Download 2Tutor.py from georgeek/LLM-Tutor: direct link, hf CLI and curl.
- Browser
- Download file 7.01 kB
-
https://huggingface.co/spaces/georgeek/LLM-Tutor/resolve/main/2Tutor.py
- Command line
-
hf download hf://spaces/georgeek/LLM-Tutor/2Tutor.py
-
curl -L -o 2Tutor.py https://huggingface.co/spaces/georgeek/LLM-Tutor/resolve/main/2Tutor.py
7.01 kB
| import streamlit as st | |
| import importlib | |
| import os | |
| import json | |
| from datetime import datetime | |
| from dotenv import load_dotenv | |
| from openai import OpenAI | |
| # Load environment variables from .env file | |
| load_dotenv() | |
| # Set page title and layout | |
| st.set_page_config(page_title="Data Science Tutor", layout="wide") | |
| # Hide Streamlit's default page navigation menu | |
| st.markdown(""" | |
| <style> | |
| /* Hide the default "Pages" menu in the top-left sidebar */ | |
| [data-testid="stSidebarNav"] { | |
| display: none; | |
| } | |
| </style> | |
| """, unsafe_allow_html=True) | |
| # Sidebar with image above the CRISP-DM Steps | |
| st.sidebar.image( | |
| "data2.jpeg", # Replace with your file path or URL | |
| use_container_width=True | |
| ) | |
| # Sidebar navigation | |
| st.sidebar.title("CRISP-DM Steps") | |
| sections = { | |
| "Main Page": None, | |
| "1. Business Understanding": "1_Business_understanding", | |
| "2. Data understanding": "2_Data_understanding", | |
| "3. Data Preparation": "3_Data_preparation", | |
| "4. Feature Engineering": "4_Feature_engineering", | |
| "5. Modeling": "5_Modeling", | |
| "6. Evaluation": "6_Evaluation", | |
| "7. Deployment & Testing": "7_Deployment", | |
| "8. ML, Deep Learning & Transformers": "8_Models" | |
| } | |
| # By default, make the first item (Main Page) selected. | |
| selected_section = st.sidebar.radio("Select a topic:", list(sections.keys()), index=0) | |
| # If the user selects βMain Page,β just show your introduction content. | |
| if sections[selected_section] is None: | |
| st.title("π Welcome to the Data Science Tutor!") | |
| st.markdown( | |
| """ | |
| <div style="color: #2FA4E7; margin-top: 1rem;"> | |
| <h2>About This App</h2> | |
| <p> | |
| This application is designed to guide you through the CRISP-DM process | |
| for data science projects. Each section in the sidebar highlights a | |
| different step in the process, providing structured lessons, best | |
| practices, and hands-on examples. | |
| </p> | |
| <h3>App Sections</h3> | |
| <ul> | |
| <li><strong>1. Business Understanding</strong> β Clarify project objectives, requirements, and success criteria.</li> | |
| <li><strong>2. Data Understanding</strong> β Explore data sources, structures, and initial insights.</li> | |
| <li><strong>3. Data Preparation</strong> β Clean, integrate, and transform the data for modeling.</li> | |
| <li><strong>4. Feature Engineering</strong> β Engineer and select relevant features for better models.</li> | |
| <li><strong>5. Modeling</strong> β Develop, train, and tune predictive models.</li> | |
| <li><strong>6. Evaluation</strong> β Assess performance metrics and refine models.</li> | |
| <li><strong>7. Deployment & Testing</strong> β Deploy models into production environments and validate.</li> | |
| <li><strong>8. ML, Deep Learning & Transformers</strong> β Delve deeper into advanced methods and architectures.</li> | |
| </ul> | |
| </div> | |
| """, | |
| unsafe_allow_html=True | |
| ) | |
| else: | |
| # Otherwise, load the selected module from the pages folder | |
| module_name = f"pages.{sections[selected_section]}" | |
| module = importlib.import_module(module_name) | |
| module.run() | |
| # OpenAI API Section | |
| api_key = os.getenv("OPENAI_API_KEY") | |
| if not api_key: | |
| st.sidebar.title("Ask AI") | |
