chore: use ruff for formatting Python snippets in docs (#12245)

.pre-commit-config.yaml

@@ -17,24 +17,15 @@ repos:
         args: [--markdown-linebreak-ext=md, --markdown-linebreak-ext=mdx]
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.15.2
+    rev: v0.16.0
     hooks:
     - id: ruff-check
       args: [ --fix ]
     - id: ruff-format
+      types_or: [python, pyi, jupyter, mdx]
 
   - repo: local
     hooks:
-      - id: ruff-format-docs
-        name: ruff-format-docs
-        language: python
-        entry: python scripts/ruff_format_docs.py --line-length=88
-        files: ^docs-website/.*\.mdx$
-        types: [text]
-        additional_dependencies:
-          - ruff
-          - add-trailing-comma
-
       - id: release-note-backticks
         name: release-note-backticks
         language: python

docs-website/docs/concepts/data-classes/filecontent.mdx

@@ -99,7 +99,9 @@ After adding `FileContent` to a `ChatMessage`, use the `file` and `files` proper
 from haystack.dataclasses import ChatMessage, FileContent
 
 file_content = FileContent.from_file_path("data/invoice.pdf")
-message = ChatMessage.from_user(content_parts=[file_content, "Extract the invoice total."])
+message = ChatMessage.from_user(
+    content_parts=[file_content, "Extract the invoice total."]
+)
 
 print(message.file)
 print(message.files)

docs-website/docs/concepts/pipelines/pipeline-loops.mdx

@@ -211,14 +211,20 @@ If your pipeline seems stuck or runs longer than expected, here are common cause
 
    ```python
    # Problematic: user input goes directly to a component inside the loop
-   result = pipe.run({
-       "generator": {"prompt": query},  # This input persists and may retrigger the loop
-   })
+   result = pipe.run(
+       {
+           "generator": {
+               "prompt": query
+           },  # This input persists and may retrigger the loop
+       }
+   )
 
    # Better: use an entry-point component outside the loop
-   result = pipe.run({
-       "prompt_builder": {"query": query},  # Entry point feeds into the loop once
-   })
+   result = pipe.run(
+       {
+           "prompt_builder": {"query": query},  # Entry point feeds into the loop once
+       }
+   )
    ```
 
    See [Greedy vs. Lazy Variadic Sockets](#greedy-vs-lazy-variadic-sockets-in-loops) for details on how inputs are consumed.

docs-website/docs/development/tracing/custom-tracer.mdx

@@ -40,36 +40,40 @@ If your tracing backend isn't supported out of the box, you can connect it to Ha
    from haystack.tracing import utils as tracing_utils
    import opentelemetry.trace
 
-   class OpenTelemetrySpan(Span):
-      def __init__(self, span: opentelemetry.trace.Span) -> None:
-          self._span = span
 
-      def set_tag(self, key: str, value: Any) -> None:
-   			 # Tracing backends usually don't support any tag value
-   			 # `coerce_tag_value` forces the value to either be a Python
-   			 # primitive (int, float, boolean, str) or tries to dump it as string.
-          coerced_value = tracing_utils.coerce_tag_value(value)
-          self._span.set_attribute(key, coerced_value)
+   class OpenTelemetrySpan(Span):
+       def __init__(self, span: opentelemetry.trace.Span) -> None:
+           self._span = span
+
+       def set_tag(self, key: str, value: Any) -> None:
+           # Tracing backends usually don't support any tag value
+           # `coerce_tag_value` forces the value to either be a Python
+           # primitive (int, float, boolean, str) or tries to dump it as string.
+           coerced_value = tracing_utils.coerce_tag_value(value)
+           self._span.set_attribute(key, coerced_value)
+
 
    class OpenTelemetryTracer(Tracer):
-      def __init__(self, tracer: opentelemetry.trace.Tracer) -> None:
-          self._tracer = tracer
+       def __init__(self, tracer: opentelemetry.trace.Tracer) -> None:
+           self._tracer = tracer
 
-      @contextlib.contextmanager
-      def trace(self, operation_name: str, tags: Optional[Dict[str, Any]] = None) -> Iterator[Span]:
-          with self._tracer.start_as_current_span(operation_name) as span:
-              span = OpenTelemetrySpan(span)
-              if tags:
-                  span.set_tags(tags)
+       @contextlib.contextmanager
+       def trace(
+           self, operation_name: str, tags: Optional[Dict[str, Any]] = None
+       ) -> Iterator[Span]:
+           with self._tracer.start_as_current_span(operation_name) as span:
+               span = OpenTelemetrySpan(span)
+               if tags:
+                   span.set_tags(tags)
 
