aiq.agent.rewoo_agent.agent

Attributes

logger

Classes

ReWOOGraphState	State schema for the ReWOO Agent Graph
ReWOOAgentGraph	Configurable LangGraph ReWOO Agent. A ReWOO Agent performs reasoning by interacting with other objects or tools

Module Contents

logger

class ReWOOGraphState(/, **data: Any)

Bases: pydantic.BaseModel

State schema for the ReWOO Agent Graph

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

task: langchain_core.messages.human.HumanMessage = None

plan: langchain_core.messages.ai.AIMessage = None

steps: langchain_core.messages.ai.AIMessage = None

intermediate_results: dict[str, langchain_core.messages.tool.ToolMessage] = None

result: langchain_core.messages.ai.AIMessage = None

class ReWOOAgentGraph(

llm: langchain_core.language_models.BaseChatModel,

planner_prompt: langchain_core.prompts.chat.ChatPromptTemplate,

solver_prompt: langchain_core.prompts.chat.ChatPromptTemplate,

tools: list[langchain_core.tools.BaseTool],

use_tool_schema: bool = True,

callbacks: list[langchain_core.callbacks.base.AsyncCallbackHandler] = None,

detailed_logs: bool = False,

)

Bases: aiq.agent.base.BaseAgent

Configurable LangGraph ReWOO Agent. A ReWOO Agent performs reasoning by interacting with other objects or tools and utilizes their outputs to make decisions. Supports retrying on output parsing errors. Argument “detailed_logs” toggles logging of inputs, outputs, and intermediate steps.

planner_prompt

solver_prompt

tools_dict

_get_tool(tool_name)

static _get_current_step(state: ReWOOGraphState) → int

static _parse_planner_output(

planner_output: str,

) → langchain_core.messages.ai.AIMessage

static _replace_placeholder(

placeholder: str,

tool_input: str | dict,

tool_output: str | dict,

) → str | dict

static _parse_tool_input(tool_input: str | dict)

async planner_node(state: ReWOOGraphState)

async executor_node(state: ReWOOGraphState)

async solver_node(state: ReWOOGraphState)

async conditional_edge(state: ReWOOGraphState)

async _build_graph(state_schema)

async build_graph()

static validate_planner_prompt(planner_prompt: str) → bool

static validate_solver_prompt(solver_prompt: str) → bool