Changelog

v1.15.18 (build 61)

• Fix a crash for some users when selecting a particular chat

v1.15.17 (build 60)

• Improvement: Auto switch the focus back to previous app when using activation hotkey
• Fix: fixed the crash when using Anthropic Claude 3 with plugins
• Fix: fixed the regression bug where font option does not apply to AI messages

v1.15.16 (build 59)

• New: Customize font size for the chat input
• Fixed an issue with license activation
• Fixed: Command N do not open a quick chat
• Fixed: BoltAI can't force stop, endpoint keeps streaming
• Fixed: New line inserted at the bottom rather than at the cursor position
• Fixed: Unable to select assistant in new chat
• Fixed: Creating a new command shows deleted models
• Fixed: Bulk edit provider in Command showing deleted API Provider
• Fixed: Chat not showing all chat content after search
• Improvement: Remove quotes from chat title

v1.15.14 (build 57)

• New: Added Llama 3 support for Groq, Perplexity AI & Together AI
• New: Automatically fetch list of models from Groq and Perplexity
• New: Set a default vision model (Settings > Advanced > Chat with images)
• Improvement: Bulk edit AI Command's parameters & new line behavior
• Improved AI Command support in Missive app
• Fixed: show all Ollama models on bulk edit
• Fixed: hide deleted AI providers
• Fixed: fix a crash on macOS 12 when opening a new chat in new window
• Fixed: pasting content from Excel
• Fixed: attempt to fix a crash when using web search with Anthropic Claude 3

v1.15.13 (build 56)

• New: you can use Web Search & Web Browsing plugin with Anthropic Claude models now (beta)
• Improvement: Support LaTeX rendering for Anthropic models
• Improvement: better support for drag-and-drop images/screenshots to BoltAI
• Improvement: copy and paste images into the chat box
• Improvement: allow deleting built-in AI services
• Fixed the issue where the chat box was missing for some users

v1.15.12

• New: you can choose to insert new line when using an AI Command. Learn more...
• Fixed the issue where cost estimation was wrong

v1.15.11

• Improved LaTeX rendering
• Remember chosen Assistant when creating a new chat
• Google Safety Setting: Allow all content when using Google Gemini models (HarmBlockThreshold = BLOCK_NONE)
• Improvement: Bulk enable/disable Commands/Assistants/Prompts

v1.15.8 (build 51)

• New: Added the new GPT-4 Turbo with Vision capability (gpt-4-turbo and gpt-4-turbo-2024-04-09)
• Improvement: Allow insecure network connection. This is neccessary to connect to local inference servers
• Improvement: Allow using Gemini & Claude models when streaming inline responses
• Fixed the issue where AI Inline not inserting new lines
• Fixed the issue where forking chat not copying images
• Fixed the issue with Edit & Generate not working as intended

v1.15.7 (build 50)

This release improves BoltAI's security & adds a new AI Command behavior

• Improved security: Better API Keys handling
• New AI Command's behavior: Insert answer above selection
• New: Start a new chat and copy configuration from other chat
• New: Supports LaTeX rendering
• New: Supports network timeout configuration

v1.15.6 (build 49)

• New: You can use Claude 3 Vision now!
• Improvement: Show "Custom Assistant" for custom system instruction
• Improvement: Remember chat configuration tab
• Fix: Keep the sidebar & chat state when toggling BoltAI
• Other bug fixes & improvements