feat: column mapping to select columns (#91)

Author: jjmachan

src/ragas/evaluation.py

@@ -14,6 +14,12 @@
 def evaluate(
     dataset: Dataset,
     metrics: list[Metric] | None = None,
+    column_map: dict[str, str] = {
+        "question": "question",
+        "contexts": "contexts",
+        "answer": "answer",
+        "ground_truths": "ground_truths",
+    },
 ) -> Result:
     """
     Run the evaluation on the dataset with different metrics
@@ -26,6 +32,10 @@ def evaluate(
     metrics : list[Metric] , optional
         List of metrics to use for evaluation. If not provided then ragas will run the
         evaluation on the best set of metrics to give a complete view.
+    column_map : dict[str, str], optional
+        The column names of the dataset to use for evaluation. If the column names of
+        the dataset are different from the default ones then you can provide the
+        mapping as a dictionary here.
 
     Returns
     -------
@@ -66,6 +76,9 @@ def evaluate(
 
         metrics = [answer_relevancy, context_relevancy, faithfulness]
 
+    # select columns from the dataset
+    dataset = dataset.from_dict({k: dataset[v] for k, v in column_map.items()})
+
     # validation
     validate_evaluation_modes(dataset, metrics)
     validate_column_dtypes(dataset)

src/ragas/validation.py

@@ -21,7 +21,7 @@ def validate_column_dtypes(ds: Dataset):
             ):
                 raise ValueError(
                     f'Dataset feature "{column_names}" should be of type'
-                    " Sequence[string]"
+                    f" Sequence[string], got {type(ds.features[column_names])}"
                 )