chore: enforce ruff docstring rules in remaining integrations

integrations/amazon_sagemaker/pyproject.toml

@@ -93,6 +93,13 @@ select = [
   "ARG",
   "B",
   "C",
+  "D102",   # Missing docstring in public method
+  "D103",   # Missing docstring in public function
+  "D205",   # 1 blank line required between summary line and description
+  "D209",   # Closing triple quotes go to new line
+  "D213",   # summary lines must be positioned on the second physical line of the docstring
+  "D417",   # Missing argument descriptions in the docstring
+  "D419",   # Docstring is empty
   "DTZ",
   "E",
   "EM",
@@ -143,7 +150,7 @@ ban-relative-imports = "parents"
 
 [tool.ruff.lint.per-file-ignores]
 # Tests can use magic values, assertions, and relative imports
-"tests/**/*" = ["PLR2004", "S101", "TID252", "ANN"]
+"tests/**/*" = ["PLR2004", "S101", "TID252", "D", "ANN"]
 
 [tool.coverage.run]
 source = ["haystack_integrations"]

integrations/amazon_sagemaker/src/haystack_integrations/components/generators/amazon_sagemaker/sagemaker.py

@@ -117,6 +117,7 @@ def resolve_secret(secret: Secret | None) -> str | None:
     def _get_telemetry_data(self) -> dict[str, Any]:
         """
         Returns data that is sent to Posthog for usage analytics.
+
         :returns: A dictionary with the following keys:
             - `model`: The name of the model.
         """

integrations/arcadedb/pyproject.toml

@@ -85,7 +85,8 @@ line-length = 120
 
 [tool.ruff.lint]
 select = [
-  "A", "ANN", "ARG", "B", "C", "DTZ", "E", "EM", "F", "FBT", "I", "ICN",
+  "A", "ANN", "ARG", "B", "C", "D102", "D103", "D205", "D209", "D213", "D417", "D419",
+  "DTZ", "E", "EM", "F", "FBT", "I", "ICN",
   "ISC", "N", "PLC", "PLE", "PLR", "PLW", "Q", "RUF", "S", "T",
   "TID", "UP", "W", "YTT",
 ]

integrations/arcadedb/src/haystack_integrations/document_stores/arcadedb/document_store.py

@@ -308,6 +308,7 @@ def sort_key(value: Any) -> tuple[Any, str]:
     def _get_metadata_projection_documents(self) -> list[dict[str, Any]]:
         """
         Private helper to fetch sample documents for schema inference.
+
         Note: Does not `_ensure_initialized()`. To avoid redundant
         initialization checks during internal calls, the caller is responsible for
         ensuring the document store is initialized before invoking this method.
@@ -319,6 +320,7 @@ def _get_metadata_projection_documents(self) -> list[dict[str, Any]]:
     def _infer_metadata_field_type(values: list[Any]) -> str:
         """
         Infers the metadata field type from a list of sampled values.
+
         :param values: A list of raw Python values sampled from the field.
         :returns: A type string — one of ``"boolean"``, ``"double"``, ``"long"``, or ``"keyword"``.
             Returns ``"keyword"`` if values are empty or of mixed types.
@@ -523,7 +525,8 @@ def update_by_filter(self, filters: dict[str, Any], meta: dict[str, Any]) -> int
 
     def count_documents_by_filter(self, filters: dict[str, Any]) -> int:
         """
-        Counts the number of documents matching the provided filter
+        Counts the number of documents matching the provided filter.
+
         :param filters: The filters to apply to the documents
         :returns: The number of documents that match the filter
         """
@@ -545,6 +548,7 @@ def count_documents_by_filter(self, filters: dict[str, Any]) -> int:
     def count_unique_metadata_by_filter(self, filters: dict[str, Any], metadata_fields: list[str]) -> dict[str, int]:
         """
         Counts unique values for each metadata field in documents matching the provided filters.
+
         :param filters: The filters to apply to the document list.
         :param metadata_fields: Metadata fields for which to count unique values.
         :returns: A dictionary where keys are metadata field names and values are the
@@ -576,6 +580,7 @@ def count_unique_metadata_by_filter(self, filters: dict[str, Any], metadata_fiel
     def get_metadata_fields_info(self) -> dict[str, dict[str, str]]:
         """
         Returns the metadata fields and their corresponding types based on sampled documents.
+
         :returns: A dictionary mapping field names to dictionaries with a `type` key.
         """
         self._ensure_initialized()
@@ -602,6 +607,7 @@ def get_metadata_fields_info(self) -> dict[str, dict[str, str]]:
     def get_metadata_field_min_max(self, metadata_field: str) -> dict[str, Any]:
         """
         For a given metadata field, finds its min and max values.
+
         :param metadata_field: The metadata field to inspect.
         :returns: A dictionary with `min` and `max` keys and their corresponding values.
         """
@@ -626,8 +632,7 @@ def get_metadata_field_unique_values(
         filters: dict[str, Any] | None = None,
     ) -> tuple[list[Any], int]:
         """
-        Retrieves unique values for a field matching a search term or all possible values
-        if no search term is given.
+        Retrieves unique values for a field matching a search term, or all values if no search term is given.
 
