# Import os to handle environment variables
#
# To run this app
# 
# streamlit run <path to this file, for example, rag\streamlit_app_basic.py>
#
import os
from dotenv import load_dotenv
import streamlit as st
import boto3
import json

load_dotenv()

st.subheader("DeepBuddy's AI chatbot")

def generate_response(input_text):



        load_dotenv()

# Initialize the Bedrock client with credentials from .env
        bedrock_runtime = boto3.client(
                service_name='bedrock-runtime',
                region_name=os.getenv('AWS_REGION'),
                aws_access_key_id=os.getenv('AWS_ACCESS_KEY_ID'),
                aws_secret_access_key=os.getenv('AWS_SECRET_ACCESS_KEY')
)

# Define your prompt for Claude
        request_body = {
                "anthropic_version": "bedrock-2023-05-31",
                "max_tokens": 1000,
                "temperature" : 0.2,
                "messages": [
                        {"role": "user", "content": user_question}
        ]
        }

# Make the API call to Claude
        response = bedrock_runtime.invoke_model(
                modelId = "anthropic.claude-3-5-sonnet-20240620-v1:0",  
                # Or "meta.llama3-70b-instruct-v1" or "anthropic.claude-3-sonnet-20240229-v1:0"
                body=json.dumps(request_body)
        )


# Parse the response
        response_body = json.loads(response['body'].read())
        # print(response_body['content'][0]['text'])
        
        # 1. Access Gen AI Model from AWS Bedrock service
        # 2. Pass the user text to the AWS Bedrock API 
        # 3. Get the response from the Gen AI Model
        # 4. Print it on the output
        st.info(response_body['content'][0]['text'])  # Display the response content

user_question = st.text_input("Ask any question. Press enter to submit", key="user_question")
if user_question:
    generate_response(user_question)