chore: enforce ruff docstring rules (D102/D103/D205/D209/D213/D417/D419) in integrations 21-30 (#3010)

Adds D102, D103, D205, D209, D213, D417, D419 ruff rules to pyproject.toml
for: langfuse, lara, llama_cpp, llama_stack, mcp, meta_llama, mistral,
mongodb_atlas, nvidia, ollama. Fixes all resulting docstring violations.

Part of #2947

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>

Author: julian-risch

integrations/langfuse/pyproject.toml

@@ -88,6 +88,13 @@ 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",
@@ -136,10 +143,10 @@ 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/**/*" = ["D", "PLR2004", "S101", "TID252", "ANN"]
 # Examples can print their output
-"examples/**" = ["T201", "ANN"]
-"example/**" = ["T201", "ANN"]
+"examples/**" = ["T201", "ANN", "D"]
+"example/**" = ["T201", "ANN", "D"]
 "tests/**" = ["T201"]
 
 [tool.coverage.run]

integrations/langfuse/src/haystack_integrations/components/connectors/langfuse/langfuse_connector.py

@@ -19,6 +19,7 @@
 class LangfuseConnector:
     """
     LangfuseConnector connects Haystack LLM framework with [Langfuse](https://langfuse.com) in order to enable the
+
     tracing of operations and data flow within various components of a pipeline.
 
     To use LangfuseConnector, add it to your pipeline without connecting it to any other components.

integrations/langfuse/src/haystack_integrations/tracing/langfuse/tracer.py

@@ -125,6 +125,7 @@ def get_data(self) -> dict[str, Any]:
         return self._data
 
     def get_correlation_data_for_logs(self) -> dict[str, Any]:
+        """Return correlation data for log enrichment."""
         return {}
 
 
@@ -234,9 +235,11 @@ def handle(self, span: LangfuseSpan, component_type: str | None) -> None:
 
     @classmethod
     def from_dict(cls, data: dict[str, Any]) -> "SpanHandler":
+        """Deserialize a SpanHandler from a dictionary."""
         return default_from_dict(cls, data)
 
     def to_dict(self) -> dict[str, Any]:
+        """Serialize this SpanHandler to a dictionary."""
         return default_to_dict(self)
 
 
@@ -273,6 +276,7 @@ class DefaultSpanHandler(SpanHandler):
     """DefaultSpanHandler provides the default Langfuse tracing behavior for Haystack."""
 
     def create_span(self, context: SpanContext) -> LangfuseSpan:
+        """Create a Langfuse span based on the given context."""
         if self.tracer is None:
             message = (
                 "Tracer is not initialized. "
@@ -343,6 +347,7 @@ def create_span(self, context: SpanContext) -> LangfuseSpan:
             return LangfuseSpan(self.tracer.start_as_current_span(name=context.name))
 
     def handle(self, span: LangfuseSpan, component_type: str | None) -> None:
+        """Process and enrich a span after component execution."""
         # If the span is at the pipeline level, we add input and output keys to the span
         at_pipeline_level = span.get_data().get(_PIPELINE_INPUT_KEY) is not None
         if at_pipeline_level:
@@ -456,6 +461,7 @@ def __init__(
     def trace(
         self, operation_name: str, tags: dict[str, Any] | None = None, parent_span: Span | None = None
     ) -> Iterator[Span]:
+        """Create and manage a tracing span as a context manager."""
         tags = tags or {}
         span_name = tags.get(_COMPONENT_NAME_KEY, operation_name)
         component_type = tags.get(_COMPONENT_TYPE_KEY)
@@ -543,6 +549,7 @@ def trace(
                 self.flush()
 
     def flush(self) -> None:
+        """Flush all pending spans to Langfuse."""
         self._tracer.flush()
 
     def current_span(self) -> Span | None:
@@ -558,13 +565,15 @@ def current_span(self) -> Span | None:
     def get_trace_url(self) -> str:
         """
         Return the URL to the tracing data.
+
         :return: The URL to the tracing data.
         """
         return self._tracer.get_trace_url() or ""
 
     def get_trace_id(self) -> str:
         """
         Return the trace ID.
+
         :return: The trace ID.
         """
         return self._tracer.get_current_trace_id() or ""

integrations/lara/pyproject.toml

@@ -95,6 +95,13 @@ 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",
@@ -149,7 +156,7 @@ 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/**/*" = ["D", "PLR2004", "S101", "TID252", "ANN"]
 
