try example again and add additional documentation

app.py

@@ -7,6 +7,23 @@ from evaluate.utils import infer_gradio_input_types, json_to_string_type, parse_
 from fixed_f1 import FixedF1
 from pathlib import Path
 
+added_description = """
+See the HF Space showing off how to combine various metrics here: 
+    [MarioBarbeque/CombinedEvaluationMetrics](https://huggingface.co/spaces/MarioBarbeque/CombinedEvaluationMetrics)
+
+In the specific use case of the `F1Fixed` metric, one writes the following:\n
+
+```python
+f1 = FixedF1(average=...)
+
+f1.add_batch(predictions=..., references=...)
+f1.compute()
+```\n
+
+where the `average` parameter can be different at instantiation time for each of the metrics. Acceptable values include `[None, 'micro', 'macro', 'weighted']` (
+or `binary` if there exist only two labels). \n
+"""
+
 metric = FixedF1()
 
 if isinstance(metric.features, list):
@@ -30,7 +47,7 @@ def compute(input_df: pd.DataFrame, method: str):
     metric.add_batch(predictions=predicted, references=references)
     outputs = metric.compute()
 
-    return f"Your metrics are as follows: \n {outputs}"
+    return f"The F1 score for these predictions is: \n {outputs}"
 
 space = gr.Interface(
     fn=compute,
@@ -48,11 +65,14 @@ space = gr.Interface(
         )
     ],
     outputs=gr.Textbox(label=metric.name),
-    description=metric.info.description,
+    description=metric.info.description + added_description,
     title=f"Metric: {metric.name}",
     article=parse_readme(local_path / "README.md"),
     examples=[
-        # [pd.DataFrame(parse_test_cases(test_cases, feature_names, gradio_input_types)[0]), "weighted"],
+        [
+            pd.DataFrame(parse_test_cases(test_cases, feature_names, gradio_input_types)[0]), 
+            "weighted"
+        ],
     ],
     cache_examples=False
     )