LangChain SQL Agent Tutorial 2025

sql_agent.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "5061e94e",
   "metadata": {},
   "source": [
    "# Chat With Structured Data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "afa36d1b",
   "metadata": {},
   "source": [
    "## Overview\n",
    "\n",
    "SQL agents enable Large Language Models (LLMs) to interact with structured databases by converting natural language questions into SQL queries, executing them, and generating human-readable answers.\n",
    "\n",
    "**Prerequisites**: This tutorial assumes familiarity with:\n",
    "- Chat models and prompts in LangChain\n",
    "- Basic SQL concepts\n",
    "- Python programming\n",
    "\n",
    "**What you'll learn**:\n",
    "- How to build a simple SQL question-answering chain\n",
    "- How to create an intelligent SQL agent\n",
    "- Security best practices for SQL agents"
   ]
  },
  {
   "attachments": {
    "image.png": {
     "image/png": "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"
    }
   },
   "cell_type": "markdown",
   "id": "43ef14ce",
   "metadata": {},
   "source": [
    "At a high-level, the steps of these systems are:\n",
    "\n",
    "Convert question to SQL query: \n",
    "\n",
    "1. Model converts user input to a SQL query.\n",
    "2. Execute SQL query: Execute the query.\n",
    "3. Answer the question: Model responds to user input using the query results.\n",
    "\n",
    "![image.png](attachment:image.png)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "3a882b1b",
   "metadata": {},
   "outputs": [],
   "source": [
    "%%capture --no-stderr\n",
    "%pip install --upgrade --quiet langchain-community langgraph"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "222bf320",
   "metadata": {},
   "source": [
    "## Setup and Installation\n",
    "\n",
    "First, we'll install the required packages for building SQL agents with LangChain."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "35a54051",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Download Dataset for SQLite DB\n",
    "\n",
    "!curl -s https://raw.githubusercontent.com/lerocha/chinook-database/master/ChinookDatabase/DataSources/Chinook_Sqlite.sql | sqlite3 Chinook.db\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f39b33d8",
   "metadata": {},
   "source": [
    "## Database Setup\n",
    "\n",
    "We'll use the Chinook database, a sample SQLite database representing a digital media store. This database contains tables for artists, albums, customers, employees, and sales data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "2b228fee",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "sqlite\n",
      "['Album', 'Artist', 'Customer', 'Employee', 'Genre', 'Invoice', 'InvoiceLine', 'MediaType', 'Playlist', 'PlaylistTrack', 'Track']\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "\"[(1, 'AC/DC'), (2, 'Accept'), (3, 'Aerosmith'), (4, 'Alanis Morissette'), (5, 'Alice In Chains'), (6, 'Antônio Carlos Jobim'), (7, 'Apocalyptica'), (8, 'Audioslave'), (9, 'BackBeat'), (10, 'Billy Cobham')]\""
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from langchain_community.utilities import SQLDatabase\n",
    "\n",
    "db = SQLDatabase.from_uri(\"sqlite:///Chinook.db\")\n",
    "print(db.dialect)\n",
    "print(db.get_usable_table_names())\n",
    "db.run(\"SELECT * FROM Artist LIMIT 10;\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fe70e83e",
   "metadata": {},
   "source": [
    "## Building a SQL Chain\n",
    "\n",
    "A **chain** approach follows a predictable sequence of steps: question → SQL query → execution → answer. This method works well for straightforward questions but has limitations with complex queries that might require multiple database interactions.\n",
    "\n",
    "Let's start by building a simple chain that processes questions in three steps."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "1405dd67",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Application State\n",
    "from typing_extensions import TypedDict\n",
    "\n",
    "class State(TypedDict):\n",
    "    question: str\n",
    "    query: str\n",
    "    result: str\n",
    "    answer: str"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9c899756",
