| # import streamlit as st | |
| # from function import GetLLMResponse | |
| # from langchain_community.llms import OpenAI | |
| # from langchain_google_genai import ChatGoogleGenerativeAI | |
| # # Page configuration | |
| # st.set_page_config(page_title="Interview Practice Bot", | |
| # page_icon="📚", | |
| # layout="wide", | |
| # initial_sidebar_state="collapsed") | |
| # def main(): | |
| # roles_and_topics = { | |
| # "Front-End Developer": ["HTML/CSS", "JavaScript and Frameworks (React, Angular, Vue.js)", "Responsive Design", "Browser Compatibility"], | |
| # "Back-End Developer": ["Server-Side Languages (Node.js, Python, Ruby, PHP)", "Database Management (SQL, NoSQL)", "API Development", "Server and Hosting Management"], | |
| # "Full-Stack Developer": ["Combination of Front-End and Back-End Topics", "Integration of Systems", "DevOps Basics"], | |
| # "Mobile Developer": ["Android Development (Java, Kotlin)", "iOS Development (Swift, Objective-C)", "Cross-Platform Development (Flutter, React Native)"], | |
| # "Data Scientist": ["Statistical Analysis", "Machine Learning Algorithms", "Data Wrangling and Cleaning", "Data Visualization"], | |
| # "Data Analyst": ["Data Collection and Processing", "SQL and Database Querying", "Data Visualization Tools (Tableau, Power BI)", "Basic Statistics"], | |
| # "Machine Learning Engineer": ["Supervised and Unsupervised Learning", "Model Deployment", "Deep Learning", "Natural Language Processing"], | |
| # "DevOps Engineer": ["Continuous Integration/Continuous Deployment (CI/CD)", "Containerization (Docker, Kubernetes)", "Infrastructure as Code (Terraform, Ansible)", "Cloud Platforms (AWS, Azure, Google Cloud)"], | |
| # "Cloud Engineer": ["Cloud Architecture", "Cloud Services (Compute, Storage, Networking)", "Security in the Cloud", "Cost Management"], | |
| # "Cybersecurity Analyst": ["Threat Detection and Mitigation", "Security Protocols and Encryption", "Network Security", "Incident Response"], | |
| # "Penetration Tester": ["Vulnerability Assessment", "Ethical Hacking Techniques", "Security Tools (Metasploit, Burp Suite)", "Report Writing and Documentation"], | |
| # "Project Manager": ["Project Planning and Scheduling", "Risk Management", "Agile and Scrum Methodologies", "Stakeholder Communication"], | |
| # "UX/UI Designer": ["User Research", "Wireframing and Prototyping", "Design Principles", "Usability Testing"], | |
| # "Quality Assurance (QA) Engineer": ["Testing Methodologies", "Automation Testing", "Bug Tracking", "Performance Testing"], | |
| # "Blockchain Developer": ["Blockchain Fundamentals", "Smart Contracts", "Cryptographic Algorithms", "Decentralized Applications (DApps)"], | |
| # "Digital Marketing Specialist": ["SEO/SEM", "Social Media Marketing", "Content Marketing", "Analytics and Reporting"], | |
| # "AI Research Scientist": ["AI Theory", "Algorithm Development", "Neural Networks", "Natural Language Processing"], | |
| # "AI Engineer": ["AI Model Deployment", "Machine Learning Engineering", "Deep Learning", "AI Tools and Frameworks"], | |
| # "Generative AI Specialist (GenAI)": ["Generative Models", "GANs (Generative Adversarial Networks)", "Creative AI Applications", "Ethics in AI"], | |
| # "Generative Business Intelligence Specialist (GenBI)": ["Automated Data Analysis", "Business Intelligence Tools", "Predictive Analytics", "AI in Business Strategy"] | |
| # } | |
| # levels = ['Beginner','Intermediate','Advanced'] | |
| # Question_Difficulty = ['Easy','Medium','Hard'] | |
| # st.header("Select AI:") | |
| # model = st.radio("Model", [ "Gemini","Open AI",]) | |
| # st.write("Selected option:", model) | |
| # # Header and description | |
| # st.title("Interview Practice Bot 📚") | |
| # st.text("Choose the role and topic for your Interview.") | |
| # # User input for quiz generation | |
