V1.0.3

• Support for the keras-llm-interpreter code interpreter, compatible with Windows, macOS, and Ubuntu operating systems. Provides locally executable binaries and Docker images for running in a sandbox environment.
• Introduced a new feature called "Role-Playing" enabling offline or online models to take on different roles. For example, you can have the LLM Model role-play as an "English Translator," "Interviewer," "Novelist," "Product Manager," "Yogi" and more, thereby providing more specialized responses.
• Support for Function Calling feature.
• Suppport for google search engine.
• Support for Google ToolBoxes: "Google Mail", "Google Calendar", "Google Drive", "Google Maps", "Youtube"
• Add AI generator features: "Intelligent Customer Support", "Real-time Translation Agent", "Virtual Personal Assistant"
• Fix some known issues.
• Support for LLM Models: gpt-4o, gemma, Qwen1.5, Llama 3, Phi-3, Yi-1.5
• Support for Multimodal Models: MiniCPM-Llama3-V-2_5, Phi-3-vision-128k-instruct
• Support GoogleVoiceService, GoogleSpeechService and musicgen Model.
• Support for Online Models: YI Cloud Platform, Groq Cloud Platform, Ali Cloud Platform, Baidu Cloud Platform, Kimi Cloud Platform.

V1.0.1

• Support RAG feature: add vector DB "Faiss", "Milvus", "PGVector"
• Support Code Models: "CodeLlama" etc.
• Support Multimodal Models.
• Support Image recognition and Image generation
• Support Network Search Engine.

V1.0.0

• Support for Ubuntu, MacOS and Windows.
• Support for loading and inference of the Foundation Models.
• Support for Quantitative Models (GGUF).
• Support for Multimodal Models GPT4-V and Gemini-pro-vision.
• Support for TTS and STT models.