   "metadata": {},
   "source": [
    "### Application State\n",
    "\n",
    "We'll use a `TypedDict` to track data flow through our application. This state object will store:\n",
    "- **question**: The user's original question\n",
    "- **query**: The generated SQL query  \n",
    "- **result**: Raw results from the database\n",
    "- **answer**: The final natural language response"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "id": "23dc7dbe",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_openai import ChatOpenAI\n",
    "\n",
    "llm = ChatOpenAI(model=\"gpt-4o\", temperature=0.0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "546db164",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "================================\u001b[1m System Message \u001b[0m================================\n",
      "\n",
      "\n",
      "Given an input question, create a syntactically correct \u001b[33;1m\u001b[1;3m{dialect}\u001b[0m query to\n",
      "run to help find the answer. Unless the user specifies in his question a\n",
      "specific number of examples they wish to obtain, always limit your query to\n",
      "at most \u001b[33;1m\u001b[1;3m{top_k}\u001b[0m results. You can order the results by a relevant column to\n",
      "return the most interesting examples in the database.\n",
      "\n",
      "Never query for all the columns from a specific table, only ask for a the\n",
      "few relevant columns given the question.\n",
      "\n",
      "Pay attention to use only the column names that you can see in the schema\n",
      "description. Be careful to not query for columns that do not exist. Also,\n",
      "pay attention to which column is in which table.\n",
      "\n",
      "Only use the following tables:\n",
      "\u001b[33;1m\u001b[1;3m{table_info}\u001b[0m\n",
      "\n",
      "================================\u001b[1m Human Message \u001b[0m=================================\n",
      "\n",
      "Question: \u001b[33;1m\u001b[1;3m{input}\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "from langchain_core.prompts import ChatPromptTemplate\n",
    "\n",
    "system_message = \"\"\"\n",
    "Given an input question, create a syntactically correct {dialect} query to\n",
    "run to help find the answer. Unless the user specifies in his question a\n",
    "specific number of examples they wish to obtain, always limit your query to\n",
    "at most {top_k} results. You can order the results by a relevant column to\n",
    "return the most interesting examples in the database.\n",
    "\n",
    "Never query for all the columns from a specific table, only ask for a the\n",
    "few relevant columns given the question.\n",
    "\n",
    "Pay attention to use only the column names that you can see in the schema\n",
    "description. Be careful to not query for columns that do not exist. Also,\n",
    "pay attention to which column is in which table.\n",
    "\n",
    "Only use the following tables:\n",
    "{table_info}\n",
    "\"\"\"\n",
    "\n",
    "user_prompt = \"Question: {input}\"\n",
    "\n",
    "query_prompt_template = ChatPromptTemplate(\n",
    "    [(\"system\", system_message), (\"user\", user_prompt)]\n",
    ")\n",
    "\n",
    "for message in query_prompt_template.messages:\n",
    "    message.pretty_print()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d0a5bec8",
   "metadata": {},
   "source": [
    "#### Creating the SQL Generation Prompt\n",
    "\n",
    "This prompt instructs the LLM to generate syntactically correct SQL queries with important constraints:\n",
    "- Limit results to avoid overwhelming responses\n",
    "- Only use existing columns and tables\n",
    "- Focus on relevant columns rather than SELECT *"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "id": "9a50c88d",
   "metadata": {},
   "outputs": [],
   "source": [
    "from typing_extensions import Annotated\n",
    "\n",
    "\n",
    "class QueryOutput(TypedDict):\n",
    "    \"\"\"Generated SQL query.\"\"\"\n",
    "\n",
    "    query: Annotated[str, ..., \"Syntactically valid SQL query.\"]\n",
    "\n",
    "\n",
    "def write_query(state: State):\n",
    "    \"\"\"Generate SQL query to fetch information.\"\"\"\n",
    "    prompt = query_prompt_template.invoke(\n",
