fix(integration): langchain integration and CI fixes

src/ragas/integrations/langchain.py

@@ -206,7 +206,7 @@ def evaluate_run(
             if example.outputs is None or "ground_truth" not in example.outputs:
                 raise ValueError("expected `ground_truth` in example outputs.")
             chain_eval["ground_truth"] = example.outputs["ground_truth"]
-        eval_output = self(chain_eval, include_run_info=True)
+        eval_output = self.invoke(chain_eval, include_run_info=True)
 
         evaluation_result = EvaluationResult(
             key=self.metric.name, score=eval_output[self.metric.name]

src/ragas/metrics/base.py

@@ -4,6 +4,7 @@
 C - contexts: context used for generation
 G - ground_truth: ground truth answer
 """
+
 from __future__ import annotations
 
 import asyncio
@@ -25,17 +26,37 @@
 EvaluationMode = Enum("EvaluationMode", "qac qa qc gc ga qga qcg")
 
 
+def get_required_columns(
+    eval_mod: EvaluationMode, ignore_columns: t.Optional[t.List[str]] = None
+) -> t.List[str]:
+    if eval_mod == EvaluationMode.qac:
+        keys = ["question", "answer", "contexts"]
+    elif eval_mod == EvaluationMode.qa:
+        keys = ["question", "answer"]
+    elif eval_mod == EvaluationMode.qc:
+        keys = ["question", "contexts"]
+    elif eval_mod == EvaluationMode.gc:
+        keys = ["contexts", "ground_truth"]
+    elif eval_mod == EvaluationMode.ga:
+        keys = ["answer", "ground_truth"]
+    elif eval_mod == EvaluationMode.qga:
+        keys = ["question", "contexts", "answer", "ground_truth"]
+    elif eval_mod == EvaluationMode.qcg:
+        keys = ["question", "contexts", "ground_truth"]
+    ignore_columns = ignore_columns or []
+
+    return [k for k in keys if k not in ignore_columns]
+
+
 @dataclass
 class Metric(ABC):
     @property
     @abstractmethod
-    def name(self) -> str:
-        ...
+    def name(self) -> str: ...
 
     @property
     @abstractmethod
-    def evaluation_mode(self) -> EvaluationMode:
-        ...
+    def evaluation_mode(self) -> EvaluationMode: ...
 
     @abstractmethod
     def init(self, run_config: RunConfig):
@@ -97,8 +118,9 @@ async def ascore(
         return score
 
     @abstractmethod
-    async def _ascore(self, row: t.Dict, callbacks: Callbacks, is_async: bool) -> float:
-        ...
+    async def _ascore(
+        self, row: t.Dict, callbacks: Callbacks, is_async: bool
+    ) -> float: ...
 
 
 @dataclass