Add BinaryContent.from_path convenience method (pydantic#3482)

Co-authored-by: Douwe Maan <[email protected]>

Author: 2 people

pydantic_ai_slim/pydantic_ai/messages.py

@@ -7,6 +7,8 @@
 from dataclasses import KW_ONLY, dataclass, field, replace
 from datetime import datetime
 from mimetypes import guess_type
+from os import PathLike
+from pathlib import Path
 from typing import TYPE_CHECKING, Annotated, Any, Literal, TypeAlias, cast, overload
 
 import pydantic
@@ -530,6 +532,25 @@ def from_data_uri(cls, data_uri: str) -> BinaryContent:
         media_type, data = data_uri[len(prefix) :].split(';base64,', 1)
         return cls.narrow_type(cls(data=base64.b64decode(data), media_type=media_type))
 
+    @classmethod
+    def from_path(cls, path: PathLike[str]) -> BinaryContent:
+        """Create a `BinaryContent` from a path.
+
+        Defaults to 'application/octet-stream' if the media type cannot be inferred.
+
+        Raises:
+            FileNotFoundError: if the file does not exist.
+            PermissionError: if the file cannot be read.
+        """
+        path = Path(path)
+        if not path.exists():
+            raise FileNotFoundError(f'File not found: {path}')
+        media_type, _ = guess_type(path)
+        if media_type is None:
+            media_type = 'application/octet-stream'
+
+        return cls.narrow_type(cls(data=path.read_bytes(), media_type=media_type))
+
     @pydantic.computed_field
     @property
     def identifier(self) -> str:

tests/test_messages.py

@@ -1,5 +1,6 @@
 import sys
 from datetime import datetime, timezone
+from pathlib import Path
 
 import pytest
 from inline_snapshot import snapshot
@@ -612,3 +613,37 @@ def test_binary_content_validation_with_optional_identifier():
             'identifier': 'foo',
         }
     )
+
+
+def test_binary_content_from_path(tmp_path: Path):
+    # test normal file
+    test_xml_file = tmp_path / 'test.xml'
+    test_xml_file.write_text('<think>about trains</think>', encoding='utf-8')
+    binary_content = BinaryContent.from_path(test_xml_file)
+    assert binary_content == snapshot(BinaryContent(data=b'<think>about trains</think>', media_type='application/xml'))
+
+    # test non-existent file
+    non_existent_file = tmp_path / 'non-existent.txt'
+    with pytest.raises(FileNotFoundError, match='File not found:'):
+        BinaryContent.from_path(non_existent_file)
+
+    # test file with unknown media type
+    test_unknown_file = tmp_path / 'test.unknownext'
+    test_unknown_file.write_text('some content', encoding='utf-8')
+    binary_content = BinaryContent.from_path(test_unknown_file)
+    assert binary_content == snapshot(BinaryContent(data=b'some content', media_type='application/octet-stream'))
+
+    # test string path
+    test_txt_file = tmp_path / 'test.txt'
+    test_txt_file.write_text('just some text', encoding='utf-8')
+    string_path = test_txt_file.as_posix()
+    binary_content = BinaryContent.from_path(string_path)  # pyright: ignore[reportArgumentType]
+    assert binary_content == snapshot(BinaryContent(data=b'just some text', media_type='text/plain'))
+
+    # test image file
+    test_jpg_file = tmp_path / 'test.jpg'
+    test_jpg_file.write_bytes(b'\xff\xd8\xff\xe0' + b'0' * 100)  # minimal JPEG header + padding
+    binary_content = BinaryContent.from_path(test_jpg_file)
+    assert binary_content == snapshot(
+        BinaryImage(data=b'\xff\xd8\xff\xe0' + b'0' * 100, media_type='image/jpeg', _identifier='bc8d49')
+    )