cli, reconstruction and changed CI/CD pipeline

.github/workflows/CD.yml

@@ -14,27 +14,25 @@ jobs:
       - name: Checkout repository
         uses: actions/checkout@v2
         with:
-          fetch-depth: 0 
+          fetch-depth: 0
 
       - name: Set up Python
         uses: actions/setup-python@v2
         with:
           python-version: '3.10'
-                
+
       - name: Cache pip
         uses: actions/cache@v2
         with:
           path: ~/.cache/pip
           key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}
           restore-keys: |
             ${{ runner.os }}-pip-
-                
+
       - name: Install dependencies
         run: |
-          python -m pip install --upgrade pip
-          pip install pytest black pipreqs pip-tools
-          pip install -r requirements.txt
-          python3 update.py
+          pip install .
+
       - name: Extract tag name
         id: extract_tag
         run: echo "TAG_NAME=$(echo $GITHUB_REF | cut -d/ -f3)" >> $GITHUB_ENV

corkit/cli.py

@@ -0,0 +1,21 @@
+import argparse
+import asyncio
+from .dataset import update
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Corkit CLI dataset update manager."
+    )
+    parser.add_argument(
+        "--batch-size",
+        type=int,
+        default=100,
+        help="Batch size for dataset updates (default: 10)"
+    )
+    args = parser.parse_args()
+
+    try:
+        asyncio.run(update(batch_size=args.batch_size))
+        print("Datasets updated successfully.")
+    except Exception as e:
+        print(f"Error during dataset update: {e}")