Upload app.py

app.py

@@ -0,0 +1,128 @@
+import os
+import PyPDF2
+from transformers import BertTokenizer, BertModel
+from transformers import LongformerModel, LongformerTokenizer
+from transformers import BigBirdModel, BigBirdTokenizer
+import numpy as np
+from groq import Groq
+import gradio as gr
+from pathlib import Path
+import torch
+
+
+# Load BERT tokenizer and model
+tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
+model = BertModel.from_pretrained('bert-base-uncased')
+
+# Load the BigBird model and tokenizer
+tokenizer = BigBirdTokenizer.from_pretrained('google/bigbird-roberta-base')
+model = BigBirdModel.from_pretrained('google/bigbird-roberta-base')
+
+
+#longformer
+# Load the Longformer model and tokenizer
+tokenizer = LongformerTokenizer.from_pretrained('allenai/longformer-base-4096')
+model = LongformerModel.from_pretrained('allenai/longformer-base-4096')
+
+#longFormer
+
+def get_longformer_embedding(text):
+    # Tokenize the text
+    inputs = tokenizer(text, return_tensors='pt', truncation=True, padding=True, max_length=4096)
+    
+    # Get the embeddings from Longformer
+    with torch.no_grad():
+        outputs = model(**inputs)
+    
+    # Use the [CLS] token's embedding as the aggregate representation
+    cls_embedding = outputs.last_hidden_state[:, 0, :].numpy()
+    
+    return cls_embedding
+
+# BIGBIRD
+def get_bigbird_embedding(text):
+    # Tokenize the text
+    inputs = tokenizer(text, return_tensors='pt', truncation=True, padding=True, max_length=4096)
+    
+    # Get the embeddings from BigBird
+    with torch.no_grad():
+        outputs = model(**inputs)
+    
+    # Use the [CLS] token's embedding as the aggregate representation
+    cls_embedding = outputs.last_hidden_state[:, 0, :].numpy()
+    
+    return cls_embedding
+
+def get_bert_embedding(text):
+    # Tokenize the text
+    inputs = tokenizer(text, return_tensors='pt', truncation=True, padding=True, max_length=512)
+    
+    # Get the embeddings from BERT
+    with torch.no_grad():
+        outputs = model(**inputs)
+    
+    # Use the [CLS] token's embedding as the aggregate representation
+    cls_embedding = outputs.last_hidden_state[:, 0, :].numpy()
+    
+    return cls_embedding
+def process_folder(file):
+    folder_path = os.path.dirname(file.name)  # Get the directory of the selected file
+    files = os.listdir(folder_path)  # List all files in the directory
+    file_paths = [os.path.join(folder_path, f) for f in files]  # Get full paths of all files
+    return f"Files in folder: {', '.join(files)}"
+
+# Function to extract text from a PDF
+def extract_text_from_pdf(pdf_file):
+    text = ''
+    with open(pdf_file, 'rb') as file:
+        reader = PyPDF2.PdfReader(file)
+        for page in reader.pages:
+            text += page.extract_text() or ''
+    return text
+
+def calculate_cosine(embedding1, embedding2):
+    # Calculate the dot product and magnitudes of the embeddings
+    dot_product = np.dot(embedding1, embedding2)
+    magnitude1 = np.linalg.norm(embedding1)
+    magnitude2 = np.linalg.norm(embedding2)
+    
+    # Calculate cosine similarity
+    similarity = dot_product / (magnitude1 * magnitude2)
+    return similarity
+def foo(files, JD):
+    # Extract text and compute embeddings for job description using different models
+    text_jd = extract_text_from_pdf(JD)    
+    JD_embedding_bert = get_bert_embedding(text_jd).flatten()  # Flatten to match the dimension
+    JD_embedding_longformer = get_longformer_embedding(text_jd).flatten()
+    JD_embedding_bigbird = get_bigbird_embedding(text_jd).flatten()
+
+    sim = []
+    
+    for d in files:
+        text = extract_text_from_pdf(d)
+        # Compute embeddings for the resume using different models
+        resume_embedding_bert = get_bert_embedding(text).flatten()  # Fixed function call
+        resume_embedding_longformer = get_longformer_embedding(text).flatten()
+        resume_embedding_bigbird = get_bigbird_embedding(text).flatten()
+        # Calculate cosine similarity for each model
+        similarity_bert = calculate_cosine(resume_embedding_bert, JD_embedding_bert)
+        similarity_longformer = calculate_cosine(resume_embedding_longformer, JD_embedding_longformer)
+        similarity_bigbird = calculate_cosine(resume_embedding_bigbird, JD_embedding_bigbird)
+        # Append the results to the array
+        sim.append(f"\nFile: {d.name:}\n"
+                   f"Bert Similarity: {similarity_bert:.4f}\n"
+                   f"Longformer Similarity: {similarity_longformer:.4f}\n"
+                   f"BigBird Similarity: {similarity_bigbird:.4f}\n")
+        
+    
+    
+    return "\n".join(sim)  # Join the list into a single string for Gradio output
+
+
+with gr.Blocks() as func:
+    inputs = [gr.File(file_count="multiple", label="Upload Resume Files"), gr.File(label="Upload Job Description")]
+    outputs = gr.Textbox(label="Similarity Scores")
+    show = gr.Button(value="Calculate Similarity")
+    show.click(foo, inputs, outputs)
+    
+func.launch()