mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-07 15:18:29 +00:00
175d5b3dd6
* feat: add training logic to agent and crew * feat: add training logic to agent executor * feat: add input parameter to cli command * feat: add utilities for the training logic * feat: polish code, logic and add private variables * feat: add docstring and type hinting to executor * feat: add constant file, add constant to code * feat: fix name of training handler function * feat: remove unused var * feat: change file handler file name * feat: Add training handler file, class and change on the code * feat: fix name error from file * fix: change import to adapt to logic * feat: add training handler test * feat: add tests for file and training_handler * feat: add test for task evaluator function * feat: change text to fit in-screen * feat: add test for train function * feat: add test for agent training_handler function * feat: add test for agent._use_trained_data
65 lines
3.1 KiB
Python
65 lines
3.1 KiB
Python
from unittest import mock
|
|
from unittest.mock import MagicMock, patch
|
|
|
|
from crewai.utilities.evaluators.task_evaluator import (
|
|
TaskEvaluator,
|
|
TrainingTaskEvaluation,
|
|
)
|
|
|
|
|
|
@patch("crewai.utilities.evaluators.task_evaluator.Converter")
|
|
def test_evaluate_training_data(converter_mock):
|
|
training_data = {
|
|
"agent_id": {
|
|
"data1": {
|
|
"initial_output": "Initial output 1",
|
|
"human_feedback": "Human feedback 1",
|
|
"improved_output": "Improved output 1",
|
|
},
|
|
"data2": {
|
|
"initial_output": "Initial output 2",
|
|
"human_feedback": "Human feedback 2",
|
|
"improved_output": "Improved output 2",
|
|
},
|
|
}
|
|
}
|
|
agent_id = "agent_id"
|
|
original_agent = MagicMock()
|
|
function_return_value = TrainingTaskEvaluation(
|
|
suggestions=[
|
|
"The initial output was already good, having a detailed explanation. However, the improved output "
|
|
"gave similar information but in a more professional manner using better vocabulary. For future tasks, "
|
|
"try to implement more elaborate language and precise terminology from the beginning."
|
|
],
|
|
quality=8.0,
|
|
final_summary="The agent responded well initially. However, the improved output showed that there is room "
|
|
"for enhancement in terms of language usage, precision, and professionalism. For future tasks, the agent "
|
|
"should focus more on these points from the start to increase performance.",
|
|
)
|
|
converter_mock.return_value.to_pydantic.return_value = function_return_value
|
|
result = TaskEvaluator(original_agent=original_agent).evaluate_training_data(
|
|
training_data, agent_id
|
|
)
|
|
|
|
assert result == function_return_value
|
|
converter_mock.assert_has_calls(
|
|
[
|
|
mock.call(
|
|
llm=original_agent.llm,
|
|
text="Assess the quality of the training data based on the llm output, human feedback , and llm "
|
|
"output improved result.\n\nInitial Output:\nInitial output 1\n\nHuman Feedback:\nHuman feedback "
|
|
"1\n\nImproved Output:\nImproved output 1\n\nInitial Output:\nInitial output 2\n\nHuman "
|
|
"Feedback:\nHuman feedback 2\n\nImproved Output:\nImproved output 2\n\nPlease provide:\n- "
|
|
"Based on the Human Feedbacks and the comparison between Initial Outputs and Improved outputs "
|
|
"provide action items based on human_feedback for future tasks\n- A score from 0 to 10 evaluating "
|
|
"on completion, quality, and overall performance from the improved output to the initial output "
|
|
"based on the human feedback\n",
|
|
model=TrainingTaskEvaluation,
|
|
instructions="I'm gonna convert this raw text into valid JSON.\n\nThe json should have the "
|
|
"following structure, with the following keys:\n- suggestions: List[str]\n- "
|
|
"quality: float\n- final_summary: str",
|
|
),
|
|
mock.call().to_pydantic(),
|
|
]
|
|
)
|