Docfinder v2.0.0

What's Changed

Added

• Local RAG (AI Chat) — ask questions about your documents using a fully local LLM. No data leaves your
  machine.
  • Automatic model selection based on system RAM: Qwen2.5-7B (16 GB+), Qwen2.5-3B (8–16 GB), or Qwen2.5-1.5B
    (any)
  • GPU acceleration: Apple Metal on Apple Silicon, CUDA on NVIDIA, CPU fallback
  • Models downloaded once to ~/.cache/docfinder/models/ via Hugging Face Hub
  • Chat button on search results with slide-up conversation panel
• RAG Settings UI — toggle AI Chat, view hardware detection, select and download models with real-time
  progress tracking
• Page-aware context retrieval — RAG uses document structure for smarter context:
  • PDF: real page boundaries
  • Markdown: heading-based sections
  • Word (.docx): groups of 10 paragraphs
  • Plain text: virtual pages of ~3000 characters
• Multi-format document support — DocFinder now indexes PDF, plain text (.txt), Markdown (.md), and Word
  (.docx) files
• Spotlight-style quick-search panel (experimental) — floating NSPanel summoned via global hotkey without
  switching to the main window

Changed

• Redesigned UI theme
• build_chunks() now stores page number in chunk metadata for all document formats
• New [rag] optional dependency group (pip install docfinder[rag])

📦 Downloads

Platform	Download
macOS	DocFinder-macOS.dmg
Windows	DocFinder-Windows-Setup.exe
Linux	DocFinder-Linux-x86_64.AppImage

Full Changelog: v1.2.0...v2.0.0

What's Changed

• Feature/rag by @filippostanghellini in #29

Full Changelog: v1.2.0...v2.0.0

Docfinder v2.0.0-beta

What's Changed

Added

• Multi-format document support — DocFinder now indexes PDF, plain text (.txt), Markdown (.md), and Word (.docx) files in addition to PDFs; drop any supported file or folder in the Index tab and it will be picked up automatically
• Spotlight-style quick-search panel (experimental) — a floating panel summoned via the global hotkey lets you search documents instantly without switching to the main window.

Changed

• Redesigned UI theme

Notes

⚠️ The Spotlight panel is experimental and still being refined — it may behave unexpectedly in some scenarios. Feedback welcome.

---

📦 Downloads

Platform	Download
macOS	DocFinder-macOS.dmg
Windows	DocFinder-Windows-Setup.exe
Linux	DocFinder-Linux-x86_64.AppImage

Full Changelog: v1.2.0...v2.0.0-beta

Docfinder v1.2.0

What's Changed

Fixed

• Windows: Fixed crash on startup — create_window() raised TypeError: unexpected keyword argument 'icon' on some pywebview builds;
  the app now falls back gracefully
• macOS: Fixed dock icon showing Python logo — the DocFinder logo is now correctly shown in the dock when running from source

Added

• Global hotkey — bring DocFinder to the front from any app with a configurable system-wide shortcut (⌘+Shift+F on macOS,
  Ctrl+Shift+F on Windows/Linux)
• Settings tab — enable/disable the hotkey and change the key combination via an interactive capture modal
• Native folder picker — "Browse…" button opens Finder/Explorer directly instead of requiring manual path input

Performance

• Indexing 2–4× faster — batch SQLite inserts, larger embedding batches (8→32), removed unnecessary GC calls and artificial
  file-batching loops
• First request instant — embedding model loaded once at startup instead of on every request

UI

• Real-time indexing progress bar with file counter and current filename
• macOS-native frosted-glass header
• ⌘K / Ctrl+K shortcut to jump to search from any tab
• Drag & drop folder support in the Index tab
• Relevance score shown as percentage

📦 Downloads

Platform	Download
macOS	DocFinder-macOS.dmg
Windows	DocFinder-Windows-Setup.exe
Linux	DocFinder-Linux-x86_64.AppImage

Full Changelog: v1.1.2...v1.2.0

What's Changed

• Indexing optimization, UI improvement and v1.2.0 release preparation by @filippostanghellini in #28

Full Changelog: v1.1.2...v1.2.0

DocFinder v1.1.2

What's Changed

✅ Fixed

• Windows: Silent startup crash resolved (multiprocessing.freeze_support()), added torch.cuda hidden imports, native error dialog, and persistent startup logging.
• UI: The Search button no longer jumps on hover.

Added

• CI: Smoke tests for macOS, Windows, and Linux (startup/log verification).

Changed

• Improved multiprocessing handling for PyInstaller-built apps.

