构建自定义 SQL 智能体 | LangChain 中文文档

在本教程中，我们将使用 LangGraph 构建一个自定义智能体，它可以回答有关 SQL 数据库的问题。

LangChain 提供了内置的智能体实现，这些实现使用 LangGraph 原语构建。如果需要更深入的定制，可以直接在 LangGraph 中实现智能体。本指南演示了 SQL 智能体的一个示例实现。如需实用入门介绍，请参阅使用更高级的 LangChain 抽象构建 SQL 智能体。

WARNING

构建基于 SQL 数据库的问答系统需要执行模型生成的 SQL 查询。这样做存在固有风险。请确保你的数据库连接权限始终尽可能窄地限定在智能体的需求范围内。这可以缓解（但不能消除）构建模型驱动系统的风险。

预构建智能体让我们能够快速上手，但我们依赖系统提示词来约束其行为——例如，我们指示智能体始终从 "list tables" 工具开始，并且始终在执行查询前运行一个查询检查工具。

我们可以通过在 LangGraph 中定制智能体来获得更高级别的控制。在这里，我们实现了一个简单的 ReAct 智能体设置，为特定的工具调用设置了专门的节点。我们将使用与预构建智能体相同的 [state]。

概念

我们将涵盖以下概念：

用于从 SQL 数据库读取数据的工具
LangGraph Graph API，包括状态、节点、边和条件边。
人在回路（人工介入）流程

设置

安装

Python · pipTypeScript · npmTypeScript · yarnTypeScript · pnpm

bash

pip install langchain langgraph

bash

npm i langchain @langchain/core @langchain/langgraph @langchain/openai sqlite3 zod

bash

yarn add langchain @langchain/core @langchain/langgraph @langchain/openai sqlite3 zod

bash

pnpm add langchain @langchain/core @langchain/langgraph @langchain/openai sqlite3 zod

LangSmith

设置 LangSmith 以检查链或智能体内部发生的情况。然后设置以下环境变量：

bash

export LANGSMITH_TRACING="true"
export LANGSMITH_API_KEY="..."

1. 选择 LLM

选择一个支持工具调用的模型：

OpenAI

    👉 Read the [OpenAI chat model integration docs](/oss/python/integrations/chat/openai)

bash

pip install -U "langchain[openai]"

Python · init_chat_modelPython · Model Class

python

import os
from langchain.chat_models import init_chat_model

os.environ["OPENAI_API_KEY"] = "sk-..."

model = init_chat_model("gpt-5.5")

python

import os
from langchain_openai import ChatOpenAI

os.environ["OPENAI_API_KEY"] = "sk-..."

model = ChatOpenAI(model="gpt-5.5")

Anthropic

    👉 Read the [Anthropic chat model integration docs](/oss/python/integrations/chat/anthropic)

bash

pip install -U "langchain[anthropic]"

Python · init_chat_modelPython · Model Class

python

import os
from langchain.chat_models import init_chat_model

os.environ["ANTHROPIC_API_KEY"] = "sk-..."

model = init_chat_model("claude-sonnet-4-6")

python

import os
from langchain_anthropic import ChatAnthropic

os.environ["ANTHROPIC_API_KEY"] = "sk-..."

model = ChatAnthropic(model="claude-sonnet-4-6")

Azure

    👉 Read the [Azure chat model integration docs](/oss/python/integrations/chat/azure_chat_openai)

bash

pip install -U "langchain[openai]"

Python · init_chat_modelPython · Model Class

python

import os
from langchain.chat_models import init_chat_model

os.environ["AZURE_OPENAI_API_KEY"] = "..."
os.environ["AZURE_OPENAI_ENDPOINT"] = "..."
os.environ["OPENAI_API_VERSION"] = "2025-03-01-preview"

model = init_chat_model(
    "azure_openai:gpt-5.5",
    azure_deployment=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"],
)

python

import os
from langchain_openai import AzureChatOpenAI

os.environ["AZURE_OPENAI_API_KEY"] = "..."
os.environ["AZURE_OPENAI_ENDPOINT"] = "..."
os.environ["OPENAI_API_VERSION"] = "2025-03-01-preview"

model = AzureChatOpenAI(
    model="gpt-5.5",
    azure_deployment=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"]
)

Google Gemini

    👉 Read the [Google GenAI chat model integration docs](/oss/python/integrations/chat/google_generative_ai)

bash

pip install -U "langchain[google-genai]"

Python · init_chat_modelPython · Model Class

python

import os
from langchain.chat_models import init_chat_model

os.environ["GOOGLE_API_KEY"] = "..."

model = init_chat_model("google_genai:gemini-2.5-flash-lite")

python

import os
from langchain_google_genai import ChatGoogleGenerativeAI

os.environ["GOOGLE_API_KEY"] = "..."

model = ChatGoogleGenerativeAI(model="gemini-2.5-flash-lite")

AWS Bedrock

    👉 Read the [AWS Bedrock chat model integration docs](/oss/python/integrations/chat/bedrock)

bash

pip install -U "langchain[aws]"

Python · init_chat_modelPython · Model Class

python

from langchain.chat_models import init_chat_model

# 请按照以下步骤配置你的凭证：
# https://docs.aws.amazon.com/bedrock/latest/userguide/getting-started.html

model = init_chat_model(
    "us.anthropic.claude-sonnet-4-6",
    model_provider="bedrock_converse",
)

python

from langchain_aws import ChatBedrock

model = ChatBedrock(model="us.anthropic.claude-sonnet-4-6")

HuggingFace

    👉 Read the [HuggingFace chat model integration docs](/oss/python/integrations/chat/huggingface)

bash

pip install -U "langchain[huggingface]"

