langchain.agents.structured_chat.base
.StructuredChatAgentΒΆ
- class langchain.agents.structured_chat.base.StructuredChatAgent[source]ΒΆ
Bases:
Agent
Structured Chat Agent.
Create a new model by parsing and validating input data from keyword arguments.
Raises ValidationError if the input data cannot be parsed to form a valid model.
- param allowed_tools: Optional[List[str]] = NoneΒΆ
- param llm_chain: langchain.chains.llm.LLMChain [Required]ΒΆ
- param output_parser: langchain.agents.agent.AgentOutputParser [Optional]ΒΆ
Output parser for the agent.
- async aplan(intermediate_steps: List[Tuple[AgentAction, str]], callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, **kwargs: Any) Union[AgentAction, AgentFinish] ΒΆ
Given input, decided what to do.
- Parameters
intermediate_steps β Steps the LLM has taken to date, along with observations
callbacks β Callbacks to run.
**kwargs β User inputs.
- Returns
Action specifying what tool to use.
- classmethod construct(_fields_set: Optional[SetStr] = None, **values: Any) Model ΒΆ
Creates a new model setting __dict__ and __fields_set__ from trusted or pre-validated data. Default values are respected, but no other validation is performed. Behaves as if Config.extra = βallowβ was set since it adds all passed values
- copy(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, update: Optional[DictStrAny] = None, deep: bool = False) Model ΒΆ
Duplicate a model, optionally choose which fields to include, exclude and change.
- Parameters
include β fields to include in new model
exclude β fields to exclude from new model, as with values this takes precedence over include
update β values to change/add in the new model. Note: the data is not validated before creating the new model: you should trust this data
deep β set to True to make a deep copy of the model
- Returns
new model instance
- classmethod create_prompt(tools: Sequence[BaseTool], prefix: str = 'Respond to the human as helpfully and accurately as possible. You have access to the following tools:', suffix: str = 'Begin! Reminder to ALWAYS respond with a valid json blob of a single action. Use tools if necessary. Respond directly if appropriate. Format is Action:```$JSON_BLOB```then Observation:.\nThought:', human_message_template: str = '{input}\n\n{agent_scratchpad}', format_instructions: str = 'Use a json blob to specify a tool by providing an action key (tool name) and an action_input key (tool input).\n\nValid "action" values: "Final Answer" or {tool_names}\n\nProvide only ONE action per $JSON_BLOB, as shown:\n\n```\n{{{{\n "action": $TOOL_NAME,\n "action_input": $INPUT\n}}}}\n```\n\nFollow this format:\n\nQuestion: input question to answer\nThought: consider previous and subsequent steps\nAction:\n```\n$JSON_BLOB\n```\nObservation: action result\n... (repeat Thought/Action/Observation N times)\nThought: I know what to respond\nAction:\n```\n{{{{\n "action": "Final Answer",\n "action_input": "Final response to human"\n}}}}\n```', input_variables: Optional[List[str]] = None, memory_prompts: Optional[List[BasePromptTemplate]] = None) BasePromptTemplate [source]ΒΆ
Create a prompt for this class.
- dict(**kwargs: Any) Dict ΒΆ
Return dictionary representation of agent.
- classmethod from_llm_and_tools(llm: BaseLanguageModel, tools: Sequence[BaseTool], callback_manager: Optional[BaseCallbackManager] = None, output_parser: Optional[AgentOutputParser] = None, prefix: str = 'Respond to the human as helpfully and accurately as possible. You have access to the following tools:', suffix: str = 'Begin! Reminder to ALWAYS respond with a valid json blob of a single action. Use tools if necessary. Respond directly if appropriate. Format is Action:```$JSON_BLOB```then Observation:.\nThought:', human_message_template: str = '{input}\n\n{agent_scratchpad}', format_instructions: str = 'Use a json blob to specify a tool by providing an action key (tool name) and an action_input key (tool input).\n\nValid "action" values: "Final Answer" or {tool_names}\n\nProvide only ONE action per $JSON_BLOB, as shown:\n\n```\n{{{{\n "action": $TOOL_NAME,\n "action_input": $INPUT\n}}}}\n```\n\nFollow this format:\n\nQuestion: input question to answer\nThought: consider previous and subsequent steps\nAction:\n```\n$JSON_BLOB\n```\nObservation: action result\n... (repeat Thought/Action/Observation N times)\nThought: I know what to respond\nAction:\n```\n{{{{\n "action": "Final Answer",\n "action_input": "Final response to human"\n}}}}\n```', input_variables: Optional[List[str]] = None, memory_prompts: Optional[List[BasePromptTemplate]] = None, **kwargs: Any) Agent [source]ΒΆ
Construct an agent from an LLM and tools.
- classmethod from_orm(obj: Any) Model ΒΆ
- get_allowed_tools() Optional[List[str]] ΒΆ
- get_full_inputs(intermediate_steps: List[Tuple[AgentAction, str]], **kwargs: Any) Dict[str, Any] ΒΆ
Create the full inputs for the LLMChain from intermediate steps.
- json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False, encoder: Optional[Callable[[Any], Any]] = None, models_as_dict: bool = True, **dumps_kwargs: Any) unicode ΒΆ
Generate a JSON representation of the model, include and exclude arguments as per dict().
encoder is an optional function to supply as default to json.dumps(), other arguments as per json.dumps().
- classmethod parse_file(path: Union[str, Path], *, content_type: unicode = None, encoding: unicode = 'utf8', proto: Protocol = None, allow_pickle: bool = False) Model ΒΆ
- classmethod parse_obj(obj: Any) Model ΒΆ
- classmethod parse_raw(b: Union[str, bytes], *, content_type: unicode = None, encoding: unicode = 'utf8', proto: Protocol = None, allow_pickle: bool = False) Model ΒΆ
- plan(intermediate_steps: List[Tuple[AgentAction, str]], callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, **kwargs: Any) Union[AgentAction, AgentFinish] ΒΆ
Given input, decided what to do.
- Parameters
intermediate_steps β Steps the LLM has taken to date, along with observations
callbacks β Callbacks to run.
**kwargs β User inputs.
- Returns
Action specifying what tool to use.
- return_stopped_response(early_stopping_method: str, intermediate_steps: List[Tuple[AgentAction, str]], **kwargs: Any) AgentFinish ΒΆ
Return response when agent has been stopped due to max iterations.
- save(file_path: Union[Path, str]) None ΒΆ
Save the agent.
- Parameters
file_path β Path to file to save the agent to.
Example: .. code-block:: python
# If working with agent executor agent.agent.save(file_path=βpath/agent.yamlβ)
- classmethod schema(by_alias: bool = True, ref_template: unicode = '#/definitions/{model}') DictStrAny ΒΆ
- classmethod schema_json(*, by_alias: bool = True, ref_template: unicode = '#/definitions/{model}', **dumps_kwargs: Any) unicode ΒΆ
- tool_run_logging_kwargs() Dict ΒΆ
- classmethod update_forward_refs(**localns: Any) None ΒΆ
Try to update ForwardRefs on fields based on this Model, globalns and localns.
- classmethod validate(value: Any) Model ΒΆ
- property llm_prefix: strΒΆ
Prefix to append the llm call with.
- property observation_prefix: strΒΆ
Prefix to append the observation with.
- property return_values: List[str]ΒΆ
Return values of the agent.