app.py

import os
import gradio as gr
from dotenv import load_dotenv
import json
from deep_translator import GoogleTranslator
import google.generativeai as genai
import time
import random

load_dotenv()

# Configure the Gemini API with your API key
GEMINI_API_KEY = os.getenv("GEMINI_API_KEY")
genai.configure(api_key=GEMINI_API_KEY)

def make_call(data):
    print(data)
    newdata = data.replace("'", '"')
    items = json.loads(newdata)
    language = items['lang']
    query = items['text']
    query = query.lower()
    translated = None

    model = genai.GenerativeModel('gemini-2.5-flash-lite')

    retries = 0
    max_retries = 5  # You can adjust this number
    base_delay = 1  # Initial delay in seconds

    while retries < max_retries:
        try:
            prompt_query = (
                f"Answer this query in a very short message with wisdom, love, and compassion, "
                f"in context to Bhagavad Gita, that feels like chatting to a person and "
                f"provide references of shlokas from chapters of Bhagavad Gita which are "
                f"relevant to the query. Keep the answer short, precise, and simple. "
                f"Query: {query}"
            )

            response = model.generate_content(prompt_query)
            answer = response.text
            translated = GoogleTranslator(source='auto', target=language).translate(answer)
            break  # Exit the loop if the call is successful
        except Exception as e:
            if "429 Quota exceeded" in str(e):
                delay = base_delay * (2 ** retries) + random.uniform(0, 1)  # Exponential backoff with jitter
                print(f"Quota exceeded. Retrying in {delay:.2f} seconds... (Attempt {retries + 1}/{max_retries})")
                time.sleep(delay)
                retries += 1
            else:
                print(f"API call failed: {e}")
                translated = f"An error occurred while fetching the answer: {e}"
                break  # Exit the loop for other errors
    else:
        # This block executes if the loop completes without a successful break (i.e., max_retries reached)
        translated = "Maximum retry attempts reached. Please try again later."


    respo = {
        "message": translated,
        "action": "nothing",
        "function": "nothing",
    }
    print(translated)
    return json.dumps(respo)

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




# import os
# import gradio as gr
# from groq import Groq
# from dotenv import load_dotenv
# import json
# from deep_translator import GoogleTranslator
# import google.generativeai as genai
# load_dotenv()


# api1 = os.getenv("GEMINI_API_KEY")
# genai.configure(api_key=api1)


# # api2 = os.getenv("Groq_key")
# # api3 = os.getenv("GRoq_key")
# # api2 = os.getenv("Groq_key")
# # api2 = os.getenv("Groq_key")
# # api2 = os.getenv("Groq_key")
# # api2 = os.getenv("Groq_key")

# # apis = [
# #     api1
# # ]
# # from google import genai

# # client = genai.Client()

# # response = client.models.generate_content(
# #     model="gemini-2.5-flash",
# #     contents="Explain how AI works in a few words",
# # )

# # print(response.text)


# def make_call(data):
#     print(data)
#     newdata = data.replace("'", '"')
#     items = json.loads(newdata)
#     language = items['lang']
#     query = items['text']
#     query = query.lower()
#     answer = None
#     while True:
#         for api in apis:
#             client = genai.Client(
#                     api_key=api,
#                 )  # Configure the model with the API key
#             # query = st.text_input("Enter your query")
#             prmptquery= f"Answer this query in a short message with wisdom, love and compassion, in context to bhagwat geeta, that feels like chatting to a person and provide references of shloks from chapters of bhagwat geeta which is relevant to the query. keep the answer short, precise and simple. 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",
#             }
#     print(translated)
#     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")