Merge pull request #50 from Snowflake-Labs/release-11082024

Update

framework-evalanche/README.md

@@ -93,6 +93,8 @@ To remove a metric as selectable in the app, deselect it in the Manage Metrics m
 CALL GENAI_UTILITIES.EVALUATION.DELETE_METRIC('Rudeness');
 ```
 
+Lastly, please be aware that Streamlit in Snowflake now supports multiple python versions. Custom metrics may only be available with consistent Python versions. For example, if you create a custom metric while running the app with Python version 3.11, the custom metric will only be available in subsequent sessions when running Python 3.11. 
+
 ## Crafting a LLM Pipeline Stored Procedure
 To run a reference dataset through your desired LLM pipelines on the data page, we must first encapsulated the pipeline logic in a Stored Procedure. To take advantage of this feature, the stored procedure must have a single VARIANT input type and return a single value. When we execute the stored procedure, a single row from the reference dataset will be passed in the form of a Python dictionary. In other words, a row in the reference dataset that looks like:
 ```markdown

framework-evalanche/pages/results.py

@@ -378,7 +378,7 @@ def show_recommendation(selection: Union[int, None], pandas_df: pd.DataFrame) ->
                 (
                     metric
                     for metric in metrics
-                    if metric.name.upper() == selected_metric_name.upper()
+                    if metric.get_column() == selected_metric_name.upper()
                 ),
                 None,
             )

framework-evalanche/src/app_utils.py

@@ -76,8 +76,9 @@ def load_staged_pickle(session: Session, staged_file_path: str) -> Any:
     # Load the pickled instance from the file
     local_file = '/tmp/' + staged_file_path.split("/")[-1]
     with open(local_file, "rb") as f:
-       loaded_instance = pickle.load(f)
-       return loaded_instance
+        loaded_instance = pickle.load(f)
+        return loaded_instance
+
 
 def delete_metric(session: Session, metric: Metric, stage_name: str):
     """Deletes metric pickle file from Snowflake stage."""
@@ -157,7 +158,11 @@ def fetch_custom_metrics_from_stage(session: Session,
         for f in files:
             stage_file_path = f"@{stage_name}/{f.split('/')[-1]}" # Non-qualified stage name in LS from @stage results
             if stage_file_path in metrics_to_show:
-                custom_metrics.append(load_staged_pickle(session, stage_file_path))
+                try:
+                    custom_metrics.append(load_staged_pickle(session, stage_file_path))
+                except TypeError:
+                    st.warning(f"Error loading metric {stage_file_path}. This can occur if the metric was created with a different python version than what is being used.")
+                    continue
         return custom_metrics
     else:
         return []

framework-evalanche/src/snowflake_utils.py

@@ -277,5 +277,5 @@ def call_sproc(session: Session, name: str) -> Any:
     return session.call(name)
 
 
-def call_async_sproc(session: Session, sproc: str, input_value: dict[str, Any]) -> Any:
+def call_async_sproc(session: Session, sproc: str, input_value: Dict[str, Any]) -> Any:
     return session.sql(f"CALL {sproc}({input_value})").collect_nowait().result()[0][0]