import gradio as gr #from huggingface_hub import InferenceClient from smolagents import CodeAgent, Tool #client = InferenceClient("HuggingFaceH4/zephyr-7b-beta") # Initialize the agent agent = CodeAgent( tools=[search_kb_tool, search_web_tool, format_response_tool], system_prompt=""" You are a Basic Troubleshooting Assistant. Understand the user's problem, attempt to resolve it using the knowledge base. If the knowledge base is insufficient, perform a web search. Provide clear, step-by-step instructions and confirm each step's outcome. """ ) # Run the agent while True: user_input = input("User: ") if user_input.lower() in ["exit", "quit"]: break response = agent.run(user_input) print("Agent:", response) ############################################################### """def respond( message, history: list[tuple[str, str]], system_message, max_tokens, temperature, top_p, ): messages = [{"role": "system", "content": system_message}] for val in history: if val[0]: messages.append({"role": "user", "content": val[0]}) if val[1]: messages.append({"role": "assistant", "content": val[1]}) messages.append({"role": "user", "content": message}) response = "" for message in client.chat_completion( messages, max_tokens=max_tokens, stream=True, temperature=temperature, top_p=top_p, ): token = message.choices[0].delta.content response += token yield response demo = gr.ChatInterface( respond, additional_inputs=[ gr.Textbox(value="You are a friendly Chatbot.", label="System message"), gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"), gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"), gr.Slider( minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)", ), ], ) if __name__ == "__main__": demo.launch() """