Python · init_chat_modelPython · Model Class

python

import os
from langchain.chat_models import init_chat_model

os.environ["HUGGINGFACEHUB_API_TOKEN"] = "hf_..."

model = init_chat_model(
    "microsoft/Phi-3-mini-4k-instruct",
    model_provider="huggingface",
    temperature=0.7,
    max_tokens=1024,
)

python

import os
from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint

os.environ["HUGGINGFACEHUB_API_TOKEN"] = "hf_..."

llm = HuggingFaceEndpoint(
    repo_id="microsoft/Phi-3-mini-4k-instruct",
    temperature=0.7,
    max_length=1024,
)
model = ChatHuggingFace(llm=llm)

OpenRouter

    👉 Read the [OpenRouter chat model integration docs](/oss/python/integrations/chat/openrouter)

bash

pip install -U "langchain-openrouter"

Python · init_chat_modelPython · Model Class

python

import os
from langchain.chat_models import init_chat_model

os.environ["OPENROUTER_API_KEY"] = "sk-..."

model = init_chat_model(
    "auto",
    model_provider="openrouter",
)

python

import os
from langchain_openrouter import ChatOpenRouter

os.environ["OPENROUTER_API_KEY"] = "sk-..."

model = ChatOpenRouter(model="auto")

OpenAI

    👉 Read the [OpenAI chat model integration docs](/oss/javascript/integrations/chat/openai)

TypeScript · npmTypeScript · pnpmTypeScript · yarnTypeScript · bun

bash

npm install @langchain/openai

bash

pnpm install @langchain/openai

bash

yarn add @langchain/openai

bash

bun add @langchain/openai

TypeScript · initChatModelTypeScript · Model Class

typescript

import { initChatModel } from "langchain";

process.env.OPENAI_API_KEY = "your-api-key";

const model = await initChatModel("gpt-5.5");

typescript

import { ChatOpenAI } from "@langchain/openai";

const model = new ChatOpenAI({
  model: "gpt-5.5",
  apiKey: "your-api-key"
});

Anthropic

    👉 Read the [Anthropic chat model integration docs](/oss/javascript/integrations/chat/anthropic)

TypeScript · npmTypeScript · pnpmTypeScript · yarnTypeScript · pnpm

bash

npm install @langchain/anthropic

bash

pnpm install @langchain/anthropic

bash

yarn add @langchain/anthropic

bash

pnpm add @langchain/anthropic

TypeScript · initChatModelTypeScript · Model Class

typescript

import { initChatModel } from "langchain";

process.env.ANTHROPIC_API_KEY = "your-api-key";

const model = await initChatModel("claude-sonnet-4-6");

typescript

import { ChatAnthropic } from "@langchain/anthropic";

const model = new ChatAnthropic({
  model: "claude-sonnet-4-6",
  apiKey: "your-api-key"
});

Azure

    👉 Read the [Azure chat model integration docs](/oss/javascript/integrations/chat/azure)

TypeScript · npmTypeScript · pnpmTypeScript · yarnTypeScript · bun

bash

npm install @langchain/azure

bash

pnpm install @langchain/azure

bash

yarn add @langchain/azure

bash

bun add @langchain/azure

TypeScript · initChatModelTypeScript · Model Class

typescript

import { initChatModel } from "langchain";

process.env.AZURE_OPENAI_API_KEY = "your-api-key";
process.env.AZURE_OPENAI_ENDPOINT = "your-endpoint";
process.env.OPENAI_API_VERSION = "your-api-version";

const model = await initChatModel("azure_openai:gpt-5.5");

typescript

import { AzureChatOpenAI } from "@langchain/openai";

const model = new AzureChatOpenAI({
  model: "gpt-5.5",
  azureOpenAIApiKey: "your-api-key",
  azureOpenAIApiEndpoint: "your-endpoint",
  azureOpenAIApiVersion: "your-api-version"
});

Google Gemini

    👉 Read the [Google GenAI chat model integration docs](/oss/javascript/integrations/chat/google_generative_ai)

TypeScript · npmTypeScript · pnpmTypeScript · yarnTypeScript · bun

bash

npm install @langchain/google-genai

bash

pnpm install @langchain/google-genai

bash

yarn add @langchain/google-genai

bash

bun add @langchain/google-genai

TypeScript · initChatModelTypeScript · Model Class

typescript

import { initChatModel } from "langchain";

process.env.GOOGLE_API_KEY = "your-api-key";

const model = await initChatModel("google-genai:gemini-2.5-flash-lite");

typescript

import { ChatGoogleGenerativeAI } from "@langchain/google-genai";

const model = new ChatGoogleGenerativeAI({
  model: "gemini-2.5-flash-lite",
  apiKey: "your-api-key"
});

Bedrock Converse

    👉 Read the [AWS Bedrock chat model integration docs](/oss/javascript/integrations/chat/bedrock_converse)

TypeScript · npmTypeScript · pnpmTypeScript · yarnTypeScript · bun

bash

npm install @langchain/aws

bash

pnpm install @langchain/aws

bash

yarn add @langchain/aws

bash

bun add @langchain/aws

TypeScript · initChatModelTypeScript · Model Class

typescript

import { initChatModel } from "langchain";

// 请按照以下步骤配置你的凭证：
// https://docs.aws.amazon.com/bedrock/latest/userguide/getting-started.html

const model = await initChatModel("bedrock:gpt-5.5");

typescript

import { ChatBedrockConverse } from "@langchain/aws";

// 请按照以下步骤配置你的凭证：
// https://docs.aws.amazon.com/bedrock/latest/userguide/getting-started.html

const model = new ChatBedrockConverse({
  model: "gpt-5.5",
  region: "us-east-2"
});

