Initial commit

app.py

@@ -1,7 +1,9 @@
+
 from sentence_transformers import SentenceTransformer, util
 from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
 from fuzzywuzzy import fuzz
 import gradio as gr
+import fitz  # PyMuPDF for PDF extraction
 
 # Load the SentenceTransformer model for embeddings
 model = SentenceTransformer('fine_tuned_job_resume_similarity_model')
@@ -19,6 +21,14 @@ TARGET_KEYWORDS = [
     "problem-solving", "teamwork", "leadership", "technical", "planning", "operations"
 ]
 
+# Function to extract text from PDF files
+def extract_text_from_pdf(pdf_file):
+    text = ""
+    with fitz.open(pdf_file) as doc:
+        for page in doc:
+            text += page.get_text("text")
+    return text
+
 # Define function to dynamically extract entities into generalized categories
 def extract_entities(text):
     entities = {"qualifications": [], "responsibilities": [], "other": []}
@@ -42,7 +52,9 @@ def fuzzy_match_keywords(cv_text, job_text, keywords):
         match_score += score if score > 60 else 0  # Consider only high-confidence matches
     return match_score / len(keywords) if keywords else 0
 
-def match_cv_to_job(cv_text, job_description):
+def match_cv_to_job(pdf_file, job_description):
+    # Extract text from PDF file
+    cv_text = extract_text_from_pdf(pdf_file)
     debug_info = "Debug Info:\n"
     
     # Extract entities from CV and job description
@@ -76,8 +88,8 @@ def match_cv_to_job(cv_text, job_description):
         (ner_match_score / 100) * 0.3 +  # NER-based entity match
         (fuzzy_keyword_score / 100) * 0.2  # Fuzzy matching for keywords
     )
-    match_percentage = similarity_score * 100
-    debug_info += f"Overall Match Percentage: {round(match_percentage):.2f}%\n"
+    match_percentage = combined_score * 100
+    debug_info += f"Overall Match Percentage: {match_percentage:.2f}%\n"
     
     return {"Match Percentage": f"{match_percentage:.2f}%"}, debug_info
 
@@ -85,13 +97,13 @@ def match_cv_to_job(cv_text, job_description):
 with gr.Blocks() as demo:
     gr.Markdown("# CV and Job Description Matcher for All Industries with NER and Fuzzy Matching")
     
-    cv_text = gr.Textbox(label="CV Text", placeholder="Enter the CV text here", lines=10)
-    job_description = gr.Textbox(label="Job Description", placeholder="Enter the entire job description text here", lines=10)
+    pdf_input = gr.File(label="Upload CV (PDF format)")
+    job_description = gr.Textbox(label="Job Description", placeholder="Enter the job description text here", lines=10)
     
     match_button = gr.Button("Calculate Match Percentage")
     output = gr.JSON(label="Match Result")
     debug_output = gr.Textbox(label="Debug Info", lines=10)
     
-    match_button.click(fn=match_cv_to_job, inputs=[cv_text, job_description], outputs=[output, debug_output])
+    match_button.click(fn=match_cv_to_job, inputs=[pdf_input, job_description], outputs=[output, debug_output])
 
 demo.launch()