Documentation Index
Fetch the complete documentation index at: https://www.getmaxim.ai/docs/llms.txt
Use this file to discover all available pages before exploring further.
View module source on GitHub
get_log_level
def get_log_level(debug: bool) -> int
class MaximUsageCallback()
__init__
def __init__(generation_id: str)
log_success_event
def log_success_event(kwargs, response_obj, start_time, end_time)
| Name | Description |
|---|
kwargs | The kwargs. |
response_obj | The response object. |
start_time | The start time. |
end_time | The end time. |
make_handle_non_streaming_wrapper
def make_handle_non_streaming_wrapper(original_method)
instrument_crewai
def instrument_crewai(maxim_logger: Logger, debug: bool = False)
- Detailed operation tracing for Crew, Flow, and Task executions
- Token usage tracking for LLM calls
- Tool execution monitoring
- Span-based operation tracking
- Error handling and reporting
The patching is done by wrapping key methods like:
- Crew.kickoff
- Agent.execute_task
- Task.execute_sync
- LLM.call and _handle_non_streaming_response
- Tool._run methods
Arguments:
| Name | Type | Description |
|---|
maxim_logger | Logger | A Maxim Logger instance for handling the tracing and logging operations. |
debug | bool | If True, show INFO and DEBUG logs. If False, show only WARNING and ERROR logs. |
