feat: Add common utility modules for file operations

- Add constants.py for shared constants (KILOBYTE, MEGABYTE)
- Add file_utils.py for reusable file-to-base64 conversion
- Extract common file validation and encoding logic

Author: eora21

libs/upstage/langchain_upstage/utils/__init__.py

@@ -0,0 +1,46 @@
+import base64
+import os
+import re
+from typing import List
+
+KILOBYTE = 1024
+MEGABYTE = 1024 * KILOBYTE
+
+
+def _process_input(
+    input_url: str, supported_extensions: List[str], max_file_size: int
+) -> str:
+    if re.match(r"^https?://", input_url):
+        return input_url
+
+    if os.path.exists(input_url):
+        if os.path.getsize(input_url) > max_file_size:
+            raise ValueError(f"File too large: max {max_file_size / MEGABYTE}MB")
+    else:
+        raise FileNotFoundError(f"File not found: {input_url}")
+
+    validate_extension(input_url, supported_extensions)
+
+    try:
+        with open(input_url, "rb") as img_file:
+            img_bytes = img_file.read()
+            base64_data = base64.b64encode(img_bytes).decode("utf-8")
+
+        return f"data:application/octet-stream;base64,{base64_data}"
+    except Exception as e:
+        raise ValueError(f"Error occurred while processing the file: {e}")
+
+
+def validate_extension(input_url: str, supported_extensions: List[str]) -> None:
+    file_ext = input_url.lower().split(".")[-1]
+    if file_ext not in supported_extensions:
+        supported = ", ".join([f".{ext}" for ext in supported_extensions])
+        raise ValueError(f"Unsupported image extension. supported: {supported}")
+
+
+def create_message(
+    input_url: str, supported_extensions: List[str], max_file_size: int
+) -> dict:
+    url = _process_input(input_url, supported_extensions, max_file_size)
+
+    return {"type": "image_url", "image_url": {"url": url}}

libs/upstage/langchain_upstage/utils/information_extraction_check.py

@@ -0,0 +1,23 @@
+import os
+from typing import Optional
+
+
+def get_from_param_or_env(
+    key: str,
+    param: Optional[str] = None,
+    env_key: Optional[str] = None,
+    default: Optional[str] = None,
+) -> str:
+    """Get a value from a param or an environment variable."""
+    if param is not None:
+        return param
+    elif env_key and env_key in os.environ and os.environ[env_key]:
+        return os.environ[env_key]
+    elif default is not None:
+        return default
+    else:
+        raise ValueError(
+            f"Did not find {key}, please add an environment variable"
+            f" `{env_key}` which contains it, or pass"
+            f"  `{key}` as a named parameter."
+        )