update dockerfile

Dockerfile

@@ -28,6 +28,7 @@ RUN apt -y install elasticsearch
 # Copy users db file along with execution script
 COPY users.yml /app
 COPY start.sh /app
+COPY load_data.py /app
 RUN chmod +x /app/start.sh
 
 RUN useradd -ms /bin/bash user -p "$(openssl passwd -1 ubuntu)"

load_data.py

@@ -0,0 +1,32 @@
+import time
+import requests
+
+
+def load_data():
+    # install datasets library with pip install datasets
+    import argilla as rg
+    from datasets import load_dataset
+
+    # load dataset from the hub
+    dataset = load_dataset("argilla/gutenberg_spacy-ner", split="train")
+
+    # read in dataset, assuming its a dataset for token classification
+    dataset_rg = rg.read_datasets(dataset, task="TokenClassification")
+
+    # log the dataset
+    rg.log(dataset_rg, "gutenberg_spacy-ner")
+
+
+if __name__ == '__main__':
+    while True:
+        try:
+            response = requests.get("http://0.0.0.0:6900/")
+            if response.status_code == 200:
+                load_data()
+                print("Data Loaded!")
+                break
+            else:
+                time.sleep(5)
+        except Exception as e:
+            print(e)
+            pass

start.sh

@@ -4,8 +4,13 @@ set -e
 
 echo "ubuntu" | sudo -S su user
 
-# Starting elasticsearch & argilla
+# Start elasticsearch
 sudo /etc/init.d/elasticsearch start
 echo "Waiting for elasticsearch to start"
 sleep 15
+
+# Load data
+python3 /app/load_data.py &
+
+# Start argilla
 uvicorn argilla:app --host "0.0.0.0"