import os import tempfile import streamlit as st import docx import textract from transformers import pipeline # Set page title st.set_page_config(page_title="Resume Analyzer and Company Suitability Checker") ##################################### # Preload Models ##################################### @st.cache_resource(show_spinner=True) def load_models(): """Load all models at startup""" with st.spinner("Loading AI models... This may take a minute on first run."): models = {} # Load summarization model models['summarizer'] = pipeline("summarization", model="google/pegasus-xsum") # Load similarity model models['similarity'] = pipeline("sentence-similarity", model="sentence-transformers/all-MiniLM-L6-v2") return models # Preload models immediately when app starts models = load_models() ##################################### # Function: Extract Text from File ##################################### def extract_text_from_file(file_obj): """ Extract text from .doc and .docx files. Returns the extracted text or an error message if extraction fails. """ filename = file_obj.name ext = os.path.splitext(filename)[1].lower() text = "" if ext == ".docx": try: document = docx.Document(file_obj) text = "\n".join(para.text for para in document.paragraphs if para.text.strip()) except Exception as e: text = f"Error processing DOCX file: {e}" elif ext == ".doc": try: with tempfile.NamedTemporaryFile(delete=False, suffix=".doc") as tmp: tmp.write(file_obj.read()) tmp_filename = tmp.name text = textract.process(tmp_filename).decode("utf-8") os.unlink(tmp_filename) except Exception as e: text = f"Error processing DOC file: {e}" else: text = "Unsupported file type." return text ##################################### # Function: Summarize Resume Text ##################################### def summarize_resume_text(resume_text, models): """ Generates a concise summary of the resume text using the summarization model. """ summarizer = models['summarizer'] # Handle long text max_input_length = 1024 # PEGASUS-XSUM limit if len(resume_text) > max_input_length: # Process in chunks if text is too long chunks = [resume_text[i:i+max_input_length] for i in range(0, min(len(resume_text), 3*max_input_length), max_input_length)] summaries = [] for chunk in chunks: chunk_summary = summarizer(chunk, max_length=100, min_length=30, do_sample=False)[0]['summary_text'] summaries.append(chunk_summary) candidate_summary = " ".join(summaries) if len(candidate_summary) > max_input_length: candidate_summary = summarizer(candidate_summary[:max_input_length], max_length=150, min_length=40, do_sample=False)[0]['summary_text'] else: candidate_summary = summarizer(resume_text, max_length=150, min_length=40, do_sample=False)[0]['summary_text'] return candidate_summary ##################################### # Function: Compare Candidate Summary to Company Prompt ##################################### def compute_suitability(candidate_summary, company_prompt, models): """ Compute the similarity between candidate summary and company prompt. Returns a score in the range [0, 1]. """ similarity_pipeline = models['similarity'] # The pipeline expects a document and a list of candidates to compare to result = similarity_pipeline( candidate_summary, [company_prompt] ) # Extract the similarity score from the result score = result[0]['score'] return score ##################################### # Streamlit Interface ##################################### st.title("Resume Analyzer and Company Suitability Checker") st.markdown( """ Upload your resume file in **.doc** or **.docx** format. The app performs the following tasks: 1. Extracts text from the resume. 2. Uses a transformer-based model to generate a concise candidate summary. 3. Compares the candidate summary with a company profile to produce a suitability score. """ ) # Use two columns with equal width col1, col2 = st.columns(2) with col1: # File uploader for resume uploaded_file = st.file_uploader("Upload Resume", type=["doc", "docx"]) if uploaded_file is not None: st.write(f"{uploaded_file.name} {uploaded_file.size/1024:.1f}KB") # Button to process the resume if st.button("Process Resume", type="primary", use_container_width=True): if uploaded_file is None: st.error("Please upload a resume file first.") else: with st.status("Processing resume...") as status: status.update(label="Extracting text from resume...") resume_text = extract_text_from_file(uploaded_file) if not resume_text or resume_text.strip() == "": status.update(label="Error: No text could be extracted", state="error") else: status.update(label=f"Extracted {len(resume_text)} characters. Generating summary...") candidate_summary = summarize_resume_text(resume_text, models) st.session_state["candidate_summary"] = candidate_summary status.update(label="Processing complete!", state="complete") # Display candidate summary if available if "candidate_summary" in st.session_state: st.subheader("Candidate Summary") st.markdown(st.session_state["candidate_summary"]) with col2: # Pre-defined company prompt for Google LLC. default_company_prompt = ( "Google LLC, a global leader in technology and innovation, specializes in internet services, cloud computing, " "artificial intelligence, and software development. As part of Alphabet Inc., Google seeks candidates with strong " "problem-solving skills, adaptability, and collaboration abilities. Technical roles require proficiency in programming " "languages such as Python, Java, C++, Go, or JavaScript, with expertise in data structures, algorithms, and system design. " "Additionally, skills in AI, cybersecurity, UX/UI design, and digital marketing are highly valued. Google fosters a culture " "of innovation, expecting candidates to demonstrate creativity, analytical thinking, and a passion for cutting-edge technology." ) # Company prompt text area. company_prompt = st.text_area( "Enter company details:", value=default_company_prompt, height=150, ) # Button to compute the suitability score. if st.button("Compute Suitability Score", type="primary", use_container_width=True): if "candidate_summary" not in st.session_state: st.error("Please process the resume first!") else: candidate_summary = st.session_state["candidate_summary"] if candidate_summary.strip() == "": st.error("Candidate summary is empty; please check your resume file.") elif company_prompt.strip() == "": st.error("Please enter the company information.") else: with st.spinner("Computing suitability score..."): score = compute_suitability(candidate_summary, company_prompt, models) # Display score with a progress bar for visual feedback st.success(f"Suitability Score: {score:.2f} (range 0 to 1)") st.progress(score) # Add interpretation of score if score > 0.75: st.info("Excellent match! Your profile appears very well suited for this company.") elif score > 0.5: st.info("Good match. Your profile aligns with many aspects of the company's requirements.") elif score > 0.3: st.info("Moderate match. Consider highlighting more relevant skills or experience.") else: st.info("Low match. Your profile may need significant adjustments to better align with this company.")