fix(core): improve langsmith loader error messages

libs/core/langchain_core/document_loaders/langsmith.py

@@ -3,7 +3,7 @@
 import datetime
 import json
 import uuid
-from collections.abc import Callable, Iterator, Sequence
+from collections.abc import Callable, Iterator, Mapping, Sequence
 from typing import Any
 
 from langsmith import Client as LangSmithClient
@@ -94,7 +94,11 @@ def __init__(
             ValueError: If both `client` and `client_kwargs` are provided.
         """  # noqa: E501
         if client and client_kwargs:
-            raise ValueError
+            msg = (
+                "Received both `client` and `client_kwargs`. "
+                "Pass `client_kwargs` only when `client` is not provided."
+            )
+            raise ValueError(msg)
         self._client = client or LangSmithClient(**client_kwargs)
         self.content_key = list(content_key.split(".")) if content_key else []
         self.format_content = format_content or _stringify
@@ -123,9 +127,7 @@ def lazy_load(self) -> Iterator[Document]:
             metadata=self.metadata,
             filter=self.filter,
         ):
-            content: Any = example.inputs
-            for key in self.content_key:
-                content = content[key]
+            content = _get_content_from_inputs(example.inputs, self.content_key)
             content_str = self.format_content(content)
             metadata = pydantic_to_dict(example)
             # Stringify datetime and UUID types.
@@ -134,6 +136,44 @@ def lazy_load(self) -> Iterator[Document]:
             yield Document(content_str, metadata=metadata)
 
 
+def _get_content_from_inputs(inputs: Any, content_key: Sequence[str]) -> Any:
+    """Resolve nested example input content for `LangSmithLoader`.
+
+    Args:
+        inputs: Example input payload returned by LangSmith.
+        content_key: Ordered key path used to extract the document content.
+
+    Returns:
+        The extracted content value.
+
+    Raises:
+        KeyError: If the requested `content_key` path cannot be resolved.
+    """
+    content = inputs
+    full_path = ".".join(content_key)
+    traversed_keys: list[str] = []
+
+    for key in content_key:
+        if not isinstance(content, Mapping):
+            current_path = ".".join(traversed_keys) or "<root>"
+            msg = (
+                f"Could not resolve content_key {full_path!r}: expected a mapping at "
+                f"{current_path!r}, but found {type(content).__name__}."
+            )
+            raise KeyError(msg)
+        if key not in content:
+            current_path = ".".join(traversed_keys) or "<root>"
+            msg = (
+                f"Could not resolve content_key {full_path!r}: missing key {key!r} "
+                f"under {current_path!r}."
+            )
+            raise KeyError(msg)
+        content = content[key]
+        traversed_keys.append(key)
+
+    return content
+
+
 def _stringify(x: str | dict[str, Any]) -> str:
     if isinstance(x, str):
         return x

libs/core/tests/unit_tests/document_loaders/test_langsmith.py

@@ -2,6 +2,7 @@
 import uuid
 from unittest.mock import MagicMock, patch
 
+import pytest
 from langsmith.schemas import Example
 
 from langchain_core.document_loaders import LangSmithLoader
@@ -13,6 +14,13 @@ def test_init() -> None:
     LangSmithLoader(api_key="secret")
 
 
+def test_init_with_client_and_client_kwargs_raises() -> None:
+    client = MagicMock()
+
+    with pytest.raises(ValueError, match="Received both `client` and `client_kwargs`"):
+        LangSmithLoader(client=client, api_key="secret")
+
+
 EXAMPLES = [
     Example(
         inputs={"first": {"second": "foo"}},
@@ -60,3 +68,15 @@ def test_lazy_load() -> None:
         )
     actual = list(loader.lazy_load())
     assert expected == actual
+
+
+@patch("langsmith.Client.list_examples", MagicMock(return_value=iter(EXAMPLES[:1])))
+def test_lazy_load_with_missing_content_key_raises() -> None:
+    loader = LangSmithLoader(
+        api_key="dummy",
+        dataset_id="mock",
+        content_key="first.third",
+    )
+
+    with pytest.raises(KeyError, match=r"Could not resolve content_key 'first\.third'"):
+        list(loader.lazy_load())