Create app.py

app.py

@@ -0,0 +1,157 @@
+import streamlit as st
+import os
+from dotenv import load_dotenv
+from groq import Groq
+import PyPDF2
+
+# Load environment variables
+load_dotenv()
+
+# Initialize Groq client
+client = Groq(
+    api_key=os.getenv("GROQ_API_KEY"),
+)
+
+def extract_text_from_pdf(file):
+    reader = PyPDF2.PdfReader(file)
+    text = ''
+    for page_num in range(len(reader.pages)):
+        page = reader.pages[page_num]
+        text += page.extract_text()
+    return text
+
+def analyze_job_description(job_description):
+    prompt = f"Here is a job description:\n\n{job_description}\n\nPlease extract the key requirements and skills needed for this position."
+    chat_completion = client.chat.completions.create(
+        messages=[
+            {
+                "role": "user",
+                "content": prompt,
+            }
+        ],
+        model="llama3-8b-8192",
+    )
+    return chat_completion.choices[0].message.content
+
+def get_resume_feedback(content, job_requirements):
+    prompt = f"Here is the content of the resume:\n\n{content}\n\nBased on the following job requirements and skills:\n\n{job_requirements}\n\nPlease provide suggestions for improving this resume, including keyword optimization and ATS compatibility checks."
+    chat_completion = client.chat.completions.create(
+        messages=[
+            {
+                "role": "user",
+                "content": prompt,
+            }
+        ],
+        model="llama3-8b-8192",
+    )
+    return chat_completion.choices[0].message.content
+
+def score_resume_against_job_description(resume_text, job_description_text):
+    resume_words = set(resume_text.lower().split())
+    job_description_words = set(job_description_text.lower().split())
+    common_words = resume_words.intersection(job_description_words)
+    score = len(common_words) / len(job_description_words) * 100
+    return score
+
+def chat_with_llm(resume_text, job_description_text, user_question):
+    prompt = f"Here is the content of the resume:\n\n{resume_text}\n\nHere is the job description:\n\n{job_description_text}\n\nQuestion: {user_question}\n\nAnswer:"
+    chat_completion = client.chat.completions.create(
+        messages=[
+            {
+                "role": "user",
+                "content": prompt,
+            }
+        ],
+        model="llama3-8b-8192",
+    )
+    return chat_completion.choices[0].message.content
+
+def main():
+    st.title("Resume Upgrader with ATS, Job Description Matching, and Chat Capabilities")
+
+    # Upload resume files
+    uploaded_resumes = st.file_uploader("Upload your resume (PDF)", type=["pdf"], accept_multiple_files=True)
+    
+    # Initialize job_description_text to avoid UnboundLocalError
+    job_description_text = None
+    
+    # Upload or input job description
+    job_description_option = st.radio("How would you like to provide the job description?", ("Upload PDF", "Enter Text"))
+
+    if job_description_option == "Upload PDF":
+        job_description_file = st.file_uploader("Upload job description (PDF)", type=["pdf"])
+        if job_description_file:
+            job_description_text = extract_text_from_pdf(job_description_file)
+    else:
+        job_description_text = st.text_area("Enter job description")
+
+    if uploaded_resumes and job_description_text:
+        st.write("Uploaded Resumes:")
+        for uploaded_file in uploaded_resumes:
+            st.write(uploaded_file.name)
+
+        if job_description_option == "Upload PDF":
+            st.write("Uploaded Job Description:")
+            st.write(job_description_file.name)
+        else:
+            st.write("Entered Job Description:")
+
+        # Extract text from all uploaded resumes
+        combined_resume_text = ""
+        for uploaded_file in uploaded_resumes:
+            combined_resume_text += extract_text_from_pdf(uploaded_file) + "\n\n"
+
+        st.write("All documents uploaded and text extracted successfully!")
+
+        # Analyze the job description
+        job_requirements = analyze_job_description(job_description_text)
+        st.write("Extracted Job Requirements and Skills:")
+        st.write(job_requirements)
+
+        # Initialize session state for resume feedback history
+        if "resume_feedback" not in st.session_state:
+            st.session_state.resume_feedback = []
+
+        # Provide options for the user
+        option = st.selectbox("What would you like to do?", ("Get Feedback and ATS Check", "Get Score", "Chat"))
+
+        if option == "Get Feedback and ATS Check":
+            if st.button("Get Feedback"):
+                feedback = get_resume_feedback(combined_resume_text, job_requirements)
+                st.session_state.resume_feedback.append((feedback, None, None))
+
+        elif option == "Get Score":
+            if st.button("Get Score"):
+                score = score_resume_against_job_description(combined_resume_text, job_description_text)
+                st.session_state.resume_feedback.append((None, None, score))
+
+        elif option == "Chat":
+            if "chat_history" not in st.session_state:
+                st.session_state.chat_history = []
+
+            user_question = st.text_input("Enter your question:")
+
+            if st.button("Ask"):
+                if user_question:
+                    response = chat_with_llm(combined_resume_text, job_description_text, user_question)
+                    st.session_state.chat_history.append((user_question, response))
+                    user_question = ""  # Clear input field
+
+            if st.session_state.chat_history:
+                st.subheader("Chat History")
+                for i, (q, a) in enumerate(st.session_state.chat_history):
+                    st.write(f"**Q{i+1}:** {q}")
+                    st.write(f"**A{i+1}:** {a}")
+
+        # Display feedback history
+        if st.session_state.resume_feedback:
+            st.subheader("Resume Improvement Suggestions and Scores")
+            for i, (feedback, ats_feedback, score) in enumerate(st.session_state.resume_feedback):
+                if feedback:
+                    st.write(f"**Feedback for Resume {i+1}:**")
+                    st.write(feedback)
+                if score is not None:
+                    st.write(f"**Match Score for Resume {i+1}:** {score:.2f}%")
+
+if __name__ == "__main__":
+    main()