Update app.py

app.py

@@ -7,7 +7,6 @@ from transformers import AutoTokenizer, AutoModelForSequenceClassification, Auto
 from sentence_transformers import SentenceTransformer, util
 from groq import Groq
 import gradio as gr
-from docxtpl import DocxTemplate
 
 # Set your API key for Groq
 os.environ["GROQ_API_KEY"] = "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"
@@ -66,17 +65,18 @@ def extract_experience(text):
     experience_years = [int(year[0]) for year in experience_years]
     return experience_years, job_titles
 
-# --- Summarization Function --- #
-def summarize_experience(experience_text):
-    """Summarizes the experience text using a pre-trained model."""
-    model_name = "facebook/bart-large-cnn"
+# --- Sentiment Analysis --- #
+def analyze_sentiment(text):
+    """Analyzes the sentiment of the text."""
+    model_name = "mrm8488/distiluse-base-multilingual-cased-v2-finetuned-stsb_multi_mt-es"
     tokenizer = AutoTokenizer.from_pretrained(model_name)
-    model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+    model = AutoModelForSequenceClassification.from_pretrained(model_name)
 
-    inputs = tokenizer(experience_text, return_tensors="pt", max_length=1024, truncation=True)
-    summary_ids = model.generate(inputs['input_ids'], max_length=150, min_length=30, length_penalty=2.0, num_beams=4, early_stopping=True)
-    summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
-    return summary
+    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
+    with torch.no_grad():
+        outputs = model(**inputs)
+        predicted_sentiment = torch.argmax(outputs.logits).item()
+    return ["Negative", "Neutral", "Positive"][predicted_sentiment]
 
 # --- Semantic Similarity Calculation --- #
 def calculate_semantic_similarity(text1, text2):
@@ -90,7 +90,7 @@ def calculate_semantic_similarity(text1, text2):
     similarity_percentage = similarity_score * 100
     return similarity_percentage
 
-# --- Communication Generation with Enhanced Response --- #
+# --- Communication Generation --- #
 def communication_generator(resume_skills, job_description_skills, skills_similarity, qualifications_similarity, experience_similarity, candidate_experience):
     """Generates a detailed communication response based on similarity scores and additional criteria."""
     # Assess candidate fit based on similarity scores
@@ -118,19 +118,6 @@ def communication_generator(resume_skills, job_description_skills, skills_simila
 
     return message
 
-# --- Sentiment Analysis --- #
-def analyze_sentiment(text):
-    """Analyzes the sentiment of the text."""
-    model_name = "mrm8488/distiluse-base-multilingual-cased-v2-finetuned-stsb_multi_mt-es"
-    tokenizer = AutoTokenizer.from_pretrained(model_name)
-    model = AutoModelForSequenceClassification.from_pretrained(model_name)
-
-    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
-    with torch.no_grad():
-        outputs = model(**inputs)
-        predicted_sentiment = torch.argmax(outputs.logits).item()
-    return ["Negative", "Neutral", "Positive"][predicted_sentiment]
-
 # --- Updated Resume Analysis Function --- #
 def analyze_resume(resume_file, job_description_file):
     # Load and preprocess resume and job description
@@ -150,10 +137,13 @@ def analyze_resume(resume_file, job_description_file):
     required_experience = sum(job_description_experience)  # Assuming total years required
 
     # Calculate similarity scores
-    skills_similarity = len(set(resume_skills).intersection(set(job_description_skills))) / len(job_description_skills) * 100
-    qualifications_similarity = len(set(resume_qualifications).intersection(set(job_description_qualifications))) / len(job_description_qualifications) * 100
+    skills_similarity = len(set(resume_skills).intersection(set(job_description_skills))) / len(job_description_skills) * 100 if job_description_skills else 0
+    qualifications_similarity = len(set(resume_qualifications).intersection(set(job_description_qualifications))) / len(job_description_qualifications) * 100 if job_description_qualifications else 0
     experience_similarity = 1.0 if total_experience >= required_experience else 0.0
 
+    # Sentiment analysis of the resume
+    sentiment_analysis_result = analyze_sentiment(resume_text)
+
     # Fit assessment logic
     fit_score = 0
     if total_experience >= required_experience:
@@ -171,38 +161,79 @@ def analyze_resume(resume_file, job_description_file):
     else:
         fit_assessment = "Not a fit"
 
