REFACTOR rename SeedDatasetProvider.fetch_dataset to fetch_dataset_async (#1735)

Co-authored-by: romanlutz <romanlutz@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: romanlutz

doc/code/datasets/4_dataset_coding.ipynb

@@ -67,7 +67,7 @@
     "    def dataset_name(self) -> str:\n",
     "        return \"dark_bench\"\n",
     "\n",
-    "    async def fetch_dataset(self, *, cache: bool = True) -> SeedDataset:\n",
+    "    async def fetch_dataset_async(self, *, cache: bool = True) -> SeedDataset:\n",
     "        # Fetch from HuggingFace\n",
     "        data = await self._fetch_from_huggingface(\n",
     "            dataset_name=\"apart/darkbench\",\n",

doc/code/datasets/4_dataset_coding.py

@@ -64,7 +64,7 @@ class SimpleDarkBench(_RemoteDatasetLoader):
     def dataset_name(self) -> str:
         return "dark_bench"
 
-    async def fetch_dataset(self, *, cache: bool = True) -> SeedDataset:
+    async def fetch_dataset_async(self, *, cache: bool = True) -> SeedDataset:
         # Fetch from HuggingFace
         data = await self._fetch_from_huggingface(
             dataset_name="apart/darkbench",

pyrit/datasets/seed_datasets/local/local_dataset_loader.py

@@ -53,7 +53,7 @@ def dataset_name(self) -> str:
         """Return the dataset name."""
         return self._dataset_name
 
-    async def fetch_dataset(self, *, cache: bool = True) -> SeedDataset:
+    async def fetch_dataset_async(self, *, cache: bool = True) -> SeedDataset:
         """
         Load the dataset from the local YAML file.
 

pyrit/datasets/seed_datasets/remote/aegis_ai_content_safety_dataset.py

@@ -120,7 +120,7 @@ def dataset_name(self) -> str:
         """Return the dataset name."""
         return "aegis_content_safety"
 
-    async def fetch_dataset(self, *, cache: bool = True) -> SeedDataset:
+    async def fetch_dataset_async(self, *, cache: bool = True) -> SeedDataset:
         """
         Fetch NVIDIA Aegis AI Content Safety dataset with optional filtering and return as SeedDataset.
 

pyrit/datasets/seed_datasets/remote/aya_redteaming_dataset.py

@@ -84,7 +84,7 @@ def dataset_name(self) -> str:
         """Return the dataset name."""
         return "aya_redteaming"
 
-    async def fetch_dataset(self, *, cache: bool = True) -> SeedDataset:
+    async def fetch_dataset_async(self, *, cache: bool = True) -> SeedDataset:
         """
         Fetch Aya Red-teaming dataset with optional filtering and return as SeedDataset.
 

pyrit/datasets/seed_datasets/remote/babelscape_alert_dataset.py

@@ -51,7 +51,7 @@ def dataset_name(self) -> str:
         """Return the dataset name."""
         return "babelscape_alert"
 
-    async def fetch_dataset(self, *, cache: bool = True) -> SeedDataset:
+    async def fetch_dataset_async(self, *, cache: bool = True) -> SeedDataset:
         """
         Fetch Babelscape ALERT dataset and return as SeedDataset.
 

pyrit/datasets/seed_datasets/remote/beaver_tails_dataset.py

@@ -52,7 +52,7 @@ def dataset_name(self) -> str:
         """Return the dataset name."""
         return "beaver_tails"
 
-    async def fetch_dataset(self, *, cache: bool = True) -> SeedDataset:
+    async def fetch_dataset_async(self, *, cache: bool = True) -> SeedDataset:
         """
         Fetch BeaverTails dataset from HuggingFace and return as SeedDataset.
 

pyrit/datasets/seed_datasets/remote/cbt_bench_dataset.py

@@ -52,7 +52,7 @@ def dataset_name(self) -> str:
         """Return the dataset name."""
         return "cbt_bench"
 
-    async def fetch_dataset(self, *, cache: bool = True) -> SeedDataset:
+    async def fetch_dataset_async(self, *, cache: bool = True) -> SeedDataset:
         """
         Fetch CBT-Bench dataset from HuggingFace and return as SeedDataset.
 

pyrit/datasets/seed_datasets/remote/ccp_sensitive_prompts_dataset.py

@@ -39,7 +39,7 @@ def dataset_name(self) -> str:
         """Return the dataset name."""
         return "ccp_sensitive_prompts"
 
-    async def fetch_dataset(self, *, cache: bool = True) -> SeedDataset:
+    async def fetch_dataset_async(self, *, cache: bool = True) -> SeedDataset:
         """
         Fetch CCP-sensitive prompts dataset and return as SeedDataset.
 

pyrit/datasets/seed_datasets/remote/comic_jailbreak_dataset.py

@@ -137,7 +137,7 @@ def dataset_name(self) -> str:
         """Return the dataset name."""
         return "comic_jailbreak"
 
-    async def fetch_dataset(self, *, cache: bool = True) -> SeedDataset:
+    async def fetch_dataset_async(self, *, cache: bool = True) -> SeedDataset:
         """
         Fetch ComicJailbreak dataset and return as SeedDataset of image+text pairs.