Add unified academic agent(notes-parser + summariser), OCR-enabled file parsing, and PDF export endpoints #2
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
Major Features: - Advanced OCR pipeline for handwritten/scanned documents - Multi-strategy OCR with quality scoring - Image preprocessing with OpenCV and PIL - AI-powered text correction using LLM - Full extracted text debugging output - Improved file handling and validation Configuration: - Increased file size limit to 100MB - Enhanced OCR settings and preprocessing options - Better error handling and logging File Management: - Added .gitignore with comprehensive rules - Created local_files directory for uploads - Removed unused test files for cleaner codebase - Added support for PPTX files Performance: - Optimized prompts for better extraction quality - Reduced token usage for faster processing - Enhanced plausibility checks for handwritten content
- Remove .env file containing API keys and secrets - Remove all __pycache__ directories and .pyc files - Keep only essential source code and documentation - These files are properly ignored in .gitignore
- Merged parsing and summarizing into single AcademicAgent - Simplified API endpoints: /parse, /parse-file, /summarize, /summarize-file - Added comprehensive PDF export functionality with formatted reports - Moved legacy files to legacy/ folder for backup - Removed context limits for better full-content processing - Enhanced summarization prompts to use bullet point format - Added reportlab and markdown dependencies for PDF generation - Maintained backward compatibility with existing functionality New Features: - /parse/export-pdf and /parse-file/export-pdf for parsing results - /summarize/export-pdf and /summarize-file/export-pdf for summary results - Professional PDF formatting with metadata, tables, and proper styling - Enhanced OCR support and file processing capabilities Breaking Changes: - Removed multiple endpoint variations - Consolidated agents into single unified system
- Updated to reflect new unified AcademicAgent architecture - Added comprehensive documentation for PDF export functionality - Simplified API endpoint documentation - Added new usage examples with PDF generation - Documented architectural changes and legacy support - Updated project structure to show new organization - Added 'What's New' section highlighting September 2025 updates - Enhanced configuration section with PDF export settings - Updated acknowledgments to include ReportLab
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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.
Description
AcademicAgentthat can parse notes and create summaries in one step. Also supportsparse_onlyandsummarize_only.POST /parse,POST /parse-filePOST /summarize,POST /summarize-filePOST /parse/export-pdf,POST /parse-file/export-pdf,POST /summarize/export-pdf,POST /summarize-file/export-pdfpdf_exporter.