Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,8 +1,11 @@
 import streamlit as st
-import fitz  # PyMuPDF
+import os
+import openai
 from dotenv import load_dotenv
+
 import os
-import requests
+from openai import AzureOpenAI
+from azure.core.credentials import AzureKeyCredential
 
 # Load environment variables from .env file
 load_dotenv()
@@ -11,26 +14,21 @@ load_dotenv()
 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")
-
-# Set custom cache and config directory for Streamlit to avoid permission issues
-os.environ["STREAMLIT_CACHE_DIR"] = os.path.join(os.getcwd(), ".streamlit")
-os.environ["STREAMLIT_CONFIG_DIR"] = os.path.join(os.getcwd(), ".streamlit")
+API_VERSION = os.getenv("AZURE_OPENAI_API_VERION")
 
 # 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()
 
-# Hugging Face API URL
-API_URL = "https://api-inference.huggingface.co/models/gpt2"  # Replace with your desired model's API URL
-headers = {
-    "Authorization": f"Bearer {HuggingFace_API_KEY}"  # Replace with your actual API key
-}
+client = AzureOpenAI(
+    api_version=API_VERSION,
+    azure_endpoint=ENDPOINT,
+    api_key=API_KEY,
+)
 
-# Function to extract relevant information from the CV using Hugging Face or Azure OpenAI
-def extract_info_from_openai(text):
+# Function to extract information from CV using Azure OpenAI GPT-4 model
+def extract_info_from_azure(text):
     prompt = f"""
     Extract the following information from this CV text:
     1. Job title
@@ -39,22 +37,36 @@ def extract_info_from_openai(text):
     4. Years of experience
     5. Education level
 
-    Text:
+    CV Text:
     {text}
     """
+    response = client.chat.completions.create(
+    messages=[
+            {
+                "role": "system",
+                "content": "You are a helpful assistant.",
+            },
+            {
+                "role": "user",
+                "content": prompt,
+            }
+        ],
+        max_tokens=4096,
+        temperature=1.0,
+        top_p=1.0,
+        model=DEPLOYMENT_NAME
+    )
 
-    data = {"inputs": prompt}
-    response = requests.post(API_URL, headers=headers, json=data)
+    try:
 
-    # If the Hugging Face response is successful, extract the generated text
-    if response.status_code == 200:
-        result = response.json()  # Parse the JSON response
-        return result.get("generated_text", "Error: Unable to generate response.")
-    else:
-        return f"Error: {response.status_code} - {response.text}"
+        result = response.choices[0].message.content
+        return result
+    except Exception as e:
+        st.error(f"Error occurred while contacting Azure OpenAI: {e}")
+        return None
 
 # Streamlit App UI
-st.title("AI Screening")
+st.title("AI Screening for CV Information Extraction")
 st.write("Enter the CV text below, and the app will extract relevant information such as job title, location, skills, experience, and education.")
 
 # Text area for entering CV content manually
@@ -65,9 +77,12 @@ if cv_text:
     st.subheader("Entered Text from CV")
     st.text_area("CV Text", cv_text, height=300)
 
-    # Extract relevant information using Hugging Face (or Azure OpenAI if you need)
-    extracted_info = extract_info_from_openai(cv_text)
+    # Extract relevant information using Azure OpenAI GPT-4
+    extracted_info = extract_info_from_azure(cv_text)
 
     # Display the extracted information
-    st.subheader("Extracted Information")
-    st.write(extracted_info)
+    if extracted_info:
+        st.subheader("Extracted Information")
+        st.write(extracted_info)
+    else:
+        st.write("Could not extract information. Please try again.")