🚀 big-AGI 1.7.0 - Attachment Theory

1.7.0 rolls in with a game-changing attachment system and more, just in time for the holidays. 🌐✨

• Attachments System Overhaul: the attachments system is brand new. You can now attach files in more than 6 ways, ensuring flexibility and efficiency in bringing content into your conversations:
  • Open files directly
  • Drag and drop from File Explorer or IDE
  • Paste screenshots or copied images
  • Snap photos using the webcam (Labs feature)
  • Use the 'paste' button (Shift + Ctrl + V) for quick clipboard access
  • Paste URLs for automatic embedding
• Intelligent File Conversion: The new system converts files to the optimal format for your active Chat LLM, enhancing the chat experience with various content types - for instance:
  • PDFs are automatically converted to text
  • Images undergo OCR for text extraction (for non-vision networks)
  • HTML tables are transformed into Markdown
  • HTML can be as-is or text
  • Text remains as text within Markdown blocks for consistency
• Desktop Webcam access for direct image uploads. (Labs) The image is OCR'd (for now), and soon fun modes will be enabled with Vision
• Overheat LLMs, raising the maximum model 'temperature' to 2 (can lead to instability, but can also be very creative)
• Oobabooga/Text-Generation-WebUI: fix support
• Ollama: update to the latest models
• Quick model settings access via Ctrl+Shift+O
• Optimized voice input and app performance
• Cosmetic improvements to the UI

1.7.0 for Developers:

• Password Protection via HTTP Basic Authentication. Learn How :rocket:
• Browserless Support: Full browsing support on Browserless docker containers Learn More :rocket:
• Full Changelog: https://github.com/enricoros/big-agi/compare/v1.6.0...v1.7.0

New Contributors:

• A special shoutout to @konsila / @LennardSchwarz for their first contribution which helped to add HTTP Basic Auth. PR #177

Stay Connected:

Join the conversation on Discord or take a look at the roadmap and join us in creating the Pro AGI toolkit ❤️