import requests
from llama_index import SimpleDirectoryReader, GPTSimpleVectorIndex, LLMPredictor, ServiceContext, PromptHelper
import gradio as gr

import os
from dotenv import load_dotenv

# Load environment variables from .env file
load_dotenv()

# Get Hugging Face API key from environment variable
hf_api_key = os.getenv("HF_API_KEY")

API_URL = "https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.3"
headers = {"Authorization": f"Bearer {hf_api_key}"}


def query(payload):
    response = requests.post(API_URL, headers=headers, json=payload)
    return response.json()

def init_index(directory_path):
    # Model parameters
    max_input_size = 4096
    num_outputs = 512
    max_chunk_overlap = 20
    chunk_size_limit = 600

    # Prompt helper and predictor
    prompt_helper = PromptHelper(max_input_size, num_outputs, max_chunk_overlap, chunk_size_limit=chunk_size_limit)
    llm_predictor = LLMPredictor(llm=query)

    # Read documents from the "docs" folder
    documents = SimpleDirectoryReader(directory_path).load_data()

    # Initialize index with document data
    service_context = ServiceContext.from_defaults(llm_predictor=llm_predictor, prompt_helper=prompt_helper)
    index = GPTSimpleVectorIndex.from_documents(documents, service_context=service_context)

    # Save the created index
    index.save_to_disk('index.json')

    return index

def chatbot(input_text):
    # Load index
    index = GPTSimpleVectorIndex.load_from_disk('index.json')

    # Get response for the question
    response = index.query(input_text, response_mode="compact")

    return response.response

# Create index
init_index("docs")

# Create UI interface to interact with the Hugging Face model
iface = gr.Interface(fn=chatbot,
                     inputs=gr.components.Textbox(lines=7, placeholder="Enter your question here"),
                     outputs="text",
                     title="Frost AI ChatBot: Your Knowledge Companion Powered by Hugging Face",
                     description="Ask any question about rahasak research papers",
                     allow_screenshot=True)
iface.launch(share=True)