ITSpecialist111/ai_automation_suggester V1.08

on GitHub

What's New in AI Automation Suggester Version 1.08

We are excited to announce the release of version 1.08 of the AI Automation Suggester integration. This update brings several important fixes and enhancements to improve functionality and user experience.

New Features and Improvements

1. Support for Google Validation in Configuration Flow

   • Description: Added validation support for the Google AI provider during the configuration flow. This ensures that your API key and model configurations are correctly validated when setting up the Google AI provider.
   • Impact: Provides a smoother setup experience and prevents misconfigurations.
   • Time Spent: 3 hours

2. Adjustable Token Limit for AI Responses

   • Description: Users can now set a custom maximum token limit for AI responses. The default limit remains at 500 tokens, but you can increase it up to 16,384 tokens for models like OpenAI's GPT-4o-mini.
   • Impact: Prevents responses from being cut off due to token limits and allows for more detailed suggestions.
   • Time Spent: 1.5 hours

3. Improved Endpoint Formatting for LocalAI and Ollama

   • Description: Updated the code to enhance the formatting for LocalAI and Ollama endpoints, ensuring correct API call structures.
   • Default Endpoint Formats:
     • LocalAI: "{protocol}://{ip_address}:{port}/v1/chat/completions"
     • Ollama: "{protocol}://{ip_address}:{port}/api/chat"
   • Impact: Enhances compatibility and reduces errors when using LocalAI and Ollama providers.
   • Time Spent: 10 minutes

Bug Fixes

1. Fixed Notification Creation Error

   • Issue: An error occurred when creating notifications: "object NoneType can't be used in 'await' expression".
   • Resolution: Adjusted the notification code to correctly handle asynchronous calls.
   • Impact: Notifications are now created without errors, ensuring you receive AI suggestions promptly.
   • Time Spent: 15 minutes

2. Re-added Upgrade Path Code

   • Issue: The upgrade path code was broken in version 1.07, causing issues when updating from earlier versions.
   • Resolution: Re-implemented the upgrade code to ensure smooth transitions between versions.
   • Impact: Users can now upgrade to the latest version without losing configurations or encountering errors.
   • Time Spent: 20 minutes

3. Resolved 'Suggestions Available' Status Mismatch

   • Issue: There was a mismatch in the display of the 'suggestions available' status due to code inconsistencies.
   • Resolution: Reworked the sensor code to accurately reflect when new suggestions are available.
   • Impact: Users receive correct status updates regarding the availability of AI suggestions.
   • Time Spent: 30 minutes

Additional Notes

• Versioning Update

  • Future releases will consider adopting a versioning scheme like 1.0.9 to align with semantic versioning standards.

We appreciate your support and feedback, which help us improve the AI Automation Suggester. For any issues or suggestions, please visit our GitHub repository.

Feel free to reach out if you need further assistance or have any other questions!