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

- **LibreOffice Integration**: Enhanced document conversion capabilities

- Automatic detection and use of LibreOffice when available

- Improved conversion quality for Office documents (DOCX, XLSX, PPTX)

- Better support for OpenDocument formats (ODT, ODS, ODP)

- Enhanced HWP/HWPX document handling with LibreOffice

- Fallback mechanisms when LibreOffice is not available

- File converter now prioritizes LibreOffice for office document conversions

- Improved error messages and conversion feedback

- Better handling of conversion failures with automatic fallback methods

- **Video Input Support**: Process and extract information from video files

- Automatic audio extraction from video formats

- Frame extraction for visual content analysis

- Support for common video formats (MP4, AVI, MOV, etc.)

- **Audio Input Support**: Direct processing of audio files

- Transcription using faster-whisper for speech-to-text

- Support for various audio formats (MP3, WAV, M4A, etc.)

- **Multimedia Processing Pipeline**: New `multimedia_processor.py` module

- Unified interface for handling video and audio inputs

- Automatic format detection and conversion

- Integration with existing document processing pipeline

- Enhanced file converter to support multimedia file types

- Updated dependencies to include faster-whisper for audio transcription

- Configurable `--timeout` parameter for `perf-test` command

- Allows custom request timeout in seconds

- No timeout if parameter is not specified (replaces hardcoded 300 seconds)

- Modified `perf-test` command to accept optional timeout parameter

- Updated error messages to show actual timeout value instead of hardcoded 300 seconds

- Auto-restart functionality for Web, API, and MCP servers with `--auto-restart` flag

- Request timeout monitoring for API server (triggers restart on timeout when auto-restart is enabled)

- Optional `--max-retries` parameter (unlimited retries if not specified)

- Configurable `--retry-delay` parameter for restart attempts

- `--timeout` parameter is now optional for both web and API (no timeout if not specified)

- `--pages` parameter is now optional for web interface (process all pages if not specified)

- Updated FastAPI from deprecated `@app.on_event` to modern lifespan context manager

- API server now tracks request processing activity via `/activity` endpoint

- Fixed deprecation warning in FastAPI shutdown event handler

- Improved process cleanup in auto-restart monitor

- Better handling of zombie processes when restarting services

- **BREAKING CHANGE**: Modified embedding synthesis method from element-wise addition to concatenation

- This change doubles the embedding dimension by concatenating two model outputs instead of adding them

- Results in better semantic representation but requires reindexing of existing documents

- Changed `np.add(emb_1, emb_2)` to `np.concatenate([emb_1, emb_2])` in `get_embedding` method

- Updated batch processing in `get_embeddings` to use list comprehension with concatenation

- Both embeddings are now L2-normalized after concatenation

- Removed `mteb_embedding.py` test file

- Previous release details...

[](http://arxiv.org/abs/2507.23217)

sudo apt-get install libreoffice libreoffice-l10n-ko # l10n-ko for Korean support

sudo yum install libreoffice

sudo dnf install libreoffice

brew install libreoffice

sudo pacman -S libreoffice-fresh

pip install faster-whisper

sudo apt-get install ffmpeg

brew install ffmpeg

sudo yum install epel-release

sudo yum install ffmpeg

choco install ffmpeg

sudo apt-get install pandoc

brew install pandoc

pip install beautifulsoup4 markdown pdfkit

sudo apt-get install fonts-nanum fonts-nanum-coding fonts-nanum-extra

sudo apt-get install tesseract-ocr tesseract-ocr-kor

brew install tesseract tesseract-lang

- **LibreOffice Integration**: Better quality conversions for Office documents when LibreOffice is installed

- **Improved Format Support**: Enhanced handling of DOCX, XLSX, PPTX, ODT, ODS, ODP, HWP/HWPX

- **Video/Audio Processing**: Extract and analyze content from video and audio files

- **Automatic Setup**: DocsRay now automatically installs dependencies and downloads models

- Auto-restart capability for all servers

- Enhanced embedding method (v1.7.0) - requires reindexing existing documents

For detailed changelog, see [CHANGELOG.md](CHANGELOG.md)

docsray perf-test document.pdf "What is this?" --timeout 600

DocsRay is built on top of these excellent open source projects:

- **llama.cpp** - GGML/GGUF model inference (MIT License)

- **PyMuPDF** - PDF processing (AGPL-3.0 License)

- **pdfplumber** - PDF text extraction (MIT License)

- **FastAPI** - Web framework (MIT License)

- **Gradio** - Web UI components (Apache-2.0 License)

- **OpenCV** - Image processing (Apache-2.0 License)

- **faster-whisper** - Audio transcription (MIT License)

- **Pandas** - Data manipulation (BSD-3-Clause License)

- **NumPy** - Numerical computing (BSD-3-Clause License)

- **scikit-learn** - Machine learning utilities (BSD-3-Clause License)

version="1.9.0",