chore: enforce ruff docstring rules (D102/D103/D205/D209/D213/D417/D419) in first 10 integrations (#3008)

Enable ruff pydocstyle rules matching haystack-ai main repo config for:
aimlapi, amazon_bedrock, anthropic, arcadedb, astra, azure_ai_search,
azure_doc_intelligence, chroma, cohere, cometapi, and the pyproject.toml template.

- Add D102, D103, D205, D209, D213, D417, D419 to ruff select in each pyproject.toml
- Ignore D rules in tests/** per-file-ignores
- Fix all resulting docstring violations (missing docstrings, blank line between summary and description)

Closes #2947

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

Author: julian-risch

integrations/aimlapi/pyproject.toml

@@ -85,6 +85,13 @@ 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",
@@ -132,7 +139,7 @@ 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/aimlapi/src/haystack_integrations/components/generators/aimlapi/chat/chat_generator.py

@@ -20,6 +20,7 @@
 class AIMLAPIChatGenerator(OpenAIChatGenerator):
     """
     Enables text generation using AIMLAPI generative models.
+
     For supported models, see AIMLAPI documentation.
 
     Users can pass any text generation parameters valid for the AIMLAPI chat completion API
@@ -73,8 +74,9 @@ def __init__(
         http_client_kwargs: dict[str, Any] | None = None,
     ) -> None:
         """
-        Creates an instance of AIMLAPIChatGenerator. Unless specified otherwise,
-        the default model is `openai/gpt-5-chat-latest`.
+        Creates an instance of AIMLAPIChatGenerator.
+
+        Unless specified otherwise, the default model is `openai/gpt-5-chat-latest`.
 
         :param api_key:
             The AIMLAPI API key.

integrations/amazon_bedrock/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",
@@ -151,7 +158,7 @@ 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_bedrock/src/haystack_integrations/common/amazon_bedrock/utils.py

@@ -30,6 +30,7 @@ def get_aws_session(
 ) -> boto3.Session | aioboto3.Session:
     """
     Creates an AWS Session with the given parameters.
+
     Checks if the provided AWS credentials are valid and can be used to connect to AWS.
 
     :param aws_access_key_id: AWS access key ID.
@@ -69,6 +70,7 @@ def get_aws_session(
 def aws_configured(**kwargs: Any) -> bool:
     """
     Checks whether AWS configuration is provided.
+
     :param kwargs: The kwargs passed down to the generator.
     :returns: True if AWS configuration is provided, False otherwise.
     """

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

@@ -53,7 +53,8 @@ def __init__(
             raise S3ConfigurationError(msg) from e
 
     def download(self, key: str, local_file_path: Path) -> None:
-        """Download a file from S3.
+        """
+        Download a file from S3.
 
         :param key: The key of the file to download.
         :param local_file_path: The folder path to download the file to.

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

@@ -24,6 +24,7 @@
 class S3Downloader:
     """
     A component for downloading files from AWS S3 Buckets to local filesystem.
+
     Supports filtering by file extensions.
     """
 
@@ -132,7 +133,8 @@ def run(
         self,
         documents: list[Document],
     ) -> dict[str, list[Document]]:
-        """Download files from AWS S3 Buckets to local filesystem.
+        """
+        Download files from AWS S3 Buckets to local filesystem.
 
         Return enriched `Document`s with the path of the downloaded file.
         :param documents: Document containing the name of the file to download in the meta field.
@@ -250,6 +252,7 @@ def to_dict(self) -> dict[str, Any]:
     def from_dict(cls, data: dict[str, Any]) -> "S3Downloader":
         """
         Deserializes the component from a dictionary.
+
         :param data:
             Dictionary to deserialize from.
         :returns:

integrations/amazon_bedrock/src/haystack_integrations/components/embedders/amazon_bedrock/document_embedder.py

@@ -22,6 +22,7 @@
 class AmazonBedrockDocumentEmbedder:
     """
     A component for computing Document embeddings using Amazon Bedrock.
+
     The embedding of each Document is stored in the `embedding` field of the Document.
 
