import os
import gradio as gr
from groq import Groq
from dotenv import load_dotenv
import json
from deep_translator import GoogleTranslator
load_dotenv()

api1 = os.getenv("GROQ_API_KEY")

apis = [
    api1,
    # api1,
]


def make_call(data):
    print(data)
    items = json.loads(data)
    language = items['lang']
    query = items['text']
    answer = None
    while True:
        for api in apis:
            client = Groq(
                    api_key=api,
                )  # Configure the model with the API key
            # query = st.text_input("Enter your query")
            prmptquery= f"Answer this query with wisdom, love and compassion, in context to bhagwat geeta, provide references of shloks from chapters of bhagwat geeta which is relevant to the query. Query= {query}"
            try:
                response = client.chat.completions.create(
                messages=[
                    {
                        "role": "user",
                        "content": prmptquery,
                    }
                ],
                model="mixtral-8x7b-32768",
                )
                answer = response.choices[0].message.content
                translated = GoogleTranslator(source='auto', target=language).translate(answer)
            except Exception as e:
                print(f"API call failed for: {e}")
            if answer:
                break
        if answer:
                break
    respo = {
                "message": translated,
                "action": "nothing",
                "function": "nothing",
            }
    return json.dumps(respo)



gradio_interface = gr.Interface(fn=make_call, inputs="text", outputs="text")
gradio_interface.launch()

# print(chat_completion)

























# # Text to 3D

# import streamlit as st
# import torch
# from diffusers import ShapEPipeline
# from diffusers.utils import export_to_gif

# # Model loading (Ideally done once at the start for efficiency)
# ckpt_id = "openai/shap-e"  
# @st.cache_resource  # Caches the model for faster subsequent runs
# def load_model():
#     return ShapEPipeline.from_pretrained(ckpt_id).to("cuda")  

# pipe = load_model()

# # App Title
# st.title("Shark 3D Image Generator")

# # User Inputs
# prompt = st.text_input("Enter your prompt:", "a shark")
# guidance_scale = st.slider("Guidance Scale", 0.0, 20.0, 15.0, step=0.5)

# # Generate and Display Images
# if st.button("Generate"):
#     with st.spinner("Generating images..."):
#         images = pipe(
#             prompt,
#             guidance_scale=guidance_scale,
#             num_inference_steps=64,
#             size=256,
#         ).images
#         gif_path = export_to_gif(images, "shark_3d.gif")

#         st.image(images[0])  # Display the first image
#         st.success("GIF saved as shark_3d.gif")