langchain_community.agent_toolkits.sql.base
.create_sql_agent¶
- langchain_community.agent_toolkits.sql.base.create_sql_agent(llm: BaseLanguageModel, toolkit: Optional[SQLDatabaseToolkit] = None, agent_type: Optional[Union[AgentType, Literal['openai-tools']]] = None, callback_manager: Optional[BaseCallbackManager] = None, prefix: Optional[str] = None, suffix: Optional[str] = None, format_instructions: Optional[str] = None, input_variables: Optional[List[str]] = None, top_k: int = 10, max_iterations: Optional[int] = 15, max_execution_time: Optional[float] = None, early_stopping_method: str = 'force', verbose: bool = False, agent_executor_kwargs: Optional[Dict[str, Any]] = None, extra_tools: Sequence[BaseTool] = (), *, db: Optional[SQLDatabase] = None, prompt: Optional[BasePromptTemplate] = None, **kwargs: Any) AgentExecutor [source]¶
Construct a SQL agent from an LLM and toolkit or database.
- Parameters
llm â Language model to use for the agent.
toolkit â SQLDatabaseToolkit for the agent to use. Must provide exactly one of âtoolkitâ or âdbâ. Specify âtoolkitâ if you want to use a different model for the agent and the toolkit.
agent_type â One of âopenai-toolsâ, âopenai-functionsâ, or âzero-shot-react-descriptionâ. Defaults to âzero-shot-react-descriptionâ. âopenai-toolsâ is recommended over âopenai-functionsâ.
callback_manager â DEPRECATED. Pass âcallbacksâ key into âagent_executor_kwargsâ instead to pass constructor callbacks to AgentExecutor.
prefix â Prompt prefix string. Must contain variables âtop_kâ and âdialectâ.
suffix â Prompt suffix string. Default depends on agent type.
format_instructions â Formatting instructions to pass to ZeroShotAgent.create_prompt() when âagent_typeâ is âzero-shot-react-descriptionâ. Otherwise ignored.
input_variables â DEPRECATED. Input variables to explicitly specify as part of ZeroShotAgent.create_prompt() when âagent_typeâ is âzero-shot-react-descriptionâ. Otherwise ignored.
top_k â Number of rows to query for by default.
max_iterations â Passed to AgentExecutor init.
max_execution_time â Passed to AgentExecutor init.
early_stopping_method â Passed to AgentExecutor init.
verbose â AgentExecutor verbosity.
agent_executor_kwargs â Arbitrary additional AgentExecutor args.
extra_tools â Additional tools to give to agent on top of the ones that come with SQLDatabaseToolkit.
db â SQLDatabase from which to create a SQLDatabaseToolkit. Toolkit is created using âdbâ and âllmâ. Must provide exactly one of âdbâ or âtoolkitâ.
prompt â Complete agent prompt. prompt and {prefix, suffix, format_instructions, input_variables} are mutually exclusive.
**kwargs â DEPRECATED. Not used, kept for backwards compatibility.
- Returns
An AgentExecutor with the specified agent_type agent.
Example
from langchain_openai import ChatOpenAI from langchain_community.agent_toolkits import create_sql_agent from langchain_community.utilities import SQLDatabase
db = SQLDatabase.from_uri(âsqlite:///Chinook.dbâ) llm = ChatOpenAI(model=âgpt-3.5-turboâ, temperature=0) agent_executor = create_sql_agent(llm, db=db, agent_type=âopenai-toolsâ, verbose=True)