chore: remove deprecated ground_truths (#2402)

Author: anistark

docs/howtos/integrations/_opik.md

@@ -208,7 +208,7 @@ dataset = fiqa_eval["baseline"].select(range(3))
 dataset = dataset.map(
     lambda x: {
         "user_input": x["question"],
-        "reference": x["ground_truths"][0],
+        "reference": x["ground_truth"],
         "retrieved_contexts": x["contexts"],
     }
 )

docs/howtos/integrations/opik.ipynb

@@ -260,13 +260,7 @@
   {
    "cell_type": "markdown",
    "metadata": {},
-   "source": [
-    "#### Evaluating datasets\n",
-    "\n",
-    "If you looking at evaluating a dataset, you can use the Ragas `evaluate` function. When using this function, the Ragas library will compute the metrics on all the rows of the dataset and return a summary of the results.\n",
-    "\n",
-    "You can use the OpikTracer callback to log the results of the evaluation to the Opik platform. For this we will configure the OpikTracer"
-   ]
+   "source": "from datasets import load_dataset\n\nfrom ragas import evaluate\nfrom ragas.metrics import answer_relevancy, context_precision, faithfulness\n\nfiqa_eval = load_dataset(\"explodinggradients/fiqa\", \"ragas_eval\")\n\n# Reformat the dataset to match the schema expected by the Ragas evaluate function\ndataset = fiqa_eval[\"baseline\"].select(range(3))\n\ndataset = dataset.map(\n    lambda x: {\n        \"user_input\": x[\"question\"],\n        \"reference\": x[\"ground_truth\"],\n        \"retrieved_contexts\": x[\"contexts\"],\n    }\n)\n\nopik_tracer_eval = OpikTracer(tags=[\"ragas_eval\"], metadata={\"evaluation_run\": True})\n\nresult = evaluate(\n    dataset,\n    metrics=[context_precision, faithfulness, answer_relevancy],\n    callbacks=[opik_tracer_eval],\n)\n\nprint(result)"
   },
   {
    "cell_type": "code",
@@ -309,7 +303,7 @@
     "dataset = dataset.map(\n",
     "    lambda x: {\n",
     "        \"user_input\": x[\"question\"],\n",
-    "        \"reference\": x[\"ground_truths\"][0],\n",
+    "        \"reference\": x[\"ground_truth\"],\n",
     "        \"retrieved_contexts\": x[\"contexts\"],\n",
     "    }\n",
     ")\n",
@@ -347,4 +341,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 2
-}
+}

src/ragas/validation.py

@@ -3,7 +3,7 @@
 import logging
 import typing as t
 
-from datasets import Dataset, Sequence
+from datasets import Dataset
 
 from ragas.dataset_schema import EvaluationDataset, MultiTurnSample, SingleTurnSample
 from ragas.metrics.base import Metric, MetricType, MultiTurnMetric, SingleTurnMetric
@@ -20,26 +20,6 @@ def remap_column_names(dataset: Dataset, column_map: dict[str, str]) -> Dataset:
     return dataset.rename_columns(inverse_column_map)
 
 
-def handle_deprecated_ground_truths(ds: Dataset) -> Dataset:
-    if "ground_truths" in ds.features and "ground_truth" not in ds.features:
-        column_names = "ground_truths"
-        if (
-            isinstance(ds.features[column_names], Sequence)
-            and ds.features[column_names].feature.dtype == "string"
-        ):
-            logger.warning(
-                "passing column names as 'ground_truths' is deprecated and will be removed in the next version, please use 'ground_truth' instead. Note that `ground_truth` should be of type string and not Sequence[string] like `ground_truths`"
-            )
-            gt = [gt[0] for gt in ds["ground_truths"]]
-            ds = ds.add_column(
-                "ground_truth",
-                gt,
-                new_fingerprint=ds._fingerprint
-                + "a",  # adding random to fingerprint to avoid caching
-            )
-    return ds
-
-
 def get_supported_metric_type(ds: EvaluationDataset):
     """
     get the supported metric type for the given dataset