dhXSrSSKJr SSKJr SSKJr SSKJr SSK J r SSK J r SSK JrJr SS KJrJrJrJr SS KJr SS KJr "S S \ 5r\R35 g)z-Toolkit for interacting with an SQL database.)List) BaseCache) Callbacks)BaseLanguageModel)BaseTool) BaseToolkit) ConfigDictField)InfoSQLDatabaseToolListSQLDatabaseToolQuerySQLCheckerToolQuerySQLDatabaseTool)QuerySQLDataBaseTool) SQLDatabasec\rSrSr%Sr\"SS9r\\S'\"SS9r \ \S'\ S\ 4Sj5r \"SS 9rS\\4S jrS\4S jrS rg )SQLDatabaseToolkita+SQLDatabaseToolkit for interacting with SQL databases. Setup: Install ``langchain-community``. .. code-block:: bash pip install -U langchain-community Key init args: db: SQLDatabase The SQL database. llm: BaseLanguageModel The language model (for use with QuerySQLCheckerTool) Instantiate: .. code-block:: python from langchain_community.agent_toolkits.sql.toolkit import SQLDatabaseToolkit from langchain_community.utilities.sql_database import SQLDatabase from langchain_openai import ChatOpenAI db = SQLDatabase.from_uri("sqlite:///Chinook.db") llm = ChatOpenAI(temperature=0) toolkit = SQLDatabaseToolkit(db=db, llm=llm) Tools: .. code-block:: python toolkit.get_tools() Use within an agent: .. code-block:: python from langchain import hub from langgraph.prebuilt import create_react_agent # Pull prompt (or define your own) prompt_template = hub.pull("langchain-ai/sql-agent-system-prompt") system_message = prompt_template.format(dialect="SQLite", top_k=5) # Create agent agent_executor = create_react_agent( llm, toolkit.get_tools(), state_modifier=system_message ) # Query agent example_query = "Which country's customers spent the most?" events = agent_executor.stream( {"messages": [("user", example_query)]}, stream_mode="values", ) for event in events: event["messages"][-1].pretty_print() T)excludedbllmreturnc.URR$)z3Return string representation of SQL dialect to use.)rdialectselfs f/var/www/html/shao/venv/lib/python3.13/site-packages/langchain_community/agent_toolkits/sql/toolkit.pyrSQLDatabaseToolkit.dialectVsww)arbitrary_types_allowedc"[URS9nSURS3n[URUS9nSURS3n[ URUS9nSURS3n[ URUR US 9nUUUU/$) zGet the tools in the toolkit.)rzInput 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 z- first! Example Input: table1, table2, table3)r descriptiona4Input 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 z# to query the correct table fields.zUse this tool to double check if your query is correct before executing it. Always use this tool before executing a query with !)rrr!)r rnamer rr r)rlist_sql_database_tool"info_sql_database_tool_descriptioninfo_sql_database_tool#query_sql_database_tool_descriptionquery_sql_database_tool"query_sql_checker_tool_descriptionquery_sql_checker_tools r get_toolsSQLDatabaseToolkit.get_tools_s!4!@ A&**+,4 4 +"5ww$F"  +,B+F+F*GH1  1 ,#7ww$G#  F&++,A / + "5wwDHH2T"  $ " " "   rc6URR5$)z4Return db context that you may want in agent prompt.)r get_contextrs rr.SQLDatabaseToolkit.get_contextsww""$$rN)__name__ __module__ __qualname____firstlineno____doc__r rr__annotations__rrpropertystrrr model_configrrr+dictr.__static_attributes__r0rrrrsn8tD)B )"40C 0  $L% 4>% N%T%rrN)r5typingrlangchain_core.cachesrlangchain_core.callbacksrlangchain_core.language_modelsrlangchain_core.toolsrlangchain_core.tools.baserpydanticr r +langchain_community.tools.sql_database.toolr r r rr*langchain_community.utilities.sql_databaserr model_rebuildr0rrrFsO38;<)1& Cp%p%f "r