Skip to content

Commit 60e6f53

Browse files
committed
Sequence Removal
1 parent 7fc322f commit 60e6f53

File tree

2 files changed

+5
-17
lines changed

2 files changed

+5
-17
lines changed

src/demo/sequence_test.py

Lines changed: 0 additions & 12 deletions
Original file line numberDiff line numberDiff line change
@@ -146,24 +146,12 @@ def generate_itinerary(destination, start_date, end_date):
146146
}
147147
]
148148
)
149-
example2 = Example(
150-
input={"destination": "Tokyo", "start_date": "2025-06-01", "end_date": "2025-06-02"},
151-
expected_tools=[
152-
{"tool_name": "search_tavily", "parameters": {"query": "Best tourist attractions in Tokyo"}},
153-
{"tool_name": "search_tavily", "parameters": {"query": "Best hotels in Tokyo"}},
154-
{"tool_name": "search_tavily", "parameters": {"query": "Flights to Tokyo from major cities"}},
155-
{"tool_name": "search_tavily", "parameters": {"query": "Weather forecast for Tokyo from 2025-06-01 to 2025-06-03"}}
156-
]
157-
)
158149

159150
judgment.assert_test(
160-
project_name="travel_agent_demo",
161151
examples=[example],
162152
scorers=[ToolOrderScorer()],
163-
model="gpt-4.1-mini",
164153
function=generate_itinerary,
165154
tracer=tracer,
166-
override=True
167155
)
168156

169157

src/judgeval/run_evaluation.py

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -201,9 +201,9 @@ def check_missing_scorer_data(results: List[ScoringResult]) -> List[ScoringResul
201201
)
202202
return results
203203

204-
def check_experiment_type(eval_name: str, project_name: str, judgment_api_key: str, organization_id: str, is_sequence: bool) -> None:
204+
def check_experiment_type(eval_name: str, project_name: str, judgment_api_key: str, organization_id: str, is_trace: bool) -> None:
205205
"""
206-
Checks if the current experiment, if one exists, has the same type (examples of sequences)
206+
Checks if the current experiment, if one exists, has the same type (examples of traces)
207207
"""
208208
try:
209209
response = requests.post(
@@ -217,7 +217,7 @@ def check_experiment_type(eval_name: str, project_name: str, judgment_api_key: s
217217
"eval_name": eval_name,
218218
"project_name": project_name,
219219
"judgment_api_key": judgment_api_key,
220-
"is_sequence": is_sequence
220+
"is_trace": is_trace
221221
},
222222
verify=True
223223
)
@@ -379,7 +379,7 @@ def run_trace_eval(trace_run: TraceRun, override: bool = False, ignore_errors: b
379379
)
380380

381381
if trace_run.append:
382-
# Check that the current experiment, if one exists, has the same type (examples of sequences)
382+
# Check that the current experiment, if one exists, has the same type (examples or traces)
383383
check_experiment_type(
384384
trace_run.eval_name,
385385
trace_run.project_name,
@@ -462,7 +462,7 @@ def run_eval(evaluation_run: EvaluationRun, override: bool = False, ignore_error
462462
)
463463

464464
if evaluation_run.append:
465-
# Check that the current experiment, if one exists, has the same type (examples of sequences)
465+
# Check that the current experiment, if one exists, has the same type (examples of traces)
466466
check_experiment_type(
467467
evaluation_run.eval_name,
468468
evaluation_run.project_name,

0 commit comments

Comments
 (0)