Changelog

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

v1.15.2 (build 45)

• Use an AI Assistant in the Chat UI
• Quickly select an AI Service & model when start a new chat
• Quickly insert a prompt from your Prompt Library. Keyboard shortcut: Command + Shift + P
• New AI Command's behavior: Copy to clipboard
• Improvement: You can now use Claude 3 & Gemini model with an AI Command
• Other bug fixes & improvements

v1.15.1 (build 44)

• BoltAI now supports Anthropic Claude 3 Haiku (claude-3-haiku-20240307)
• Refactor: Renders user message (prompt) as plaintext. Read more
• Fix: You can delete the legacy Anthropic AI Provider now

v1.15.0 (build 43)

• New: BoltAI now supports Anthropic Claude 3, Google Gemini and Groq
• General bug fixes & improvements

v1.14.1 (build 42)

• Improvement: add the option to not remember model settings
• Improvement: fetch mistral model list from Mistral AI API
• Fixed: reverse the customizable shortcut feature
• Fixed issue with Mistral AI where some users

v1.14.0 (build 41)

This release added first-class support for Ollama and improved AI Command feature.

• New: Supports Ollama natively. Automatically fetch model list from Ollama.
• Improvement: Bulk editing AI Command
• Improvement: Better AI Commands listing view
• Improvement: Better keyboard shortcut support
• Fix: Use Dall E 3 for AI Inline
• Fix: Fixed the issues with sidebar when toggling a folder
• Fix: Fixed the issue where AI message bubbles not changing font size

v1.13.6 (build 40)

• Use AI Commands with a custom AI provider
• New chat message list implementation: faster and better
• Support pasting images directly into the chat input field
• Fixed an issue where streaming message paused & stuck randomly
• Fixed a crash issue related to the text-to-speech feature