app.py

import os
import gradio as gr
from dotenv import load_dotenv
from langchain.llms import HuggingFaceEndpoint

# Load environment variables
load_dotenv()

# Initialize the model
repo_id = "meta-llama/Llama-2-70b"
llm = HuggingFaceEndpoint(
    endpoint_url=repo_id,
    temperature=0.7,
    huggingfacehub_api_token=os.getenv("HF_TOKEN"),
    timeout=1800  # 30 minutes timeout
)

def generate_response(prompt):
    try:
        response = llm.invoke(prompt)
        return response
    except Exception as e:
        return f"An error occurred: {str(e)}"

# Create Gradio interface
iface = gr.Interface(
    fn=generate_response,
    inputs=gr.Textbox(lines=5, placeholder="Enter your prompt here..."),
    outputs="text",
    title="Llama-2-70b Model Interface",
    description="Enter a prompt and get a response from the Llama-2-70b model."
)

# Launch the interface
if __name__ == "__main__":
    iface.launch()