    "        {\n",
    "            \"dialect\": db.dialect,\n",
    "            \"top_k\": 10,\n",
    "            \"table_info\": db.get_table_info(),\n",
    "            \"input\": state[\"question\"],\n",
    "        }\n",
    "    )\n",
    "    structured_llm = llm.with_structured_output(QueryOutput)\n",
    "    result = structured_llm.invoke(prompt)\n",
    "    return {\"question\": state[\"question\"], \"query\": result[\"query\"]}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "id": "aab9a90a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'question': 'How many Employees are there?',\n",
       " 'query': 'SELECT COUNT(*) AS EmployeeCount FROM Employee;'}"
      ]
     },
     "execution_count": 92,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "write_query({\"question\": \"How many Employees are there?\"})"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "923858bc",
   "metadata": {},
   "source": [
    "### Step 2: Execute SQL Query\n",
    "\n",
    "#### Implementing Query Generation\n",
    "\n",
    "The `write_query` function combines our prompt template with structured output to reliably generate SQL queries. It automatically includes database schema information and dialect-specific formatting.\n",
    "\n",
    "⚠️ **Security Warning**: This step executes generated SQL queries directly on your database. In production:\n",
    "- Use read-only database connections\n",
    "- Implement query validation\n",
    "- Consider adding human approval steps"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "id": "a2fb514f",
   "metadata": {},
   "outputs": [],
   "source": [
    "def execute_query(state: State):\n",
    "    \"\"\"Execute SQL query.\"\"\"\n",
    "    return {\n",
    "        \"question\": state[\"question\"], \n",
    "        \"query\": state[\"query\"], \n",
    "        \"result\": db.run(state[\"query\"])\n",
    "    }"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "id": "199d2224",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'question': 'How many employees are there?',\n",
       " 'query': 'SELECT COUNT(EmployeeId) AS EmployeeCount FROM Employee;',\n",
       " 'result': '[(8,)]'}"
      ]
     },
     "execution_count": 96,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "execute_query({\n",
    "    \"question\": \"How many employees are there?\", \n",
    "    \"query\": \"SELECT COUNT(EmployeeId) AS EmployeeCount FROM Employee;\"\n",
    "})"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "232a7a51",
   "metadata": {},
   "source": [
    "### Step 3: Generate Natural Language Answer\n",
    "\n",
    "The final step converts raw database results into a human-readable response. The LLM uses the original question, generated query, and results to formulate an appropriate answer."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "id": "c31665c5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'answer': 'There are 8 employees.'}"
      ]
     },
     "execution_count": 97,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def generate_answer(state: State):\n",
    "    \"\"\"Answer question using retrieved information as context.\"\"\"\n",
    "    prompt = (\n",
    "        \"Given the following user question, corresponding SQL query, \"\n",
    "        \"and SQL result, answer the user question.\\n\\n\"\n",
    "        f'Question: {state[\"question\"]}\\n'\n",
    "        f'SQL Query: {state[\"query\"]}\\n'\n",
    "        f'SQL Result: {state[\"result\"]}'\n",
    "    )\n",
    "    response = llm.invoke(prompt)\n",
    "    return {\"answer\": response.content}\n",
    "\n",
    "generate_answer({\n",
    "    \"question\": \"How many employees are there?\", \n",
    "    \"query\": \"SELECT COUNT(EmployeeId) AS EmployeeCount FROM Employee;\",\n",
    "    \"result\": \"[(8,)]\"\n",
    "})"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f9fe2ee5",
   "metadata": {},
   "source": [
    "### Chaining Everything Together\n",
    "\n",
    "Now we'll connect our three functions into a sequential chain using LangChain's `RunnableLambda`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "id": "32e79a8f",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_core.runnables import RunnableLambda\n",
