Update app.py

app.py

@@ -3,30 +3,93 @@ import sqlite3
 import uuid
 import langchain
 from langchain_google_genai import GoogleGenerativeAI
-from langchain_core.prompts import ChatPromptTemplate,MessagesPlaceholder
+from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
 from langchain_core.output_parsers import StrOutputParser
 from langchain_community.chat_message_histories import SQLChatMessageHistory
 from langchain_core.runnables.history import RunnableWithMessageHistory
 
-st.write('hello welecome to data science tutor')
-# Database file name
-DB_PATH = "database.db"
-
-# Function to create a database and table if not exists
-def create_database():
-    if not os.path.exists(DB_PATH):  # Check if database exists
-        conn = sqlite3.connect(DB_PATH)
-        cursor = conn.cursor()
-
-        # Create a sample table
-        cursor.execute("""
-            CREATE TABLE IF NOT EXISTS users (
-                id INTEGER PRIMARY KEY AUTOINCREMENT,
-                name TEXT NOT NULL,
-                age INTEGER NOT NULL
-            )
-        """)
-        conn.commit()
-        conn.close()
-        st.success("Database and table created successfully!")
-        
+# Load API key from file
+# ✅ Access Hugging Face Secret API Key
+GOOGLE_API_KEY = st.secrets.get("GOOGLE_API_KEY")
+
+# Set up the Gemini 2.0 Flash model
+llm = GoogleGenerativeAI(api_key=GOOGLE_API_KEY, model="gemini-1.5-pro")
+
+# Initialize SQLite database for chat history
+conn = sqlite3.connect("chat_history.db")
+cursor = conn.cursor()
+cursor.execute("""
+CREATE TABLE IF NOT EXISTS chat (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    session_id TEXT,
+    role TEXT,
+    content TEXT
+)
+""")
+conn.commit()
+
+def save_message(session_id, role, content):
+    cursor.execute("INSERT INTO chat (session_id, role, content) VALUES (?, ?, ?)", (session_id, role, content))
+    conn.commit()
+
+def load_chat_history(session_id):
+    cursor.execute("SELECT role, content FROM chat WHERE session_id = ?", (session_id,))
+    return cursor.fetchall()
+
+def chat_history(session_id):
+    return SQLChatMessageHistory(
+        session_id=session_id,
+        connection='sqlite:///chat_history.db'
+    )
+
+# Generate unique session ID for each user
+if "session_id" not in st.session_state:
+    st.session_state.session_id = str(uuid.uuid4())
+
+session_id = st.session_state.session_id
+chat_history_instance = chat_history(session_id)
+
+# Define Chat Prompt Template
+chat_prompt = ChatPromptTemplate(
+    messages=[('system', ''''You are an AI assistant.You are a Data Science tutor. You provide answers only about Data Science.Answer every question as deeply as possible.
+                            If asked anything outside this topic, do not respond and instead prompt the user to ask a Data Science-related question. 
+                            Only provide responses related to Data Science.
+                          '''),
+              MessagesPlaceholder(variable_name="history", optional=True),
+              ('human', '{prompt}')]
+)
+
+# Define output parser
+out_parser = StrOutputParser()
+
+# Create a chain
+chain = chat_prompt | llm | out_parser
+
+# Define Runnable with message history
+chat = RunnableWithMessageHistory(
+    chain,
+    chat_history,
+    input_messages_key='prompt',
+    history_messages_key='history'
+)
+
+# Streamlit UI
+st.title("Conversational AI Data Science Tutor")
+st.write("Ask me anything about Data Science!")
+
+# Load chat history from database
+st.session_state.messages = load_chat_history(session_id)
+
+for role, content in st.session_state.messages:
+    with st.chat_message(role):
+        st.markdown(content)
+
+user_input = st.text_input("You:", "", key="user_input")
+if user_input:
+    save_message(session_id, "user", user_input)
+    st.session_state.messages.append(("user", user_input))
+    config = {'configurable': {'session_id': session_id}}
+    response = chat.invoke({'prompt': user_input}, config)
+    save_message(session_id, "assistant", response)
+    st.session_state.messages.append(("assistant", response))
+    st.chat_message("assistant").markdown(response)