fix: duplicated labels in labels and number of rows update listener in raw pipeline

src/distilabel_dataset_generator/apps/textcat.py

@@ -279,11 +279,13 @@ def generate_dataset(
         else:
             dataframe["labels"] = dataframe["labels"].apply(
                 lambda x: (
-                    [
-                        label.lower().strip()
-                        for label in x
-                        if label.lower().strip() in labels
-                    ]
+                    list(
+                        set(
+                            label.lower().strip()
+                            for label in x
+                            if label.lower().strip() in labels
+                        )
+                    )
                     if isinstance(x, list)
                     else None
                 )
@@ -556,3 +558,8 @@ with app:
         inputs=[system_prompt, difficulty, clarity, labels, num_labels, num_rows],
         outputs=[pipeline_code],
     )
+    num_rows.change(
+        fn=generate_pipeline_code,
+        inputs=[system_prompt, difficulty, clarity, labels, num_labels, num_rows],
+        outputs=[pipeline_code],
+    )

src/distilabel_dataset_generator/pipelines/textcat.py

@@ -199,7 +199,7 @@ def get_labeller_generator(system_prompt, labels, num_labels):
             tokenizer_id=MODEL,
             api_key=_get_next_api_key(),
             generation_kwargs={
-                "temperature": 0.8,
+                "temperature": 0.7,
                 "max_new_tokens": 2048,
             },
         ),