Create app.py

app.py

@@ -0,0 +1,123 @@
+import streamlit as st
+from pyngrok import ngrok
+import google.generativeai as genai
+import fitz  # PyMuPDF for PDF text extraction
+import spacy
+from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+from docx import Document
+import re
+from nltk.corpus import words
+import dateparser
+from datetime import datetime
+import os
+
+# Replace with your ngrok auth token
+ngrok.set_auth_token("2keP9BS91BCtRFtnf5Ss4tOpzq4_2c6463MYzXPqFM3a95gUM")
+url = ngrok.connect(8501)
+print(f"Public URL: {url}")
+
+# Load SpaCy model
+nlp_spacy = spacy.load('en_core_web_sm')
+
+# Load Babelscape NER model
+tokenizer_ner = AutoTokenizer.from_pretrained("Babelscape/wikineural-multilingual-ner")
+model_ner = AutoModelForTokenClassification.from_pretrained("Babelscape/wikineural-multilingual-ner")
+nlp_ner = pipeline('ner', model=model_ner, tokenizer=tokenizer_ner, aggregation_strategy="simple")
+
+# Load GLinER model
+gliner_tokenizer = AutoTokenizer.from_pretrained("DAMO-NLP-SG/gliner-large")
+gliner_model = AutoModelForSeq2SeqLM.from_pretrained("DAMO-NLP-SG/gliner-large")
+
+class EnhancedNERPipeline:
+    def __init__(self, nlp_spacy, nlp_ner, gliner_model, gliner_tokenizer):
+        self.nlp_spacy = nlp_spacy
+        self.nlp_ner = nlp_ner
+        self.gliner_model = gliner_model
+        self.gliner_tokenizer = gliner_tokenizer
+
+    def __call__(self, text):
+        doc = self.nlp_spacy(text)
+        ner_results = self.nlp_ner(text)
+        gliner_companies = extract_info_with_gliner(text, "company names")
+        gliner_experience = extract_info_with_gliner(text, "years of experience")
+        gliner_education = extract_info_with_gliner(text, "educational institutions")
+        
+        combined_entities = doc.ents + tuple(ner_results)
+        doc._.gliner_companies = gliner_companies.split(', ')
+        doc._.gliner_experience = gliner_experience
+        doc._.gliner_education = gliner_education.split(', ')
+        doc.ents = [ent for ent in combined_entities if ent.label_ not in ["ORG"]]
+        return doc
+
+def extract_info_with_gliner(text, info_type):
+    input_text = f"Extract {info_type} from: {text}"
+    input_ids = gliner_tokenizer(input_text, return_tensors="pt").input_ids
+    outputs = gliner_model.generate(input_ids, max_length=100)
+    return gliner_tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# Create the enhanced pipeline
+enhanced_nlp = EnhancedNERPipeline(nlp_spacy, nlp_ner, gliner_model, gliner_tokenizer)
+
+def extract_companies(doc):
+    gliner_companies = set(doc._.gliner_companies)
+    spacy_babelscape_companies = set([ent.text for ent in doc.ents if ent.label_ == "ORG"])
+    return list(gliner_companies.union(spacy_babelscape_companies))
+
+def extract_experience(doc):
+    gliner_experience = int(re.search(r'\d+', doc._.gliner_experience).group()) if doc._.gliner_experience else 0
+    spacy_experience = max([datetime.now().year - date.year for ent in doc.ents if ent.label_ == "DATE" and (date := dateparser.parse(ent.text)) and date.year <= datetime.now().year] or [0])
+    return max(gliner_experience, spacy_experience)
+
+def extract_education(doc):
+    gliner_education = set(doc._.gliner_education)
+    spacy_babelscape_education = set([ent.text for ent in doc.ents if ent.label_ == "ORG" and any(keyword in ent.text.lower() for keyword in ["university", "college", "institute", "school"])])
+    return list(gliner_education.union(spacy_babelscape_education))
+
+def main():
+    st.title("Enhanced Resume Analyzer with GLinER Focus")
+    
+    api_key = st.text_input("Enter your Google Gemini API key", type="password")
+    uploaded_file = st.file_uploader("Choose a PDF or DOCX file", type=["pdf", "docx"])
+
+    if uploaded_file is not None and api_key:
+        try:
+            model = authenticate_gemini(api_key)
+            if model is None:
+                return
+
+            if uploaded_file.type == "application/pdf":
+                resume_text = extract_text_from_pdf(uploaded_file)
+            elif uploaded_file.type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
+                resume_text = extract_text_from_doc(uploaded_file)
+            else:
+                st.error("Unsupported file format.")
+                return
+
+            doc = enhanced_nlp(resume_text)
+
+            companies = extract_companies(doc)
+            experience = extract_experience(doc)
+            education = extract_education(doc)
+            
+            phone = extract_info_with_gliner(resume_text, "phone number")
+            email = extract_info_with_gliner(resume_text, "email address")
+            linkedin = extract_info_with_gliner(resume_text, "LinkedIn profile")
+
+            st.subheader("Extracted Information")
+            st.write(f"**Years of Experience:** {experience}")
+            st.write("**Companies:**", ", ".join(companies))
+            st.write("**Education:**", ", ".join(education))
+            st.write(f"**Phone Number:** {phone}")
+            st.write(f"**Email:** {email}")
+            st.write(f"**LinkedIn:** {linkedin}")
+
+            summary = generate_summary(resume_text, model)
+            st.subheader("Resume Summary")
+            st.write(summary)
+
+        except Exception as e:
+            st.error(f"Error during processing: {e}")
+
+if __name__ == "__main__":
+    main()