Create app.py

app.py

@@ -0,0 +1,70 @@
+from transformers import AutoTokenizer, AutoModel
+import pdfplumber
+import torch
+from sklearn.metrics.pairwise import cosine_similarity
+import re
+
+# Load the Hugging Face MiniLM model for sentence embeddings
+model_name = "sentence-transformers/all-MiniLM-L6-v2"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModel.from_pretrained(model_name)
+
+# Function to extract text from a PDF resume
+def extract_text_from_pdf(pdf_file):
+    with pdfplumber.open(pdf_file) as pdf:
+        text = ""
+        for page in pdf.pages:
+            text += page.extract_text()
+    return text
+
+# Preprocess the text: lowercasing, removing special characters, and extra spaces
+def preprocess_text(text):
+    text = text.lower()  # Convert to lowercase
+    text = re.sub(r'\s+', ' ', text)  # Remove extra spaces
+    text = re.sub(r'[^\w\s]', '', text)  # Remove punctuation
+    return text
+
+# Function to get embeddings from the text using MiniLM model
+def get_embeddings(text):
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512)
+    with torch.no_grad():
+        outputs = model(**inputs)
+    embeddings = outputs.last_hidden_state.mean(dim=1)  # Mean of all token embeddings
+    return embeddings
+
+# Calculate cosine similarity between job description and resume
+def calculate_similarity(job_desc, resume):
+    job_embeddings = get_embeddings(job_desc)
+    resume_embeddings = get_embeddings(resume)
+    similarity = cosine_similarity(job_embeddings, resume_embeddings)
+    return similarity[0][0]
+
+# Main function to match LIC profile with job description
+def lic_profile_matcher(job_description, resume_pdf):
+    # Extract text from PDF resume
+    resume_text = extract_text_from_pdf(resume_pdf)
+    
+    # Preprocess the text (clean and standardize)
+    processed_resume = preprocess_text(resume_text)
+    
+    # Calculate similarity score between job description and resume
+    similarity_score = calculate_similarity(job_description, processed_resume)
+    
+    # Define the threshold for matching
+    if similarity_score > 0.7:
+        return f"Candidate is a good fit with a similarity score of {similarity_score:.2f}."
+    else:
+        return f"Candidate is not a good fit with a similarity score of {similarity_score:.2f}."
+
+# Example job description for LIC role
+job_description = """
+We are looking for a motivated sales agent with experience in selling life insurance products. 
+Experience in customer service, understanding of insurance policies, and excellent communication skills are required.
+"""
+
+# Resume PDF (path to the uploaded PDF file)
+resume_pdf = "path/to/your/resume.pdf"  # Replace with the actual path to your PDF resume
+
+# Use the LIC Profile Matcher function
+result = lic_profile_matcher(job_description, resume_pdf)
+print(result)