下面的示例中显示的输出使用的是 OpenAI。

2. 配置数据库

你将为本教程创建一个 SQLite 数据库。SQLite 是一种轻量级数据库，易于安装和使用。我们将加载 chinook 数据库，这是一个代表数字媒体商店的示例数据库。

为了方便起见，我们将数据库（Chinook.db）托管在一个公共 GCS 存储桶上。

python

import pathlib
import requests

url = "https://storage.googleapis.com/benchmarks-artifacts/chinook/Chinook.db"
local_path = pathlib.Path("Chinook.db")

if local_path.exists():
    print(f"{local_path} already exists, skipping download.")
else:
    response = requests.get(url, timeout=60)
    if response.status_code == 200:
        local_path.write_bytes(response.content)
        print(f"File downloaded and saved as {local_path}")
    else:
        print(f"Failed to download the file. Status code: {response.status_code}")

我们将使用 Python 内置的 sqlite3 模块与数据库交互：

python

import sqlite3

con = sqlite3.connect("Chinook.db")
cursor = con.cursor()

cursor.execute("SELECT name FROM sqlite_master WHERE type='table';")
tables = [row[0] for row in cursor.fetchall() if not row[0].startswith("sqlite_")]

print("Dialect: sqlite")
print(f"Available tables: {tables}")

cursor.execute("SELECT * FROM Artist LIMIT 5;")
print(f"Sample output: {cursor.fetchall()}")
con.close()

Dialect: sqlite
Available tables: ['Album', 'Artist', 'Customer', 'Employee', 'Genre', 'Invoice', 'InvoiceLine', 'MediaType', 'Playlist', 'PlaylistTrack', 'Track']
Sample output: [(1, 'AC/DC'), (2, 'Accept'), (3, 'Aerosmith'), (4, 'Alanis Morissette'), (5, 'Alice In Chains')]

import fs from "node:fs/promises";
import path from "node:path";

const url =
  "https://storage.googleapis.com/benchmarks-artifacts/chinook/Chinook.db";
const localPath = path.resolve("Chinook.db");

async function resolveDbPath() {
  const exists = await fs
    .access(localPath)
    .then(() => true)
    .catch(() => false);
  if (exists) {
    console.log(`${localPath} already exists, skipping download.`);
    return localPath;
  }
  const resp = await fetch(url);
  if (!resp.ok)
    throw new Error(`Failed to download DB. Status code: ${resp.status}`);
  const buf = Buffer.from(await resp.arrayBuffer());
  await fs.writeFile(localPath, buf);
  console.log(`File downloaded and saved as ${localPath}`);
  return localPath;
}

我们将使用 sqlite3 库与数据库交互：

import sqlite3 from "sqlite3";

const dialect = "sqlite";

async function runQuery(query: string, params: unknown[] = []): Promise<any[]> {
  const dbPath = await resolveDbPath();
  const db = new sqlite3.Database(dbPath);
  return new Promise((resolve, reject) => {
    db.all(query, params, (err, rows) => {
      db.close();
      if (err) reject(err);
      else resolve(rows);
    });
  });
}

const tableRows = await runQuery(
  "SELECT name FROM sqlite_master WHERE type='table' AND name NOT LIKE 'sqlite_%';",
);
const tableNames = tableRows.map((row) => String(row.name));
console.log(`Dialect: ${dialect}`);
console.log(`Available tables: ${tableNames.join(", ")}`);
const sampleResults = await runQuery("SELECT * FROM Artist LIMIT 5;");
console.log(`Sample output: ${JSON.stringify(sampleResults)}`);

Dialect: sqlite
Available tables: Album, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track
Sample output: [{"ArtistId":1,"Name":"AC/DC"},{"ArtistId":2,"Name":"Accept"},{"ArtistId":3,"Name":"Aerosmith"},{"ArtistId":4,"Name":"Alanis Morissette"},{"ArtistId":5,"Name":"Alice In Chains"}]

3. 添加用于数据库交互的工具

WARNING

以下数据库工具仅为演示目的而编写的最小封装。它们不适用于安全场景，也不应被用于生产环境。在执行模型生成的 SQL 之前，请使用范围受限的数据库权限，并添加特定于应用程序的验证。

我们可以使用 langchain.tools 中的 @tool 装饰器将数据库工具实现为精简封装：

python

import sqlite3
from langchain.tools import tool

# 以下是仅用于演示目的的最小工具。

@tool
def sql_db_list_tables() -> str:
    """Input is an empty string, output is a comma-separated list of tables in the database."""
    con = sqlite3.connect("Chinook.db")
    try:
        cursor = con.cursor()
        cursor.execute("SELECT name FROM sqlite_master WHERE type='table';")
        tables = [
            row[0]
            for row in cursor.fetchall()
            if not row[0].startswith("sqlite_")
        ]
        return ", ".join(tables)
    finally:
        con.close()

@tool
def sql_db_schema(table_names: str) -> str:
    """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"""
    con = sqlite3.connect("Chinook.db")
    try:
        cursor = con.cursor()
        cursor.execute("SELECT name FROM sqlite_master WHERE type='table';")
        valid_tables = {
            row[0] for row in cursor.fetchall() if not row[0].startswith("sqlite_")
        }
        results = []
        for table in table_names.split(","):
            table = table.strip()
            if table not in valid_tables:
                results.append(
                    f"Error: table_names {{{table!r}}} not found in database"
                )
                continue
            cursor.execute(
                "SELECT sql FROM sqlite_master WHERE type='table' AND name=?;",
                (table,),
            )
            schema_row = cursor.fetchone()
            if schema_row:
                results.append(schema_row[0])
                try:
                    quoted_table = '"' + table.replace('"', '""') + '"'
                    cursor.execute(f"SELECT * FROM {quoted_table} LIMIT 3;")
                    rows = cursor.fetchall()
                    if rows:
                        col_names = [description[0] for description in cursor.description]
                        results.append(
                            f"/*\n3 rows from {table} table:\n"
                            + "\t".join(col_names)
                            + "\n"
                            + "\n".join(
                                "\t".join(str(x) for x in row) for row in rows
                            )
                            + "\n*/"
                        )
                except Exception as e:
                    results.append(f"Error fetching sample rows: {e}")
        return "\n\n".join(results)
    finally:
        con.close()

