Skip to content

Releases: Olow304/memvid

v0.1.3 - Memvid

05 Jun 15:56
@Olow304 Olow304
v0.1.3
644607c
Compare
Choose a tag to compare
v0.1.3 - Memvid Latest
Latest

🎉 v0.1.3 Release

🐳 Docker Support for Advanced Codecs

  • Cross-platform H.265/HEVC encoding - No more codec dependency nightmares!
  • Automated Docker container management for non-MP4 codecs
  • Works seamlessly on Windows (WSL), macOS, and Linux
  • Handles all FFmpeg operations in isolated environment

🤖 Multi-LLM Provider Support

  • Added Google Gemini support - Use provider='google' in MemvidChat
  • Added Anthropic Claude support - Use provider='anthropic' in MemvidChat
  • New modular LLMClient class for easy provider management
  • Consistent interface across all LLM providers

⚙️ Enhanced Configuration System

  • Centralized configuration management via config.py
  • Per-codec configuration profiles for optimal compression
  • Flexible FFmpeg parameter customization
  • Support for different video container formats (MP4, MKV, AVI)

✨ New Examples

codec_comparison.py

Compare different video codecs side-by-side:

  • Test H.264, H.265, and MP4V compression ratios
  • Benchmark encoding/decoding performance
  • Find the optimal codec for your use case

file_chat.py

Enhanced document processing and chat:

  • Process entire directories or specific files
  • Configurable chunking parameters
  • Support for PDF, EPUB, HTML, and text files
  • Load and chat with existing memories
  • Graceful FAISS index fallback for small datasets

🔧 Improvements

Better Error Handling

]- Improved error messages for missing dependencies

  • Better handling of codec-specific issues

Configuration Flexibility

  • Customizable chunk sizes and overlap
  • Per-codec video parameters (CRF, preset, profile)
  • Configurable frame rates and sizes

Package Structure

  • Moved LLM providers to optional dependencies: pip install memvid[llm]
  • Added EPUB support as optional: pip install memvid[epub]
  • Core dependencies remain minimal

📦 Installation

# Basic installation
pip install memvid==0.1.3

API Keys

Set your API keys as environment variables:

export OPENAI_API_KEY="sk-..."
export GOOGLE_API_KEY="AIza..."
export ANTHROPIC_API_KEY="sk-ant-..."

🙏 Acknowledgments

Special thanks to our contributors who made this release possible with Docker support, codec testing, and multi-LLM integration!

@TyJK

Contributors

TyJK
Assets 3
Loading

v0.1.2 - Memvid

28 May 16:48
@Olow304 Olow304
v0.1.2
1fe05a6
Compare
Choose a tag to compare
v0.1.2 - Memvid

🎉 Memvid v0.1.2 - Cross-Platform Compatibility

🚀 What's New

🔧 Major Improvements

  • 🌐 Universal Installation: Memvid now uses OpenCV's built-in QR decoder, eliminating all platform-specific installation issues. No more libzbar not found errors on Windows, macOS, or Linux!
  • 📚 Native PDF Support: Added add_pdf() method to MemvidEncoder for direct PDF processing
    encoder = MemvidEncoder()
    encoder.add_pdf("book.pdf") # That's it!
  • 🔌 Flexible Dependencies: Switched from pinned to flexible version requirements, resolving numpy compatibility
    issues across different Python environments

✨ New Features

  • Added comprehensive PDF book chat example
  • Improved error messages for missing optional dependencies
  • Enhanced documentation with troubleshooting guides

🐛 Bug Fixes

  • Fixed numpy dtype compatibility errors
  • Resolved architecture mismatch issues on Apple Silicon
  • Fixed import errors in mixed Python environments

📖 Documentation

  • Added detailed installation instructions with virtual environment setup
  • Created CONTRIBUTING.md with development guidelines
  • Updated README with badges, use cases, and comparison table
  • Added complete working examples

💡 Upgrading

pip install --upgrade memvid==0.1.2

For PDF support:
pip install PyPDF2

🙏 Thanks

Special thanks to early adopters who reported installation issues. Memvid is now truly plug-and-play across all
platforms!

Loading