Merge commit '22a8c6cf484edc78ec8db5cabd3da9c8b59e1d20' into minh/speech_transcription_tutorial

Author: minh-hoque

.github/scripts/check_notebooks.py

@@ -0,0 +1,61 @@
+import subprocess
+import sys
+from pathlib import Path
+
+import nbformat
+
+
+def get_changed_notebooks(base_ref: str = "origin/main") -> list[Path]:
+    """
+    Returns a list of changed notebook paths in the current git branch
+    compared to the specified base reference.
+    """
+    result = subprocess.run(
+        ["git", "diff", "--name-only", base_ref, "--", "*.ipynb"],
+        capture_output=True,
+        text=True,
+        check=True,
+    )
+    return [Path(line.strip()) for line in result.stdout.splitlines() if line.strip()]
+
+
+def is_valid_notebook(path: Path) -> bool:
+    """
+    Checks if the notebook at the given path is valid by attempting to read it
+    with nbformat.
+    """
+    try:
+        with open(path, "r", encoding="utf-8") as f:
+            nbformat.read(f, as_version=4)
+        return True
+    except Exception as e:
+        print(f"{path}: INVALID - {e}")
+        return False
+
+
+def main() -> None:
+    """
+    Main function to validate the format of changed notebooks.
+    """
+    changed_notebooks = get_changed_notebooks()
+    if not changed_notebooks:
+        print("No changed .ipynb files to validate.")
+        sys.exit(0)
+
+    print(f"Validating {len(changed_notebooks)} notebook(s)...")
+    errors = 0
+    for path in changed_notebooks:
+        if not path.exists():
+            continue  # skip deleted files
+        if not is_valid_notebook(path):
+            errors += 1
+
+    if errors:
+        print(f"{errors} invalid notebook(s) found.")
+        sys.exit(1)
+    else:
+        print("All changed notebooks are valid.")
+
+
+if __name__ == "__main__":
+    main()

.github/workflows/validate-notebooks.yaml

@@ -0,0 +1,25 @@
+name: Validate Changed Notebooks
+
+on: [pull_request]
+
+jobs:
+  validate-notebooks:
+    name: Validate Notebooks
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0  # needed for git diff to work
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.12'
+
+      - name: Install dependencies
+        run: pip install nbformat
+
+      - name: Validate changed .ipynb files
+        run: python .github/scripts/check_notebooks.py

.gitignore

@@ -141,3 +141,6 @@ examples/fine-tuned_qa/local_cache/*
 # PyCharm files
 .idea/
 .cursorignore
+
+# VS Code files
+.vscode/

authors.yaml

@@ -297,3 +297,8 @@ brandonbaker-openai:
   name: "Brandon Baker"
   website: "https://www.linkedin.com/in/brandonbaker18"
   avatar: "https://avatars.githubusercontent.com/u/208719822"
+
+tompakeman-oai:
+  name: "Tom Pakeman"
+  website: "https://www.linkedin.com/in/tom-pakeman/"
+  avatar: "https://avatars.githubusercontent.com/u/204937754"

examples/Embedding_Wikipedia_articles_for_search.ipynb

@@ -571,7 +571,7 @@
     "\n",
     "Now that we've split our library into shorter self-contained strings, we can compute embeddings for each.\n",
     "\n",
-    "(For large embedding jobs, use a script like [api_request_parallel_processor.py](api_request_parallel_processor.py) to parallelize requests while throttling to stay under rate limits.)"
+    "(For large embedding jobs, use a script like [api_request_parallel_processor.py](https://github.com/openai/openai-cookbook/blob/main/examples/api_request_parallel_processor.py) to parallelize requests while throttling to stay under rate limits.)"
    ]
   },
   {