Create utils.py

utils.py

@@ -0,0 +1,40 @@
+import spacy
+import fitz  # PyMuPDF
+import re
+from transformers import pipeline
+
+def load_models():
+    nlp = spacy.load("en_core_web_sm")
+    llm = pipeline("text-generation", model="openai-community/gpt2")
+    return nlp, llm
+
+def parse_resume(uploaded_file, nlp):
+    doc = fitz.open(stream=uploaded_file.read(), filetype="pdf")
+    text = "\n".join(page.get_text() for page in doc)
+    doc = nlp(text)
+    name = [ent.text for ent in doc.ents if ent.label_ == "PERSON"]
+    email = re.findall(r"[\w\.-]+@[\w\.-]+", text)
+    skills = [token.text.lower() for token in doc if token.pos_ == "NOUN"]
+    edu_keywords = ["bachelor", "master", "phd", "degree", "certification", "diploma"]
+    edu = [sent.text for sent in doc.sents if any(k in sent.text.lower() for k in edu_keywords)]
+    return text, {
+        "name": name[0] if name else "N/A",
+        "email": email[0] if email else "N/A",
+        "skills": list(set(skills)),
+        "education": edu,
+    }
+
+def get_recommendations(parsed):
+    score = 50 + len(parsed["skills"]) % 50
+    feedback = "Try adding more specific technical skills and quantifiable achievements."
+    return score, feedback
+
+def generate_career_insights(parsed, llm, suggestion_type="roadmap"):
+    prompt_map = {
+        "certifications": f"Suggest relevant certifications for someone with skills: {parsed['skills']} and education: {parsed['education']}",
+        "degrees": f"Suggest higher education paths based on: {parsed['education']}",
+        "roadmap": f"Create a 1-year career roadmap for someone with these skills: {parsed['skills']} and education: {parsed['education']}",
+        "counselor": f"Act like a career counselor. Give personalized advice to this candidate: Skills={parsed['skills']} Education={parsed['education']}"
+    }
+    res = llm(prompt_map[suggestion_type], max_length=512, do_sample=True, temperature=0.7)
+    return res[0]['generated_text']