GPT-4o has been released, and I’m joining the excitement by enabling my comfyui agent open-source project to support GPT-4o integration into comfyui, achieving visual functions.The project address is:<a target="_blank" rel="ugc" href="https://github.com/heshengtao/comfyui_LLM_party">heshengtao/comfyui_LLM_party: A set of block-based LLM agent node libraries designed for ComfyUI development.(一组面向comfyui开发的积木化LLM智能体节点库)</a>In my open-source project, you can use these features：<ol><li>You can right-click in the comfyui interface, select <code>llm</code> from the context menu, and you will find the nodes for this project. [how to use nodes](how_to_use_<a target="_blank" rel="ugc" href="http://nodes.md">nodes.md</a>)</li><li>Supports API integration or local large model integration. Modular implementation for tool invocation.When entering the base_url, please use a URL that ends with <code>/v1/</code>.You can use [ollama](<a target="_blank" rel="ugc" href="https://github.com/ollama/ollama">https://github.com/ollama/ollama</a>) to manage your model. Then, enter <code>http://localhost:11434/v1/</code> for the base_url, ollama for the api_key, and your model name for the model_name, such as: llama3. If the call fails with a 503 error, you can try turning off the proxy server.</li><li>Local knowledge base integration with RAG support.</li><li>Ability to invoke code interpreters.</li><li>Enables online queries, including Google search support.</li><li>Implement conditional statements within ComfyUI to categorize user queries and provide targeted responses.</li><li>Supports looping links for large models, allowing two large models to engage in debates.</li><li>Attach any persona mask, customize prompt templates.</li><li>Supports various tool invocations, including weather lookup, time lookup, knowledge base, code execution, web search, and single-page search.</li><li>Use LLM as a tool node.</li><li>Rapidly develop your own web applications using API + Streamlit.The picture below is an example of a drawing application.</li><li>Added a dangerous omnipotent interpreter node that allows the large model to perform any task.</li><li>It is recommended to use the <code>show_text</code> node under the <code>function</code> submenu of the right-click menu as the display output for the LLM node.</li></ol>

Files with SHA256: 10a1f362c09c976943d993572f38886e1ccec9aff6e64728419d89c983101b17