Spaces:
Sleeping
Sleeping
| import google.generativeai as genai | |
| import streamlit as st | |
| import fitz | |
| import spacy | |
| from docx import Document | |
| import dateparser | |
| from datetime import datetime | |
| from giner import GiNER | |
| # Load SpaCy model | |
| nlp = spacy.load('en_core_web_sm') | |
| # Load GLiNER model | |
| giner = GiNER("roberta-large") | |
| def extract_text_from_pdf(file): | |
| pdf = fitz.open(stream=file.read(), filetype="pdf") | |
| text = "" | |
| for page in pdf: | |
| text += page.get_text() | |
| return text | |
| def extract_text_from_doc(file): | |
| doc = Document(file) | |
| return " ".join([paragraph.text for paragraph in doc.paragraphs]) | |
| def authenticate_gemini(api_key): | |
| try: | |
| genai.configure(api_key=api_key) | |
| model = genai.GenerativeModel('gemini-pro') | |
| return model | |
| except Exception as e: | |
| st.error(f"Authentication failed: {e}") | |
| return None | |
| def generate_summary(text, model): | |
| prompt = f"Summarize the following resume:\n\n{text}\n\nProvide a brief overview of the candidate's qualifications, experience, and key skills." | |
| response = model.generate_content(prompt) | |
| return response.text | |
| def extract_info(text): | |
| doc = nlp(text) | |
| giner_results = giner.annotate(text) | |
| # Extract companies | |
| companies = set([ent.text for ent in doc.ents if ent.label_ == "ORG"]) | |
| companies.update([entity['text'] for entity in giner_results if entity['type'] == "ORG"]) | |
| # Extract experience | |
| 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]) | |
| # Extract education | |
| 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"])]) | |
| education.update([entity['text'] for entity in giner_results if entity['type'] == "ORG" and any(keyword in entity['text'].lower() for keyword in ["university", "college", "institute", "school"])]) | |
| # Extract contact information | |
| email = next((ent.text for ent in doc.ents if ent.label_ == "EMAIL"), "Not found") | |
| phone = next((ent.text for ent in doc.ents if ent.label_ == "PHONE_NUMBER"), "Not found") | |
| # Use GLiNER for additional entity extraction | |
| for entity in giner_results: | |
| if entity['type'] == "PER" and email == "Not found": | |
| email = entity['text'] | |
| elif entity['type'] == "PHONE" and phone == "Not found": | |
| phone = entity['text'] | |
| return list(companies), experience, list(education), email, phone | |
| def main(): | |
| st.title("Enhanced Resume Analyzer") | |
| api_key = st.secrets["GEMINI_API_KEY"] # Use Streamlit secrets | |
| uploaded_file = st.file_uploader("Choose a PDF or DOCX file", type=["pdf", "docx"]) | |
| if uploaded_file is not None: | |
| 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 | |
| companies, experience, education, email, phone = extract_info(resume_text) | |
| st.subheader("Extracted Information") | |
| st.write(f"*Years of Experience:* {experience}") | |
| st.write("*Companies:*", ", ".join(companies)) | |
| st.write("*Education:*", ", ".join(education)) | |
| st.write(f"*Email:* {email}") | |
| st.write(f"*Phone:* {phone}") | |
| summary = generate_summary(resume_text, model) | |
| st.subheader("Resume Summary") | |
| st.write(summary) | |
| except Exception as e: | |
| st.error(f"Error during processing: {str(e)}") | |
| st.exception(e) # This will print the full traceback | |
| if __name__ == "__main__": | |
| main() |