app.py

import gradio as gr
import os
from huggingface_hub import login

# # api_key = os.getenv('llama3token')
# # login(api_key)

# HF_TOKEN = os.getenv('llama3token')
# login(HF_TOKEN)

# demo = gr.load("deepseek-ai/DeepSeek-R1-Distill-Llama-8B", src="models")
# demo.launch()


import streamlit as st
import requests

# Hugging Face API URL
# API_URL = "https://api-inference.huggingface.co/models/deepseek-ai/DeepSeek-R1-Distill-Llama-8B" # 
# The model meta-llama/Meta-Llama-3-8B is too large to be loaded automatically (16GB > 10GB). Please use Spaces (https://huggingface.co/spaces) or Inference Endpoints (https://huggingface.co/inference-endpoints).
# API_URL = "https://api-inference.huggingface.co/models/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
API_URL = "https://api-inference.huggingface.co/models/meta-llama/Llama-3.2-3B-Instruct"

HF_TOKEN = os.getenv('hftoken')


# Function to query the Hugging Face API
def query(payload):
    headers = {"Authorization": f"Bearer {HF_TOKEN}"}
    response = requests.post(API_URL, headers=headers, json=payload)
    print(response.json())
    return response.json()

# Streamlit app
st.title("DeepSeek-R1-Distill-Qwen-32B Chatbot")

# Input text box
user_input = st.text_input("Enter your message:")

if user_input:
    # Query the Hugging Face API with the user input
    payload = {"inputs": user_input}
    output = query(payload)
    
    # Display the output
    if isinstance(output, list) and len(output) > 0 and 'generated_text' in output[0]:
        st.write("Response:")
        st.write(output[0]['generated_text'])
    else:
        st.write("Error: Unable to generate a response. Please try again.")