Update GUI to differentiate private / public datasets (#1)

- Update GUI to differentiate private / public datasets (c14707a572ca962572423e208b48f689c436b043)


Co-authored-by: Christopher Akiki <[email protected]>

app.py

@@ -7,19 +7,32 @@ import string
 
 import gradio as gr
 import requests
+from huggingface_hub import HfApi
 
+hf_api = HfApi()
+roots_datasets = {dset.id.split("/")[-1]:dset for dset in hf_api.list_datasets(author="bigscience-data", use_auth_token=os.environ.get("bigscience_data_token"))}
 
 def get_docid_html(docid):
     data_org, dataset, docid = docid.split("/")
-
-    docid_html = """<a
-        class="underline-on-hover"
-        title="I am hovering over the text"
-        style="color:#2D31FA;"
-        href="https://huggingface.co/datasets/bigscience-data/{}"
-        target="_blank">{}</a><span style="color: #7978FF;">/{}</span>""".format(
-        dataset, data_org + "/" + dataset, docid
-    )
+    metadata = roots_datasets[dataset]
+    if metadata.private:
+        docid_html = (
+            f"<a "
+            f'class="underline-on-hover"'
+            f'title="This dataset is private. See the introductory text for more information"'
+            f'style="color:#AA4A44;"'
+            f'href="https://huggingface.co/datasets/bigscience-data/{dataset}"'
+            f'target="_blank"><b>🔒{dataset}</b></a><span style="color: #7978FF;">/{docid}</span>'
+        )
+    else:
+        docid_html = (
+            f"<a "
+            f'class="underline-on-hover"'
+            f'title="This dataset is licensed {metadata.tags[0].split(":")[-1]}"'
+            f'style="color:#2D31FA;"'
+            f'href="https://huggingface.co/datasets/bigscience-data/{dataset}"'
+            f'target="_blank"><b>{dataset}</b></a><span style="color: #7978FF;">/{docid}</span>'
+        )        
     return docid_html