Fix doctest (#888)

python/langsmith/evaluation/_runner.py

@@ -199,6 +199,7 @@ def evaluate(
         Using the `evaluate` API with an off-the-shelf LangChain evaluator:
 
         >>> from langsmith.evaluation import LangChainStringEvaluator
+        >>> from langchain_openai import ChatOpenAI
         >>> def prepare_criteria_data(run: Run, example: Example):
         ...     return {
         ...         "prediction": run.outputs["output"],
@@ -218,6 +219,7 @@ def evaluate(
         ...                     "usefulness": "The prediction is useful if it is correct"
         ...                     " and/or asks a useful followup question."
         ...                 },
+        ...                 "llm": ChatOpenAI(model="gpt-4o"),
         ...             },
         ...             prepare_data=prepare_criteria_data,
         ...         ),

python/langsmith/evaluation/integrations/_langchain.py

@@ -44,13 +44,15 @@ class LangChainStringEvaluator:
         Converting a LangChainStringEvaluator to a RunEvaluator:
 
         >>> from langsmith.evaluation import LangChainStringEvaluator
+        >>> from langchain_openai import ChatOpenAI
         >>> evaluator = LangChainStringEvaluator(
         ...     "criteria",
         ...     config={
         ...         "criteria": {
         ...             "usefulness": "The prediction is useful if"
         ...             " it is correct and/or asks a useful followup question."
         ...         },
+        ...         "llm": ChatOpenAI(model="gpt-4o"),
         ...     },
         ... )
         >>> run_evaluator = evaluator.as_run_evaluator()
@@ -111,6 +113,7 @@ class LangChainStringEvaluator:
         ...             "accuracy": "Score 1: Completely inaccurate\nScore 5: Somewhat accurate\nScore 10: Completely accurate"
         ...         },
         ...         "normalize_by": 10,
+        ...         "llm": ChatAnthropic(model="claude-3-opus-20240229"),
         ...     },
         ...     prepare_data=prepare_data,
         ... )