app.py

import gradio as gr
from huggingface_hub import InferenceClient

# Initialize the InferenceClient with your model from Hugging Face
client = InferenceClient(model="pro-grammer/MindfulAI")

def respond(message, history: list[tuple[str, str]], system_message, max_tokens, temperature, top_p):
    # Build a prompt string manually
    prompt = system_message + "\n"
    for user_msg, assistant_msg in history:
        prompt += f"Human: {user_msg}\nAssistant: {assistant_msg}\n"
    prompt += f"Human: {message}\nAssistant:"
    
    response = ""
    # Use text_generation instead of chat_completion
    for token in client.text_generation(
        prompt,
        max_new_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        # Depending on the API response structure, extract the generated text
        token_text = token.get("generated_text", "")
        response += token_text
        yield response

demo = gr.ChatInterface(
    fn=respond,
    title="MindfulAI Chat",
    description="Chat with MindfulAI – your AI Therapist powered by your model.",
    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()