-    # Prepare output message
-    response_message = (
-        f"Skills Similarity: {skills_similarity:.2f}%\n"
-        f"Qualifications Similarity: {qualifications_similarity:.2f}%\n"
-        f"Experience Similarity: {experience_similarity * 100:.2f}%\n"
-        f"Candidate Experience: {total_experience} years\n"
-        f"Sentiment: Neutral\n"
-        f"Response Message: After a detailed analysis of the candidate's resume, we found the following insights:\n\n"
-        f"Skills Match: {skills_similarity:.2f}% (based on required technologies: {', '.join(job_description_skills)})\n"
-        f"Qualifications Match: {qualifications_similarity:.2f}%\n"
-        f"Experience Match: {experience_similarity * 100:.2f}% (relevant experience: {total_experience} years)\n"
-        f"The overall assessment indicates that the candidate is a {fit_assessment} for the role."
+    # Prepare output messages for tab display
+    summary_message = (
+        f"### Summary of Analysis\n"
+        f"- **Skills Similarity**: {skills_similarity:.2f}%\n"
+        f"- **Qualifications Similarity**: {qualifications_similarity:.2f}%\n"
+        f"- **Experience Similarity**: {experience_similarity * 100:.2f}%\n"
+        f"- **Candidate Experience**: {total_experience} years\n"
+        f"- **Fit Assessment**: {fit_assessment}\n"
+        f"- **Sentiment Analysis**: {sentiment_analysis_result}\n"
+    )
+
+    skills_message = (
+        f"### Skills Overview\n"
+        f"- **Resume Skills:**\n" + "\n".join(f"  - {skill}" for skill in resume_skills) + "\n"
+        f"- **Job Description Skills:**\n" + "\n".join(f"  - {skill}" for skill in job_description_skills) + "\n"
+    )
+
+    qualifications_message = (
+        f"### Qualifications Overview\n"
+        f"- **Resume Qualifications:** " + ", ".join(resume_qualifications) + "\n" +
+        f"- **Job Description Qualifications:** " + ", ".join(job_description_qualifications) + "\n"
     )
 
-    return response_message
+    experience_message = (
+        f"### Experience Overview\n"
+        f"- **Total Experience:** {total_experience} years\n"
+        f"- **Required Experience:** {required_experience} years\n"
+    )
+
+    # Generate communication based on analysis
+    communication = communication_generator(resume_skills, job_description_skills, skills_similarity, qualifications_similarity, experience_similarity, total_experience)
+
+    return summary_message, skills_message, qualifications_message, experience_message, communication
 
 def run_gradio_interface():
     with gr.Blocks() as demo:
         gr.Markdown("## Resume and Job Description Analyzer")
         resume_file = gr.File(label="Upload Resume")
         job_description_file = gr.File(label="Upload Job Description")
-        output_display = gr.Textbox(label="Analysis Output", interactive=False)
+
+        # Define outputs for each tab
+        summary_output = gr.Textbox(label="Summary of Analysis", interactive=False, lines=10)
+        skills_output = gr.Textbox(label="Skills Overview", interactive=False, lines=10)
+        qualifications_output = gr.Textbox(label="Qualifications Overview", interactive=False, lines=10)
+        experience_output = gr.Textbox(label="Experience Overview", interactive=False, lines=10)
+        communication_output = gr.Textbox(label="Communication", interactive=False, lines=10)
+
+        # Create tabs for output sections
+        with gr.Tab("Analysis Summary"):
+            summary_output.render()
+
+        with gr.Tab("Skills Overview"):
+            skills_output.render()
+
+        with gr.Tab("Qualifications Overview"):
+            qualifications_output.render()
+
+        with gr.Tab("Experience Overview"):
+            experience_output.render()
+
+        with gr.Tab("Communication"):
+            communication_output.render()
 
         def analyze(resume, job_desc):
             if resume and job_desc:
-                return analyze_resume(resume, job_desc)
+                summary, skills, qualifications, experience, communication = analyze_resume(resume, job_desc)
+                return summary, skills, qualifications, experience, communication
             return "Please upload both files."
 
         analyze_button = gr.Button("Analyze")
-        analyze_button.click(analyze, inputs=[resume_file, job_description_file], outputs=output_display)
+        analyze_button.click(analyze, inputs=[resume_file, job_description_file], outputs=[summary_output, skills_output, qualifications_output, experience_output, communication_output])
 
     demo.launch()
 
 if __name__ == "__main__":
-    run_gradio_interface()
+    run_gradio_interface()