-              yield span
+               yield span
 
-      def current_span(self) -> Optional[Span]:
-          current_span = trace.get_current_span()
-          if isinstance(current_span, NonRecordingSpan):
-              return None
+       def current_span(self) -> Optional[Span]:
+           current_span = trace.get_current_span()
+           if isinstance(current_span, NonRecordingSpan):
+               return None
 
-          return OpenTelemetrySpan(current_span)
+           return OpenTelemetrySpan(current_span)
    ```
 
 2. Tell Haystack to use your custom tracer:

docs-website/docs/development/tracing/opentelemetry.mdx

@@ -132,12 +132,12 @@ Use [Jaeger](https://www.jaegertracing.io/docs/1.6/getting-started/) as a lightw
    from haystack_integrations.tracing.opentelemetry import OpenTelemetryTracer
 
    # Service name is required for most backends
-   resource = Resource(attributes={
-       ResourceAttributes.SERVICE_NAME: "haystack"
-   })
+   resource = Resource(attributes={ResourceAttributes.SERVICE_NAME: "haystack"})
 
    tracer_provider = TracerProvider(resource=resource)
-   processor = BatchSpanProcessor(OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces"))
+   processor = BatchSpanProcessor(
+       OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces")
+   )
    tracer_provider.add_span_processor(processor)
    trace.set_tracer_provider(tracer_provider)
 

docs-website/docs/document-stores/arcadedbdocumentstore.mdx

@@ -57,10 +57,12 @@ document_store = ArcadeDBDocumentStore(
     recreate_type=True,
 )
 
-document_store.write_documents([
-    Document(content="This is first", embedding=[0.0] * 768),
-    Document(content="This is second", embedding=[0.1, 0.2, 0.3] + [0.0] * 765),
-])
+document_store.write_documents(
+    [
+        Document(content="This is first", embedding=[0.0] * 768),
+        Document(content="This is second", embedding=[0.1, 0.2, 0.3] + [0.0] * 765),
+    ]
+)
 print(document_store.count_documents())
 ```
 

docs-website/docs/memory-stores/cogneememorystore.mdx

@@ -102,7 +102,9 @@ store.add_memories(
 
 # Write transient session context to the session cache.
 store.add_memories(
-    messages=[ChatMessage.from_user("Alice is currently debugging a vector store issue.")],
+    messages=[
+        ChatMessage.from_user("Alice is currently debugging a vector store issue.")
+    ],
     session_id="alice_session_1",
 )
 

docs-website/docs/memory-stores/mem0memorystore.mdx

@@ -79,7 +79,9 @@ Mem0 supports narrowing the scope of reads and writes with `user_id`, `run_id`,
 
 ```python
 store.add_memories(
-    messages=[ChatMessage.from_user("Alice is working on a documentation search system.")],
+    messages=[
+        ChatMessage.from_user("Alice is working on a documentation search system.")
+    ],
     user_id="alice",
     run_id="docs-assistant-session-1",
     infer=True,

docs-website/docs/pipeline-components/converters/imagefiletodocument.mdx

@@ -44,7 +44,6 @@ Optionally, you can provide metadata using the `meta` parameter. This can be a s
 This component is primarily meant to be used in pipelines.
 
 ```python
-
 from haystack.components.converters.image import ImageFileToDocument
 
 converter = ImageFileToDocument()

docs-website/docs/pipeline-components/converters/imagefiletoimagecontent.mdx

@@ -42,7 +42,6 @@ This component is often used in query pipelines just before a `ChatPromptBuilder
 ### On its own
 
