(v0.2.0)【Model Debut】More model support and more flexible workflow gameplay!

✨v0.2.0✨【模特登场】【Model Debut】

This release includes the following features:

LLM

1. The LLM node has been split, separating the LLM loader and the LLM model chain for more flexible reuse of these models.
2. Adapted all models with an interface similar to OpenAI, such as: Tongyi Qianwen/qwen, Zhipu Qingyan/GLM, deepseek, kimi/moonshot. Please fill in the base_url, api_key, and model_name of these models into the LLM node to call them.
3. Added a new LVM loader, now you can call LVM models locally, supporting the llava-llama-3-8b-v1_1-gguf model. Other LVM models, if in GUFF format, should theoretically also be runnable.
4. MacOS and mps devices are now supported! Thanks to bigcat88 for their contribution!

Tools

1. Added Wikipedia tool, web summary tool, and arXiv paper tool.
2. Another workflow can now be used as a tool. However, this version is not yet perfected and is just barely usable.

Workflow

1. Wrote a fastapi.py file, if you run it directly, you will get an OpenAI interface at http://127.0.0.1:8817/v1/, any application that can call GPT can now use your comfyui workflow! I will produce a tutorial to demonstrate how to operate it in detail~
2. Wrote an Excel iterator, which can output your CSV table row by row to the next node.

本次发行包含如下功能：

LLM

1. 拆分了LLM节点，将LLM的加载器和LLM模型链拆分，方便更灵活的复用这些模型。
2. 适配了所有具有类似openai接口的模型，例如：通义千问/qwen、智谱清言/GLM、deepseek、kimi/moonshot。请将这些模型的base_url、api_key、model_name填入LLM节点以调用它们。
3. 新增了一个LVM加载器，现在可以本地调用LVM模型了，支持llava-llama-3-8b-v1_1-gguf模型，其他LVM模型如果是GUFF格式，理论上应该也可以运行。
4. 目前已经支持了macOS以及mps设备!感谢bigcat88对此的贡献！

工具

1. 新增了维基百科工具、网页总结工具、arxiv论文工具。
2. 可以将另一个工作流作为一个工具使用。不过目前这个版本还没有完善，只是勉强能用。

工作流

1. 写了一个fastapi.py文件，如果你直接运行它，你就获得了一个http://127.0.0.1:8817/v1/上的openai接口，任何可以调用GPT的应用都可以调用你的comfyui工作流了！详细怎么操作我会出一期教程来演示~
2. 写了一个Excel迭代器，可以将你的csv表格按行输出到下一个节点。