@tool
def sql_db_query(query: str) -> str:
    """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."""
    con = sqlite3.connect("Chinook.db")
    try:
        cursor = con.cursor()
        cursor.execute(query)
        res = cursor.fetchall()
        return str(res)
    except Exception as e:
        return f"Error: {e}"
    finally:
        con.close()

tools = [sql_db_list_tables, sql_db_schema, sql_db_query]

# 使用不同的循环变量，以免遮蔽 `tool` 装饰器，
# 该装饰器稍后会被复用来封装查询工具以进行人工审查。
for t in tools:
    print(f"{t.name}: {t.description}\n")

sql_db_list_tables: Input is an empty string, output is a comma-separated list of tables in the database.

sql_db_schema: 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

sql_db_query: 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.

我们将创建自定义工具来与数据库交互：

import { tool } from "langchain";
import * as z from "zod";

async function getTableNames() {
  const rows = await runQuery(
    "SELECT name FROM sqlite_master WHERE type='table' AND name NOT LIKE 'sqlite_%';",
  );
  return rows.map((row) => String(row.name));
}

function quoteSqliteIdentifier(identifier: string) {
  return `"${identifier.replaceAll('"', '""')}"`;
}

const listTablesTool = tool(
  async () => {
    const tableNames = await getTableNames();
    return tableNames.join(", ");
  },
  {
    name: "sql_db_list_tables",
    description:
      "Input is an empty string, output is a comma-separated list of tables in the database.",
    schema: z.object({}),
  },
);

const getSchemaTool = tool(
  async ({ table_names }) => {
    const validTables = new Set(await getTableNames());
    const results: string[] = [];
    for (const table of table_names.split(",").map((t) => t.trim())) {
      if (!validTables.has(table)) {
        results.push(`Error: table_names {'${table}'} not found in database`);
        continue;
      }
      const schemaRows = await runQuery(
        "SELECT sql FROM sqlite_master WHERE type='table' AND name=?;",
        [table],
      );
      const schema = schemaRows[0]?.sql;
      if (schema) {
        results.push(String(schema));
        try {
          const rows = await runQuery(
            `SELECT * FROM ${quoteSqliteIdentifier(table)} LIMIT 3;`,
          );
          if (rows.length > 0) {
            const colNames = Object.keys(rows[0]);
            results.push(
              `/*\n3 rows from ${table} table:\n${colNames.join("\t")}\n` +
                rows
                  .map((row) =>
                    colNames.map((col) => String(row[col])).join("\t"),
                  )
                  .join("\n") +
                "\n*/",
            );
          }
        } catch (e) {
          results.push(`Error fetching sample rows: ${e}`);
        }
      }
    }
    return results.join("\n\n");
  },
  {
    name: "sql_db_schema",
    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",
    schema: z.object({
      table_names: z.string().describe("Comma-separated list of table names"),
    }),
  },
);

const queryTool = tool(
  async ({ query }) => {
    try {
      const result = await runQuery(query);
      return JSON.stringify(result);
    } catch (error) {
      return `Error: ${error instanceof Error ? error.message : String(error)}`;
    }
  },
  {
    name: "sql_db_query",
    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.",
    schema: z.object({
      query: z.string().describe("SQL query to execute"),
    }),
  },
);

const tools = [listTablesTool, getSchemaTool, queryTool];

for (const toolItem of tools) {
  console.log(`${toolItem.name}: ${toolItem.description}\n`);
}

sql_db_list_tables: Input is an empty string, output is a comma-separated list of tables in the database.

sql_db_schema: 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

sql_db_query: 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.

4. 定义应用步骤

我们为以下步骤构建专门的节点：

列出数据库表
调用 "get schema" 工具
生成查询
检查查询

将这些步骤放在专门的节点中，使我们能够 (1) 在需要时强制进行工具调用，以及 (2) 自定义与每个步骤关联的提示词。

python

from typing import Literal

from langchain.messages import AIMessage
from langchain_core.runnables import RunnableConfig
from langgraph.graph import END, START, MessagesState, StateGraph
from langgraph.prebuilt import ToolNode

get_schema_tool = next(tool for tool in tools if tool.name == "sql_db_schema")
get_schema_node = ToolNode([get_schema_tool], name="get_schema")

run_query_tool = next(tool for tool in tools if tool.name == "sql_db_query")
run_query_node = ToolNode([run_query_tool], name="run_query")

# 示例：创建一个预定的工具调用
def list_tables(state: MessagesState):
    tool_call = {
        "name": "sql_db_list_tables",
        "args": {},
        "id": "abc123",
        "type": "tool_call",
    }
    tool_call_message = AIMessage(content="", tool_calls=[tool_call])

    list_tables_tool = next(tool for tool in tools if tool.name == "sql_db_list_tables")
    tool_message = list_tables_tool.invoke(tool_call)
    response = AIMessage(f"Available tables: {tool_message.content}")

    return {"messages": [tool_call_message, tool_message, response]}

# 示例：强制模型创建工具调用
def call_get_schema(state: MessagesState):
    # 请注意，LangChain 要求所有模型都接受 `tool_choice="any"`
    # 以及 `tool_choice=<string name of tool>`。
    llm_with_tools = model.bind_tools([get_schema_tool], tool_choice="any")
    response = llm_with_tools.invoke(state["messages"])

    return {"messages": [response]}

generate_query_system_prompt = """
You are an agent designed to interact with a SQL database.
Given an input question, create a syntactically correct {dialect} query to run,
then look at the results of the query and return the answer. Unless the user
specifies a specific number of examples they wish to obtain, always limit your
query to at most {top_k} results.