 ```python
-
 from haystack.components.converters.image import ImageFileToImageContent
 
 converter = ImageFileToImageContent(detail="high", size=(800, 600))

docs-website/docs/pipeline-components/converters/outputadapter.mdx

@@ -101,7 +101,6 @@ assert result["output_adapter"]["output"] == "Haystack"
 You can also define your own custom filters, which can then be added to an `OutputAdapter` instance through its init method and used in templates. Here’s an example of this approach:
 
 ```python
-
 from haystack import Pipeline, component, Document
 from haystack.components.converters import OutputAdapter
 

docs-website/docs/pipeline-components/embedders/edenaidocumentembedder.mdx

@@ -78,7 +78,9 @@ document_store = InMemoryDocumentStore()
 
 indexing_pipeline = Pipeline()
 indexing_pipeline.add_component("converter", TextFileToDocument())
-indexing_pipeline.add_component("embedder", EdenAIDocumentEmbedder(model="openai/text-embedding-3-small"))
+indexing_pipeline.add_component(
+    "embedder", EdenAIDocumentEmbedder(model="openai/text-embedding-3-small")
+)
 indexing_pipeline.add_component("writer", DocumentWriter(document_store=document_store))
 
 indexing_pipeline.connect("converter", "embedder")

docs-website/docs/pipeline-components/embedders/edenaitextembedder.mdx

@@ -93,8 +93,12 @@ documents_with_embeddings = document_embedder.run(documents)["documents"]
 document_store.write_documents(documents_with_embeddings)
 
 query_pipeline = Pipeline()
-query_pipeline.add_component("text_embedder", EdenAITextEmbedder(model="openai/text-embedding-3-small"))
-query_pipeline.add_component("retriever", InMemoryEmbeddingRetriever(document_store=document_store))
+query_pipeline.add_component(
+    "text_embedder", EdenAITextEmbedder(model="openai/text-embedding-3-small")
+)
+query_pipeline.add_component(
+    "retriever", InMemoryEmbeddingRetriever(document_store=document_store)
+)
 query_pipeline.connect("text_embedder.embedding", "retriever.query_embedding")
 
 result = query_pipeline.run({"text_embedder": {"text": "Who lives in Berlin?"}})

docs-website/docs/pipeline-components/embedders/mistraltextembedder.mdx

@@ -55,7 +55,6 @@ Remember to set the`MISTRAL_API_KEY` as an environment variable first or pass it
 Here is how you can use the component on its own:
 
 ```python
-
 from haystack_integrations.components.embedders.mistral.text_embedder import (
     MistralTextEmbedder,
 )

docs-website/docs/pipeline-components/generators/anthropicchatgenerator.mdx

@@ -111,18 +111,27 @@ from haystack.dataclasses import ChatMessage
 generation_kwargs = {"extra_headers": {"anthropic-beta": "prompt-caching-2024-07-31"}}
 
 claude_llm = AnthropicChatGenerator(
-    api_key=Secret.from_env_var("ANTHROPIC_API_KEY"), generation_kwargs=generation_kwargs
+    api_key=Secret.from_env_var("ANTHROPIC_API_KEY"),
+    generation_kwargs=generation_kwargs,
 )
 
-system_message = ChatMessage.from_system("Replace with some long text documents, code or instructions")
+system_message = ChatMessage.from_system(
+    "Replace with some long text documents, code or instructions"
+)
 system_message.meta["cache_control"] = {"type": "ephemeral"}
 
-messages = [system_message, ChatMessage.from_user("A query about the long text for example")]
+messages = [
+    system_message,
+    ChatMessage.from_user("A query about the long text for example"),
+]
 result = claude_llm.run(messages)
 
 # and now invoke again with
 
-messages = [system_message, ChatMessage.from_user("Another query about the long text etc")]
+messages = [
+    system_message,
+    ChatMessage.from_user("Another query about the long text etc"),
+]
 result = claude_llm.run(messages)
 
 # and so on, either invoking component directly or in the pipeline

docs-website/docs/pipeline-components/generators/anthropicfoundrychatgenerator.mdx

@@ -80,7 +80,9 @@ You can stream output as it's generated. Pass a callback to `streaming_callback`
 ```python
 from haystack.components.generators.utils import print_streaming_chunk
 from haystack.dataclasses import ChatMessage
-from haystack_integrations.components.generators.anthropic import AnthropicFoundryChatGenerator
+from haystack_integrations.components.generators.anthropic import (
+    AnthropicFoundryChatGenerator,
+)
 
 generator = AnthropicFoundryChatGenerator(
     resource="my-resource",
@@ -102,13 +104,17 @@ See [Streaming Support](guides-to-generators/choosing-the-right-generator.mdx#st
 ```python
 import asyncio
 from haystack.dataclasses import ChatMessage
-from haystack_integrations.components.generators.anthropic import AnthropicFoundryChatGenerator
+from haystack_integrations.components.generators.anthropic import (
+    AnthropicFoundryChatGenerator,
+)
+
 
 async def main():
     generator = AnthropicFoundryChatGenerator(resource="my-resource")
     result = await generator.run_async([ChatMessage.from_user("Hello!")])
     print(result["replies"][0].text)
 
