src/streamlit_app.py

import streamlit as st
import fitz  # PyMuPDF
from langchain_openai import ChatOpenAI
from azure.core.credentials import AzureKeyCredential
from dotenv import load_dotenv
import io
import os
import openai
import logging
from langchain_core.messages import HumanMessage, SystemMessage
from azure.identity import ManagedIdentityCredential  # For Managed Identity
from azure.core.credentials import AzureKeyCredential
import requests
#openAI
# from langchain_openai import AzureChatOpenAI


# Load environment variables from .env file
load_dotenv()

#set env
ENDPOINT = os.getenv("AZURE_OPENAI_ENDPOINT")
API_KEY = os.getenv("AZURE_OPENAI_API_KEY")
DEPLOYMENT_NAME = os.getenv("AZURE_OPENAI_DEPLOYMENT_NAME")
azure_openai_embedding_model  = os.getenv("AZURE_OPENAI_EMBEDDING_MODEL")
HuggingFace_API_KEY = os.getenv("HUGGINGFACE_API_KEY")
HuggingFace_API_URL = os.getenv("HUGGINGFACE_API_URL")

# Check if the necessary environment variables are loaded
if not API_KEY or not ENDPOINT or not DEPLOYMENT_NAME:
    st.error("Azure OpenAI credentials are missing. Please check your .env file.")
    st.stop()

# Initialize the OpenAI client
#client = OpenAIClient(endpoint=ENDPOINT, credential=AzureKeyCredential(API_KEY))

#myCode 
headers = {
    "Authorization": f"Bearer {HuggingFace_API_KEY}"  # Replace with your actual API key
}


# Function to extract text from the PDF
def extract_text_from_pdf(pdf_file):
    # Read the uploaded file as a byte stream
    pdf_bytes = pdf_file.read()

    # Open the PDF from the byte stream
    doc = fitz.open("pdf", pdf_bytes)  # Fix: use the correct format to open the byte stream
    text = ""
    for page in doc:
        text += page.get_text()
    return text



# Function to extract relevant information from the CV using Azure OpenAI (ChatGPT)
def extract_info_from_openai(text):
    prompt = f"""
    Extract the following information from this CV text:
    1. Job title
    2. Location
    3. Skills
    4. Years of experience
    5. Education level

    Text:
    {text}
    """

    system_message = SystemMessage(content=prompt)
    messages = [system_message]


    data = {"inputs": "Hello, Hugging Face!"}
    #data = {"inputs": prompt}
    response = requests.post(API_URL, headers=headers, json=data)
    # Call the invoke method to get the response
    # response = client.invoke(messages)
    
    # # Request to Azure OpenAI (GPT-4)
    # response = client.completions.create(
    #     deployment_name=DEPLOYMENT_NAME,
    #     prompt=prompt,
    #     max_tokens=5000,
    #     temperature=0.7
    # )

    # Parse the AI response
    result = response.text #.json() #response.result
    return result #result.choices[0].text.strip()

# Streamlit App
st.title("AI Screening")
st.title("CV Information Extractor with Azure OpenAI (GPT-4)")
st.write("Upload a CV PDF file, and the app will extract relevant information such as job title, location, skills, experience, and education.")

# File uploader
uploaded_file = st.file_uploader("Choose a PDF file", type="pdf")

if uploaded_file is not None:
    # Extract text from PDF
    text = extract_text_from_pdf(uploaded_file)

    # Display the extracted text (optional)
    st.subheader("Extracted Text from CV")
    st.text_area("Text from CV", text, height=300)

    # Extract relevant info using Azure OpenAI (GPT-4)
    extracted_info = extract_info_from_openai(text)

    # Display the extracted information
    st.subheader("Extracted Information")
    st.write(extracted_info)