LLM Agent from an Image

Tools

• llm_from_image_infer Generate a system prompt idea for a language model based on the content of an input image. This function performs two steps: 1. It uses a vision-language model (Kosmos-2) to generate a descriptive caption of the input image. 2. It then uses a text generation pipeline (Zephyr-7B) to create a chatbot configuration from that caption, including a title, system prompt, and example user message. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: Tuple[str, str]:, - The generated caption describing the image., - A suggested LLM system prompt structure including:, - A chatbot title, - A system message defining the bot’s personality, - An example user input message

No tool matches.

As the server's own listing gives them. We never call a tool.