| api_key = st.sidebar.text_input("Enter your OpenAI API Key", type="password") | |
| client = OpenAI() | |
| # Create side menus for toggles from the pages/ list | |
| st.sidebar.title("Focus Areas") | |
| focus_areas = [ | |
| "Compare Models", | |
| "Delivery Speed vs Costs", | |
| "Ethical Considerations in AI", | |
| "Interpretability & Explainability", | |
| "Business Impact & ROI", | |
| "Scalability & Performance", | |
| "Data Privacy & Security" | |
| ] | |
| selected_focus_areas = [area for area in focus_areas if st.sidebar.checkbox(area)] | |
| # Main chat section | |
| st.title("Data Science Tutor Chat") | |
| st.image("https://miro.medium.com/v2/resize:fit:100/format:webp/1*NfE0G4nEj4xX7Z_8dSx83g.png") | |
| # Initialize conversation in the session state | |
| if "messages" not in st.session_state: | |
| st.session_state["messages"] = [ | |
| {"role": "assistant", "content": "How can I assist you with Data Science today?"} | |
| ] | |
| # Initialize context prompt added state | |
| if "context_prompt_added" not in st.session_state: | |
| st.session_state["context_prompt_added"] = False | |
| st.write("---") | |
| st.subheader("Chat") | |
| for msg in st.session_state["messages"]: | |
| st.chat_message(msg["role"]).write(msg["content"]) | |
| if prompt := st.chat_input("Enter your question here:"): | |
| # Add context to the messages if toggles are selected | |
| focus_context = "" | |
| if selected_focus_areas: | |
| focus_context = f"Focus on {', '.join(selected_focus_areas)} in your response." | |
| # Add prompting instructions | |
| prompting_instructions = """ | |
| You are a Data Science tutor. Your responses should be focused on Data Science related subjects. | |
| If a question is not related to Data Science, respond with: "Sorry, I can only assist with Data Science related questions." | |
| Ensure that your responses are not harmful, denigratory, or discriminatory for security and privacy reasons. | |
| """ | |
| # Add context based on the selected section | |
| section_context = f"The user is currently viewing the {selected_section} section. " | |
| # If the context prompt hasn't been added yet, build & inject it once; | |
| # otherwise, just add the user's raw question. | |
| if not st.session_state["context_prompt_added"]: | |
| st.session_state["messages"].append({"role": "user", "content": f"{section_context}{prompt}\n{focus_context}\n{prompting_instructions}"}) | |
| st.session_state["context_prompt_added"] = True | |
| else: | |
| st.session_state["messages"].append({"role": "user", "content": f"{section_context}{prompt}"}) | |
| # Display the latest user message in the chat | |
| st.chat_message("user").write(st.session_state["messages"][-1]["content"]) | |
| # Now call GPT-4 with the entire conversation | |
| completion = client.chat.completions.create( | |
| model="gpt-4", | |
| messages=st.session_state["messages"] | |
| ) | |
| response_text = completion.choices[0].message.content.strip() | |
| st.session_state["messages"].append({"role": "assistant", "content": response_text}) | |
| st.chat_message("assistant").write(response_text) | |
| # Log the conversation | |
| log_entry = { | |
| "timestamp": datetime.now().isoformat(), | |
| "user_query": prompt, | |
| "assistant_response": response_text, | |
| "focus_areas": selected_focus_areas, | |
| "selected_section": selected_section | |
| } | |
| log_file_path = os.path.join("logs", "conversation_logs.json") | |
| os.makedirs(os.path.dirname(log_file_path), exist_ok=True) | |
| if os.path.exists(log_file_path): | |
| with open(log_file_path, "r") as log_file: | |
| logs = json.load(log_file) | |
| else: | |
| logs = [] | |
| logs.append(log_entry) | |
| with open(log_file_path, "w") as log_file: | |
| json.dump(logs, log_file, indent=4) |