+
 asyncio.run(main())
 ```
 
@@ -125,7 +131,9 @@ pip install anthropic-haystack
 ```python
 from haystack.dataclasses import ChatMessage
 from haystack.utils import Secret
-from haystack_integrations.components.generators.anthropic import AnthropicFoundryChatGenerator
+from haystack_integrations.components.generators.anthropic import (
+    AnthropicFoundryChatGenerator,
+)
 
 generator = AnthropicFoundryChatGenerator(
     model="claude-sonnet-4-5",
@@ -143,7 +151,9 @@ print(response)
 from haystack import Pipeline
 from haystack.components.builders import ChatPromptBuilder
 from haystack.dataclasses import ChatMessage
-from haystack_integrations.components.generators.anthropic import AnthropicFoundryChatGenerator
+from haystack_integrations.components.generators.anthropic import (
+    AnthropicFoundryChatGenerator,
+)
 
 pipe = Pipeline()
 pipe.add_component("prompt_builder", ChatPromptBuilder())

docs-website/docs/pipeline-components/generators/edenaichatgenerator.mdx

@@ -118,7 +118,10 @@ question = "What is Eden AI?"
 result = rag_pipeline.run(
     {
         "fetcher": {"urls": ["https://www.edenai.co/"]},
-        "prompt_builder": {"template_variables": {"query": question}, "template": messages},
+        "prompt_builder": {
+            "template_variables": {"query": question},
+            "template": messages,
+        },
     },
 )
 

docs-website/docs/pipeline-components/preprocessors/embeddingbaseddocumentsplitter.mdx

@@ -43,7 +43,6 @@ pip install sentence-transformers-haystack
 ```
 
 ```python
-
 from haystack import Document
 from haystack_integrations.components.embedders.sentence_transformers import (
     SentenceTransformersDocumentEmbedder,

docs-website/docs/pipeline-components/preprocessors/pythoncodesplitter.mdx

@@ -112,7 +112,11 @@ result = splitter.run(
 )
 
 for chunk in result["documents"]:
-    print(chunk.meta["start_line"], chunk.meta["end_line"], chunk.meta.get("include_classes"))
+    print(
+        chunk.meta["start_line"],
+        chunk.meta["end_line"],
+        chunk.meta.get("include_classes"),
+    )
 ```
 
 ### With docstring stripping for RAG
@@ -145,7 +149,9 @@ splitter = PythonCodeSplitter(
     max_effective_lines=100,
     strip_docstrings=True,
 )
-result = splitter.run(documents=[Document(content=source, meta={"file_name": "my_module.py"})])
+result = splitter.run(
+    documents=[Document(content=source, meta={"file_name": "my_module.py"})]
+)
 for chunk in result["documents"]:
     print(chunk.content)
     print(chunk.meta.get("docstrings"))

docs-website/docs/pipeline-components/retrievers/azureaisearchbm25retriever.mdx

@@ -81,7 +81,6 @@ retriever.run(query="How many languages are spoken around the world today?")
 The below example shows how to use the `AzureAISearchBM25Retriever` in a RAG pipeline. Set your `OPENAI_API_KEY` as an environment variable and then run the following code:
 
 ```python
-
 from haystack_integrations.components.retrievers.azure_ai_search import (
     AzureAISearchBM25Retriever,
 )

