Upload folder using huggingface_hub

Dockerfile

@@ -1,6 +1,6 @@
 FROM python:3.10
 
-ARG SPOTLIGHT_VERSION=1.5.0rc1
+ARG SPOTLIGHT_VERSION=1.5.0
 
 RUN useradd -m -u 1000 user
 

README.md

@@ -1,13 +1,14 @@
 ---
-title: 
+title: Spotlight beans
 emoji: 🔬
 colorFrom: indigo
 colorTo: green
 sdk: docker
 app_port: 7860
-# models: []
-# datasets: []
-# tags: []
+datasets: [beans, renumics/spotlight-beans-enrichment]
+tags: [renumics, spotlight, EDA, enriched, data-centric-ai, viewer]
 pinned: false
 license: mit
----
+---
+
+# Explore beans with [Renumics Spotlight](https://github.com/renumics/spotlight)!

run.py

@@ -9,7 +9,7 @@ from typing import Optional
 
 import datasets
 import huggingface_hub
-from renumics import spotlight
+from renumics import spotlight  # type: ignore
 
 
 def login() -> None:
@@ -32,6 +32,7 @@ class HFSettings:
     revision: Optional[str] = None
 
     enrichment: Optional[str] = None
+    enrichment_revision: Optional[str] = None
 
     @classmethod
     def from_environ(cls) -> "HFSettings":
@@ -50,6 +51,7 @@ class HFSettings:
             os.environ.get("HF_SPLIT") or None,
             os.environ.get("HF_REVISION") or None,
             os.environ.get("HF_ENRICHMENT") or None,
+            os.environ.get("HF_ENRICHMENT_REVISION") or None,
         )
 
     def __str__(self) -> str:
@@ -75,7 +77,7 @@ if __name__ == "__main__":
             hf_settings.enrichment,
             hf_settings.subset,
             split=hf_settings.split,
-            revision=hf_settings.revision,
+            revision=hf_settings.enrichment_revision,
         )
         if len(ds_enrichment) != len(ds):
             raise RuntimeError(
@@ -83,6 +85,12 @@ if __name__ == "__main__":
                 f"mismatches length of the original dataset ({len(ds)})"
             )
         ds = datasets.concatenate_datasets([ds, ds_enrichment], split=ds.split, axis=1)
+
+    dtypes = {}
+    for col in ds.column_names:
+        if "embedding" in col and isinstance(ds.features[col], datasets.Sequence):
+            dtypes[col] = spotlight.dtypes.embedding_dtype
+
     if not isinstance(ds, datasets.Dataset):
         raise TypeError(
             f"Loaded Hugging Face dataset is of type {type(ds)} instead of "
@@ -90,4 +98,6 @@ if __name__ == "__main__":
             "(use environment variables `HF_SUBSET` and `HF_SPLIT` respective)?"
         )
     print(f"Serving Hugging Face dataset {hf_settings}.")
-    spotlight.show(ds, host="0.0.0.0", port=7860, wait="forever")
+    spotlight.show(
+        ds, host="0.0.0.0", port=7860, wait="forever", dtype=dtypes, analyze=True
+    )