From 708787dddb2fa3cdb2d1dabefa00c01ffec572f6 Mon Sep 17 00:00:00 2001
From: Eugene Yurtsev <eyurtsev@gmail.com>
Date: Thu, 27 Apr 2023 14:33:59 -0400
Subject: [PATCH] Blob: Add validator and use future annotations (#3650)

Minor changes to the Blob schema.

---------

Co-authored-by: Zander Chase <130414180+vowelparrot@users.noreply.github.com>
---
 .../document_loaders/blob_loaders/schema.py     | 17 +++++++++++++----
 .../document_loader/blob_loaders/test_schema.py |  9 +++++++++
 2 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/langchain/document_loaders/blob_loaders/schema.py b/langchain/document_loaders/blob_loaders/schema.py
index f4a9f6be..6ea20fdb 100644
--- a/langchain/document_loaders/blob_loaders/schema.py
+++ b/langchain/document_loaders/blob_loaders/schema.py
@@ -4,14 +4,16 @@ The goal is to facilitate decoupling of content loading from content parsing cod
 
 In addition, content loading code should provide a lazy loading interface by default.
 """
+from __future__ import annotations
+
 import contextlib
 import mimetypes
 from abc import ABC, abstractmethod
 from io import BufferedReader, BytesIO
 from pathlib import PurePath
-from typing import Generator, Iterable, Optional, Union
+from typing import Any, Generator, Iterable, Mapping, Optional, Union
 
-from pydantic import BaseModel
+from pydantic import BaseModel, root_validator
 
 PathLike = Union[str, PurePath]
 
@@ -44,6 +46,13 @@ class Blob(BaseModel):
         """The source location of the blob as string if known otherwise none."""
         return str(self.path) if self.path else None
 
+    @root_validator(pre=True)
+    def check_blob_is_valid(cls, values: Mapping[str, Any]) -> Mapping[str, Any]:
+        """Verify that either data or path is provided."""
+        if "data" not in values and "path" not in values:
+            raise ValueError("Either data or path must be provided")
+        return values
+
     def as_string(self) -> str:
         """Read data as a string."""
         if self.data is None and self.path:
@@ -87,7 +96,7 @@ class Blob(BaseModel):
         encoding: str = "utf-8",
         mime_type: Optional[str] = None,
         guess_type: bool = True,
-    ) -> "Blob":
+    ) -> Blob:
         """Load the blob from a path like object.
 
         Args:
@@ -116,7 +125,7 @@ class Blob(BaseModel):
         encoding: str = "utf-8",
         mime_type: Optional[str] = None,
         path: Optional[str] = None,
-    ) -> "Blob":
+    ) -> Blob:
         """Initialize the blob from in-memory data.
 
         Args:
diff --git a/tests/unit_tests/document_loader/blob_loaders/test_schema.py b/tests/unit_tests/document_loader/blob_loaders/test_schema.py
index 4791d976..fa4a3dca 100644
--- a/tests/unit_tests/document_loader/blob_loaders/test_schema.py
+++ b/tests/unit_tests/document_loader/blob_loaders/test_schema.py
@@ -90,6 +90,15 @@ def test_mime_type_inference(
     assert blob.mimetype == expected_mime_type
 
 
+def test_blob_initialization_validator() -> None:
+    """Test that blob initialization validates the arguments."""
+    with pytest.raises(ValueError, match="Either data or path must be provided"):
+        Blob()
+
+    assert Blob(data=b"Hello, World!") is not None
+    assert Blob(path="some_path") is not None
+
+
 def test_blob_loader() -> None:
     """Simple test that verifies that we can implement a blob loader."""