CreateAI Platform Release Notes - August 2024

• Multimodal Support: Seamlessly integrate various media formats like images, audio, and text into your AI projects. Upload multiple images alongside text input to enable image analysis and generation capabilities. Additionally, handle audio data for audio input and output, opening up possibilities for voice interactions.
• Scalable Backend: Improved LLM throughput capacity and backend infrastructure to support thousands of concurrent users across all models. Includes load testing and collaboration with AWS and GCP to validate token limits and load
• Ethical AI Evaluation: Assess the performance and ethical standards of your AI models and applications with our comprehensive Ethical AI Engine. This powerful tool utilizes advanced language models to evaluate factors like response accuracy, processing speed, and hallucination tendencies, bias, discrimination, and handling of sensitive content.

CreateAI Platform Release Notes - July 2024

• New Models: We’ve reached 40+ models available including GPT 4o Mini, GPT 4 Turbo, Whisper Audio, Claude Opus, Clause Sonnet, Claude Haiku, and Gemini Pro Vision. Our team continuously monitors and updates the CreateAI platform with the latest text, - and now - audio, and image models available in the market, while removing deprecated versions.
• Enterprise Integration: Empower your applications with seamless access to iSearch, ASU websites, ServiceNow, Salesforce, Google Drive, and Slack, enabling unified data access for your AI projects.
• LLM-Assisted Topic Model Interpretation: Leverage CreateAI large language models in conjunction with our topic modeling toolkit to automatically identify and categorize topics from vast amounts of user data, streamlining analysis.
• Isolated Development and Beta Testing Environments: Enhance the reliability of your AI projects by utilizing distinct areas for development and beta testing, ensuring a more stable and controlled testing process.

CreateAI Platform Release Notes - June 2024

• State-of-the-Art AI Model Library: We’ve reached 30+ models available including GPT 4o, Llama3 8b, Llama3 70b, Bison, and Gemini Flash 1.5. Our team continuously monitors the market and integrates the newest and most advanced text models into our platform. 
• Automatic Deprecation Management: We automatically remove deprecated models, ensuring you only have access to the most advanced and relevant options.
• Easy Model Switching: Effortlessly switch out models in your projects to leverage new features and improvements without the need to rebuild your entire project.
• Easy API Documentation: Comprehensive documentation provides transparency into our APIs, making it simple to integrate and build your own custom front-end experiences. Get your project up and running ASAP.
• Conversational Bot Interface: Find what you need quickly using our new conversational bot interface. Simply ask questions naturally to receive relevant documentation excerpts and guidance.
• ASU LLM Library (Python): Standardize access to ASU LLMs for internal users, ensuring consistency and ease of use.