📦 Downloads

Platform	Download
macOS	DocFinder-macOS.dmg
Windows	DocFinder-Windows-Setup.exe
Linux	DocFinder-Linux-x86_64.AppImage

Full Changelog: v1.1.1...v1.1.2

What's Changed

• Fix windows bug by @filippostanghellini in #19

Full Changelog: v1.1.1...v1.1.2

DocFinder v1.1.1

What's Changed

✨ Added

• Improved User Interface with better design and user experience

🔄 Changed

• License changed from MIT to AGPL-3.0 to comply with PyMuPDF licensing requirements
• Switched PDF parsing from pypdf to PyMuPDF for faster and more reliable text extraction
• Completely revamped README with better structure and documentation

📦 Downloads

Platform	Download
macOS	DocFinder-macOS.dmg
Windows	DocFinder-Windows-Setup.exe
Linux	DocFinder-Linux-x86_64.AppImage

Full Changelog: v1.0.1...v1.1.1

What's Changed

• UI improvements and v1.1.1 release preparation by @filippostanghellini in #17

Full Changelog: v1.0.1...v1.1.1

DocFinder v1.0.1

🐛 Bug Fix Release

Fixed

• Fixed Linux build failing due to disk space issues on CI runner
• Excluded unnecessary CUDA/GPU libraries from bundle (GPU support still works via system libraries)
• Optimized bundle size by using CPU-only PyTorch for builds

Downloads

• macOS: DocFinder-macOS.dmg
• Windows: DocFinder-Windows-Setup.exe
• Linux: DocFinder-Linux-x86_64.AppImage

Notes

GPU acceleration (NVIDIA CUDA, AMD ROCm, Apple Metal) is still fully supported - the application uses GPU libraries from your system at runtime.

Full Changelog: v1.0.0...v1.0.1

DocFinder v1.0.0

🎉 First Desktop Release

DocFinder is now available as a native desktop application!

Downloads

Platform	File	Notes
macOS	DocFinder-macOS.dmg	Drag to Applications
Windows	DocFinder-Windows-Setup.exe	Run installer
Linux	DocFinder-Linux-x86_64.AppImage	Make executable

What's New

• 🖥️ Native desktop GUI using pywebview
• 📦 Standalone app - no Python required
• 🔍 Full semantic PDF search
• 📁 Index folders directly from the app
• 💾 Database stored in ~/Documents/DocFinder/

Installation Notes

See README for security bypass instructions (unsigned app).

Full Changelog: v0.2.0...v1.0.0

What's Changed

• Refactor PDF chunking and indexing for streaming by @filippostanghellini in #12
• Add desktop GUI and build scripts for DocFinder by @filippostanghellini in #14

Full Changelog: v0.2.0...v1.0.0

v0.2.0 - Performance Optimizations & Security Improvements

This release brings major performance improvements, memory optimizations, and critical security fixes!

Highlights

• 1.7x faster on Apple Silicon with ONNX backend
• 30% less memory usage with batch processing
• Critical security fixes for path traversal vulnerabilities
• Developer tools for better development workflow

🆕 What's New

Features

ONNX Backend Support

• Automatic hardware detection for Apple Silicon, NVIDIA CUDA, AMD ROCm
• Up to 1.7x faster on compatible hardware
• Configurable backend selection via EmbeddingConfig

Memory Optimization

• Mini-batch processing (4 texts at a time) prevents OOM errors
• Batch file indexing (2 files at a time) for large document sets
• Strategic garbage collection after each batch
• Successfully indexes large collections on 16GB RAM systems

Development Tools

• Makefile for common development tasks
• Pre-commit hooks for code quality
• check-ci.sh to test CI checks locally before pushing

Security Fixes

• 🚨 CRITICAL: Path Traversal Vulnerabilities Fixed (CWE-22)
  • Canonical path validation with os.path.realpath()
  • String prefix check for safe directory containment
  • Restricted file access to safe base directories
  • Null byte validation
  • Symlink attack prevention
• Fixed log injection vulnerability using safe format strings
• All paths validated before filesystem operations
• All GitHub CodeQL security checks passed

Bug Fixes

• Fixed Windows path handling for cross-platform compatibility
• Fixed path handling with spaces in directory names
• Fixed web form validation for special characters
• Fixed memory exhaustion on 16GB RAM systems
• All lint and formatting issues resolved

Performance Improvements

Platform	Speed Improvement	Memory Reduction
Apple Silicon (M4)	~1.7x faster	-30% RAM
NVIDIA GPU	2-5x faster	Optimized
AMD GPU (ROCm)	Optimized	Optimized
Intel Mac (ONNX)	~1.5x faster	Improved

Upgrade Guide

# Standard installation
pip install --upgrade docfinder

# With GPU support (NVIDIA)
pip install --upgrade "docfinder[gpu]"

Initial Release

Changelog

All notable changes to this project will be documented in this file.

The format is based on Keep a Changelog,
and this project adheres to Semantic Versioning.

Unreleased

0.1.0 - 2025-11-08

Added

• Initial release of DocFinder
• PDF text extraction and chunking with pypdf
• Local semantic embeddings using sentence-transformers and onnxruntime
• SQLite-based vector storage with BLOB storage
• Command-line interface for indexing, searching, and pruning
• Top-k semantic search using cosine similarity
• Optional FastAPI web interface for interactive document search
• Multi-platform support (macOS, Linux, Windows)
• Python 3.10+ compatibility
• Comprehensive test suite with pytest
• CI/CD pipeline with GitHub Actions
• Code quality checks with ruff
• Security scanning with CodeQL and dependency review
• Automated coverage reporting

Changed

• Implemented lazy imports for web dependencies to allow basic CLI usage without web extras

Fixed

• Fixed import errors when using CLI without web extras installed
• Fixed linting issues for consistent code style
• Updated ruff configuration to use non-deprecated settings