You can order the results by a relevant column to return the most interesting
examples in the database. Never query for all the columns from a specific table,
only ask for the relevant columns given the question.

DO NOT make any DML statements (INSERT, UPDATE, DELETE, DROP etc.) to the database.
""".format(
    dialect="sqlite",
    top_k=5,
)

def generate_query(state: MessagesState):
    system_message = {
        "role": "system",
        "content": generate_query_system_prompt,
    }
    # 我们在这里不强制工具调用，以便模型
    # 在获得解决方案时自然地做出响应。
    llm_with_tools = model.bind_tools([run_query_tool])
    response = llm_with_tools.invoke([system_message] + state["messages"])

    return {"messages": [response]}

check_query_system_prompt = """
You are a SQL expert with a strong attention to detail.
Double check the {dialect} query for common mistakes, including:
- Using NOT IN with NULL values
- Using UNION when UNION ALL should have been used
- Using BETWEEN for exclusive ranges
- Data type mismatch in predicates
- Properly quoting identifiers
- Using the correct number of arguments for functions
- Casting to the correct data type
- Using the proper columns for joins

If there are any of the above mistakes, rewrite the query. If there are no mistakes,
just reproduce the original query.

You will call the appropriate tool to execute the query after running this check.
""".format(dialect="sqlite")

def check_query(state: MessagesState):
    system_message = {
        "role": "system",
        "content": check_query_system_prompt,
    }

    # 生成一条人工用户消息用于检查
    tool_call = state["messages"][-1].tool_calls[0]
    user_message = {"role": "user", "content": tool_call["args"]["query"]}
    llm_with_tools = model.bind_tools([run_query_tool], tool_choice="any")
    response = llm_with_tools.invoke([system_message, user_message])
    response.id = state["messages"][-1].id

    return {"messages": [response]}

import {
  AIMessage,
  HumanMessage,
  SystemMessage,
  ToolMessage,
} from "@langchain/core/messages";
import { ToolNode } from "@langchain/langgraph/prebuilt";
import {
  END,
  GraphNode,
  MessagesValue,
  START,
  StateGraph,
  StateSchema,
} from "@langchain/langgraph";

// 为 schema 和查询执行创建工具节点
const getSchemaNode = new ToolNode([getSchemaTool]);
const runQueryNode = new ToolNode([queryTool]);

// 定义状态 schema
const MessagesState = new StateSchema({
  messages: MessagesValue,
});

// 示例：创建一个预定的工具调用
const listTables: GraphNode<typeof MessagesState> = async (state) => {
  const toolCall = {
    name: "sql_db_list_tables",
    args: {},
    id: "abc123",
    type: "tool_call" as const,
  };
  const toolCallMessage = new AIMessage({
    content: "",
    tool_calls: [toolCall],
  });

  const toolMessage = await listTablesTool.invoke({});
  const response = new AIMessage(`Available tables: ${toolMessage}`);

  return {
    messages: [
      toolCallMessage,
      new ToolMessage({ content: toolMessage, tool_call_id: "abc123" }),
      response,
    ],
  };
};

// 示例：强制模型创建工具调用
const callGetSchema: GraphNode<typeof MessagesState> = async (state) => {
  const llmWithTools = model!.bindTools([getSchemaTool], {
    tool_choice: "any",
  });
  const response = await llmWithTools.invoke(state.messages);

  return { messages: [response] };
};

const topK = 5;

const generateQuerySystemPrompt = `
You are an agent designed to interact with a SQL database.
Given an input question, create a syntactically correct ${dialect}
query to run, then look at the results of the query and return the answer. Unless
the user specifies a specific number of examples they wish to obtain, always limit
your query to at most ${topK} results.

You can order the results by a relevant column to return the most interesting
examples in the database. Never query for all the columns from a specific table,
only ask for the relevant columns given the question.

DO NOT make any DML statements (INSERT, UPDATE, DELETE, DROP etc.) to the database.
`;

const generateQuery: GraphNode<typeof MessagesState> = async (state) => {
  const systemMessage = new SystemMessage(generateQuerySystemPrompt);
  // 我们在这里不强制工具调用，以便模型
  // 在获得解决方案时自然地做出响应。
  const llmWithTools = model!.bindTools([queryTool]);
  const response = await llmWithTools.invoke([
    systemMessage,
    ...state.messages,
  ]);

  return { messages: [response] };
};

const checkQuerySystemPrompt = `
You are a SQL expert with a strong attention to detail.
Double check the ${dialect} query for common mistakes, including:
- Using NOT IN with NULL values
- Using UNION when UNION ALL should have been used
- Using BETWEEN for exclusive ranges
- Data type mismatch in predicates
- Properly quoting identifiers
- Using the correct number of arguments for functions
- Casting to the correct data type
- Using the proper columns for joins

If there are any of the above mistakes, rewrite the query. If there are no mistakes,
just reproduce the original query.