docs-website/docs/pipeline-components/retrievers/elasticsearchbm25retriever.mdx

@@ -92,7 +92,6 @@ retriever.run(query="How many languages are spoken around the world today?")
 Set your `OPENAI_API_KEY` as an environment variable and then run the following code:
 
 ```python
-
 from haystack_integrations.components.retrievers.elasticsearch import (
     ElasticsearchBM25Retriever,
 )

docs-website/docs/pipeline-components/retrievers/elasticsearchsqlretriever.mdx

@@ -74,7 +74,9 @@ from haystack_integrations.document_stores.elasticsearch import (
 )
 from haystack.document_stores.types import DuplicatePolicy
 
-document_store = ElasticsearchDocumentStore(hosts="http://localhost:9200/", index="my_index")
+document_store = ElasticsearchDocumentStore(
+    hosts="http://localhost:9200/", index="my_index"
+)
 
 documents = [
     Document(content="There are over 7,000 languages spoken around the world today."),

docs-website/docs/pipeline-components/retrievers/opensearchsqlretriever.mdx

@@ -74,7 +74,9 @@ from haystack_integrations.document_stores.opensearch import (
 )
 from haystack.document_stores.types import DuplicatePolicy
 
-document_store = OpenSearchDocumentStore(hosts="http://localhost:9200", index="my_index")
+document_store = OpenSearchDocumentStore(
+    hosts="http://localhost:9200", index="my_index"
+)
 
 documents = [
     Document(content="There are over 7,000 languages spoken around the world today."),

docs-website/docs/pipeline-components/retrievers/sqlalchemytableretriever.mdx

@@ -63,7 +63,9 @@ pip install psycopg2-binary
 A self-contained example using an in-memory SQLite database seeded via `init_script`:
 
 ```python
-from haystack_integrations.components.retrievers.sqlalchemy import SQLAlchemyTableRetriever
+from haystack_integrations.components.retrievers.sqlalchemy import (
+    SQLAlchemyTableRetriever,
+)
 
 retriever = SQLAlchemyTableRetriever(
     drivername="sqlite",
@@ -83,7 +85,9 @@ Connecting to a real backend looks the same — swap the driver and pass connect
 
 ```python
 from haystack.utils import Secret
-from haystack_integrations.components.retrievers.sqlalchemy import SQLAlchemyTableRetriever
+from haystack_integrations.components.retrievers.sqlalchemy import (
+    SQLAlchemyTableRetriever,
+)
 
 retriever = SQLAlchemyTableRetriever(
     drivername="postgresql+psycopg2",
@@ -105,7 +109,9 @@ from haystack.utils import Secret
 from haystack.components.builders import ChatPromptBuilder
 from haystack.components.generators.chat import OpenAIChatGenerator
 from haystack.dataclasses import ChatMessage
-from haystack_integrations.components.retrievers.sqlalchemy import SQLAlchemyTableRetriever
+from haystack_integrations.components.retrievers.sqlalchemy import (
+    SQLAlchemyTableRetriever,
+)
 
 retriever = SQLAlchemyTableRetriever(
     drivername="postgresql+psycopg2",

docs-website/docs/pipeline-components/writers/cogneewriter.mdx

@@ -83,7 +83,9 @@ To write to the session cache instead of the permanent graph, pass a `session_id
 ```python
 session_writer = CogneeWriter(memory_store=store, session_id="alice_session_1")
 session_writer.run(
-    messages=[ChatMessage.from_user("Alice is currently debugging a vector store issue.")],
+    messages=[
+        ChatMessage.from_user("Alice is currently debugging a vector store issue.")
+    ],
     user_id="a1b2c3d4-e5f6-7890-abcd-ef1234567890",
 )
 ```

docs-website/docs/tools/tool.mdx

@@ -238,9 +238,7 @@ By default, a tool's return value is converted to a string using a default handl
 You can use `outputs_to_string` to customize this behavior using one of two formats:
 1. **Single output format**: Use `source`, `handler`, and/or `raw_result` at the root level.
     ```python
-    {
-        "source": "docs", "handler": format_documents, "raw_result": False
-    }
+    {"source": "docs", "handler": format_documents, "raw_result": False}
     ```
     - `source`: (Optional) Specifies the key to extract from the tool's output dictionary. If omitted, the entire result is passed to the handler.
     - `handler`: (Optional) A function that takes the output (or the extracted source value) and returns the final result.
@@ -252,7 +250,7 @@ You can use `outputs_to_string` to customize this behavior using one of two form
     ```python
     {
         "formatted_docs": {"source": "docs", "handler": format_documents},
-        "summary": {"source": "summary_text", "handler": str.upper}
+        "summary": {"source": "summary_text", "handler": str.upper},
     }
     ```
     Each entry defines a `source` key and can optionally include a `handler`. The individual outputs are processed,

docs-website/ruff.toml

@@ -0,0 +1,15 @@
+# Ruff configuration for the docs website.
+#
+# It applies to the Python code blocks embedded in .mdx pages, and is picked up  automatically by both `hatch run fmt`
+# and the ruff-format pre-commit hook, so the two always agree on what gets formatted.
+
+extend = "../pyproject.toml"
+
+extension = { "mdx" = "markdown" }
+
+line-length = 88
+
+extend-exclude = ["node_modules", "build", ".docusaurus", "scripts"]
+
+[format]
+skip-magic-trailing-comma = false

docs-website/versioned_docs/version-2.18/concepts/secret-management.mdx

@@ -138,7 +138,6 @@ new_env_secret = Secret.from_dict(env_secret_dict)
 Both types of secrets can be resolved to their actual values using the `resolve_value` method. This method returns the token or the value of the environment variable.
 
