Init Commit

app.py

@@ -1,6 +1,5 @@
 from sentence_transformers import SentenceTransformer, util
 import gradio as gr
-import nltk
 
 # Load the SentenceTransformer model for sentence similarity
 try:
@@ -8,68 +7,53 @@ try:
 except Exception as e:
     print(f"Error loading SentenceTransformer model: {e}")
 
-# Download NLTK punkt tokenizer if not already installed (run this once)
-nltk.download('punkt_tab')
-
-def match_cv_to_jobs(cv_text, job_descriptions):
+def match_cv_to_job(cv_text, job_description):
     debug_info = "Debug Info:\n"
-    results = []
     
-    # Encode the CV text directly without summarization
+    # Encode the entire CV text
     try:
         cv_embedding = model.encode(cv_text, convert_to_tensor=True)
         debug_info += f"CV Embedding: {cv_embedding}\n"
     except Exception as e:
         debug_info += f"Error encoding CV text: {e}\n"
-        return [], debug_info
+        return None, debug_info
     
-    # Split job description into sentences
+    # Encode the entire job description
     try:
-        description_sentences = nltk.tokenize.sent_tokenize(job_descriptions)
+        job_description_embedding = model.encode(job_description, convert_to_tensor=True)
+        debug_info += f"Job Description Embedding: {job_description_embedding}\n"
     except Exception as e:
-        debug_info += f"Error tokenizing job description: {e}\n"
-        return [], debug_info
-    
-    for sentence in description_sentences:
-        try:
-            # Encode each sentence from the job description
-            sentence_embedding = model.encode(sentence, convert_to_tensor=True)
-            debug_info += f"\nJob Description Sentence Embedding: {sentence_embedding}\n"
-            
-            # Compute similarity score
-            similarity_score = util.pytorch_cos_sim(cv_embedding, sentence_embedding).item()
-            debug_info += f"Similarity Score for sentence: {similarity_score}\n"
-            
-            results.append({
-                "Job Description Sentence": sentence,
-                "Similarity Score": similarity_score
-            })
-        except Exception as e:
-            debug_info += f"Error processing sentence '{sentence}': {e}\n"
-            continue
+        debug_info += f"Error encoding job description: {e}\n"
+        return None, debug_info
     
-    # Sort results by similarity score in descending order
+    # Compute similarity score between the entire CV and the entire job description
     try:
-        results = sorted(results, key=lambda x: x["Similarity Score"], reverse=True)
+        similarity_score = util.pytorch_cos_sim(cv_embedding, job_description_embedding).item()
+        debug_info += f"Overall Similarity Score: {similarity_score}\n"
+        
+        # Convert similarity score to a percentage for easier interpretation
+        match_percentage = similarity_score * 100
+        debug_info += f"Overall Match Percentage: {match_percentage:.2f}%\n"
     except Exception as e:
-        debug_info += f"Error sorting results: {e}\n"
+        debug_info += f"Error calculating similarity score: {e}\n"
+        return None, debug_info
     
-    return results, debug_info
+    return {"Match Percentage": f"{match_percentage:.2f}%"}, debug_info
 
 # Gradio interface
 with gr.Blocks() as demo:
-    gr.Markdown("# CV and Job Description Matcher with Sentence Similarity")
+    gr.Markdown("# CV and Job Description Matcher with Overall Similarity Score")
     
-    # Input fields for CV and job descriptions
+    # Input fields for CV and job description
     cv_text = gr.Textbox(label="CV Text", placeholder="Enter the CV text here", lines=10)
-    job_descriptions = gr.Textbox(label="Job Descriptions", placeholder="Enter the entire job description text here", lines=10)
+    job_description = gr.Textbox(label="Job Description", placeholder="Enter the entire job description text here", lines=10)
     
     # Button and output area
-    match_button = gr.Button("Match CV to Job Descriptions")
-    output = gr.JSON(label="Match Results")
-    debug_output = gr.Textbox(label="Debug Info", lines=10)  # Add a debug box to display debug info
+    match_button = gr.Button("Calculate Match Percentage")
+    output = gr.JSON(label="Match Result")
+    debug_output = gr.Textbox(label="Debug Info", lines=10)  # Debug box for detailed output
     
     # Set button click to run the function
-    match_button.click(fn=match_cv_to_jobs, inputs=[cv_text, job_descriptions], outputs=[output, debug_output])
+    match_button.click(fn=match_cv_to_job, inputs=[cv_text, job_description], outputs=[output, debug_output])
 
 demo.launch()