     Usage example:
@@ -66,8 +67,9 @@ def __init__(
         **kwargs: Any,
     ) -> None:
         """
-        Initializes the AmazonBedrockDocumentEmbedder with the provided parameters. The parameters are passed to the
-        Amazon Bedrock client.
+        Initializes the AmazonBedrockDocumentEmbedder with the provided parameters.
+
+        The parameters are passed to the Amazon Bedrock client.
 
         Note that the AWS credentials are not required if the AWS environment is configured correctly. These are loaded
         automatically from the environment or the AWS configuration file and do not need to be provided explicitly via
@@ -154,6 +156,7 @@ def _prepare_texts_to_embed(self, documents: list[Document]) -> list[str]:
     def _embed_cohere(self, documents: list[Document]) -> list[Document]:
         """
         Internal method to embed Documents using Cohere models.
+
         Batch inference is supported.
         """
 
@@ -196,6 +199,7 @@ def _embed_cohere(self, documents: list[Document]) -> list[Document]:
     def _embed_titan(self, documents: list[Document]) -> list[Document]:
         """
         Internal method to embed Documents using Amazon Titan models.
+
         NOTE: Batch inference is not supported, so embeddings are created one by one.
         """
 
@@ -224,7 +228,8 @@ def _embed_titan(self, documents: list[Document]) -> list[Document]:
 
     @component.output_types(documents=list[Document])
     def run(self, documents: list[Document]) -> dict[str, list[Document]]:
-        """Embed the provided `Document`s using the specified model.
+        """
+        Embed the provided `Document`s using the specified model.
 
         :param documents: The `Document`s to embed.
         :returns: A dictionary with the following keys:

integrations/amazon_bedrock/src/haystack_integrations/components/embedders/amazon_bedrock/text_embedder.py

@@ -54,8 +54,9 @@ def __init__(
         **kwargs: Any,
     ) -> None:
         """
-        Initializes the AmazonBedrockTextEmbedder with the provided parameters. The parameters are passed to the
-        Amazon Bedrock client.
+        Initializes the AmazonBedrockTextEmbedder with the provided parameters.
+
+        The parameters are passed to the Amazon Bedrock client.
 
         Note that the AWS credentials are not required if the AWS environment is configured correctly. These are loaded
         automatically from the environment or the AWS configuration file and do not need to be provided explicitly via
@@ -118,7 +119,8 @@ def resolve_secret(secret: Secret | None) -> str | None:
 
     @component.output_types(embedding=list[float])
     def run(self, text: str) -> dict[str, list[float]]:
-        """Embeds the input text using the Amazon Bedrock model.
+        """
+        Embeds the input text using the Amazon Bedrock model.
 
         :param text: The input text to embed.
         :returns: A dictionary with the following keys:

integrations/amazon_bedrock/src/haystack_integrations/components/generators/amazon_bedrock/adapters.py

@@ -27,6 +27,7 @@ def __init__(self, model_kwargs: dict[str, Any], max_length: int | None) -> None
     def prepare_body(self, prompt: str, **inference_kwargs: Any) -> dict[str, Any]:
         """
         Prepares the body for the Amazon Bedrock request.
+
         Each subclass should implement this method to prepare the request body for the specific model.
 
         :param prompt: The prompt to be sent to the model.
@@ -374,7 +375,8 @@ class AI21LabsJurassic2Adapter(BedrockModelAdapter):
     """
 
     def prepare_body(self, prompt: str, **inference_kwargs: Any) -> dict[str, Any]:
-        """Prepares the body for the Jurassic 2 model.
+        """
+        Prepares the body for the Jurassic 2 model.
 
         :param prompt: The prompt to be sent to the model.
         :param inference_kwargs: Additional keyword arguments passed to the handler.

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

@@ -180,8 +180,9 @@ def __init__(
         tools_cachepoint_config: dict[str, str] | None = None,
     ) -> None:
         """
-        Initializes the `AmazonBedrockChatGenerator` with the provided parameters. The parameters are passed to the
-        Amazon Bedrock client.
+        Initializes the `AmazonBedrockChatGenerator` with the provided parameters.
+
+        The parameters are passed to the Amazon Bedrock client.
 
         Note that the AWS credentials are not required if the AWS environment is configured correctly. These are loaded
         automatically from the environment or the AWS configuration file and do not need to be provided explicitly via