Releases: ckt1031/obsidian-wordwise-plugin
Releases · ckt1031/obsidian-wordwise-plugin
0.7.4
0.7.4
- Added support for Cohere's new
command-r-plus
model, featuring a 128K context window and enhanced response quality. Learn more: Introducing Command R+. - Reorganized Perplexity (PPLX) models: Removed some older models and added new Sonar models.
- Integrated Gemini Model API support: The plugin now uses the model API, enabling compatibility with future Gemini model releases without hard-coding.
- Fixed an issue where the reset models confirmation was not functioning correctly.
- Improved layout for the advanced configuration settings tab: Settings are now separated into sections for a clearer, more intuitive user experience.
0.7.3
0.7.3
- New Cohere model:
command-r
, which is free and outperforms GPT-3.5 Turbo, LLaMA 70B Chat, and Mixtral. - New Anthropic's Claude 3.0 Haiku:
claude-3-haiku-20240307
, which is fast and affordable, with a 200K context window. It also outperforms GPT-3.5 Turbo and Gemini 1.0 Pro.
0.7.2
- Resolved issue with encoded user prompts
- Improved debug logging for messages
0.7.1
- Now supports the new Claude 3.0 with
claude-3-opus-20240229
andclaude-3-sonnet-20240229
models. - Enhanced prompt clarity by eliminating unnecessary wording.
0.7.0
- New Fuzzy Log Search: Utilizing the
Fuse.js
library, our search feature now supports fuzzy logic, allowing for precise and user-friendly search results across your text.
-
Revamped Settings Layout: The settings page has been restructured into distinct sections including 'Danger Zone,' 'Text Generation Logs,' and 'Prompts.'
-
Text Generation Logs Management:
- Additional Updates:
- LocalForage now includes vault-specific storage to prevent different vaults on the same device and app from sharing storage, as identified in previous tests.
- Added an input box for importing settings via data strings.
- Improved prompt responses by integrating System Messages when available for enhanced accuracy and quality.
- Enhanced prompt optimization to maintain code blocks and avoid encoding.
- The README has been updated with detailed information about AI providers.
0.6.2
- Fixed QR Code too long error, if it fails to render, just show the copy clipboard button only.
0.6.1
0.6.1
0.6.0
- Supports OpenRouter.
- Supports OpenAI Compatible API with custom model list fetching.
- Removed unnecessary encryption for settings exporting.
0.5.2
- Fixed API Testing notice model showing
object Object
- Improved
config.ts
with mapping all default hosts. - Hide Base URL option as advanced configuration.
- Define the enum in
config.ts
rather thantypes.ts
0.5.1
feat(release): 0.5.1