Reasoning
Reasoning agent model.
WaldiezReasoningAgent ¶
Bases: WaldiezAgent
Reasoning agent model.
WaldiezReasoningAgentData ¶
Bases: WaldiezAgentData
Reasoning agent data model.
answer_approach property
¶
answer_approach: str
Get the answer approach of the reasoning agent.
Returns:
Type | Description |
---|---|
str | The answer approach of the reasoning agent. |
beam_size property
¶
beam_size: int
Get the beam size of the reasoning agent.
Returns:
Type | Description |
---|---|
int | The beam size of the reasoning agent. |
exploration_constant property
¶
exploration_constant: float
Get the exploration constant of the reasoning agent.
Returns:
Type | Description |
---|---|
float | The exploration constant of the reasoning agent. |
forest_size property
¶
forest_size: int
Get the forest size of the reasoning agent.
Returns:
Type | Description |
---|---|
int | The forest size of the reasoning agent. |
get_reasoning_config ¶
Get the reasoning configuration based on the reason_config method.
Returns:
Type | Description |
---|---|
dict[str, Any] | The reasoning configuration. |
Source code in waldiez/models/agents/reasoning/reasoning_agent_data.py
max_depth property
¶
max_depth: int
Get the maximum depth of the reasoning agent.
Returns:
Type | Description |
---|---|
int | The maximum depth of the reasoning agent. |
WaldiezReasoningAgentReasonConfig ¶
Bases: WaldiezBase
Reasoning agent's reason configuration model.
Configuration for the reasoning method.
Attributes:
Name | Type | Description |
---|---|---|
method | Literal['beam_search', 'mcts', 'lats', 'dfs'] | The search strategy to use, default is "beam_search". |
max_depth | int | Maximum depth of reasoning tree, default is 3. |
forest_size | int | Number of independent trees to maintain, default is 1. |
rating_scale | int | Scale for grading responses, e.g. 1-10, default is 10. |
beam_size | int | Number of parallel paths to maintain, default is 3 (for beam_search). |
answer_approach | Literal['pool', 'best'] | How to select final answer, default is "pool" (only for beam_search). |
nsim | int | Number of simulations to run, default is 3 (only for mcts and lats). |
exploration_constant | float | UCT exploration parameter, default is 1.41 (only for mcts and lats). |
reasoning_agent ¶
Reasoning agent model.
WaldiezReasoningAgent ¶
Bases: WaldiezAgent
Reasoning agent model.
reasoning_agent_data ¶
Reasoning agent data model.
WaldiezReasoningAgentData ¶
Bases: WaldiezAgentData
Reasoning agent data model.
answer_approach property
¶
answer_approach: str
Get the answer approach of the reasoning agent.
Returns:
Type | Description |
---|---|
str | The answer approach of the reasoning agent. |
beam_size property
¶
beam_size: int
Get the beam size of the reasoning agent.
Returns:
Type | Description |
---|---|
int | The beam size of the reasoning agent. |
exploration_constant property
¶
exploration_constant: float
Get the exploration constant of the reasoning agent.
Returns:
Type | Description |
---|---|
float | The exploration constant of the reasoning agent. |
forest_size property
¶
forest_size: int
Get the forest size of the reasoning agent.
Returns:
Type | Description |
---|---|
int | The forest size of the reasoning agent. |
get_reasoning_config ¶
Get the reasoning configuration based on the reason_config method.
Returns:
Type | Description |
---|---|
dict[str, Any] | The reasoning configuration. |
Source code in waldiez/models/agents/reasoning/reasoning_agent_data.py
max_depth property
¶
max_depth: int
Get the maximum depth of the reasoning agent.
Returns:
Type | Description |
---|---|
int | The maximum depth of the reasoning agent. |
reasoning_agent_reason_config ¶
Reasoning agent's reason configuration model.
ReasonConfigMethod module-attribute
¶
ReasonConfigMethod = Literal[
"beam_search", "mcts", "lats", "dfs"
]
Possible reasoning methods.
WaldiezReasoningAgentReasonConfig ¶
Bases: WaldiezBase
Reasoning agent's reason configuration model.
Configuration for the reasoning method.
Attributes:
Name | Type | Description |
---|---|---|
method | Literal['beam_search', 'mcts', 'lats', 'dfs'] | The search strategy to use, default is "beam_search". |
max_depth | int | Maximum depth of reasoning tree, default is 3. |
forest_size | int | Number of independent trees to maintain, default is 1. |
rating_scale | int | Scale for grading responses, e.g. 1-10, default is 10. |
beam_size | int | Number of parallel paths to maintain, default is 3 (for beam_search). |
answer_approach | Literal['pool', 'best'] | How to select final answer, default is "pool" (only for beam_search). |
nsim | int | Number of simulations to run, default is 3 (only for mcts and lats). |
exploration_constant | float | UCT exploration parameter, default is 1.41 (only for mcts and lats). |