parser_name=f"zerox_{DocumentType.PDF.value}", | ||
| ): | ||
| elements.append(element) | ||
| if parser_overrides[document.document_type.value] == "zerox": |
There was a problem hiding this comment.
Consider consolidating duplicated logic in the added branch for OCR override and ensure warning message clarity.
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.
Important
Update
r2r-dashboardimage version, add OCR parser support, and fix type error in SDK.r2r-dashboardimage version to1.0.3incompose.full.swarm.yaml,compose.full.yaml, andcompose.yaml.R2RIngestionProviderinr2r/base.py.ocrparser override inUnstructuredIngestionProviderinunstructured/base.py.ingestion_modeincreate()method indocuments.pyto acceptIngestionMode | str.3.5.8inpyproject.toml.This description was created by
for dbc0495. It will automatically update as commits are pushed.