Update app.py

app.py

@@ -1,111 +1,92 @@
-import streamlit as st
+import threading
+import time  # Simulate a long task for demonstration
 from transformers import pipeline
 from datasets import load_dataset
-import signal
-
-# Timeout and Exception Handling
-class TimeoutException(Exception):
-    pass
-
-def timeout_handler(signum, frame):
-    raise TimeoutException("Operation timed out!")
-
-# Set a timeout handler
-signal.signal(signal.SIGALRM, timeout_handler)
-
-# Caching function for the model to avoid reloading
-@st.cache_resource
-def load_qa_model():
-    with st.spinner("Loading question-answering model..."):
-        try:
-            signal.alarm(30)  # Set a 30-second timeout for model loading
-            model = pipeline("question-answering", model="distilbert-base-uncased")  # Smaller model for faster loading
-            signal.alarm(0)  # Cancel the alarm if loaded successfully
-            st.success("Model loaded successfully!")
-            return model
-        except TimeoutException:
-            st.error("Model loading timed out. Please try again later.")
-            return None
-
-# Load QA Model
-qa_pipeline = load_qa_model()
-
-# Caching function for loading datasets
-@st.cache_data
-def load_job_dataset():
-    with st.spinner("Loading job dataset..."):
-        return load_dataset("lukebarousse/data_jobs", split="train[:100]")  # Smaller sample for faster loading
-
-def load_course_dataset():
-    with st.spinner("Loading course dataset..."):
-        return load_dataset("azrai99/coursera-course-dataset", split="train[:50]")  # Smaller sample for testing
+import streamlit as st
 
 # Load datasets
-job_dataset = load_job_dataset()
-course_dataset = load_course_dataset()
-
-# Helper function for question generation
-def generate_questions(profile_data):
-    questions = [
-        f"What skills do you have in {profile_data.get('tech_skills', 'technology')}?",
-        "What are your preferred working conditions?",
-        "What motivates you in a job?",
-        "Are you interested in work-from-home opportunities?",
-        "Do you have a preference for job location?",
-        "Are you open to roles requiring a degree?",
-        "Do you have a preferred organization size?",
-        "What are your expected salary requirements?",
-        "What challenges do you enjoy solving?",
-        "Do you have experience with any specific programming languages or tools?"
-    ]
-    return questions
-
-# Streamlit Interface
-st.title("Career and Course Recommendations App")
-
-# Profile Setup Section
-st.header("Profile Setup")
-profile_data = {}
-profile_data["name"] = st.text_input("Your Name")
-profile_data["tech_skills"] = st.text_input("Technical Skills (comma-separated)")
-profile_data["preferred_location"] = st.text_input("Preferred Location")
-profile_data["work_preference"] = st.selectbox("Work Preference", ["On-site", "Remote", "Hybrid"])
-
-# Intelligent Q&A Session
-st.header("Intelligent Q&A Session")
-if st.button("Start Q&A Session"):
-    questions = generate_questions(profile_data)
-    answers = []
-    for i, question in enumerate(questions):
-        answer = st.text_input(f"Q{i+1}: {question}")
-        answers.append(answer)
-
-    profile_data["answers"] = answers
-    st.success("Q&A Session Completed!")
-
-# Career Recommendations Based on Profile
-st.header("Career Recommendations")
-if qa_pipeline and "tech_skills" in profile_data:
-    job_recommendations = [
-        job["job_title"]
-        for job in job_dataset
-        if "job_skills" in job and any(skill.lower() in job["job_skills"].lower() for skill in profile_data["tech_skills"].split(","))
-    ]
-    st.write("Recommended Jobs:")
-    for job in job_recommendations[:5]:  # Limit to 5 recommendations
-        st.write(f"- {job}")
-
-# Course Recommendations Based on Profile
-st.header("Course Recommendations")
-if qa_pipeline and "tech_skills" in profile_data:
-    course_recommendations = [
-        course["Title"]
-        for course in course_dataset
-        if "Skills" in course and any(skill.lower() in course["Skills"].lower() for skill in profile_data["tech_skills"].split(","))
-    ]
-    st.write("Recommended Courses:")
-    for course in course_recommendations[:5]:  # Limit to 5 recommendations
-        st.write(f"- {course}")
+jobs_dataset = load_dataset("lukebarousse/data_jobs")["train"]
+universities_url = "https://www.4icu.org/top-universities-world/"
+courses_dataset = load_dataset("azrai99/coursera-course-dataset")["train"]
+
+# Function to handle long-running tasks with timeout
+def run_with_timeout(target_func, timeout, *args, **kwargs):
+    result = [None]
+    exception = [None]
+    
+    def wrapper():
+        try:
+            result[0] = target_func(*args, **kwargs)
+        except Exception as e:
+            exception[0] = e
+    
+    thread = threading.Thread(target=wrapper)
+    thread.start()
+    thread.join(timeout=timeout)
+    
+    if thread.is_alive():
+        st.warning("The operation timed out. Please try again.")
+        return None
+    if exception[0]:
+        raise exception[0]
+    return result[0]
+
+# Example function to simulate a long task (you can replace it with your actual task)
+def example_long_task():
+    time.sleep(10)  # Simulating a task that takes 10 seconds
+    return "Task completed successfully."
+
+# Load QA pipeline for Q&A session
+qa_pipeline = pipeline("question-answering", model="distilbert-base-uncased-distilled-squad")
+
+# Streamlit UI
+st.title("Intelligent Career & Course Recommendation System")
+
+# Profile setup
+st.subheader("Profile Setup")
+profile_data = {
+    "name": st.text_input("Enter your name"),
+    "interests": st.text_input("List your interests (comma-separated)"),
+    "tech_skills": st.text_input("List your technical skills (comma-separated)"),
+}
+
+if st.button("Save Profile"):
+    if profile_data["name"] and profile_data["interests"] and profile_data["tech_skills"]:
+        st.session_state.profile_data = profile_data
+        st.success("Profile saved successfully!")
+    else:
+        st.warning("Please fill in all fields.")
+
+# Q&A session after profile setup
+if "profile_data" in st.session_state:
+    st.subheader("Q&A Session")
+    question = st.text_input("Ask a question about your career or courses:")
+    
+    if st.button("Submit Question"):
+        if question:
+            answer = run_with_timeout(qa_pipeline, timeout=5, question=question, context=str(jobs_dataset))  # Using jobs dataset as context
+            if answer:
+                st.write(f"Answer: {answer['answer']}")
+        else:
+            st.warning("Please enter a question.")
+
+# Job and course recommendations based on interests and skills
+if "profile_data" in st.session_state:
+    st.subheader("Career and Course Recommendations")
+    interests = [interest.strip().lower() for interest in st.session_state.profile_data["interests"].split(",")]
+    tech_skills = [skill.strip().lower() for skill in st.session_state.profile_data["tech_skills"].split(",")]
+    
+    # Job Recommendations
+    st.write("### Job Recommendations:")
+    for job in jobs_dataset:
+        job_skills = [skill.lower() for skill in job["job_skills"]]
+        if any(skill in job_skills for skill in tech_skills):
+            st.write(f"- **{job['job_title']}** at {job['company_name']}, Location: {job['job_location']}")
+    
+    # Course Recommendations
+    st.write("### Course Recommendations:")
+    for course in courses_dataset:
+        course_skills = [skill.lower() for skill in course["Skills"]]
+        if any(interest in course["Title"].lower() for interest in interests):
+            st.write(f"- **{course['Title']}** by {course['Organization']}. [Link to course]({course['course_url']})")
 
-# Debugging: Log Profile Data
-st.write("Profile Data:", profile_data)