feat: Add batch uploader and document re-parsing tools to Python SDK #38
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
added 4 commits
January 9, 2026 19:40
# Conflicts: # .gitignore # api/apps/sdk/doc.py # sdk/python/ragflow_sdk/modules/dataset.py
…ailed_documents.py
|
keyang.lk seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account. You have signed the CLA already but the status is still pending? Let us recheck it. |
Contributor
There was a problem hiding this comment.
Pull request overview
This PR adds comprehensive batch processing tools to the RAGFlow Python SDK, including a batch uploader for efficient bulk document uploads and a tool for re-parsing failed documents. The implementation includes extensive test coverage, documentation, and example scripts.
Key Changes:
- New tools module with BatchUploader, DocumentExtractor, FieldMapper, FileReader, and FailedDocumentReparser
- Batch document upload API endpoint with metadata support
- Optimized document parsing with batch processing
- Comprehensive test suites with unit tests
- Enhanced error handling and response parsing in SDK core
Reviewed changes
Copilot reviewed 22 out of 24 changed files in this pull request and generated 30 comments.
Show a summary per file
| File | Description |
|---|---|
sdk/python/ragflow_sdk/tools/batch_uploader.py |
Implements batch upload with snapshot-based resume support and retry logic |
sdk/python/ragflow_sdk/tools/reparse_failed_documents.py |
Tool for identifying and re-parsing failed documents with pagination |
sdk/python/ragflow_sdk/tools/document_extractor.py |
Iterator-based document extraction from various file formats |
sdk/python/ragflow_sdk/tools/field_mapper.py |
Flexible field mapping with auto-detection capabilities |
sdk/python/ragflow_sdk/tools/file_reader.py |
Multi-format file reader supporting JSON, CSV, Excel, etc. |
sdk/python/ragflow_sdk/tools/models.py |
Data models for tools including Snapshot, FileCursor, Document |
sdk/python/test/test_tools/ |
Comprehensive unit tests for all new tools |
api/apps/sdk/doc.py |
New batch upload API endpoint and optimized document parsing |
sdk/python/ragflow_sdk/ragflow.py |
Enhanced response parsing with proper error handling |
sdk/python/ragflow_sdk/modules/dataset.py |
New upload_documents_with_meta method with batch support |
sdk/python/pyproject.toml |
Added test dependencies (pandas, pytest-cov, etc.) |
sdk/python/examples/ |
Example scripts for batch upload and document reparsing |
web/.env |
PORT changed from 9222 to 9223 |
| snapshot_file=snapshot_file, | ||
| file_extension=file_extension | ||
| ): | ||
| current_file_path = file_path |
There was a problem hiding this comment.
Variable current_file_path is not used.
Suggested change
| current_file_path = file_path |
| """Disable beartype by monkey patching beartype_this_package to do nothing.""" | ||
| try: | ||
| import beartype.claw | ||
| original_beartype_this_package = beartype.claw.beartype_this_package |
There was a problem hiding this comment.
Variable original_beartype_this_package is not used.
Suggested change
| original_beartype_this_package = beartype.claw.beartype_this_package |
| return res.json() | ||
| except Exception as e: | ||
| error_url = url or res.url if hasattr(res, 'url') else 'unknown' | ||
| raise Exception(f"Failed to parse JSON response (status {res.status_code}): {str(e)}. Response text: {res.text[:500]}") |
There was a problem hiding this comment.
Variable error_url is not used.
Suggested change
| raise Exception(f"Failed to parse JSON response (status {res.status_code}): {str(e)}. Response text: {res.text[:500]}") | |
| raise Exception( | |
| f"Failed to parse JSON response (status {res.status_code}, URL: {error_url}): " | |
| f"{str(e)}. Response text: {res.text[:500]}" | |
| ) |
| # Create test file | ||
| filename = f"test.{extension}" | ||
| create_method = getattr(self, create_func) | ||
| filepath = create_method(temp_dir, filename, test_data) |
There was a problem hiding this comment.
Variable filepath is not used.
Suggested change
| filepath = create_method(temp_dir, filename, test_data) | |
| _ = create_method(temp_dir, filename, test_data) |
Comment on lines
+293
to
+295
| filepath = create_method(temp_dir, filename, test_data) | ||
| else: # xlsx or xls | ||
| filepath = self._create_excel_file(temp_dir, filename, test_data) |
There was a problem hiding this comment.
Variable filepath is not used.
Suggested change
| filepath = create_method(temp_dir, filename, test_data) | |
| else: # xlsx or xls | |
| filepath = self._create_excel_file(temp_dir, filename, test_data) | |
| create_method(temp_dir, filename, test_data) | |
| else: # xlsx or xls | |
| self._create_excel_file(temp_dir, filename, test_data) |
| import os | ||
| import tempfile | ||
| import pytest | ||
| from unittest.mock import Mock, MagicMock, patch, call |
There was a problem hiding this comment.
Import of 'MagicMock' is not used.
Import of 'patch' is not used.
Import of 'call' is not used.
Suggested change
| from unittest.mock import Mock, MagicMock, patch, call | |
| from unittest.mock import Mock |
| import tempfile | ||
| import pytest | ||
| from unittest.mock import Mock, MagicMock, patch, call | ||
| from pathlib import Path |
There was a problem hiding this comment.
Import of 'Path' is not used.
Suggested change
| from pathlib import Path |
| from pathlib import Path | ||
|
|
||
| from ragflow_sdk.tools import BatchUploader, DocumentExtractor, FieldMapper | ||
| from ragflow_sdk.tools.models import Snapshot, FileCursor |
There was a problem hiding this comment.
Import of 'Snapshot' is not used.
Suggested change
| from ragflow_sdk.tools.models import Snapshot, FileCursor | |
| from ragflow_sdk.tools.models import FileCursor |
| # | ||
|
|
||
| import pytest | ||
| from unittest.mock import Mock, MagicMock, patch, call |
There was a problem hiding this comment.
Import of 'MagicMock' is not used.
Import of 'patch' is not used.
Suggested change
| from unittest.mock import Mock, MagicMock, patch, call | |
| from unittest.mock import Mock |
|
|
||
| beartype.claw.beartype_this_package = noop_beartype_this_package | ||
| os.environ['BEARTYPE_DISABLE'] = '1' | ||
| except ImportError: |
There was a problem hiding this comment.
'except' clause does nothing but pass and there is no explanatory comment.
Suggested change
| except ImportError: | |
| except ImportError: | |
| # beartype is an optional dependency in tests; if it's not installed, just skip the monkey-patch. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
Summary
This PR extends the RAGFlow Python SDK with powerful batch processing tools for document management, including a batch uploader and a tool for re-parsing failed documents.
Key Features
BatchUploaderclass for efficient bulk document uploads with progress tracking and error handlingChanges
ragflow_sdk/tools/batch_uploader.py- Batch upload functionalityragflow_sdk/tools/reparse_failed_documents.py- Document re-parsing toolragflow_sdk/tools/document_extractor.py- Document extraction utilitiesragflow_sdk/tools/field_mapper.py- Field mapping systemragflow_sdk/tools/file_reader.py- Multi-format file readerragflow_sdk/tools/models.py- Data models for toolsragflow_sdk/modules/dataset.pywith batch operation supportSolution Description