chore: enforce ruff docstring rules in integrations 11-20 (deepeval, elasticsearch, faiss, fastembed, firecrawl, github, google_genai, hanlp, jina, kreuzberg)

integrations/deepeval/pyproject.toml

@@ -87,6 +87,13 @@ 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 = "all"
 
 [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/deepeval/src/haystack_integrations/components/evaluators/deepeval/evaluator.py

@@ -19,8 +19,10 @@
 @component
 class DeepEvalEvaluator:
     """
-    A component that uses the [DeepEval framework](https://docs.confident-ai.com/docs/evaluation-introduction)
-    to evaluate inputs against a specific metric. Supported metrics are defined by `DeepEvalMetric`.
+    A component that uses DeepEval to evaluate inputs against a specific metric.
+
+    Uses the [DeepEval framework](https://docs.confident-ai.com/docs/evaluation-introduction).
+    Supported metrics are defined by `DeepEvalMetric`.
 
     Usage example:
     ```python

integrations/elasticsearch/pyproject.toml

@@ -90,6 +90,13 @@ 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",
@@ -139,7 +146,7 @@ ban-relative-imports = "parents"
 
 [tool.ruff.lint.per-file-ignores]
 # Tests can use magic values, assertions, relative imports, and don't need type annotations
-"tests/**/*" = ["PLR2004", "S101", "TID252", "ANN"]
+"tests/**/*" = ["D", "PLR2004", "S101", "TID252", "ANN"]
 
 [tool.coverage.run]
 source = ["haystack_integrations"]

integrations/elasticsearch/src/haystack_integrations/components/retrievers/elasticsearch/bm25_retriever.py

@@ -14,8 +14,9 @@
 @component
 class ElasticsearchBM25Retriever:
     """
-    ElasticsearchBM25Retriever retrieves documents from the ElasticsearchDocumentStore using BM25 algorithm to find the
-    most similar documents to a user's query.
+    Retrieves documents from ElasticsearchDocumentStore using the BM25 algorithm.
+
+    Finds the most similar documents to a user's query.
 
     This retriever is only compatible with ElasticsearchDocumentStore.
 

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

@@ -50,8 +50,7 @@
 
 class ElasticsearchDocumentStore:
     """
-    An ElasticsearchDocumentStore instance that works with Elastic Cloud or your own
-    Elasticsearch cluster.
+    An ElasticsearchDocumentStore instance that works with Elastic Cloud or your own Elasticsearch cluster.
 
     Usage example (Elastic Cloud):
     ```python
@@ -309,6 +308,7 @@ def count_documents(self) -> int:
     async def count_documents_async(self) -> int:
         """
         Asynchronously returns how many documents are present in the document store.
+
         :returns: Number of documents in the document store.
         """
         self._ensure_initialized()
@@ -407,7 +407,9 @@ async def filter_documents_async(self, filters: dict[str, Any] | None = None) ->
     def _deserialize_document(hit: dict[str, Any]) -> Document:
         """
         Creates a `Document` from the search hit provided.
+
         This is mostly useful in self.filter_documents().
+
         :param hit: A search hit from Elasticsearch.
         :returns: `Document` created from the search hit.
         """
@@ -1136,8 +1138,7 @@ def _extract_distinct_counts_from_aggregations(
 
     def count_unique_metadata_by_filter(self, filters: dict[str, Any], metadata_fields: list[str]) -> dict[str, int]:
         """
-        Returns the number of unique values for each specified metadata field of the documents
-        that match the provided filters.
+        Returns the number of unique values for each specified metadata field that match the provided filters.
 
         :param filters: The filters to apply to count documents.
             For filter syntax, see [Haystack metadata filtering](https://docs.haystack.deepset.ai/docs/metadata-filtering)
@@ -1180,8 +1181,7 @@ async def count_unique_metadata_by_filter_async(
         self, filters: dict[str, Any], metadata_fields: list[str]
     ) -> dict[str, int]:
         """
-        Asynchronously returns the number of unique values for each specified metadata field of the documents
-        that match the provided filters.
+        Asynchronously returns unique value counts for each specified metadata field matching the provided filters.
 
         :param filters: The filters to apply to count documents.
             For filter syntax, see [Haystack metadata filtering](https://docs.haystack.deepset.ai/docs/metadata-filtering)
@@ -1352,6 +1352,7 @@ def get_metadata_field_unique_values(
     ) -> tuple[list[str], dict[str, Any] | None]:
         """
         Returns unique values for a metadata field, optionally filtered by a search term in the content.
+
         Uses composite aggregations for proper pagination beyond 10k results.
 
         See: https://www.elastic.co/docs/reference/aggregations/search-aggregations-bucket-composite-aggregation
@@ -1418,6 +1419,7 @@ async def get_metadata_field_unique_values_async(
     ) -> tuple[list[str], dict[str, Any] | None]:
         """
         Asynchronously returns unique values for a metadata field, optionally filtered by a search term in the content.
+
         Uses composite aggregations for proper pagination beyond 10k results.
 
         See: https://www.elastic.co/docs/reference/aggregations/search-aggregations-bucket-composite-aggregation

integrations/faiss/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"]
 "example/**/*" = ["T201"]
 
 [tool.coverage.run]

integrations/faiss/src/haystack_integrations/components/retrievers/faiss/embedding_retriever.py

@@ -61,6 +61,8 @@ def __init__(
         filter_policy: str | FilterPolicy = FilterPolicy.REPLACE,
     ) -> None:
         """
+        Initialize FAISSEmbeddingRetriever.
+
         :param document_store: An instance of `FAISSDocumentStore`.
         :param filters: Filters applied to the retrieved Documents at initialisation time. At runtime, these are merged
             with any runtime filters according to the `filter_policy`.

integrations/fastembed/pyproject.toml

@@ -83,6 +83,13 @@ 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",
@@ -134,7 +141,7 @@ 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 contain "print" commands
 "examples/**/*" = ["T201", "E501"]
 

integrations/fastembed/src/haystack_integrations/components/embedders/fastembed/fastembed_document_embedder.py

@@ -14,6 +14,7 @@
 class FastembedDocumentEmbedder:
     """
     FastembedDocumentEmbedder computes Document embeddings using Fastembed embedding models.
+
     The embedding of each Document is stored in the `embedding` field of the Document.
 
