ChatAgent#
- class langchain.agents.chat.base.ChatAgent[source]#
Bases:
Agent
Deprecated since version 0.1.0: Use
create_react_agent
instead.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: List[str] | None = None#
Allowed tools for the agent. If None, all tools are allowed.
- param output_parser: AgentOutputParser [Optional]#
Output parser for the agent.
- async aplan(intermediate_steps: List[Tuple[AgentAction, str]], callbacks: List[BaseCallbackHandler] | BaseCallbackManager | None = None, **kwargs: Any) AgentAction | AgentFinish #
Async given input, decided what to do.
- Parameters:
intermediate_steps (List[Tuple[AgentAction, str]]) β Steps the LLM has taken to date, along with observations.
callbacks (List[BaseCallbackHandler] | BaseCallbackManager | None) β Callbacks to run.
**kwargs (Any) β User inputs.
- Returns:
Action specifying what tool to use.
- Return type:
- classmethod create_prompt(tools: Sequence[BaseTool], system_message_prefix: str = 'Answer the following questions as best you can. You have access to the following tools:', system_message_suffix: str = 'Begin! Reminder to always use the exact characters `Final Answer` when responding.', human_message: str = '{input}\n\n{agent_scratchpad}', format_instructions: str = 'The way you use the tools is by specifying a json blob.\nSpecifically, this json should have a `action` key (with the name of the tool to use) and a `action_input` key (with the input to the tool going here).\n\nThe only values that should be in the "action" field are: {tool_names}\n\nThe $JSON_BLOB should only contain a SINGLE action, do NOT return a list of multiple actions. Here is an example of a valid $JSON_BLOB:\n\n```\n{{{{\nΒ "action": $TOOL_NAME,\nΒ "action_input": $INPUT\n}}}}\n```\n\nALWAYS use the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction:\n```\n$JSON_BLOB\n```\nObservation: the result of the action\n... (this Thought/Action/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question', input_variables: List[str] | None = None) BasePromptTemplate [source]#
Create a prompt from a list of tools.
- Parameters:
tools (Sequence[BaseTool]) β A list of tools.
system_message_prefix (str) β The system message prefix. Default is SYSTEM_MESSAGE_PREFIX.
system_message_suffix (str) β The system message suffix. Default is SYSTEM_MESSAGE_SUFFIX.
human_message (str) β The human message. Default is HUMAN_MESSAGE.
format_instructions (str) β The format instructions. Default is FORMAT_INSTRUCTIONS.
input_variables (List[str] | None) β The input variables. Default is None.
- Returns:
A prompt template.
- Return type:
- classmethod from_llm_and_tools(llm: BaseLanguageModel, tools: Sequence[BaseTool], callback_manager: BaseCallbackManager | None = None, output_parser: AgentOutputParser | None = None, system_message_prefix: str = 'Answer the following questions as best you can. You have access to the following tools:', system_message_suffix: str = 'Begin! Reminder to always use the exact characters `Final Answer` when responding.', human_message: str = '{input}\n\n{agent_scratchpad}', format_instructions: str = 'The way you use the tools is by specifying a json blob.\nSpecifically, this json should have a `action` key (with the name of the tool to use) and a `action_input` key (with the input to the tool going here).\n\nThe only values that should be in the "action" field are: {tool_names}\n\nThe $JSON_BLOB should only contain a SINGLE action, do NOT return a list of multiple actions. Here is an example of a valid $JSON_BLOB:\n\n```\n{{{{\nΒ "action": $TOOL_NAME,\nΒ "action_input": $INPUT\n}}}}\n```\n\nALWAYS use the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction:\n```\n$JSON_BLOB\n```\nObservation: the result of the action\n... (this Thought/Action/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question', input_variables: List[str] | None = None, **kwargs: Any) Agent [source]#
Construct an agent from an LLM and tools.
- Parameters:
llm (BaseLanguageModel) β The language model.
tools (Sequence[BaseTool]) β A list of tools.
callback_manager (BaseCallbackManager | None) β The callback manager. Default is None.
output_parser (AgentOutputParser | None) β The output parser. Default is None.
system_message_prefix (str) β The system message prefix. Default is SYSTEM_MESSAGE_PREFIX.
system_message_suffix (str) β The system message suffix. Default is SYSTEM_MESSAGE_SUFFIX.
human_message (str) β The human message. Default is HUMAN_MESSAGE.
format_instructions (str) β The format instructions. Default is FORMAT_INSTRUCTIONS.
input_variables (List[str] | None) β The input variables. Default is None.
kwargs (Any) β Additional keyword arguments.
- Returns:
An agent.
- Return type:
- get_allowed_tools() List[str] | None #
Get allowed tools.
- Return type:
List[str] | None
- get_full_inputs(intermediate_steps: List[Tuple[AgentAction, str]], **kwargs: Any) Dict[str, Any] #
Create the full inputs for the LLMChain from intermediate steps.
- Parameters:
intermediate_steps (List[Tuple[AgentAction, str]]) β Steps the LLM has taken to date, along with observations.
**kwargs (Any) β User inputs.
- Returns:
Full inputs for the LLMChain.
- Return type:
Dict[str, Any]
- plan(intermediate_steps: List[Tuple[AgentAction, str]], callbacks: List[BaseCallbackHandler] | BaseCallbackManager | None = None, **kwargs: Any) AgentAction | AgentFinish #
Given input, decided what to do.
- Parameters:
intermediate_steps (List[Tuple[AgentAction, str]]) β Steps the LLM has taken to date, along with observations.
callbacks (List[BaseCallbackHandler] | BaseCallbackManager | None) β Callbacks to run.
**kwargs (Any) β User inputs.
- Returns:
Action specifying what tool to use.
- Return type:
- return_stopped_response(early_stopping_method: str, intermediate_steps: List[Tuple[AgentAction, str]], **kwargs: Any) AgentFinish #
Return response when agent has been stopped due to max iterations.
- Parameters:
early_stopping_method (str) β Method to use for early stopping.
intermediate_steps (List[Tuple[AgentAction, str]]) β Steps the LLM has taken to date, along with observations.
**kwargs (Any) β User inputs.
- Returns:
Agent finish object.
- Return type:
- Raises:
ValueError β If early_stopping_method is not in [βforceβ, βgenerateβ].
- save(file_path: Path | str) None #
Save the agent.
- Parameters:
file_path (Path | str) β Path to file to save the agent to.
- Return type:
None
Example: .. code-block:: python
# If working with agent executor agent.agent.save(file_path=βpath/agent.yamlβ)
- tool_run_logging_kwargs() Dict #
Return logging kwargs for tool run.
- Return type:
Dict
- property llm_prefix: str#
Prefix to append the llm call with.
- property observation_prefix: str#
Prefix to append the observation with.
- property return_values: List[str]#
Return values of the agent.