GPT AI Power: Complete AI Pack Pro 1.8.95 NULLED

= 1.8.95 =

This release includes couple of improvements for the chat bot:

- **OpenAI Assistant API Integration**: The chatbot now supports the OpenAI Assistant API. To use it, go to your chatbot settings and click the "Sync" button next to the models. This will synchronize your assistants.

[Learn more here](https://docs.aipower.org/docs/Chatbot/ai-settings#selecting-assistant).

- **Improved Markdown Formatting**: Switched to a better third-party library for parsing markdown.
- **Simplified Interface**: I've removed the AI Name and Avatar options to keep the chat window clean and simple.

The next release will introduce a conversation sidebar for viewing and managing conversations.

**Note:** If you're using a caching plugin, please remember to clear your site cache to make sure that the changes take effect.

= 1.8.93 =
Fixed compatibility issues with OpenRouter integration following their API update today. Adjustments were made to align with their new API structure.

= 1.8.89 =
- New moderation model added: omni-moderation-latest
- Fixed issues with widget preview display.
- Fixed widget toggle functionality.
- Fixed chatbot duplication.

= 1.8.79 =

- Added support for the o1-preview and o1-mini models. Please note that access to these models requires your organization to be at usage tier 5 or higher. See [usage tiers](https://platform.openai.com/docs/guides/rate-limits/usage-tiers) for more details. If you are accessing o1-preview or o1-mini via OpenRouter, make sure to disable streaming.
- Users can now enable or disable audio directly from the chat interface. More information [here](https://docs.aipower.org/docs/ChatGPT/advanced-setup/voice-chat).
- Fixed a spacing issue in AI Form outputs for consistent formatting.
- Updated chat logs to use current_time('timestamp') instead of time() for more accurate local time records.
- Added a "Limits" button to check OpenRouter usage and credits.

= 1.8.74 =
[New]
- Now you can revise chatbot responses that didn't meet your expectations. Use this feature to improve future interactions.
[Read tutorial](https://docs.aipower.org/docs/ChatGPT/advanced-setup/context#response-quality)
- Added detailed stats including log size, conversation count, question count, and insights into the most popular models and providers.

= 1.8.60 =

[NEW]

- Introduced the ability to specify different embedding models for different chatbots. This final step before implementing OpenRouter allows you to select different AI engines with different embedding models, thus combining two different providers in one go.
- Added a new embedding model for Google: embedding-text-004.
- Added new Google models to chatbots and AI forms, such as Gemini 1.5 Pro Latest. Make sure to hit the sync button when using Google as a provider.
- Added dimension display in AI training. You can now specify dimensions when creating a Qdrant collection via the plugin interface. Make sure to sync your collections.
- Added an option to enable or disable past conversations in the chatbox. You can disable it from ChatGPT - Settings tab. Dont forget to clear your cache.
- Displayed vector and points count for Qdrant. Make sure to sync your collections.
- Added delete button for AI forms and image generator logs.

[IMPROVEMENT]

- Larger text fields for AI Assistant prompts.
- Proper handling for markdown format in chat response.
- Improved semantic search functionality.
- Removed deprecated syntax for embedding variables within strings in image generator logs.
- Added numeric validation for logs in the content writer.
- Removed console logs from the code.

[FIX]

- Restricted scrollbar styling to only affect the bot interface.
- Fixed an issue with the widget where it stopped functioning after being cleared.
- Fixed an issue in the AI Assistant where the loading spinner continued running after receiving responses in Gutenberg.
- Fixed an issue where it was not possible to delete conversation starters in custom chatbots.
- Fixed a permission issue in AutoGPT.
- Fixed an issue in AI forms where a quota limit notification was not displaying.
- Fixed an issue in AI forms where special characters in the notification message caused display problems.
- Fixed an issue in embedding where accessing a non-existent post ID could produce error.
- Fixed an issue in custom chatbots where tokens did not reset after a certain interval.

= 1.8.53 =
[NEW]
- Introducing Conversation Starters! Imrpove user engagement with custom Conversation Starters for your chatbot.

= 1.8.40 =
- Better error handling for Gemini Pro.

= 1.8.29 =
- Added Qdrant as an alternative vector database provider alongside Pinecone.
- Revised the Call to Action built-in prompt in Content Writer.
- Fixed a formatting issue affecting numerical data in AI Forms logs.