Feature Updates
- Added Pipe executor, which can execute programs (tools) within a specified directory, such as directly executing Python programs output by models via Python interpreter
- Provided Calculator, Iconv and Python example tools that can be called via Pipe executor
- Added Uploader executor to allow users to upload files to a specified directory, including tools, RAG knowledge bases, or website components
- Supported Bot export and import, allowing export of Bot name, description, icon, and Modelfile as a single Bot file, similar to an application configuration file; installation can automatically import default Bot files
- Allows users to choose the sorting method for Bots in chat rooms
- Supported Bot icon replacement
- Added Kuwa API server compatible with OpenAI API
- Provided default examples for connecting to cloud multimodal APIs: gpt-4o-mini-vision, DALL-E, Gemini pro 1.5 vision
- Supported setting the upper limit of uploaded files via Web interface
- Supported installation and execution in environments with Web proxy within enterprises
- Supported acceleration of model inference using Intel GPU
- Added automatic installation and update scripts for Docker version, thanks to @wcwutw
- RAG Toolchain default Embedding model replaced with Microsoft's intfloat/multilingual-e5-small model, licensed under MIT
- RAG (DocQA, WebQA, SearchQA, DB QA) added display_hide_ref_content, retriever_ttl_sec parameters
- Increased support for downloaded tools' default models, including Meta Llama 3.1 8B with Function calling and lightweight Google Gemma 2 2B
Bug Fixes
- #21: Docker version does not generate https:// links after a reverse proxy, thanks to @Phate334
- #23: Two-minute timeout issue, thanks to @x85432
- #24: Modelfile parsing issue
- #25: Importing Prompts does not apply Modelfile
windows\src\tee.batis misjudged as a virus- RAG reference data does not display original file names
- Updated Windows version dependency download link