You will call the appropriate tool to execute the query after running this check.
`;

const checkQuery: GraphNode<typeof MessagesState> = async (state) => {
  const systemMessage = new SystemMessage(checkQuerySystemPrompt);

  // 生成一条人工用户消息用于检查
  const lastMessage = state.messages[state.messages.length - 1];
  if (!lastMessage.tool_calls || lastMessage.tool_calls.length === 0) {
    throw new Error("No tool calls found in the last message");
  }
  const toolCall = lastMessage.tool_calls[0];
  const userMessage = new HumanMessage(toolCall.args.query);
  const llmWithTools = model!.bindTools([queryTool], {
    tool_choice: "any",
  });
  const response = await llmWithTools.invoke([systemMessage, userMessage]);
  // 保留原始消息 ID
  response.id = lastMessage.id;

  return { messages: [response] };
};

5. 实现智能体

我们现在可以使用 Graph API 将这些步骤组装成一个工作流。我们在查询生成步骤定义了一个条件边：如果生成了查询，则路由到查询检查器；如果不存在工具调用，则结束——此时 LLM 已经回答了查询。

python

def should_continue(state: MessagesState) -> Literal[END, "check_query"]:
    messages = state["messages"]
    last_message = messages[-1]
    if not last_message.tool_calls:
        return END
    else:
        return "check_query"

builder = StateGraph(MessagesState)
builder.add_node(list_tables)
builder.add_node(call_get_schema)
builder.add_node(get_schema_node, "get_schema")
builder.add_node(generate_query)
builder.add_node(check_query)
builder.add_node(run_query_node, "run_query")

builder.add_edge(START, "list_tables")
builder.add_edge("list_tables", "call_get_schema")
builder.add_edge("call_get_schema", "get_schema")
builder.add_edge("get_schema", "generate_query")
builder.add_conditional_edges(
    "generate_query",
    should_continue,
)
builder.add_edge("check_query", "run_query")
builder.add_edge("run_query", "generate_query")

agent = builder.compile()

我们可以在下面可视化该应用：

python

import pathlib

pathlib.Path("graph.png").write_bytes(agent.get_graph().draw_mermaid_png())

import { ConditionalEdgeRouter } from "@langchain/langgraph";

const shouldContinue: ConditionalEdgeRouter<
  typeof MessagesState,
  "check_query"
> = (state) => {
  const messages = state.messages;
  const lastMessage = messages[messages.length - 1];
  if (!lastMessage.tool_calls || lastMessage.tool_calls.length === 0) {
    return END;
  } else {
    return "check_query";
  }
};

const builder = new StateGraph(MessagesState)
  .addNode("list_tables", listTables)
  .addNode("call_get_schema", callGetSchema)
  .addNode("get_schema", getSchemaNode)
  .addNode("generate_query", generateQuery)
  .addNode("check_query", checkQuery)
  .addNode("run_query", runQueryNode)
  .addEdge(START, "list_tables")
  .addEdge("list_tables", "call_get_schema")
  .addEdge("call_get_schema", "get_schema")
  .addEdge("get_schema", "generate_query")
  .addConditionalEdges("generate_query", shouldContinue)
  .addEdge("check_query", "run_query")
  .addEdge("run_query", "generate_query");

const agent = builder.compile();

我们可以在下面可视化该应用：

import * as fs from "node:fs/promises";

const drawableGraph = await agent.getGraphAsync();
const image = await drawableGraph.drawMermaidPng();
const imageBuffer = new Uint8Array(await image.arrayBuffer());

await fs.writeFile("graph.png", imageBuffer);

SQL agent graph

我们现在可以调用图：

python

question = "Which genre on average has the longest tracks?"

stream = agent.stream_events(
    {"messages": [{"role": "user", "content": question}]},
    version="v3",
)
for message in stream.messages:
    for token in message.text:
        print(token, end="", flush=True)

final_state = stream.output

const question = "Which genre on average has the longest tracks?";

const stream = await agent.streamEvents(
  { messages: [{ role: "user", content: question }] },
  { version: "v3" },
);

for await (const message of stream.messages) {
  for await (const token of message.text) {
    process.stdout.write(token);
  }
}

const finalState = await stream.output;

================================ Human Message =================================

Which genre on average has the longest tracks?
================================== Ai Message ==================================

Available tables: Album, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track
================================== Ai Message ==================================
Tool Calls:
  sql_db_schema (call_yzje0tj7JK3TEzDx4QnRR3lL)
 Call ID: call_yzje0tj7JK3TEzDx4QnRR3lL
  Args:
    table_names: Genre, Track
================================= Tool Message =================================
Name: sql_db_schema

CREATE TABLE "Genre" (
	"GenreId" INTEGER NOT NULL,
	"Name" NVARCHAR(120),
	PRIMARY KEY ("GenreId")
)

/*
3 rows from Genre table:
GenreId	Name
1	Rock
2	Jazz
3	Metal
*/

CREATE TABLE "Track" (
	"TrackId" INTEGER NOT NULL,
	"Name" NVARCHAR(200) NOT NULL,
	"AlbumId" INTEGER,
	"MediaTypeId" INTEGER NOT NULL,
	"GenreId" INTEGER,
	"Composer" NVARCHAR(220),
	"Milliseconds" INTEGER NOT NULL,
	"Bytes" INTEGER,
	"UnitPrice" NUMERIC(10, 2) NOT NULL,
	PRIMARY KEY ("TrackId"),
	FOREIGN KEY("MediaTypeId") REFERENCES "MediaType" ("MediaTypeId"),
	FOREIGN KEY("GenreId") REFERENCES "Genre" ("GenreId"),
	FOREIGN KEY("AlbumId") REFERENCES "Album" ("AlbumId")
)

