feat: Add configurable environment variable names to S3FileDownloader init params (#3015)

* feat: Add configurable environment variable names to S3FileDownloader init params

* Modify default values for S3Storage.from_env class method

* docs: Update docstrings

* docs: Fix ruff docstring error

Author: maxdswain

integrations/amazon_bedrock/src/haystack_integrations/common/s3/utils.py

@@ -100,9 +100,28 @@ def download(self, key: str, local_file_path: Path) -> None:
                 raise S3StorageError(msg) from e
 
     @classmethod
-    def from_env(cls, *, session: Session, config: Config) -> "S3Storage":
-        """Create a S3Storage object from environment variables."""
-        s3_bucket = os.getenv("S3_DOWNLOADER_BUCKET")
+    def from_env(
+        cls, *, session: Session, config: Config, s3_bucket_name_env: str = "S3_DOWNLOADER_BUCKET"
+    ) -> "S3Storage":
+        """
+        Create a S3Storage object from environment variables.
+
+        The following environment variables are read:
+        - `S3_DOWNLOADER_BUCKET` (or the value of `s3_bucket_name_env`): The name of the S3 bucket
+        to download files from. Required — raises `ValueError` if not set.
+        - `S3_DOWNLOADER_PREFIX`: Optional prefix to apply to all S3 keys (e.g. `"folder/subfolder/"`).
+        - `AWS_ENDPOINT_URL`: Optional custom endpoint URL, useful for S3-compatible services
+        such as MinIO or LocalStack.
+
+        :param session: The boto3 `Session` to use when creating the S3 client.
+        :param config: The botocore `Config` to apply to the S3 client.
+        :param s3_bucket_name_env: The name of the environment variable of the S3 bucket to download files from.
+            By default, the value is `"S3_DOWNLOADER_BUCKET"`.
+        :returns: A fully initialized `S3Storage` instance.
+        :raises ValueError: If the environment variable specified by `s3_bucket_name_env` is not set
+            or is empty.
+        """
+        s3_bucket = os.getenv(s3_bucket_name_env)
         if not s3_bucket:
             msg = (
                 "Missing environment variable S3_DOWNLOADER_BUCKET."

integrations/amazon_bedrock/src/haystack_integrations/components/downloaders/s3/s3_downloader.py

@@ -45,6 +45,7 @@ def __init__(
         max_workers: int = 32,
         max_cache_size: int = 100,
         s3_key_generation_function: Callable[[Document], str] | None = None,
+        s3_bucket_name_env: str = "S3_DOWNLOADER_BUCKET",
     ) -> None:
         """
         Initializes the `S3Downloader` with the provided parameters.
@@ -77,6 +78,8 @@ def __init__(
             The function must accept a `Document` object and return a string.
             If the environment variable `S3_DOWNLOADER_PREFIX` is set, its value will be automatically
             prefixed to the generated S3 key.
+        :param s3_bucket_name_env: The name of the environment variable of the S3 bucket to download files from.
+            By default, the value is `"S3_DOWNLOADER_BUCKET"`.
         :raises ValueError: If the `file_root_path` is not set through
             the constructor or the `FILE_ROOT_PATH` environment variable.
 
@@ -105,6 +108,7 @@ def __init__(
         self.max_cache_size = max_cache_size
         self.file_name_meta_key = file_name_meta_key
         self.s3_key_generation_function = s3_key_generation_function
+        self.s3_bucket_name_env = s3_bucket_name_env
 
         self._storage: S3Storage | None = None
 
@@ -126,7 +130,9 @@ def warm_up(self) -> None:
         """Warm up the component by initializing the settings and storage."""
         if self._storage is None:
             self.file_root_path.mkdir(parents=True, exist_ok=True)
-            self._storage = S3Storage.from_env(session=self._session, config=self._config)
+            self._storage = S3Storage.from_env(
+                session=self._session, config=self._config, s3_bucket_name_env=self.s3_bucket_name_env
+            )
 
     @component.output_types(documents=list[Document])
     def run(
@@ -246,6 +252,7 @@ def to_dict(self) -> dict[str, Any]:
             file_extensions=self.file_extensions,
             file_name_meta_key=self.file_name_meta_key,
             s3_key_generation_function=s3_key_generation_function_name,
+            s3_bucket_name_env=self.s3_bucket_name_env,
         )
 
     @classmethod

integrations/amazon_bedrock/tests/test_s3_downloader.py

@@ -59,6 +59,7 @@ def test_init_custom_parameters(self, mock_boto3_session, tmp_path):
             max_cache_size=100,
             max_workers=32,
             file_name_meta_key="file_id",
+            s3_bucket_name_env="b",
         )
         assert d.file_extensions == [".pdf", ".txt"]
 
@@ -79,6 +80,7 @@ def test_to_dict(self, mock_boto3_session: Any, tmp_path, boto3_config: dict[str
                 "max_workers": 32,
                 "file_name_meta_key": "file_name",
                 "s3_key_generation_function": None,
+                "s3_bucket_name_env": "S3_DOWNLOADER_BUCKET",
             },
         }
         assert d.to_dict() == expected
@@ -95,6 +97,7 @@ def test_from_dict(self, mock_boto3_session: Any, tmp_path, boto3_config: dict[s
                 "aws_profile_name": {"type": "env_var", "env_vars": ["AWS_PROFILE"], "strict": False},
                 "file_root_path": str(tmp_path),
                 "s3_key_generation_function": None,
+                "s3_bucket_name_env": "S3_DOWNLOADER_BUCKET",
             },
         }
         d = S3Downloader.from_dict(data)
@@ -108,6 +111,7 @@ def test_to_dict_with_parameters(self, tmp_path):
             max_workers=40,
             file_name_meta_key="new_file_key",
             s3_key_generation_function=s3_key_generation_function,
+            s3_bucket_name_env="b",
         )
         expected = {
             "type": TYPE,
@@ -123,6 +127,7 @@ def test_to_dict_with_parameters(self, tmp_path):
                 "max_workers": 40,
                 "file_name_meta_key": "new_file_key",
                 "s3_key_generation_function": "tests.test_s3_downloader.s3_key_generation_function",
+                "s3_bucket_name_env": "b",
             },
         }
         assert d.to_dict() == expected