Upload 7 files

app.py

@@ -0,0 +1,34 @@
+import streamlit as st
+from chatbot.assistant import chat_with_hf_bot
+from parser.resume_parser import extract_text_from_pdf
+from matcher.skill_matcher import match_skills
+from analytics.tracker import log_question
+from db.database import init_db, save_chat
+
+st.set_page_config(page_title="AI Career Coach", layout="wide")
+init_db()
+
+st.title("🎓 AI Career Coach")
+st.subheader("Chatbot + Resume Analysis + Weekly Guidance")
+
+tab1, tab2 = st.tabs(["💬 Chatbot", "📄 Resume Matcher"])
+
+with tab1:
+    user_input = st.text_input("Ask career-related questions:")
+    if user_input:
+        response = chat_with_hf_bot(user_input)
+        save_chat(user_input, response)
+        log_question(user_input)
+        st.success(response)
+
+with tab2:
+    uploaded_file = st.file_uploader("Upload your Resume (PDF only)", type="pdf")
+    if uploaded_file:
+        resume_text = extract_text_from_pdf(uploaded_file)
+        st.markdown("**Extracted Skills from Resume:**")
+        st.write(resume_text)
+
+        matched_roles = match_skills(resume_text)
+        st.markdown("**Suggested Roles based on Resume:**")
+        for role in matched_roles:
+            st.write(f"✅ {role}")

database.py

@@ -0,0 +1,20 @@
+import sqlite3
+
+def init_db():
+    conn = sqlite3.connect("db/careercoach.db")
+    c = conn.cursor()
+    c.execute('''CREATE TABLE IF NOT EXISTS chats (
+        id INTEGER PRIMARY KEY AUTOINCREMENT,
+        question TEXT,
+        answer TEXT,
+        timestamp DATETIME DEFAULT CURRENT_TIMESTAMP
+    )''')
+    conn.commit()
+    conn.close()
+
+def save_chat(question, answer):
+    conn = sqlite3.connect("db/careercoach.db")
+    c = conn.cursor()
+    c.execute("INSERT INTO chats (question, answer) VALUES (?, ?)", (question, answer))
+    conn.commit()
+    conn.close()

job_descriptions.json

@@ -0,0 +1,15 @@
+[
+    {
+      "role": "Data Scientist",
+      "description": "Proficient in Python, SQL, machine learning, data visualization, and statistical modeling."
+    },
+    {
+      "role": "Frontend Developer",
+      "description": "Skilled in HTML, CSS, JavaScript, React, and responsive web design."
+    },
+    {
+      "role": "AI Engineer",
+      "description": "Experience with deep learning, NLP, PyTorch, TensorFlow, and deploying ML models."
+    }
+  ]
+  

requirements.txt

@@ -0,0 +1,4 @@
+streamlit
+requests
+pymupdf
+sqlite3

resume_parser.py

@@ -0,0 +1,19 @@
+import PyPDF2
+import re
+
+def extract_text_from_pdf(pdf_file):
+    text = ""
+    reader = PyPDF2.PdfReader(pdf_file)
+    for page in reader.pages:
+        text += page.extract_text()
+    return text
+
+def clean_text(text):
+    text = re.sub(r'\s+', ' ', text)
+    text = text.strip()
+    return text
+
+def parse_resume(pdf_file):
+    raw_text = extract_text_from_pdf(pdf_file)
+    cleaned_text = clean_text(raw_text)
+    return cleaned_text

skill_matcher.py

@@ -0,0 +1,20 @@
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+import json
+
+def load_job_descriptions(path='data/job_descriptions.json'):
+    with open(path, 'r') as f:
+        jobs = json.load(f)
+    return jobs
+
+def compare_with_jobs(resume_text, job_descriptions):
+    results = []
+    vectorizer = TfidfVectorizer().fit_transform([resume_text] + [job["description"] for job in job_descriptions])
+    vectors = vectorizer.toarray()
+
+    resume_vector = vectors[0]
+    for idx, job in enumerate(job_descriptions):
+        job_vector = vectors[idx + 1]
+        similarity = cosine_similarity([resume_vector], [job_vector])[0][0]
+        results.append({"role": job["role"], "match": round(similarity * 100, 2)})
+    return sorted(results, key=lambda x: x["match"], reverse=True)

tracker.py

@@ -0,0 +1,7 @@
+import json
+from datetime import datetime
+
+def log_question(question):
+    log_entry = {"question": question, "timestamp": str(datetime.now())}
+    with open("data/weekly_tracker.json", "a") as f:
+        f.write(json.dumps(log_entry) + "\n")