Update src/streamlit_app.py

src/streamlit_app.py

@@ -4,40 +4,33 @@ from dotenv import load_dotenv
 import io
 import os
 import requests
+
 # Load environment variables from .env file
 load_dotenv()
 
-#openAI
-# from langchain_openai import AzureChatOpenAI
-
-# 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")
-
-
-#set env
+# Check and set environment variables
 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")
+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")
 
 # 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()
 
-#myCode 
+# 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
 }
 
-
-# Function to extract text from the PDF
+# Function to extract text from the uploaded PDF
 def extract_text_from_pdf(pdf_file):
     # Read the uploaded file as a byte stream
     pdf_bytes = pdf_file.read()
@@ -49,9 +42,7 @@ def extract_text_from_pdf(pdf_file):
         text += page.get_text()
     return text
 
-
-
-# Function to extract relevant information from the CV using Azure OpenAI (ChatGPT)
+# Function to extract relevant information from the CV using Hugging Face or Azure OpenAI
 def extract_info_from_openai(text):
     prompt = f"""
     Extract the following information from this CV text:
@@ -65,46 +56,34 @@ def extract_info_from_openai(text):
     {text}
     """
 
-   
-
-
-    # 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
+
+    # 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 extract text.")
+    else:
+        return f"Error: {response.status_code} - {response.text}"
+
+# Streamlit App UI
 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
+    # Extract text from the uploaded 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)
+    # Extract relevant information using Hugging Face (or Azure OpenAI if you need)
     extracted_info = extract_info_from_openai(text)
 
     # Display the extracted information
     st.subheader("Extracted Information")
-    st.write(extracted_info)
+    st.write(extracted_info)