Upload 3 files

app.py

@@ -0,0 +1,60 @@
+import streamlit as st
+from utils import (
+    extract_text_from_pdf,
+    analyze_cv_text,
+    get_personalized_roadmap,
+    get_skill_score,
+    generate_job_recommendations,
+)
+
+st.set_page_config(page_title="Smart CV Analyzer", layout="wide")
+
+st.title("📄 Smart CV Analyzer & Career Roadmap Generator")
+
+uploaded_file = st.file_uploader("Upload your CV (PDF)", type=["pdf"])
+
+if uploaded_file:
+    text = extract_text_from_pdf(uploaded_file)
+    with st.spinner("Analyzing your CV..."):
+        analysis = analyze_cv_text(text)
+        roadmap = get_personalized_roadmap(text)
+        score = get_skill_score(text)
+
+    st.success("✅ CV Analysis Completed")
+
+    st.subheader("🔍 Career Field & Key Insights")
+    st.write(analysis)
+
+    st.subheader("📈 Skill Score")
+    st.metric(label="Skill Score (1-100)", value=score)
+
+    st.subheader("🗺️ Personalized Career Roadmap")
+    st.text_area("6-Month Roadmap", roadmap, height=300)
+
+    # Job Filters
+    st.subheader("💼 Job Listings (via Adzuna API)")
+    with st.form("job_filters"):
+        col1, col2 = st.columns(2)
+        with col1:
+            location = st.text_input("Preferred Location", value="United States")
+        with col2:
+            job_type = st.selectbox("Job Type", ["", "full_time", "part_time", "contract", "internship"])
+        experience = st.selectbox("Experience Level", ["", "entry", "mid", "senior"])
+        submitted = st.form_submit_button("Search Jobs")
+
+    if submitted:
+        jobs = generate_job_recommendations(text, location)
+        if jobs:
+            for job in jobs:
+                st.markdown(f"### [{job.get('title')}]({job.get('redirect_url')})")
+                st.write(f"**Company:** {job.get('company', {}).get('display_name', 'N/A')}")
+                st.write(f"**Location:** {job.get('location', {}).get('display_name', 'N/A')}")
+                st.write(f"**Salary:** ${job.get('salary_min', 0)} - ${job.get('salary_max', 0)}")
+                st.markdown("---")
+        else:
+            st.warning("No jobs found matching your profile.")
+
+    # Report Download
+    st.subheader("📥 Download Report")
+    report = f"Skill Score: {score}/100\n\nInsights:\n{analysis}\n\nRoadmap:\n{roadmap}"
+    st.download_button("Download Full Report", report, file_name="cv_analysis_report.txt")

job_api.py

@@ -0,0 +1,24 @@
+import os
+import requests
+
+ADZUNA_APP_ID = os.getenv("ADZUNA_APP_ID")
+ADZUNA_APP_KEY = os.getenv("ADZUNA_APP_KEY")
+
+def fetch_job_listings_adzuna(keywords, location="United States", results_limit=10):
+    url = f"https://api.adzuna.com/v1/api/jobs/us/search/1"
+    params = {
+        "app_id": ADZUNA_APP_ID,
+        "app_key": ADZUNA_APP_KEY,
+        "what": keywords,
+        "where": location,
+        "results_per_page": results_limit,
+        "content-type": "application/json",
+    }
+    try:
+        response = requests.get(url, params=params)
+        response.raise_for_status()
+        data = response.json()
+        return data.get("results", [])
+    except Exception as e:
+        print(f"Error fetching job listings: {e}")
+        return []

utils.py

@@ -0,0 +1,44 @@
+import os
+import re
+import spacy
+import PyPDF2
+import openai
+from transformers import pipeline
+from job_api import fetch_job_listings_adzuna
+
+openai.api_key = os.getenv("OPENAI_API_KEY")
+
+nlp_spacy = spacy.load("en_core_web_sm")
+
+llm = pipeline("text-generation", model="mistralai/Mistral-7B-Instruct-v0.1", device="cpu", max_new_tokens=512)
+
+def extract_text_from_pdf(pdf_file):
+    reader = PyPDF2.PdfReader(pdf_file)
+    return " ".join([page.extract_text() for page in reader.pages if page.extract_text()])
+
+def extract_keywords(text):
+    doc = nlp_spacy(text)
+    return list(set([token.lemma_.lower() for token in doc if token.pos_ in ["NOUN", "PROPN", "VERB"] and len(token.text) > 2]))
+
+def analyze_cv_text(text):
+    prompt = f"Analyze this CV and suggest the top skills and job domain:
+{text[:1500]}"
+    result = llm(prompt)[0]["generated_text"]
+    return result
+
+def get_personalized_roadmap(text):
+    prompt = f"Based on this CV, generate a 6-month career improvement roadmap including skills, certifications, education, and goals:
+{text[:1500]}"
+    response = llm(prompt)[0]["generated_text"]
+    return response
+
+def get_skill_score(text):
+    prompt = f"Give a skill strength score (1-100) based on this CV:
+{text[:1500]}"
+    result = llm(prompt)[0]["generated_text"]
+    score = re.findall(r"(\d+)", result)
+    return int(score[0]) if score else 50
+
+def generate_job_recommendations(text, location):
+    keywords = " ".join(extract_keywords(text))
+    return fetch_job_listings_adzuna(keywords, location)