import streamlit as st import os from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace from langchain_core.messages import HumanMessage, SystemMessage # Set environment variables hf = os.getenv('HF_TOKEN') os.environ['HUGGINGFACEHUB_API_KEY'] = hf os.environ['HF_TOKEN'] = hf # Initialize DeepSeek model (you can replace this with your own model if needed) def load_deepseek_model(): deep_seek_model = HuggingFaceEndpoint( repo_id="deepseek-ai/DeepSeek-R1", provider="nebius", temperature=0.7, max_new_tokens=150, task="conversational" ) return ChatHuggingFace(llm=deep_seek_model) sql_mentor = load_deepseek_model() # Streamlit page setup st.set_page_config(page_title="SQL Mentor Chat", layout="centered") # Improved custom CSS st.markdown(""" """, unsafe_allow_html=True) # Page title st.markdown("
Learn SQL interactively from your AI mentor!
", unsafe_allow_html=True) # Sidebar for user preference st.sidebar.title("Mentor Preferences") exp = st.sidebar.selectbox("Choose your experience level:", ["Beginner", "Intermediate", "Expert"]) # Session state key PAGE_KEY = "chat_history" # Initialize session state if PAGE_KEY not in st.session_state: st.session_state[PAGE_KEY] = [] # Chat input box st.markdown("