docs: add script to add typescript translations (#3394)

A script to add typescript translations. We can improve by automatically
adding markdown tabs appropriately and parallelizing the llm calls

docs/_scripts/add_translation.py

@@ -0,0 +1,157 @@
+"""Add typescript translation to a given markdown file."""
+
+import argparse
+import re
+
+import requests
+from langchain_anthropic import ChatAnthropic
+
+URL = "https://gist.githubusercontent.com/eyurtsev/e7486731415463a9bc5b4682358859c8/raw/b5a5fda9c7e3387cfcb781f25082814d43675d50/gistfile1.txt"
+response = requests.get(URL)
+response.raise_for_status()
+reference_snippets = response.text
+
+model = ChatAnthropic(model="claude-3-5-sonnet-latest")
+
+
+def _get_tqdm():
+    try:
+        from tqdm import tqdm
+    except ImportError:
+        # If not available return a simple identity function
+        def tqdm(iterable, *args, **kwargs):
+            return iterable
+
+    return tqdm
+
+
+_tqdm = _get_tqdm()
+
+opening_pattern = re.compile(r"^\s*```python(?:\s+.*)?\s*$")
+closing_pattern = re.compile(r"^\s*```\s*$")
+
+
+def extract_python_snippets(markdown: str) -> list[str]:
+    """
+    Extract all python code blocks (including their fence lines) from the markdown content.
+    A python block is defined as any block that starts with a line containing an opening fence
+    with '```python' (optionally with extra parameters) and ends with a closing fence '```'.
+    """
+    snippets = []
+    inside_block = False
+    current_snippet = []
+
+    for line in markdown.splitlines(keepends=True):
+        if not inside_block:
+            if opening_pattern.match(line):
+                inside_block = True
+                current_snippet = [line]
+        else:
+            current_snippet.append(line)
+            if closing_pattern.match(line):
+                inside_block = False
+                snippets.append("".join(current_snippet))
+                current_snippet = []
+    return snippets
+
+
+def translate_snippet(python_snippet: str) -> str:
+    """Translate a python code block into a TypeScript code block using Langchain.
+    The response is expected to be a properly fenced TypeScript code block (i.e.
+    starting with ```typescript and ending with ```).
+    """
+    ai_message = model.invoke(
+        [
+            {
+                "role": "system",
+                "content": (
+                    f"You have access to the following up-to-date example TypeScript code "
+                    f"snippets that show examples of building with langgraph "
+                    f"and langchain:\n\n{reference_snippets}\n\n"
+                    "Use this context to translate the following Python code to equivalent "
+                    "TypeScript. Ensure that your output is a valid fenced TypeScript "
+                    "code block (i.e. starts with ```typescript and ends with ```)."
+                ),
+            },
+            {
+                "role": "user",
+                "content": f"Translate this Python snippet to TypeScript:\n\n{python_snippet}",
+            },
+        ]
+    )
+
+    # Use a regular expression to search for a TypeScript code block in the response.
+    pattern = r"```typescript\s*(.*?)\s*```"
+    match = re.search(pattern, ai_message.content, re.DOTALL)
+    if match:
+        # Reconstruct the code block with proper fences.
+        typescript_code = match.group(1).strip()
+        return f"```typescript\n{typescript_code}\n```"
+    else:
+        raise ValueError("No TypeScript code block found in the model's response.")
+
+
+def insert_translations_into_markdown(
+    markdown: str, typescript_snippets: list[str]
+) -> str:
+    """Walks through the original markdown content and, after each
+    Python snippet block, inserts the corresponding translated TypeScript snippet.
+    It assumes that the ordering of the Python snippets
+    (from extract_python_snippets) matches the order they appear in the markdown.
+    """
+    output_lines = []
+    lines = markdown.splitlines(keepends=True)
+    inside_block = False
+    snippet_index = 0
+
+    for line in lines:
+        output_lines.append(line)
+        if not inside_block and opening_pattern.match(line):
+            # We've encountered the start of a python code block.
+            inside_block = True
+        elif inside_block:
+            if closing_pattern.match(line):
+                # End of a python snippet block.
+                inside_block = False
+                if snippet_index < len(typescript_snippets):
+                    # Insert an extra newline for clarity, then the translated TypeScript snippet.
+                    output_lines.append("\n")
+                    output_lines.append(typescript_snippets[snippet_index])
+                    output_lines.append("\n")
+                    snippet_index += 1
+    return "".join(output_lines)
+
+
+def main(file_path: str) -> None:
+    # Read the markdown file.
+    with open(file_path, "r") as f:
+        markdown_content = f.read()
+
+    # 1. Extract all Python snippets.
+    python_snippets = extract_python_snippets(markdown_content)[:1]
+
+    # 2. Translate each Python snippet to TypeScript.
+    typescript_snippets = []
+    # Replace with .batch() for faster translation
+    for python_snippet in _tqdm(python_snippets):
+        ts_snippet = translate_snippet(python_snippet)
+        typescript_snippets.append(ts_snippet)
+
+    # 3. Insert the TypeScript translations after their respective Python snippets.
+    updated_markdown = insert_translations_into_markdown(
+        markdown_content, typescript_snippets
+    )
+
+    # Overwrite the original markdown file with the updated content.
+    with open(file_path, "w") as f:
+        f.write(updated_markdown)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(
+        description="Translate Python snippets in a markdown file to TypeScript and insert them after each Python snippet."
+    )
+    parser.add_argument("file_path", type=str, help="Path to the markdown file.")
+    args = parser.parse_args()
+
+    main(args.file_path)