Push

Dockerfile

@@ -21,4 +21,9 @@ COPY /web/blueprint/build ./web/blueprint/build
 # Copy python files.
 COPY /src ./src/
 
-CMD ["uvicorn", "src.server:app", "--host", "0.0.0.0", "--port", "5432"]
+CMD [ \
+  "uvicorn", "src.server:app", \
+  "--host", "0.0.0.0", \
+  "--port", "5432", \
+  "-k", "uvicorn.workers.UvicornWorker" \
+  ]

data/datasets/local/spotify/data-00000-of-00001.parquet

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:32224657332b09187a737c73ab634f9d14c9ba9a240bd105f1b9819cde2afcef
-size 37128682

data/datasets/local/spotify/manifest.json

@@ -1,27 +0,0 @@
-{
-  "files": [
-    "data-00000-of-00001.parquet"
-  ],
-  "data_schema": {
-    "fields": {
-      "artist": {
-        "dtype": "string"
-      },
-      "song": {
-        "dtype": "string"
-      },
-      "link": {
-        "dtype": "string"
-      },
-      "text": {
-        "dtype": "string"
-      },
-      "__line_number__": {
-        "dtype": "int64"
-      },
-      "__rowid__": {
-        "dtype": "string"
-      }
-    }
-  }
-}

data/datasets/local/spotify/text/sbert/data-00000-of-00001.parquet

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9796beb630cc3503f3c2ac9db8f71e4c1604570836d78bbf364e801cd427c39e
-size 2709987

data/datasets/local/spotify/text/sbert/embeddings-00000-of-00001.keys.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d5df43291782b8c731d4ce56537946654c642a01dc9a4e37de394836362f6b45
-size 3727400

data/datasets/local/spotify/text/sbert/embeddings-00000-of-00001.npy

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:94e10c23d7229541e1f60b791a659d13673b10a03649abf0ae092e0e18c5aee3
-size 170446976

data/datasets/local/spotify/text/sbert/signal_manifest.json

@@ -1,37 +0,0 @@
-{
-  "files": [
-    "data-00000-of-00001.parquet"
-  ],
-  "parquet_id": "sbert(text)",
-  "data_schema": {
-    "fields": {
-      "__rowid__": {
-        "dtype": "string"
-      },
-      "text": {
-        "fields": {
-          "sbert": {
-            "repeated_field": {
-              "fields": {
-                "embedding": {
-                  "dtype": "embedding"
-                }
-              },
-              "dtype": "string_span"
-            },
-            "signal": {
-              "signal_name": "sbert"
-            }
-          }
-        }
-      }
-    }
-  },
-  "signal": {
-    "signal_name": "sbert"
-  },
-  "enriched_path": [
-    "text"
-  ],
-  "embedding_filename_prefix": "embeddings-00000-of-00001"
-}

src/server.py

@@ -68,7 +68,6 @@ app.mount('/', StaticFiles(directory=DIST_PATH, html=True, check_dir=False))
 @app.on_event('startup')
 def startup() -> None:
   """Download dataset files from the HF space that was uploaded before building the image."""
-  # Setup.
   repo_id = CONFIG.get('HF_DATA_FROM_SPACE', None)
 
   if repo_id:
@@ -89,6 +88,8 @@ def startup() -> None:
       persistent_output_dir = get_dataset_output_dir(data_path(), dataset.namespace,
                                                      dataset.dataset_name)
 
+      # Huggingface doesn't let you selectively download files so we just copy the data directory
+      # out of the cloned space.
       shutil.rmtree(persistent_output_dir, ignore_errors=True)
       shutil.move(spaces_dataset_output_dir, persistent_output_dir)