| # ## Layout in columns | |
| # col4, col1, col2 = st.columns([1, 1, 1]) | |
| # col5, col3 = st.columns([1, 1]) | |
| # with col4: | |
| # selected_level = st.selectbox('Select level of understanding', levels) | |
| # with col1: | |
| # selected_topic_level = st.selectbox('Select Role', list(roles_and_topics.keys())) | |
| # with col2: | |
| # selected_topic = st.selectbox('Select Topic', roles_and_topics[selected_topic_level]) | |
| # with col5: | |
| # selected_Question_Difficulty = st.selectbox('Select Question Difficulty', Question_Difficulty) | |
| # with col3: | |
| # num_quizzes = st.slider('Number of Questions', min_value=1, max_value= 10, value=1) | |
| # submit = st.button('Generate Questions') | |
| # st.write(selected_topic_level, selected_topic, num_quizzes, selected_Question_Difficulty, selected_level, model) | |
| # # Final Response | |
| # if submit: | |
| # questions,answers = GetLLMResponse(selected_topic_level, selected_topic, num_quizzes, selected_Question_Difficulty, selected_level, model) | |
| # with st.spinner("Generating Quizzes..."): | |
| # questions,answers = GetLLMResponse(selected_topic_level, selected_topic, num_quizzes, selected_Question_Difficulty, selected_level, model) | |
| # st.success("Quizzes Generated!") | |
| # # Display questions and answers in a table | |
| # if questions: | |
| # st.subheader("Quiz Questions and Answers:") | |
| # # Prepare data for the table | |
| # col1, col2 = st.columns(2) | |
| # with col1: | |
| # st.subheader("Questions") | |
| # st.write(questions) | |
| # with col2: | |
| # st.subheader("Answers") | |
| # st.write(answers) | |
| # else: | |
| # st.warning("No Quiz Questions and Answers") | |
| # else: | |
| # st.warning("Click the 'Generate Quizzes' button to create quizzes.") | |
| # if __name__ == "__main__": | |
| # main() | |
| import openai | |
| import streamlit as st | |
| from langchain_community.llms import OpenAI | |
| # Set your OpenAI API key | |
| openai.api_key = st.secrets["OPENAI_API_KEY"] | |
| def generate_question(role, topic, difficulty_level): | |
| prompt = f"Generate an interview question for the role of {role} on the topic of {topic} with difficulty level {difficulty_level}." | |
| response = OpenAI( | |
| engine="text-davinci-003", # or any other engine you prefer | |
| prompt=prompt, | |
| max_tokens=50 | |
| ) | |
| return response | |
| def evaluate_answer(question, user_answer): | |
| prompt = f"Question: {question}\nUser's Answer: {user_answer}\nEvaluate the answer and provide feedback. Also, provide the best possible answer." | |
| response = openai( | |
| engine="text-davinci-003", | |
| prompt=prompt, | |
| max_tokens=150 | |
| ) | |
| return response | |
| st.title("Mock Interview Bot") | |
| role = st.selectbox("Select the role:", ["Software Engineer", "Data Scientist", "Product Manager"]) | |
| topic = st.text_input("Enter the topic:") | |
| difficulty_level = st.selectbox("Select difficulty level:", ["Easy", "Medium", "Hard"]) | |
| if st.button("Generate Question"): | |
| if role and topic and difficulty_level: | |
| question = generate_question(role, topic, difficulty_level) | |
| st.session_state['current_question'] = question | |
| st.write(f"Question: {question}") | |
| st.session_state['question_answered'] = False | |
| if 'current_question' in st.session_state and not st.session_state.get('question_answered', False): | |
| answer = st.text_area("Your Answer:") | |
| if st.button("Submit Answer"): | |
| if answer: | |
| st.session_state['user_answer'] = answer | |
| st.session_state['question_answered'] = True | |
| if 'user_answer' in st.session_state: | |
| with st.spinner("Evaluating your answer..."): | |
| feedback = evaluate_answer(st.session_state['current_question'], st.session_state['user_answer']) | |
| st.write(f"Feedback and Best Answer:\n{feedback}") | |