pr comm

Author: nina-kollman

packages/sample-app/sample_app/experiment/made_by_traceloop/compliance_exp.py

@@ -86,7 +86,7 @@ async def run_content_compliance_experiment():
 
     # Run the experiment
     results, errors = await client.experiment.run(
-        dataset_slug="content-compliance",  # Set a ddataset slug that exists in the traceloop platform
+        dataset_slug="content-compliance",  # Set a dataset slug that exists in the traceloop platform
         dataset_version="v1",
         task=content_safety_task,
         evaluators=evaluators,

packages/sample-app/sample_app/experiment/made_by_traceloop/correctness_exp.py

@@ -76,12 +76,8 @@ async def run_correctness_experiment():
 
     # Configure correctness evaluators
     evaluators = [
-        EvaluatorMadeByTraceloop.answer_relevancy(
-            description="Check if the answer is relevant to the question"
-        ),
-        EvaluatorMadeByTraceloop.faithfulness(
-            description="Verify the answer is faithful to the context"
-        ),
+        EvaluatorMadeByTraceloop.answer_relevancy(),
+        EvaluatorMadeByTraceloop.faithfulness(),
     ]
 
     print("Running experiment with evaluators:")
@@ -92,7 +88,7 @@ async def run_correctness_experiment():
 
     # Run the experiment
     results, errors = await client.experiment.run(
-        dataset_slug="correctness",  # Set a ddataset slug that exists in the traceloop platform
+        dataset_slug="correctness",  # Set a dataset slug that exists in the traceloop platform
         dataset_version="v1",
         task=quality_task,
         evaluators=evaluators,

packages/sample-app/sample_app/experiment/made_by_traceloop/formatting_exp.py

@@ -125,7 +125,7 @@ async def run_formatting_experiment():
 
     # Run the experiment
     results, errors = await client.experiment.run(
-        dataset_slug="formatting",  # Set a ddataset slug that exists in the traceloop platform
+        dataset_slug="formatting",  # Set a dataset slug that exists in the traceloop platform
         dataset_version="v1",
         task=validation_task,
         evaluators=evaluators,

packages/sample-app/sample_app/experiment/made_by_traceloop/quality_exp.py

@@ -102,7 +102,7 @@ async def run_advanced_quality_experiment():
 
     # Run the experiment
     results, errors = await client.experiment.run(
-        dataset_slug="quality",  # Set a ddataset slug that exists in the traceloop platform
+        dataset_slug="quality",  # Set a dataset slug that exists in the traceloop platform
         dataset_version="v1",
         task=advanced_quality_task,
         evaluators=evaluators,

packages/sample-app/sample_app/experiment/made_by_traceloop/security_exp.py

@@ -82,7 +82,7 @@ async def run_security_experiment():
 
     # Run the experiment
     results, errors = await client.experiment.run(
-        dataset_slug="security",  # Set a ddataset slug that exists in the traceloop platform
+        dataset_slug="security",  # Set a dataset slug that exists in the traceloop platform
         dataset_version="v1",
         task=security_task,
         evaluators=evaluators,

packages/sample-app/sample_app/experiment/made_by_traceloop/style_exp.py

@@ -88,7 +88,7 @@ async def run_style_experiment():
 
     # Run the experiment
     results, errors = await client.experiment.run(
-        dataset_slug="style",  # Set a ddataset slug that exists in the traceloop platform
+        dataset_slug="style",  # Set a dataset slug that exists in the traceloop platform
         dataset_version="v1",
         task=style_task,
         evaluators=evaluators,