 [tool.coverage.run]
 source = ["haystack_integrations"]

integrations/llama_cpp/pyproject.toml

@@ -99,6 +99,13 @@ 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",
@@ -142,7 +149,7 @@ 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/**/*" = ["D", "PLR2004", "S101", "TID252", "ANN"]
 # Examples can print their output
 "examples/**" = ["T201"]
 "tests/**" = ["T201"]

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

@@ -211,8 +211,11 @@ def __init__(
         model_clip_path: str | None = None,
     ) -> None:
         """
+        Initialize LlamaCppChatGenerator.
+
         :param model: The path of a quantized model for text generation, for example, "zephyr-7b-beta.Q4_0.gguf".
             If the model path is also specified in the `model_kwargs`, this parameter will be ignored.
+
         :param n_ctx: The number of tokens in the context. When set to 0, the context will be taken from the model.
         :param n_batch: Prompt processing maximum batch size.
         :param model_kwargs: Dictionary containing keyword arguments used to initialize the LLM for text generation.
@@ -274,6 +277,7 @@ def __init__(
         self._inference_lock = asyncio.Lock()
 
     def warm_up(self) -> None:
+        """Load and initialize the llama.cpp model."""
         if self._model is not None:
             return
 
@@ -462,6 +466,7 @@ def _handle_streaming_response(
     ) -> dict[str, list[ChatMessage]]:
         """
         Take streaming responses from llama.cpp, convert to Haystack StreamingChunk objects, stream them,
+
         and finally convert them to a ChatMessage.
 
         :param response_stream: The streaming responses from llama.cpp.

integrations/llama_cpp/src/haystack_integrations/components/generators/llama_cpp/generator.py

@@ -38,8 +38,11 @@ def __init__(
         generation_kwargs: dict[str, Any] | None = None,
     ) -> None:
         """
+        Initialize LlamaCppGenerator.
+
         :param model: The path of a quantized model for text generation, for example, "zephyr-7b-beta.Q4_0.gguf".
             If the model path is also specified in the `model_kwargs`, this parameter will be ignored.
+
         :param n_ctx: The number of tokens in the context. When set to 0, the context will be taken from the model.
         :param n_batch: Prompt processing maximum batch size.
         :param model_kwargs: Dictionary containing keyword arguments used to initialize the LLM for text generation.
@@ -69,6 +72,7 @@ def __init__(
         self.model: Llama | None = None
 
     def warm_up(self) -> None:
+        """Load and initialize the llama.cpp model."""
         if self.model is None:
             self.model = Llama(**self.model_kwargs)
 

integrations/llama_stack/pyproject.toml

@@ -84,6 +84,13 @@ 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",
@@ -137,7 +144,7 @@ ban-relative-imports = "parents"
 
 [tool.ruff.lint.per-file-ignores]
 # Tests can use magic values, assertions, and relative imports
-"tests/**/*" = ["PLR2004", "S101", "TID252", "ANN", "E501", "F841"]
+"tests/**/*" = ["D", "PLR2004", "S101", "TID252", "ANN", "E501", "F841"]
 # Examples can print their output and don't need type annotations
 "examples/**/*" = ["T201", "ANN"]
 

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

@@ -20,6 +20,7 @@
 class LlamaStackChatGenerator(OpenAIChatGenerator):
     """
     Enables text generation using Llama Stack framework.
+
     Llama Stack Server supports multiple inference providers, including Ollama, Together,
     and vLLM and other cloud providers.
     For a complete list of inference providers, see [Llama Stack docs](https://llama-stack.readthedocs.io/en/latest/providers/inference/index.html).
@@ -70,8 +71,10 @@ def __init__(
         http_client_kwargs: dict[str, Any] | None = None,
     ) -> None:
         """
-        Creates an instance of LlamaStackChatGenerator. To use this chat generator,
-        you need to setup Llama Stack Server with an inference provider and have a model available.
+        Creates an instance of LlamaStackChatGenerator.
+
+        To use this chat generator, you need to setup Llama Stack Server with an inference provider and have a model
+        available.
 
         :param model:
             The name of the model to use for chat completion.

integrations/mcp/pyproject.toml

@@ -99,6 +99,13 @@ 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",
@@ -153,8 +160,8 @@ ban-relative-imports = "parents"
 
 [tool.ruff.lint.per-file-ignores]
 # Tests can use magic values, assertions, and relative imports
-"tests/**/*" = ["PLR2004", "S101", "TID252", "ANN"]
-"examples/**/*" = ["T201", "E501", "ANN"]
+"tests/**/*" = ["D", "PLR2004", "S101", "TID252", "ANN"]
+"examples/**/*" = ["T201", "E501", "ANN", "D"]
 
 [tool.coverage.run]
 source = ["haystack_integrations"]