Upload 7 files

app.py

@@ -0,0 +1,51 @@
+import streamlit as st
+from utils import parse_resume, get_recommendations, load_models
+from job_api import get_jobs
+from visa_suggester import suggest_visas
+from roadmap import generate_roadmap
+from cert_suggester import suggest_certifications, suggest_degrees
+import base64
+
+st.set_page_config(page_title="Universal Smart CV Analyzer", layout="wide")
+
+st.title("🌍 Universal Smart CV Analyzer & Career Roadmap Generator")
+
+st.markdown("Upload your CV to get skill scores, job suggestions, visa paths, certifications, and a personalized roadmap.")
+
+uploaded_file = st.file_uploader("Upload your CV (PDF or DOCX)", type=["pdf", "docx"])
+
+if uploaded_file:
+    with st.spinner("Analyzing your CV..."):
+        resume_text = parse_resume(uploaded_file)
+        nlp_model, llm_model = load_models()
+
+        skill_score, domain, extracted_skills, education = get_recommendations(resume_text, nlp_model, llm_model)
+
+        st.subheader("🧠 CV Analysis Results")
+        st.write(f"**Detected Domain:** {domain}")
+        st.write(f"**Skill Score:** {skill_score} / 100")
+        st.write("**Extracted Skills:**", ", ".join(extracted_skills))
+        st.write("**Education/Qualification Detected:**", education)
+
+        st.subheader("📈 Career Roadmap")
+        roadmap_html = generate_roadmap(domain, extracted_skills, llm_model)
+        st.components.v1.html(roadmap_html, height=400, scrolling=True)
+
+        st.subheader("🎓 Certification & Higher Education Suggestions")
+        certs = suggest_certifications(domain, extracted_skills)
+        degrees = suggest_degrees(domain, education)
+        st.write("**Recommended Certifications:**")
+        st.write(certs)
+        st.write("**Recommended Higher Education Options:**")
+        st.write(degrees)
+
+        st.subheader("🛫 Visa & Country Guidance")
+        visa_info = suggest_visas(domain, extracted_skills)
+        st.write(visa_info)
+
+        st.subheader("💼 Job Listings (Powered by Adzuna)")
+        job_listings = get_jobs(domain)
+        for job in job_listings:
+            st.markdown(f"**{job['title']}** - {job['location']}")
+            st.markdown(f"[Apply Here]({job['url']})")
+            st.markdown("---")

cert_suggester.py

@@ -0,0 +1,15 @@
+def suggest_certifications(domain, skills):
+    if domain.lower() == "engineering":
+        return "Recommended: PMP, Six Sigma, AutoCAD, MATLAB, Certified Manufacturing Engineer"
+    elif domain.lower() == "software":
+        return "Recommended: AWS Certified Developer, Google Cloud, Azure, Data Science Professional Certificate"
+    else:
+        return "Recommended: Coursera/edX certificates related to your field"
+
+def suggest_degrees(domain, education):
+    if "Bachelor" in education or "BSc" in education:
+        return f"Consider: Master's in {domain}, MBA in Tech Management"
+    elif "Master" in education or "MSc" in education:
+        return f"Consider: PhD in {domain}, Specialized Certifications"
+    else:
+        return "Consider: Bachelors or Associate Degree in field of interest"

job_api.py

@@ -0,0 +1,28 @@
+import requests
+
+ADZUNA_APP_ID = "your_adzuna_app_id"
+ADZUNA_APP_KEY = "your_adzuna_app_key"
+
+def get_jobs(keyword="engineer", location="USA", max_results=5):
+    url = f"https://api.adzuna.com/v1/api/jobs/us/search/1"
+    params = {
+        "app_id": ADZUNA_APP_ID,
+        "app_key": ADZUNA_APP_KEY,
+        "what": keyword,
+        "where": location,
+        "results_per_page": max_results,
+        "content-type": "application/json",
+    }
+    response = requests.get(url, params=params)
+    if response.status_code == 200:
+        data = response.json()
+        jobs = []
+        for job in data.get("results", []):
+            jobs.append({
+                "title": job["title"],
+                "location": job["location"]["display_name"],
+                "url": job["redirect_url"]
+            })
+        return jobs
+    else:
+        return [{"title": "Error fetching jobs", "location": "", "url": ""}]

requirements.txt

@@ -0,0 +1,6 @@
+streamlit
+transformers
+spacy
+PyPDF2
+docx2txt
+requests

roadmap.py

@@ -0,0 +1,15 @@
+from datetime import datetime
+
+def generate_roadmap(domain, skills, llm_model):
+    prompt = f"""
+    You are a career advisor. Generate a 3-step 6-month career roadmap with bullet points for someone with skills {skills} in the field of {domain}.
+    Suggest skills to improve, certifications, and countries to target.
+    """
+    result = llm_model(prompt, max_new_tokens=300)[0]['generated_text']
+
+    return f"""
+    <div style="border: 2px solid #ccc; padding: 1em; border-radius: 10px;">
+        <h4>📅 Roadmap from {datetime.today().strftime('%B %Y')}:</h4>
+        <pre style="white-space: pre-wrap;">{result}</pre>
+    </div>
+    """

utils.py

@@ -0,0 +1,39 @@
+import docx2txt
+import PyPDF2
+import spacy
+from transformers import pipeline
+import re
+
+def parse_resume(file):
+    if file.type == "application/pdf":
+        pdf_reader = PyPDF2.PdfReader(file)
+        text = ""
+        for page in pdf_reader.pages:
+            text += page.extract_text()
+        return text
+    elif file.type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
+        return docx2txt.process(file)
+    else:
+        return ""
+
+def load_models():
+    nlp_model = spacy.load("en_core_web_sm")
+    llm_model = pipeline("text-generation", model="mistralai/Mistral-7B-Instruct-v0.1")
+    return nlp_model, llm_model
+
+def get_recommendations(text, nlp_model, llm_model):
+    doc = nlp_model(text)
+    skills = [ent.text.lower() for ent in doc.ents if ent.label_ in ["SKILL", "WORK_OF_ART", "ORG"]]
+    education = extract_education(text)
+
+    prompt = f"Given these skills: {', '.join(set(skills))}, classify the most likely job field and rate CV quality (0-100):"
+    response = llm_model(prompt, max_new_tokens=100)[0]['generated_text']
+
+    domain = "Engineering" if "engineer" in response.lower() else "General"
+    score = int("".join(filter(str.isdigit, response)))
+
+    return score, domain, list(set(skills)), education
+
+def extract_education(text):
+    match = re.findall(r"(Bachelor|Master|PhD|MBA|BSc|MSc|B\.Tech|M\.Tech)[^\n\r]*", text, re.IGNORECASE)
+    return ", ".join(set(match)) if match else "Not detected"

visa_suggester.py

@@ -0,0 +1,7 @@
+def suggest_visas(domain, skills):
+    if domain.lower() in ["engineering", "it", "software"]:
+        return "Suggested Visas: H1-B (USA), Blue Card (EU), Global Talent Visa (UK, Australia)"
+    elif domain.lower() in ["healthcare", "nursing"]:
+        return "Suggested Visas: TN Visa (Canada/USA), Skilled Worker Visa (UK)"
+    else:
+        return "Suggested Visas: General Skilled Migration (AU), Work Permit (EU), O-1 (USA)"