app.py

import os
import requests
import gradio as gr

# Your Hugging Face API token
hf_token = os.getenv("hf_token")
api_url = "https://api-inference.huggingface.co/models/antony-pk/llama-3-8b-Instruct-bnb-4bit-e10-emp-gold-jul16"

def query_huggingface_api(prompt):
    headers = {"Authorization": f"Bearer {hf_token}"}
    payload = {"inputs": prompt}
    response = requests.post(api_url, headers=headers, json=payload)
    return response.json()

def generate_response(prompt):
    response = query_huggingface_api(prompt)
    return response.get("generated_text", "No response received")

# Create the Gradio interface
interface = gr.Interface(
    fn=generate_response,
    inputs="text",
    outputs="text",
    title="LLama Model Interaction",
    description="Enter a prompt to receive a response from the private LLama model."
)

# Launch the Gradio interface
interface.launch()