    "\n",
    "chain = RunnableLambda(write_query) | RunnableLambda(execute_query) | RunnableLambda(generate_answer)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "id": "96739c27",
   "metadata": {},
   "outputs": [],
   "source": [
    "results = chain.invoke({\"question\": \"How many employees are there?\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "id": "e1d5f848",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Results: {'answer': 'There are 8 employees.'}\n",
      "\n",
      "Answer: There are 8 employees.\n"
     ]
    }
   ],
   "source": [
    "print(\"Results:\", results)\n",
    "print(\"\\nAnswer:\", results[\"answer\"])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5c9db114",
   "metadata": {},
   "source": [
    "## Building a SQL Agent\n",
    "\n",
    "While chains work well for simple questions, **agents** provide more flexibility by reasoning about when and how to query the database. Agents can:\n",
    "\n",
    "- Execute multiple queries to answer complex questions\n",
    "- Recover from errors by regenerating queries\n",
    "- Explore database schema dynamically\n",
    "- Handle follow-up questions contextually\n",
    "\n",
    "### SQL Database Toolkit\n",
    "\n",
    "The `SQLDatabaseToolkit` provides a comprehensive set of tools for database interaction:\n",
    "- Create and execute queries\n",
    "- Check query syntax\n",
    "- Retrieve table descriptions\n",
    "- ... and more"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "id": "a44a31d7",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Tool: QuerySQLDatabaseTool\n",
      "Description: Input to this tool is a detailed and correct SQL query, output is a result from the database. If the query is not correct, an error message will be returned. If an error is returned, rewrite the query, check the query, and try again. If you encounter an issue with Unknown column 'xxxx' in 'field list', use sql_db_schema to query the correct table fields.\n",
      "------------------------------------------------------------\n",
      "Tool: InfoSQLDatabaseTool\n",
      "Description: Input to this tool is a comma-separated list of tables, output is the schema and sample rows for those tables. Be sure that the tables actually exist by calling sql_db_list_tables first! Example Input: table1, table2, table3\n",
      "------------------------------------------------------------\n",
      "Tool: ListSQLDatabaseTool\n",
      "Description: Input is an empty string, output is a comma-separated list of tables in the database.\n",
      "------------------------------------------------------------\n",
      "Tool: QuerySQLCheckerTool\n",
      "Description: Use this tool to double check if your query is correct before executing it. Always use this tool before executing a query with sql_db_query!\n",
      "------------------------------------------------------------\n"
     ]
    }
   ],
   "source": [
    "from langchain_community.agent_toolkits import SQLDatabaseToolkit\n",
    "\n",
    "toolkit = SQLDatabaseToolkit(db=db, llm=llm)\n",
    "\n",
    "tools = toolkit.get_tools()\n",
    "\n",
    "for tool in tools:\n",
    "    print(f\"Tool: {tool.__class__.__name__}\")\n",
    "    print(f\"Description: {tool.description}\\n{'-'*60}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "id": "4ff8c501",
   "metadata": {},
   "outputs": [],
   "source": [
    "system_message = \"\"\"\n",
    "You are an agent designed to interact with a SQL database.\n",
    "Given an input question, create a syntactically correct {dialect} query to run,\n",
    "then look at the results of the query and return the answer. Unless the user\n",
    "specifies a specific number of examples they wish to obtain, always limit your\n",
    "query to at most {top_k} results.\n",
    "\n",
    "You can order the results by a relevant column to return the most interesting\n",
    "examples in the database. Never query for all the columns from a specific table,\n",
    "only ask for the relevant columns given the question.\n",
    "\n",
    "You MUST double check your query before executing it. If you get an error while\n",
    "executing a query, rewrite the query and try again.\n",
    "\n",
