Skip to main content

​
build_default_summary_prompt

def build_default_summary_prompt(conversation_text: str):
Create the default prompt used for conversation summarization. Parameters:
  • conversation_text (str): The conversation to be summarized.
Returns: str: A formatted prompt instructing the model to produce a structured markdown summary.

​
generate_tool_prompt

def generate_tool_prompt(tool_schema_list: List[Dict[str, Any]]):
Returns: str: A string representing the tool prompt.

​
extract_tool_call

def extract_tool_call(content: str):
Extract the tool call from the model response, if present. Parameters:
  • response (Any): The model’s response object.
Returns: Optional[Dict[str, Any]]: The parsed tool call if present, otherwise None.

​
safe_model_dump

def safe_model_dump(obj):
Safely dump a Pydantic model to a dictionary. This method attempts to use the model_dump method if available, otherwise it falls back to the dict method.

​
convert_to_function_tool

def convert_to_function_tool(tool: Union[FunctionTool, Callable]):
Convert a tool to a FunctionTool from Callable.

​
convert_to_schema

def convert_to_schema(tool: Union[FunctionTool, Callable, Dict[str, Any]]):
Convert a tool to a schema from Callable or FunctionTool.

​
get_info_dict

def get_info_dict(
    session_id: Optional[str],
    usage: Optional[Dict[str, int]],
    termination_reasons: List[str],
    num_tokens: int,
    tool_calls: List[ToolCallingRecord],
    external_tool_call_requests: Optional[List[ToolCallRequest]] = None
):
Returns a dictionary containing information about the chat session. Parameters:
  • session_id (str, optional): The ID of the chat session.
  • usage (Dict[str, int], optional): Information about the usage of the LLM.
  • termination_reasons (List[str]): The reasons for the termination of the chat session.
  • num_tokens (int): The number of tokens used in the chat session.
  • tool_calls (List[ToolCallingRecord]): The list of function calling records, containing the information of called tools.
  • external_tool_call_requests (Optional[List[ToolCallRequest]]): The requests for external tool calls.
Returns: Dict[str, Any]: The chat session information.

​
handle_logprobs

def handle_logprobs(choice: Choice):