 ```python
-
 ## Resolve the token-based secret
 token_value = api_key_secret.resolve_value()
 

docs-website/versioned_docs/version-2.18/development/tracing.mdx

@@ -66,17 +66,22 @@ To use OpenTelemetry as your tracing backend, follow these steps:
      from opentelemetry.semconv.resource import ResourceAttributes
 
      # Service name is required for most backends
-     resource = Resource(attributes={
-         ResourceAttributes.SERVICE_NAME: "haystack"  # Correct constant
-     })
+     resource = Resource(
+         attributes={
+             ResourceAttributes.SERVICE_NAME: "haystack"  # Correct constant
+         }
+     )
 
      tracer_provider = TracerProvider(resource=resource)
-     processor = BatchSpanProcessor(OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces"))
+     processor = BatchSpanProcessor(
+         OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces")
+     )
      tracer_provider.add_span_processor(processor)
      trace.set_tracer_provider(tracer_provider)
 
      # Tell Haystack to auto-detect the configured tracer
      import haystack.tracing
+
      haystack.tracing.auto_enable_tracing()
 
      # Explicitly tell Haystack to use your tracer
@@ -156,36 +161,40 @@ To use your custom tracing backend with Haystack, follow these steps:
    from haystack.tracing import utils as tracing_utils
    import opentelemetry.trace
 
-   class OpenTelemetrySpan(Span):
-      def __init__(self, span: opentelemetry.trace.Span) -> None:
-          self._span = span
 
-      def set_tag(self, key: str, value: Any) -> None:
-   			 # Tracing backends usually don't support any tag value
-   			 # `coerce_tag_value` forces the value to either be a Python
-   			 # primitive (int, float, boolean, str) or tries to dump it as string.
-          coerced_value = tracing_utils.coerce_tag_value(value)
-          self._span.set_attribute(key, coerced_value)
+   class OpenTelemetrySpan(Span):
+       def __init__(self, span: opentelemetry.trace.Span) -> None:
+           self._span = span
+
+       def set_tag(self, key: str, value: Any) -> None:
+           # Tracing backends usually don't support any tag value
+           # `coerce_tag_value` forces the value to either be a Python
+           # primitive (int, float, boolean, str) or tries to dump it as string.
+           coerced_value = tracing_utils.coerce_tag_value(value)
+           self._span.set_attribute(key, coerced_value)
+
 
    class OpenTelemetryTracer(Tracer):
-      def __init__(self, tracer: opentelemetry.trace.Tracer) -> None:
-          self._tracer = tracer
+       def __init__(self, tracer: opentelemetry.trace.Tracer) -> None:
+           self._tracer = tracer
 
-      @contextlib.contextmanager
-      def trace(self, operation_name: str, tags: Optional[Dict[str, Any]] = None) -> Iterator[Span]:
-          with self._tracer.start_as_current_span(operation_name) as span:
-              span = OpenTelemetrySpan(span)
-              if tags:
-                  span.set_tags(tags)
+       @contextlib.contextmanager
+       def trace(
+           self, operation_name: str, tags: Optional[Dict[str, Any]] = None
+       ) -> Iterator[Span]:
+           with self._tracer.start_as_current_span(operation_name) as span:
+               span = OpenTelemetrySpan(span)
+               if tags:
+                   span.set_tags(tags)
 
-              yield span
+               yield span
 
-      def current_span(self) -> Optional[Span]:
-          current_span = trace.get_current_span()
-          if isinstance(current_span, NonRecordingSpan):
-              return None
+       def current_span(self) -> Optional[Span]:
+           current_span = trace.get_current_span()
+           if isinstance(current_span, NonRecordingSpan):
+               return None
 
-          return OpenTelemetrySpan(current_span)
+           return OpenTelemetrySpan(current_span)
    ```
 
