Update run eval imports in init (#5858)

langchain/evaluation/run_evaluators/__init__.py

@@ -1,20 +1,22 @@
 """Evaluation classes that interface with traced runs and datasets."""
-
-
 from langchain.evaluation.run_evaluators.base import (
-    RunEvalInputMapper,
-    RunEvaluator,
+    RunEvaluatorChain,
+    RunEvaluatorInputMapper,
     RunEvaluatorOutputParser,
 )
 from langchain.evaluation.run_evaluators.implementations import (
+    ChoicesOutputParser,
+    StringRunEvaluatorInputMapper,
     get_criteria_evaluator,
     get_qa_evaluator,
 )
 
 __all__ = [
-    "RunEvaluator",
-    "RunEvalInputMapper",
+    "RunEvaluatorChain",
+    "RunEvaluatorInputMapper",
     "RunEvaluatorOutputParser",
     "get_qa_evaluator",
     "get_criteria_evaluator",
+    "StringRunEvaluatorInputMapper",
+    "ChoicesOutputParser",
 ]

langchain/evaluation/run_evaluators/base.py

@@ -15,7 +15,7 @@ from langchain.chains.llm import LLMChain
 from langchain.schema import RUN_KEY, BaseOutputParser
 
 
-class RunEvalInputMapper:
+class RunEvaluatorInputMapper:
     """Map the inputs of a run to the inputs of an evaluation."""
 
     @abstractmethod
@@ -37,7 +37,7 @@ class RunEvaluatorOutputParser(BaseOutputParser[EvaluationResult]):
 class RunEvaluatorChain(Chain, RunEvaluator):
     """Evaluate Run and optional examples."""
 
-    input_mapper: RunEvalInputMapper
+    input_mapper: RunEvaluatorInputMapper
     """Maps the Run and Optional example to a dictionary for the eval chain."""
     eval_chain: LLMChain
     """The evaluation chain."""

langchain/evaluation/run_evaluators/implementations.py

@@ -10,8 +10,8 @@ from langchain.evaluation.qa.eval_chain import QAEvalChain
 from langchain.evaluation.qa.eval_prompt import PROMPT as QA_DEFAULT_PROMPT
 from langchain.evaluation.qa.eval_prompt import SQL_PROMPT
 from langchain.evaluation.run_evaluators.base import (
-    RunEvalInputMapper,
     RunEvaluatorChain,
+    RunEvaluatorInputMapper,
     RunEvaluatorOutputParser,
 )
 from langchain.evaluation.run_evaluators.criteria_prompt import (
@@ -25,7 +25,7 @@ _QA_PROMPTS = {
 }
 
 
-class StringRunEvalInputMapper(RunEvalInputMapper, BaseModel):
+class StringRunEvaluatorInputMapper(RunEvaluatorInputMapper, BaseModel):
     """Maps the Run and Optional[Example] to a dictionary."""
 
     prediction_map: Mapping[str, str]
@@ -97,7 +97,7 @@ def get_qa_evaluator(
     eval_chain = QAEvalChain.from_llm(llm=llm, prompt=prompt, **kwargs)
     input_mapper = kwargs.pop(
         "input_mapper",
-        StringRunEvalInputMapper(
+        StringRunEvaluatorInputMapper(
             input_map={input_key: "query"},
             prediction_map={prediction_key: "result"},
             answer_map={answer_key: "answer"},
@@ -179,7 +179,7 @@ def get_criteria_evaluator(
     prompt_ = prompt.partial(criteria=criteria_str)
     input_mapper = kwargs.pop(
         "input_mapper",
-        StringRunEvalInputMapper(
+        StringRunEvaluatorInputMapper(
             input_map={input_key: "input"},
             prediction_map={prediction_key: "output"},
         ),