    "DO NOT make any DML statements (INSERT, UPDATE, DELETE, DROP etc.) to the\n",
    "database.\n",
    "\n",
    "To start you should ALWAYS look at the tables in the database to see what you\n",
    "can query. Do NOT skip this step.\n",
    "\n",
    "Then you should query the schema of the most relevant tables.\n",
    "\"\"\".format(\n",
    "    dialect=\"SQLite\",\n",
    "    top_k=5,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "id": "67f0e8c3",
   "metadata": {},
   "outputs": [],
   "source": [
    "#Initializing agent\n",
    "# We will use a prebuilt LangGraph agent to build our agent\n",
    "\n",
    "from langchain_core.messages import HumanMessage\n",
    "from langgraph.prebuilt import create_react_agent\n",
    "\n",
    "agent_executor = create_react_agent(llm, tools, prompt=system_message)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "id": "db5fa4ac",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "========================================\n",
      "Type: HumanMessage\n",
      "Content:\n",
      "Hi, Which country's customers spent the most?\n",
      "\n",
      "========================================\n",
      "Type: AIMessage\n",
      "Content:\n",
      "\n",
      "\n",
      "========================================\n",
      "Type: ToolMessage\n",
      "Content:\n",
      "Album, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track\n",
      "\n",
      "========================================\n",
      "Type: AIMessage\n",
      "Content:\n",
      "\n",
      "\n",
      "========================================\n",
      "Type: ToolMessage\n",
      "Content:\n",
      "\n",
      "CREATE TABLE \"Customer\" (\n",
      "\t\"CustomerId\" INTEGER NOT NULL, \n",
      "\t\"FirstName\" NVARCHAR(40) NOT NULL, \n",
      "\t\"LastName\" NVARCHAR(20) NOT NULL, \n",
      "\t\"Company\" NVARCHAR(80), \n",
      "\t\"Address\" NVARCHAR(70), \n",
      "\t\"City\" NVARCHAR(40), \n",
      "\t\"State\" NVARCHAR(40), \n",
      "\t\"Country\" NVARCHAR(40), \n",
      "\t\"PostalCode\" NVARCHAR(10), \n",
      "\t\"Phone\" NVARCHAR(24), \n",
      "\t\"Fax\" NVARCHAR(24), \n",
      "\t\"Email\" NVARCHAR(60) NOT NULL, \n",
      "\t\"SupportRepId\" INTEGER, \n",
      "\tPRIMARY KEY (\"CustomerId\"), \n",
      "\tFOREIGN KEY(\"SupportRepId\") REFERENCES \"Employee\" (\"EmployeeId\")\n",
      ")\n",
      "\n",
      "/*\n",
      "3 rows from Customer table:\n",
      "CustomerId\tFirstName\tLastName\tCompany\tAddress\tCity\tState\tCountry\tPostalCode\tPhone\tFax\tEmail\tSupportRepId\n",
      "1\tLuís\tGonçalves\tEmbraer - Empresa Brasileira de Aeronáutica S.A.\tAv. Brigadeiro Faria Lima, 2170\tSão José dos Campos\tSP\tBrazil\t12227-000\t+55 (12) 3923-5555\t+55 (12) 3923-5566\[email protected]\t3\n",
      "2\tLeonie\tKöhler\tNone\tTheodor-Heuss-Straße 34\tStuttgart\tNone\tGermany\t70174\t+49 0711 2842222\tNone\[email protected]\t5\n",
      "3\tFrançois\tTremblay\tNone\t1498 rue Bélanger\tMontréal\tQC\tCanada\tH2G 1A7\t+1 (514) 721-4711\tNone\[email protected]\t3\n",
      "*/\n",
      "\n",
      "========================================\n",
      "Type: ToolMessage\n",
      "Content:\n",
      "\n",
      "CREATE TABLE \"Invoice\" (\n",
      "\t\"InvoiceId\" INTEGER NOT NULL, \n",
      "\t\"CustomerId\" INTEGER NOT NULL, \n",
      "\t\"InvoiceDate\" DATETIME NOT NULL, \n",
      "\t\"BillingAddress\" NVARCHAR(70), \n",
      "\t\"BillingCity\" NVARCHAR(40), \n",
      "\t\"BillingState\" NVARCHAR(40), \n",
      "\t\"BillingCountry\" NVARCHAR(40), \n",
      "\t\"BillingPostalCode\" NVARCHAR(10), \n",
      "\t\"Total\" NUMERIC(10, 2) NOT NULL, \n",
      "\tPRIMARY KEY (\"InvoiceId\"), \n",
      "\tFOREIGN KEY(\"CustomerId\") REFERENCES \"Customer\" (\"CustomerId\")\n",
      ")\n",
      "\n",
      "/*\n",
      "3 rows from Invoice table:\n",
      "InvoiceId\tCustomerId\tInvoiceDate\tBillingAddress\tBillingCity\tBillingState\tBillingCountry\tBillingPostalCode\tTotal\n",
      "1\t2\t2021-01-01 00:00:00\tTheodor-Heuss-Straße 34\tStuttgart\tNone\tGermany\t70174\t1.98\n",
      "2\t4\t2021-01-02 00:00:00\tUllevålsveien 14\tOslo\tNone\tNorway\t0171\t3.96\n",
      "3\t8\t2021-01-03 00:00:00\tGrétrystraat 63\tBrussels\tNone\tBelgium\t1000\t5.94\n",
      "*/\n",