/*
3 rows from Track table:
TrackId	Name	AlbumId	MediaTypeId	GenreId	Composer	Milliseconds	Bytes	UnitPrice
1	For Those About To Rock (We Salute You)	1	1	1	Angus Young, Malcolm Young, Brian Johnson	343719	11170334	0.99
2	Balls to the Wall	2	2	1	U. Dirkschneider, W. Hoffmann, H. Frank, P. Baltes, S. Kaufmann, G. Hoffmann	342562	5510424	0.99
3	Fast As a Shark	3	2	1	F. Baltes, S. Kaufman, U. Dirkscneider & W. Hoffman	230619	3990994	0.99
*/
================================== Ai Message ==================================
Tool Calls:
  sql_db_query (call_cb9ApLfZLSq7CWg6jd0im90b)
 Call ID: call_cb9ApLfZLSq7CWg6jd0im90b
  Args:
    query: SELECT Genre.Name, AVG(Track.Milliseconds) AS AvgMilliseconds FROM Track JOIN Genre ON Track.GenreId = Genre.GenreId GROUP BY Genre.GenreId ORDER BY AvgMilliseconds DESC LIMIT 5;
================================== Ai Message ==================================
Tool Calls:
  sql_db_query (call_DMVALfnQ4kJsuF3Yl6jxbeAU)
 Call ID: call_DMVALfnQ4kJsuF3Yl6jxbeAU
  Args:
    query: SELECT Genre.Name, AVG(Track.Milliseconds) AS AvgMilliseconds FROM Track JOIN Genre ON Track.GenreId = Genre.GenreId GROUP BY Genre.GenreId ORDER BY AvgMilliseconds DESC LIMIT 5;
================================= Tool Message =================================
Name: sql_db_query

[('Sci Fi & Fantasy', 2911783.0384615385), ('Science Fiction', 2625549.076923077), ('Drama', 2575283.78125), ('TV Shows', 2145041.0215053763), ('Comedy', 1585263.705882353)]
================================== Ai Message ==================================

The genre with the longest tracks on average is "Sci Fi & Fantasy," with an average track length of approximately 2,911,783 milliseconds. Other genres with relatively long tracks include "Science Fiction," "Drama," "TV Shows," and "Comedy."

TIP

查看上述运行的 LangSmith trace。

TIP

查看上述运行的 LangSmith trace。

6. 实现人在回路（人工介入）审查

在智能体的 SQL 查询被执行之前，检查它们是否有任何意外操作或低效之处，是审慎的做法。

这里我们利用 LangGraph 的人在回路（人工介入）功能，在执行 SQL 查询之前暂停运行，等待人工审查。利用 LangGraph 的持久化层，我们可以无限期地暂停运行（或者至少只要持久化层存活多久就可以暂停多久）。

让我们把 sql_db_query 工具封装到一个接收人类输入的节点中。我们可以使用中断函数来实现这一点。在下面，我们允许输入来批准工具调用、编辑其参数或提供用户反馈。

python

from langchain.tools import tool
from langgraph.types import interrupt
from langchain_core.runnables import RunnableConfig

@tool(
    run_query_tool.name,
    description=run_query_tool.description,
    args_schema=run_query_tool.args_schema,
)
def run_query_tool_with_interrupt(config: RunnableConfig, **tool_input):
    request = {
        "action": run_query_tool.name,
        "args": tool_input,
        "description": "Please review the tool call",
    }
    response = interrupt([request])  
    # 批准工具调用
    if response["type"] == "accept":
        tool_response = run_query_tool.invoke(tool_input, config)
    # 更新工具调用参数
    elif response["type"] == "edit":
        tool_input = response["args"]["args"]
        tool_response = run_query_tool.invoke(tool_input, config)
    # 用用户反馈回复 LLM
    elif response["type"] == "response":
        user_feedback = response["args"]
        tool_response = user_feedback
    else:
        raise ValueError(f"Unsupported interrupt response type: {response['type']}")

    return tool_response

# 重新定义工具节点以使用 interrupt 版本
run_query_node = ToolNode([run_query_tool_with_interrupt], name="run_query")

import { RunnableConfig } from "@langchain/core/runnables";
import { interrupt } from "@langchain/langgraph";

const queryToolWithInterrupt = tool(
  async (input, config: RunnableConfig) => {
    const request = {
      action: queryTool.name,
      args: input,
      description: "Please review the tool call",
    };
    const response = interrupt([request]); 
    // 批准工具调用
    if (response.type === "accept") {
      const toolResponse = await queryTool.invoke(input, config);
      return toolResponse;
    }
    // 更新工具调用参数
    else if (response.type === "edit") {
      const editedInput = response.args.args;
      const toolResponse = await queryTool.invoke(editedInput, config);
      return toolResponse;
    }
    // 用用户反馈回复 LLM
    else if (response.type === "response") {
      const userFeedback = response.args;
      return userFeedback;
    } else {
      throw new Error(`Unsupported interrupt response type: ${response.type}`);
    }
  },
  {
    name: queryTool.name,
    description: queryTool.description,
    schema: queryTool.schema,
  },
);

INFO

上述实现遵循更广泛的人在回路（人工介入）指南中的工具中断示例。有关详细信息和替代方案，请参阅该指南。

现在让我们重新组装图。我们将用人工审查取代程序化检查。请注意，我们现在包含了一个检查点器；这是暂停和恢复运行所必需的。

python

from langgraph.checkpoint.memory import InMemorySaver

def should_continue(state: MessagesState) -> Literal[END, "run_query"]:
    messages = state["messages"]
    last_message = messages[-1]
    if not last_message.tool_calls:
        return END
    else:
        return "run_query"

builder = StateGraph(MessagesState)
builder.add_node(list_tables)
builder.add_node(call_get_schema)
builder.add_node(get_schema_node, "get_schema")
builder.add_node(generate_query)
builder.add_node(run_query_node, "run_query")

builder.add_edge(START, "list_tables")
builder.add_edge("list_tables", "call_get_schema")
builder.add_edge("call_get_schema", "get_schema")
builder.add_edge("get_schema", "generate_query")
builder.add_conditional_edges(
    "generate_query",
    should_continue,
)
builder.add_edge("run_query", "generate_query")

