Update app.py

app.py

@@ -1,26 +1,35 @@
+import os
 import streamlit as st
-import google.generativeai as gemini_pro
+import google.generativeai as genai
 import pandas as pd
 from io import StringIO
+import fitz  # PyMuPDF
 
-# Initialize Google Generative AI Gemini-pro model
-gemini_pro.initialize(api_key='YOUR_GOOGLE_API_KEY')
+# Configure Google Generative AI
+genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
+model = genai.GenerativeModel('gemini-1.5-flash')
 
-def analyze_resume(resume_text):
-    # Using the Gemini-pro model to analyze the resume
-    response = gemini_pro.analyze_text(resume_text)
-    return response
+def extract_text_from_pdf(file):
+    """Extract text from PDF."""
+    text = ""
+    doc = fitz.open(stream=file.read(), filetype="pdf")
+    for page in doc:
+        text += page.get_text()
+    return text
+
+def get_gemini_response(prompt):
+    """Function to load Google Gemini model and provide queries as response."""
+    response = model.generate_content([prompt])
+    return response[0]['text']  # Adjust this line based on actual response structure
 
 def extract_skills(resume_text):
-    # Extract skills from resume text
-    response = gemini_pro.extract_entities(resume_text, entity_type='skills')
-    skills = [entity['text'] for entity in response['entities']]
+    prompt = f"Extract the skills from the following resume:\n\n{resume_text}"
+    skills = get_gemini_response(prompt)
     return skills
 
 def match_job_description(resume_text, job_description):
-    # Match resume with job description
-    response = gemini_pro.compare_texts(resume_text, job_description)
-    score = response['similarity_score']
+    prompt = f"Compare the following resume with the job description and provide a match score:\n\nResume:\n{resume_text}\n\nJob Description:\n{job_description}"
+    score = get_gemini_response(prompt)
     return score
 
 # Streamlit application layout
@@ -30,18 +39,14 @@ st.header('Upload Resume')
 uploaded_file = st.file_uploader('Choose a file', type=['pdf', 'docx', 'txt'])
 
 if uploaded_file is not None:
-    # Extract text from uploaded file
-    stringio = StringIO(uploaded_file.getvalue().decode("utf-8"))
-    resume_text = stringio.read()
+    if uploaded_file.type == "application/pdf":
+        resume_text = extract_text_from_pdf(uploaded_file)
+    else:
+        resume_text = uploaded_file.getvalue().decode("utf-8")
 
     st.subheader('Resume Text')
     st.write(resume_text)
 
-    st.subheader('Analyze Resume')
-    if st.button('Analyze'):
-        analysis_result = analyze_resume(resume_text)
-        st.write('Analysis Result:', analysis_result)
-
     st.subheader('Extract Skills')
     if st.button('Extract Skills'):
         skills = extract_skills(resume_text)