KeyArgo
/
smolagents
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Fix MultiStepAgent docstring (#336) 

* Fix MultiStepAgent docstring

* Force PR doc build
This commit is contained in:
Albert Villanova del Moral 2025-01-23 17:38:09 +01:00 committed by GitHub
parent b333e08f66
commit 0217d3fd58
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 4 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
docs/source/en/reference/agents.md
View File

@ -35,17 +35,14 @@ We provide two types of agents, based on the main [`Agent`] class.
Both require arguments `model` and list of tools `tools` at initialization. Both require arguments `model` and list of tools `tools` at initialization.
### Classes of agents ### Classes of agents
[[autodoc]] MultiStepAgent [[autodoc]] MultiStepAgent
[[autodoc]] CodeAgent [[autodoc]] CodeAgent
[[autodoc]] ToolCallingAgent [[autodoc]] ToolCallingAgent
### ManagedAgent ### ManagedAgent
[[autodoc]] ManagedAgent [[autodoc]] ManagedAgent

8
src/smolagents/agents.py
View File

@ -164,8 +164,8 @@ class MultiStepAgent:
While the objective is not reached, the agent will perform a cycle of action (given by the LLM) and observation (obtained from the environment). While the objective is not reached, the agent will perform a cycle of action (given by the LLM) and observation (obtained from the environment).
Args: Args:
tools (`list[[`Tool`]]`): List of tools that the agent can use. tools (`list[Tool]`): [`Tool`]s that the agent can use.
model (Callable[[list[dict[str, str]]], [`ChatMessage`]]): Model that will generate the agent's actions. model (`Callable[[list[dict[str, str]]], ChatMessage]`): Model that will generate the agent's actions.
system_prompt (`str`, *optional*): System prompt that will be used to generate the agent's actions. system_prompt (`str`, *optional*): System prompt that will be used to generate the agent's actions.
tool_description_template (`str`, *optional*): Template used to describe the tools in the system prompt. tool_description_template (`str`, *optional*): Template used to describe the tools in the system prompt.
max_steps (`int`, default `6`): Maximum number of steps the agent can take to solve the task. max_steps (`int`, default `6`): Maximum number of steps the agent can take to solve the task.
@ -173,8 +173,8 @@ class MultiStepAgent:
add_base_tools (`bool`, default `False`): Whether to add the base tools to the agent's tools. add_base_tools (`bool`, default `False`): Whether to add the base tools to the agent's tools.
verbosity_level (`int`, default `1`): Level of verbosity of the agent's logs. verbosity_level (`int`, default `1`): Level of verbosity of the agent's logs.
grammar (`dict[str, str]`, *optional*): Grammar used to parse the LLM output. grammar (`dict[str, str]`, *optional*): Grammar used to parse the LLM output.
managed_agents (`list`, *optional*): List of managed agents that the agent can call. managed_agents (`list`, *optional*): Managed agents that the agent can call.
step_callbacks (`list[Callable]`, *optional*): List of callbacks that will be called at each step. step_callbacks (`list[Callable]`, *optional*): Callbacks that will be called at each step.
planning_interval (`int`, *optional*): Interval at which the agent will run a planning step. planning_interval (`int`, *optional*): Interval at which the agent will run a planning step.
""" """