import gradio as gr
import requests

# Define the Hugging Face API endpoint and your API token
API_URL = "https://z94ka3s1dsuof4va.us-east-1.aws.endpoints.huggingface.cloud"
API_TOKEN = "hf\_XgrSWzAWKtqKXgSFLZMZsQeSSjCcMbqUIt"  # Replace with your actual API token

# Function to query the Hugging Face model
def query_huggingface_model(input_text):
    headers = {"Authorization": f"Bearer {API_TOKEN}"}
    payload = {"inputs": input_text}
    response = requests.post(API_URL, headers=headers, json=payload)
    
    if response.status_code == 200:
        return response.json()
    else:
        return {"error": f"Request failed with status code {response.status_code}"}

# Define a function to process the input and return the model's output
def generate_response(input_text):
    response = query_huggingface_model(input_text)
    if "error" in response:
        return response["error"]
    else:
        return response[0]['generated_text']

# Create a Gradio interface
iface = gr.Interface(
    fn=generate_response,
    inputs=gr.Textbox(lines=2, placeholder="Enter your text here..."),
    outputs="text",
    title="LLaMA-2-7B Guanaco Dolly Mini Model",
    description="Generate responses using the LLaMA-2-7B Guanaco Dolly Mini model from Hugging Face."
)

# Launch the interface
iface.launch()