Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,114 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 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
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+
+# 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)