checkpointer = InMemorySaver()  
agent = builder.compile(checkpointer=checkpointer)

import { Command, MemorySaver } from "@langchain/langgraph";

const shouldContinueWithHuman: ConditionalEdgeRouter<
  typeof MessagesState,
  "run_query"
> = (state) => {
  const messages = state.messages;
  const lastMessage = messages[messages.length - 1];
  if (!lastMessage.tool_calls || lastMessage.tool_calls.length === 0) {
    return END;
  } else {
    return "run_query";
  }
};

const builderWithHuman = new StateGraph(MessagesState)
  .addNode("list_tables", listTables)
  .addNode("call_get_schema", callGetSchema)
  .addNode("get_schema", getSchemaNode)
  .addNode("generate_query", generateQuery)
  .addNode("run_query", runQueryNodeWithInterrupt)
  .addEdge(START, "list_tables")
  .addEdge("list_tables", "call_get_schema")
  .addEdge("call_get_schema", "get_schema")
  .addEdge("get_schema", "generate_query")
  .addConditionalEdges("generate_query", shouldContinueWithHuman)
  .addEdge("run_query", "generate_query");

const checkpointer = new MemorySaver(); 
const agentWithHuman = builderWithHuman.compile({ checkpointer });

我们可以像之前一样调用图。这一次，执行被中断了：

python

question = "Which genre on average has the longest tracks?"

stream = agent.stream_events(
    {"messages": [{"role": "user", "content": question}]},
    config,
    version="v3",
)
for message in stream.messages:
    for token in message.text:
        print(token, end="", flush=True)
if stream.interrupted:
    action = stream.interrupts[0]
    print("INTERRUPTED:")
    for request in action.value:
        print(json.dumps(request, indent=2))

const hitlQuestion = "Which genre on average has the longest tracks?";

const hitlStream = await agentWithHuman.streamEvents(
  { messages: [{ role: "user", content: hitlQuestion }] },
  { ...config, version: "v3" },
);

for await (const message of hitlStream.messages) {
  for await (const token of message.text) {
    process.stdout.write(token);
  }
}

// 检查中断
if (hitlStream.interrupted) {
  console.log("\nINTERRUPTED:");
  console.log(JSON.stringify(hitlStream.interrupts[0], null, 2));
}

...

INTERRUPTED:
{
  "action": "sql_db_query",
  "args": {
    "query": "SELECT Genre.Name, AVG(Track.Milliseconds) AS AvgLength FROM Track JOIN Genre ON Track.GenreId = Genre.GenreId GROUP BY Genre.Name ORDER BY AvgLength DESC LIMIT 5;"
  },
  "description": "Please review the tool call"
}

我们可以使用 Command 接受或编辑工具调用：

python

from langgraph.types import Command

stream = agent.stream_events(
    Command(resume={"type": "accept"}),
    # Command(resume={"type": "edit", "args": {"query": "..."}}),
    config,
    version="v3",
)
for message in stream.messages:
    for token in message.text:
        print(token, end="", flush=True)
if stream.interrupted:
    action = stream.interrupts[0]
    print("INTERRUPTED:")
    for request in action.value:
        print(json.dumps(request, indent=2))

const resumeStream = await agentWithHuman.streamEvents(
  new Command({ resume: { type: "accept" } }),
  // new Command({ resume: { type: "edit", args: { query: "..." } } }),
  { ...config, version: "v3" },
);

for await (const message of resumeStream.messages) {
  for await (const token of message.text) {
    process.stdout.write(token);
  }
}

================================== Ai Message ==================================
Tool Calls:
  sql_db_query (call_t4yXkD6shwdTPuelXEmY3sAY)
 Call ID: call_t4yXkD6shwdTPuelXEmY3sAY
  Args:
    query: SELECT Genre.Name, AVG(Track.Milliseconds) AS AvgLength FROM Track JOIN Genre ON Track.GenreId = Genre.GenreId GROUP BY Genre.Name ORDER BY AvgLength DESC LIMIT 5;
================================= Tool Message =================================
Name: sql_db_query

[('Sci Fi & Fantasy', 2911783.0384615385), ('Science Fiction', 2625549.076923077), ('Drama', 2575283.78125), ('TV Shows', 2145041.0215053763), ('Comedy', 1585263.705882353)]
================================== Ai Message ==================================

The genre with the longest average track length is "Sci Fi & Fantasy" with an average length of about 2,911,783 milliseconds. Other genres with long average track lengths include "Science Fiction," "Drama," "TV Shows," and "Comedy."

有关详细信息，请参阅人在回路（人工介入）指南。

下一步

查看评估图指南，了解如何评估 LangGraph 应用（包括像这样的 SQL 智能体）时使用 LangSmith。

概念 ​

设置 ​

安装 ​

LangSmith ​

1. 选择 LLM ​

OpenAI ​

Anthropic ​

Azure ​

Google Gemini ​

AWS Bedrock ​

HuggingFace ​

OpenRouter ​

OpenAI ​

Anthropic ​

Azure ​

Google Gemini ​

Bedrock Converse ​

2. 配置数据库 ​

3. 添加用于数据库交互的工具 ​

4. 定义应用步骤 ​

5. 实现智能体 ​

6. 实现人在回路（人工介入）审查 ​

下一步 ​

概念

设置

安装

LangSmith

1. 选择 LLM

OpenAI

Anthropic

Azure

Google Gemini

AWS Bedrock

HuggingFace

OpenRouter

OpenAI

Anthropic

Azure

Google Gemini

Bedrock Converse

2. 配置数据库

3. 添加用于数据库交互的工具

4. 定义应用步骤

5. 实现智能体

6. 实现人在回路（人工介入）审查

下一步