import gradio as gr
import os
from huggingface_hub import InferenceClient

# Hugging Face token'i Space secrets'tan al
HF_TOKEN = os.getenv("HF_TOKEN")
client = InferenceClient(
    token=HF_TOKEN,
    model="bahakizil/gemma3-financial-sentiment"   # kendi model repo adın
)

def respond(message, history, system_message, max_tokens, temperature, top_p):
    # Mesaj geçmişini derle
    messages = [{"role": "system", "content": system_message}]
    messages.extend(history)
    messages.append({"role": "user", "content": message})

    response = ""
    for msg in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        choices = msg.choices
        if choices and choices[0].delta.content:
            response += choices[0].delta.content
            yield response

# Gradio Chat arayüzü
chatbot = gr.ChatInterface(
    respond,
    type="messages",
    additional_inputs=[
        gr.Textbox(
            value="You are a financial sentiment analysis expert.",
            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)"),
    ],
)

with gr.Blocks() as demo:
    chatbot.render()

if __name__ == "__main__":
    demo.launch()