Skip to content

add tracing feature to evaluator script #111

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Sep 1, 2024
Merged

add tracing feature to evaluator script #111

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 14 additions & 0 deletions apps/11_promptflow/evaluators/main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@
from promptflow.core import AzureOpenAIModelConfiguration
from promptflow.evals.evaluate import evaluate
from promptflow.evals.evaluators import RelevanceEvaluator
from promptflow.tracing import start_trace, trace

BASE_DIR = Path(__file__).absolute().parent

Expand All @@ -32,6 +33,12 @@ def init_args() -> argparse.Namespace:
choices=[t.value for t in EvaluatorType],
help="Evaluator type",
)
parser.add_argument(
"-r",
"--trace",
action="store_true",
help="Enable tracing",
)
parser.add_argument(
"-v",
"--verbose",
Expand All @@ -41,6 +48,7 @@ def init_args() -> argparse.Namespace:
return parser.parse_args()


@trace
def run_relevance_evaluator(model_config):
relevance_eval = RelevanceEvaluator(model_config)

Expand All @@ -63,6 +71,7 @@ def __call__(self, *, answer: str, **kwargs):
return {"answer_length": len(answer)}


@trace
def run_answer_length_evaluator():
evaluator = AnswerLengthEvaluator()
answer_length = evaluator(answer="What is the speed of light?")
Expand All @@ -76,6 +85,7 @@ def get_apology_evaluator(model_config):
)


@trace
def run_apology_evaluator(model_config):
apology_eval = get_apology_evaluator(model_config)

Expand All @@ -87,6 +97,7 @@ def run_apology_evaluator(model_config):
print(apology_score)


@trace
def run_test_dataset(model_config):
result = evaluate(
data=f"{BASE_DIR}/data.jsonl", # provide your data here
Expand All @@ -112,6 +123,9 @@ def run_test_dataset(model_config):
if args.verbose:
logging.basicConfig(level=logging.DEBUG)

if args.trace:
start_trace()

load_dotenv()

model_config = AzureOpenAIModelConfiguration(
Expand Down