Bugfix/sample pipeline cc 25m (#461)

This PR:

- adds the missing fields `surt_url` and `top_level_domain` needed to
run the sample CC pipeline
-  adjusts `n_rows_to_load` to 100k to match the HF dataset card

---------

Co-authored-by: Matthias Richter <matthias.r1092@gmail.com>

examples/pipelines/filter-cc-25m/components/load_from_hf_hub/fondant_component.yaml

@@ -1,6 +1,6 @@
 name: Load from hub
 description: Component that loads a dataset from the hub
-image: ghcr.io/ml6team/load_from_hf_hub:dev
+image: ghcr.io/ml6team/load_from_hf_hub:latest
 
 produces:
   images:
@@ -15,6 +15,10 @@ produces:
         type: string
       webpage+url:
         type: string
+      surt+url:
+        type: string
+      top+level+domain:
+        type: string
 
 args:
   dataset_name:

examples/pipelines/filter-cc-25m/filter_pipeline.py

@@ -30,14 +30,16 @@ def create_directory_if_not_exists(path):
     "license_location": "images_license+location",
     "license_type": "images_license+type",
     "webpage_url": "images_webpage+url",
+    "surt_url": "images_surt+url",
+    "top_level_domain": "images_top+level+domain",
 }
 
 load_from_hf_hub = ComponentOp(
     component_dir="components/load_from_hf_hub",
     arguments={
         "dataset_name": "fondant-ai/fondant-cc-25m",
         "column_name_mapping": load_component_column_mapping,
-        "n_rows_to_load": 1000,  # Here you can modify the number of images you want to download.
+        "n_rows_to_load": 10000,  # Here you can modify the number of images you want to download.
     },
 )
 

examples/pipelines/filter-cc-25m/pipeline.py

@@ -30,22 +30,19 @@ def create_directory_if_not_exists(path):
     "license_location": "images_license+location",
     "license_type": "images_license+type",
     "webpage_url": "images_webpage+url",
+    "surt_url": "images_surt+url",
+    "top_level_domain": "images_top+level+domain",
 }
 
 load_from_hf_hub = ComponentOp(
     component_dir="components/load_from_hf_hub",
     arguments={
         "dataset_name": "fondant-ai/fondant-cc-25m",
         "column_name_mapping": load_component_column_mapping,
-        "n_rows_to_load": 1000,  # Here you can modify the number of images you want to download.
+        "n_rows_to_load": 10000,  # Here you can modify the number of images you want to download.
     },
 )
 
-# Filter mime type component
-filter_mime_type = ComponentOp(
-    component_dir="components/filter_file_type", arguments={"mime_type": "image/png"}
-)
-
 # Download images component
 download_images = ComponentOp.from_registry(name="download_images", arguments={})