构建一个 SQL 代理¶

%%capture --no-stderr
%pip install -U langgraph langchain_community "langchain[openai]"

from langchain.chat_models import init_chat_model

llm = init_chat_model("openai:gpt-4.1")

import requests

url = "https://storage.googleapis.com/benchmarks-artifacts/chinook/Chinook.db"

response = requests.get(url)

if response.status_code == 200:
    # Open a local file in binary write mode
    with open("Chinook.db", "wb") as file:
        # Write the content of the response (the file) to the local file
        file.write(response.content)
    print("File downloaded and saved as Chinook.db")
else:
    print(f"Failed to download the file. Status code: {response.status_code}")

from langchain_community.utilities import SQLDatabase

db = SQLDatabase.from_uri("sqlite:///Chinook.db")

print(f"Dialect: {db.dialect}")
print(f"Available tables: {db.get_usable_table_names()}")
print(f'Sample output: {db.run("SELECT * FROM Artist LIMIT 5;")}')

from langchain_community.agent_toolkits import SQLDatabaseToolkit

toolkit = SQLDatabaseToolkit(db=db, llm=llm)

tools = toolkit.get_tools()

for tool in tools:
    print(f"{tool.name}: {tool.description}\n")

from langgraph.prebuilt import create_react_agent

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.

You MUST double check your query before executing it. If you get an error while
executing a query, rewrite the query and try again.

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

To start you should ALWAYS look at the tables in the database to see what you
can query. Do NOT skip this step.

Then you should query the schema of the most relevant tables.
""".format(
    dialect=db.dialect,
    top_k=5,
)

agent = create_react_agent(
    llm,
    tools,
    prompt=system_prompt,
)

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

for step in agent.stream(
    {"messages": [{"role": "user", "content": question}]},
    stream_mode="values",
):
    step["messages"][-1].pretty_print()

from typing import Literal
from langchain_core.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")


# Example: create a predetermined tool call
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]}


# Example: force a model to create a tool call
def call_get_schema(state: MessagesState):
    # Note that LangChain enforces that all models accept `tool_choice="any"`
    # as well as `tool_choice=<string name of tool>`.
    llm_with_tools = llm.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=db.dialect,
    top_k=5,
)


def generate_query(state: MessagesState):
    system_message = {
        "role": "system",
        "content": generate_query_system_prompt,
    }
    # We do not force a tool call here, to allow the model to
    # respond naturally when it obtains the solution.
    llm_with_tools = llm.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=db.dialect)


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

    # Generate an artificial user message to check
    tool_call = state["messages"][-1].tool_calls[0]
    user_message = {"role": "user", "content": tool_call["args"]["query"]}
    llm_with_tools = llm.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]}

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()

from IPython.display import Image, display
from langchain_core.runnables.graph import CurveStyle, MermaidDrawMethod, NodeStyles

display(Image(agent.get_graph().draw_mermaid_png()))

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

for step in agent.stream(
    {"messages": [{"role": "user", "content": question}]},
    stream_mode="values",
):
    step["messages"][-1].pretty_print()