      "\n",
      "========================================\n",
      "Type: ToolMessage\n",
      "Content:\n",
      "\n",
      "CREATE TABLE \"InvoiceLine\" (\n",
      "\t\"InvoiceLineId\" INTEGER NOT NULL, \n",
      "\t\"InvoiceId\" INTEGER NOT NULL, \n",
      "\t\"TrackId\" INTEGER NOT NULL, \n",
      "\t\"UnitPrice\" NUMERIC(10, 2) NOT NULL, \n",
      "\t\"Quantity\" INTEGER NOT NULL, \n",
      "\tPRIMARY KEY (\"InvoiceLineId\"), \n",
      "\tFOREIGN KEY(\"TrackId\") REFERENCES \"Track\" (\"TrackId\"), \n",
      "\tFOREIGN KEY(\"InvoiceId\") REFERENCES \"Invoice\" (\"InvoiceId\")\n",
      ")\n",
      "\n",
      "/*\n",
      "3 rows from InvoiceLine table:\n",
      "InvoiceLineId\tInvoiceId\tTrackId\tUnitPrice\tQuantity\n",
      "1\t1\t2\t0.99\t1\n",
      "2\t1\t4\t0.99\t1\n",
      "3\t2\t6\t0.99\t1\n",
      "*/\n",
      "\n",
      "========================================\n",
      "Type: AIMessage\n",
      "Content:\n",
      "The relevant tables for determining which country's customers spent the most are the `Customer` and `Invoice` tables. The `Invoice` table contains the total amounts spent, while the `Customer` table includes the country information.\n",
      "\n",
      "I will now write a query that aggregates the total spending by country.\n",
      "\n",
      "The query will:\n",
      "- Join the `Customer` and `Invoice` tables on `CustomerId`.\n",
      "- Group by `Country`.\n",
      "- Sum the `Total` from the `Invoice` table.\n",
      "- Order the results in descending order to find the top spenders.\n",
      "\n",
      "Here is the query I will use:\n",
      "\n",
      "```sql\n",
      "SELECT c.Country, SUM(i.Total) AS TotalSpent\n",
      "FROM Customer c\n",
      "JOIN Invoice i ON c.CustomerId = i.CustomerId\n",
      "GROUP BY c.Country\n",
      "ORDER BY TotalSpent DESC\n",
      "LIMIT 5;\n",
      "```\n",
      "\n",
      "Now, let me double-check this query for correctness.\n",
      "\n",
      "========================================\n",
      "Type: ToolMessage\n",
      "Content:\n",
      "```sql\n",
      "SELECT c.Country, SUM(i.Total) AS TotalSpent\n",
      "FROM Customer c\n",
      "JOIN Invoice i ON c.CustomerId = i.CustomerId\n",
      "GROUP BY c.Country\n",
      "ORDER BY TotalSpent DESC\n",
      "LIMIT 5;\n",
      "```\n",
      "\n",
      "========================================\n",
      "Type: AIMessage\n",
      "Content:\n",
      "\n",
      "\n",
      "========================================\n",
      "Type: ToolMessage\n",
      "Content:\n",
      "[('USA', 523.06), ('Canada', 303.96), ('France', 195.1), ('Brazil', 190.1), ('Germany', 156.48)]\n",
      "\n",
      "========================================\n",
      "Type: AIMessage\n",
      "Content:\n",
      "The countries whose customers spent the most are as follows:\n",
      "\n",
      "1. **USA** - $523.06\n",
      "2. **Canada** - $303.96\n",
      "3. **France** - $195.10\n",
      "4. **Brazil** - $190.10\n",
      "5. **Germany** - $156.48\n",
      "\n",
      "These amounts represent the total spending by customers from each country.\n",
      "\n"
     ]
    }
   ],
   "source": [
    "question = \"Hi, Which country's customers spent the most?\"\n",
    "\n",
    "results = agent_executor.invoke(\n",
    "    {\"messages\": [HumanMessage(content=question)]}\n",
    ")\n",
    "\n",
    "for msg in results[\"messages\"]:\n",
    "    print(\"=\"*40)\n",
    "    print(f\"Type: {type(msg).__name__}\")\n",
    "    if hasattr(msg, \"content\"):\n",
    "        print(\"Content:\")\n",
    "        print(msg.content)\n",
    "    else:\n",
    "        print(msg)\n",
    "    print()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "20449650",
   "metadata": {},
   "source": [
    "## ⚠️ Security Best Practices ⚠️\n",
    "\n",
    "When deploying SQL agents in production, implement these security measures:\n",
    "\n",
    "### Database Security\n",
    "1. **Read-Only Access**: Use database connections with SELECT-only permissions\n",
    "2. **Limited Scope**: Connect only to necessary databases and tables\n",
    "3. **User Isolation**: Create dedicated database users for the agent"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}