         **Note**: values of different types are kept distinct even when they compare equal in Python, so
         the int `1`, the float `1.0`, the bool `True` and the str `"1"` are returned as four separate

integrations/azure_doc_intelligence/pyproject.toml

@@ -96,6 +96,13 @@ select = [
     "ARG",
     "B",
     "C",
+    "D102",   # Missing docstring in public method
+    "D103",   # Missing docstring in public function
+    "D205",   # 1 blank line required between summary line and description
+    "D209",   # Closing triple quotes go to new line
+    "D213",   # summary lines must be positioned on the second physical line of the docstring
+    "D417",   # Missing argument descriptions in the docstring
+    "D419",   # Docstring is empty
     "DTZ",
     "E",
     "EM",

integrations/azure_form_recognizer/pyproject.toml

@@ -101,6 +101,13 @@ select = [
     "ARG",
     "B",
     "C",
+    "D102",   # Missing docstring in public method
+    "D103",   # Missing docstring in public function
+    "D205",   # 1 blank line required between summary line and description
+    "D209",   # Closing triple quotes go to new line
+    "D213",   # summary lines must be positioned on the second physical line of the docstring
+    "D417",   # Missing argument descriptions in the docstring
+    "D419",   # Docstring is empty
     "DTZ",
     "E",
     "EM",

integrations/litellm/pyproject.toml

@@ -78,7 +78,10 @@ disallow_incomplete_defs = true
 line-length = 120
 
 [tool.ruff.lint]
-select = ["A", "B", "E", "F", "I", "N", "Q", "RUF", "S", "T", "UP", "W"]
+select = [
+  "A", "B", "D102", "D103", "D205", "D209", "D213", "D417", "D419",
+  "E", "F", "I", "N", "Q", "RUF", "S", "T", "UP", "W",
+]
 ignore = ["T201", "B027", "S105", "S106", "S107"]
 
 [tool.ruff.lint.isort]

integrations/litellm/src/haystack_integrations/components/generators/litellm/chat/chat_generator.py

@@ -33,7 +33,8 @@
 
 @component
 class LiteLLMChatGenerator:
-    """Completes chats using any of 100+ LLM providers via LiteLLM.
+    """
+    Completes chats using any of 100+ LLM providers via LiteLLM.
 
     LiteLLM routes to OpenAI, Anthropic, Google, AWS Bedrock, Azure, Cohere,
     Mistral, Groq, and many more through a single unified interface.
@@ -74,7 +75,8 @@ def __init__(
         generation_kwargs: dict[str, Any] | None = None,
         tools: ToolsType | None = None,
     ) -> None:
-        """Create a LiteLLMChatGenerator instance.
+        """
+        Create a LiteLLMChatGenerator instance.
 
         :param api_key:
             The API key for the provider. Optional: when not set, LiteLLM resolves
@@ -144,7 +146,8 @@ def run(
         *,
         tools: ToolsType | None = None,
     ) -> dict[str, list[ChatMessage]]:
-        """Invoke chat completion via LiteLLM.
+        """
+        Invoke chat completion via LiteLLM.
 
         :param messages: Input messages as ChatMessage instances.
             If a string is provided, it is converted to a list containing a ChatMessage with user role.
@@ -183,7 +186,8 @@ async def run_async(
         *,
         tools: ToolsType | None = None,
     ) -> dict[str, list[ChatMessage]]:
-        """Async version of run(). Invoke chat completion via LiteLLM.
+        """
+        Async version of run(). Invoke chat completion via LiteLLM.
 
         :param messages: Input messages as ChatMessage instances.
             If a string is provided, it is converted to a list containing a ChatMessage with user role.
@@ -316,7 +320,8 @@ def _build_chat_message(response: Any, choice: Any) -> ChatMessage:
 def _convert_litellm_chunk_to_streaming_chunk(
     chunk: Any, previous_chunks: list[StreamingChunk], component_info: ComponentInfo
 ) -> StreamingChunk:
-    """Convert a single litellm streaming chunk into a Haystack ``StreamingChunk``.
+    """
+    Convert a single litellm streaming chunk into a Haystack ``StreamingChunk``.
 
     The structured fields (``tool_calls``, ``finish_reason``, ``index``) are populated so that
     ``_convert_streaming_chunks_to_chat_message`` can reconstruct tool calls and metadata; it reads