     Usage example:
@@ -110,6 +111,7 @@ def __init__(
     def to_dict(self) -> dict[str, Any]:
         """
         Serializes the component to a dictionary.
+
         :returns:
             Dictionary with serialized data.
         """

integrations/fastembed/src/haystack_integrations/components/embedders/fastembed/fastembed_sparse_document_embedder.py

@@ -106,6 +106,7 @@ def __init__(
     def to_dict(self) -> dict[str, Any]:
         """
         Serializes the component to a dictionary.
+
         :returns:
             Dictionary with serialized data.
         """

integrations/fastembed/src/haystack_integrations/components/rankers/fastembed/ranker.py

@@ -14,8 +14,9 @@
 @component
 class FastembedRanker:
     """
-    Ranks Documents based on their similarity to the query using
-    [Fastembed models](https://qdrant.github.io/fastembed/examples/Supported_Models/).
+    Ranks Documents based on their similarity to the query using Fastembed models.
+
+    See https://qdrant.github.io/fastembed/examples/Supported_Models/ for supported models.
 
     Documents are indexed from most to least semantically relevant to the query.
 
@@ -129,6 +130,7 @@ def warm_up(self) -> None:
     def _prepare_fastembed_input_docs(self, documents: list[Document]) -> list[str]:
         """
         Prepare the input by concatenating the document text with the metadata fields specified.
+
         :param documents: The list of Document objects.
 
         :return: A list of strings to be given as input to Fastembed model.

integrations/firecrawl/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",
@@ -147,7 +154,7 @@ 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/firecrawl/src/haystack_integrations/components/fetchers/firecrawl/firecrawl_crawler.py

@@ -125,6 +125,7 @@ async def run_async(
     def warm_up(self) -> None:
         """
         Warm up the Firecrawl client by initializing the clients.
+
         This is useful to avoid cold start delays when crawling many URLs.
         """
         if self._firecrawl_client is None:

integrations/firecrawl/src/haystack_integrations/components/websearch/firecrawl/firecrawl_websearch.py

@@ -71,6 +71,7 @@ def __init__(
     def warm_up(self) -> None:
         """
         Warm up the Firecrawl clients by initializing the sync and async clients.
+
         This is useful to avoid cold start delays when performing searches.
         """
         if self._firecrawl_client is None:

integrations/github/pyproject.toml

@@ -86,6 +86,13 @@ 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",
@@ -135,7 +142,7 @@ 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"]
 # Ignore RUF001 for all files in the prompts directory
 "src/haystack_integrations/components/prompts/**/*" = ["RUF001"]
 

integrations/google_genai/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",
@@ -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/**/*" = ["D", "PLR2004", "S101", "TID252", "ANN"]
 # Examples can use print statements
 "examples/**/*" = ["T201"]
 

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

@@ -315,6 +315,7 @@ def _handle_streaming_response(
     ) -> dict[str, list[ChatMessage]]:
         """
         Handle streaming response from Google Gen AI generate_content_stream.
+
         :param response_stream: The streaming response from generate_content_stream.
         :param streaming_callback: The callback function for streaming chunks.
         :returns: A dictionary with the replies.
@@ -346,6 +347,7 @@ async def _handle_streaming_response_async(
     ) -> dict[str, list[ChatMessage]]:
         """
         Handle async streaming response from Google Gen AI generate_content_stream.
+
         :param response_stream: The async streaming response from generate_content_stream.
         :param streaming_callback: The async callback function for streaming chunks.
         :returns: A dictionary with the replies.

integrations/google_genai/src/haystack_integrations/components/generators/google_genai/chat/utils.py

@@ -57,8 +57,9 @@
 
 def _process_response_format(generation_kwargs: dict[str, Any]) -> dict[str, Any]:
     """
-    Process `response_format` from generation_kwargs into Google GenAI's native
-    `response_schema` and `response_mime_type` parameters.
+    Process `response_format` from generation_kwargs into Google GenAI native parameters.
+
+    Converts `response_format` into `response_schema` and `response_mime_type`.
 
     Accepts either a Pydantic BaseModel class or a JSON schema dict.  When
     `response_format` is present, it is popped and replaced with the two
@@ -181,7 +182,6 @@ def remove_key_from_schema(
     """
     Recursively traverse a schema and remove all occurrences of the target key.
 
-
     :param schema: The schema dictionary/list/value to process
     :param target_key: The key to remove from all dictionaries in the schema
 
@@ -441,7 +441,8 @@ def _convert_tools_to_google_genai_format(tools: ToolsType) -> list[types.Tool]:
 def _convert_usage_metadata_to_serializable(
     usage_metadata: UsageMetadata | GenerateContentResponseUsageMetadata | None,
 ) -> dict[str, Any]:
-    """Build a JSON-serializable usage dict from a UsageMetadata object.
+    """
+    Build a JSON-serializable usage dict from a UsageMetadata object.
 
     Iterates over known UsageMetadata attribute names and adds each non-None value
     in serialized form. Full list of fields: https://ai.google.dev/api/generate-content#UsageMetadata

integrations/hanlp/pyproject.toml

@@ -100,6 +100,13 @@ 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",
@@ -152,7 +159,7 @@ 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"]