Update load_data.py

load_data.py

@@ -9,11 +9,12 @@ from datasets import load_dataset, concatenate_datasets
 
 from argilla.listeners import listener
 
-HF_TOKEN = os.environ.get("HF_TOKEN") #set HF_TOKEN
-HUB_DATASET_NAME = os.environ.get('HUB_DATASET_NAME') #set dataset name
+HF_TOKEN = os.environ.get("HF_TOKEN") #get HF_TOKEN
+HUB_DATASET_NAME = os.environ.get('HUB_DATASET_NAME') #get dataset name
+
 
 @listener(
-    dataset="somos-alpaca-es", 
+    dataset="job-title-tagging", 
     query="status:Validated", # https://docs.argilla.io/en/latest/guides/features/queries.html
     execution_interval_in_seconds=1200, # interval to check the execution of `save_validated_to_hub`
 )
@@ -44,7 +45,7 @@ class LoadDatasets:
             print(e)
             old_ds = None
             
-        dataset = load_dataset("somosnlp/somos-clean-alpaca-es", split="train")
+        dataset = load_dataset("LukasGe/argilla-test", split="train")
     
         
         if old_ds:
@@ -64,8 +65,8 @@ class LoadDatasets:
         # Log the dataset
         rg.log(
             records,
-            name="somos-alpaca-es",
-            tags={"description": "SomosNLP Hackathon dataset"},
+            name="job-title-tagging",
+            tags={"description": "Tagging of the DVS Job Titles"},
             batch_size=200
         )