Skip to content

armgit / camel

Public Imported from GitHub
0

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

Auto-update documentation after merge [skip ci]

camel-docs-bot4cee64d690c9
diff --git a/docs/mintlify/reference/camel.agents.chat_agent.mdx b/docs/mintlify/reference/camel.agents.chat_agent.mdx
index 067669802..cc4593ceb 100644
--- a/docs/mintlify/reference/camel.agents.chat_agent.mdx
+++ b/docs/mintlify/reference/camel.agents.chat_agent.mdx
@@ -241,6 +241,9 @@ Class for managing conversations of CAMEL Chat Agents.
- **mask_tool_output** (Optional[bool]): Whether to return a sanitized placeholder instead of the raw tool output. (default: :obj:`False`)
- **pause_event** (Optional[asyncio.Event]): Event to signal pause of the agent's operation. When clear, the agent will pause its execution. (default: :obj:`None`)
- **prune_tool_calls_from_memory** (bool): Whether to clean tool call messages from memory after response generation to save token usage. When enabled, removes FUNCTION/TOOL role messages and ASSISTANT messages with tool_calls after each step. (default: :obj:`False`)
+- **retry_attempts** (int, optional): Maximum number of retry attempts for rate limit errors. (default: :obj:`3`)
+- **retry_delay** (float, optional): Initial delay in seconds between retries. Uses exponential backoff. (default: :obj:`1.0`)
+- **step_timeout** (Optional[float], optional): Timeout in seconds for the entire step operation. If None, no timeout is applied. (default: :obj:`None`)
<a id="camel.agents.chat_agent.ChatAgent.__init__"></a>
@@ -266,7 +269,10 @@ def __init__(
tool_execution_timeout: Optional[float] = None,
mask_tool_output: bool = False,
pause_event: Optional[asyncio.Event] = None,
- prune_tool_calls_from_memory: bool = False
+ prune_tool_calls_from_memory: bool = False,
+ retry_attempts: int = 3,
+ retry_delay: float = 1.0,
+ step_timeout: Optional[float] = None
):
```
@@ -751,6 +757,20 @@ a StreamingChatAgentResponse that behaves like
ChatAgentResponse but can also be iterated for
streaming updates.
+<a id="camel.agents.chat_agent.ChatAgent._step_impl"></a>
+
+### _step_impl
+
+```python
+def _step_impl(
+ self,
+ input_message: Union[BaseMessage, str],
+ response_format: Optional[Type[BaseModel]] = None
+):
+```
+
+Implementation of non-streaming step logic.
+
<a id="camel.agents.chat_agent.ChatAgent.chat_history"></a>
### chat_history
@@ -833,19 +853,6 @@ def _get_model_response(
Internal function for agent step model response.
-**Parameters:**
-
-- **openai_messages** (List[OpenAIMessage]): The OpenAI messages to process.
-- **num_tokens** (int): The number of tokens in the context.
-- **current_iteration** (int): The current iteration of the step.
-- **response_format** (Optional[Type[BaseModel]]): The response format to use.
-- **tool_schemas** (Optional[List[Dict[str, Any]]]): The tool schemas to use.
-- **prev_num_openai_messages** (int): The number of openai messages logged in the previous iteration.
-
-**Returns:**
-
- ModelResponse: The model response.
-
<a id="camel.agents.chat_agent.ChatAgent._sanitize_messages_for_logging"></a>
### _sanitize_messages_for_logging