Lint + black action (#11)

* lint + add black in github actions

.github/workflows/pull_request.yaml

@@ -0,0 +1,17 @@
+name: lint
+
+on:
+  pull_request:
+    branches:
+      - '*'
+
+jobs:
+  tests:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out repository code
+        uses: actions/checkout@v3
+      - name: black linter
+        uses: psf/black@stable
+        with:
+          options: "--check --diff"

embed_documents.py

@@ -12,7 +12,11 @@ if __name__ == "__main__":
     df = df.dropna()
     print(f"after drop: {len(df)}")
 
-    dm = DeepLakeDocumentsManager(vector_store_path, overwrite=overwrite, required_columns=["url", "source", "content", "title"])
+    dm = DeepLakeDocumentsManager(
+        vector_store_path,
+        overwrite=overwrite,
+        required_columns=["url", "source", "content", "title"],
+    )
     dm.batch_add(df)
     zipped_file_path = dm.to_zip()
     print(f"Contents zipped to: {zipped_file_path}")

gradio_app.py

@@ -18,6 +18,7 @@ logging.basicConfig(level=logging.INFO)
 
 AVAILABLE_SOURCES = ["towardsai", "wikipedia", "langchain_course"]
 
+
 def check_auth(username: str, password: str) -> bool:
     valid_user = username == cfg.USERNAME
     valid_password = password == cfg.PASSWORD

markdown_parser.py

@@ -70,9 +70,10 @@ if __name__ == "__main__":
 
     chunks = []
 
-    from tqdm import tqdm
     import json
 
+    from tqdm import tqdm
+
     with open("title_link_langchaincourse.json", "r") as f:
         title_link_data = json.load(f)