Update app.py

app.py

@@ -1,4 +1,3 @@
-import spacy
 import streamlit as st
 import subprocess
 from sklearn.feature_extraction.text import TfidfVectorizer
@@ -7,27 +6,17 @@ import PyPDF2
 import nltk
 from nltk.corpus import stopwords
 from nltk.tokenize import word_tokenize
+from transformers import pipeline
 from gemini_flash import GeminiFlash  # Adjust if Gemini Flash is available
 
 # Ensure that NLTK's stopwords are available
 nltk.download('punkt')
 nltk.download('stopwords')
 
-# Function to install spaCy model
-def download_spacy_model():
-    try:
-        # Attempt to load the model
-        nlp = spacy.load("en_core_web_sm")
-    except OSError:
-        # If not installed, download the model
-        subprocess.run(["python", "-m", "spacy", "download", "en_core_web_sm"], check=True)
-        nlp = spacy.load("en_core_web_sm")
-    return nlp
-
-# Load spaCy model (ensure it is downloaded)
-nlp = download_spacy_model()
-
-# Initialize Gemini Flash for prompt engineering (if available)
+# Initialize Hugging Face NER pipeline
+ner_model = pipeline("ner", model="dbmdz/bert-large-cased-finetuned-conll03-english")
+
+# Initialize Gemini Flash for prompt engineering
 prompt_engineer = GeminiFlash()
 
 # Streamlit Interface
@@ -61,10 +50,9 @@ if job_description:
     # Display preprocessed job description
     st.text_area("Processed Job Description", preprocessed_job_description)
 
-# Step 3: Named Entity Recognition (NER) on Resume
+# Step 3: Named Entity Recognition (NER) on Resume using Hugging Face Transformers
 if resume_text:
-    doc = nlp(resume_text)
-    entities = [(ent.text, ent.label_) for ent in doc.ents]
+    entities = ner_model(resume_text)
 
     # Display extracted entities
     st.subheader("Named Entities from Resume")