 2. Tell Haystack to use your custom tracer:
@@ -279,12 +288,12 @@ Use [Jaeger](https://www.jaegertracing.io/docs/1.6/getting-started/) as a lightw
    from opentelemetry.sdk.trace.export import BatchSpanProcessor
 
    # Service name is required for most backends
-   resource = Resource(attributes={
-       ResourceAttributes.SERVICE_NAME: "haystack"
-   })
+   resource = Resource(attributes={ResourceAttributes.SERVICE_NAME: "haystack"})
 
    tracer_provider = TracerProvider(resource=resource)
-   processor = BatchSpanProcessor(OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces"))
+   processor = BatchSpanProcessor(
+       OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces")
+   )
    tracer_provider.add_span_processor(processor)
    trace.set_tracer_provider(tracer_provider)
    ```

docs-website/versioned_docs/version-2.18/pipeline-components/converters/imagefiletodocument.mdx

@@ -39,7 +39,6 @@ Optionally, you can provide metadata using the `meta` parameter. This can be a s
 This component is primarily meant to be used in pipelines.
 
 ```python
-
 from haystack.components.converters.image import ImageFileToDocument
 
 converter = ImageFileToDocument()

docs-website/versioned_docs/version-2.18/pipeline-components/converters/imagefiletoimagecontent.mdx

@@ -37,7 +37,6 @@ This component is often used in query pipelines just before a `ChatPromptBuilder
 ### On its own
 
 ```python
-
 from haystack.components.converters.image import ImageFileToImageContent
 
 converter = ImageFileToImageContent(detail="high", size=(800, 600))

docs-website/versioned_docs/version-2.18/pipeline-components/converters/outputadapter.mdx

@@ -96,7 +96,6 @@ assert result["output_adapter"]["output"] == "Haystack"
 You can also define your own custom filters, which can then be added to an `OutputAdapter` instance through its init method and used in templates. Here’s an example of this approach:
 
 ```python
-
 from haystack import Pipeline, component, Document
 from haystack.components.converters import OutputAdapter
 

docs-website/versioned_docs/version-2.18/pipeline-components/embedders/mistraltextembedder.mdx

@@ -50,7 +50,6 @@ Remember to set the`MISTRAL_API_KEY` as an environment variable first or pass it
 Here is how you can use the component on its own:
 
 ```python
-
 from haystack_integrations.components.embedders.mistral.text_embedder import (
     MistralTextEmbedder,
 )

docs-website/versioned_docs/version-2.18/pipeline-components/generators/anthropicchatgenerator.mdx

@@ -78,18 +78,27 @@ from haystack.dataclasses import ChatMessage
 generation_kwargs = {"extra_headers": {"anthropic-beta": "prompt-caching-2024-07-31"}}
 
 claude_llm = AnthropicChatGenerator(
-    api_key=Secret.from_env_var("ANTHROPIC_API_KEY"), generation_kwargs=generation_kwargs
+    api_key=Secret.from_env_var("ANTHROPIC_API_KEY"),
+    generation_kwargs=generation_kwargs,
 )
 
-system_message = ChatMessage.from_system("Replace with some long text documents, code or instructions")
+system_message = ChatMessage.from_system(
+    "Replace with some long text documents, code or instructions"
+)
 system_message.meta["cache_control"] = {"type": "ephemeral"}
 
-messages = [system_message, ChatMessage.from_user("A query about the long text for example")]
+messages = [
+    system_message,
+    ChatMessage.from_user("A query about the long text for example"),
+]
 result = claude_llm.run(messages)
 
 ## and now invoke again with
 
-messages = [system_message, ChatMessage.from_user("Another query about the long text etc")]
+messages = [
+    system_message,
+    ChatMessage.from_user("Another query about the long text etc"),
+]
 result = claude_llm.run(messages)
 
 ## and so on, either invoking component directly or in the pipeline

docs-website/versioned_docs/version-2.18/pipeline-components/generators/guides-to-generators/choosing-the-right-generator.mdx

@@ -141,7 +141,6 @@ Here are the components that support shared hosted models in Haystack:
   Here is an example using OctoAI and [`OpenAIChatGenerator`](../openaichatgenerator.mdx):
 
 ```python
-
 from haystack.components.generators.chat import OpenAIChatGenerator
 from haystack.utils import Secret
 from haystack.dataclasses import ChatMessage

docs-website/versioned_docs/version-2.18/pipeline-components/generators/vertexaicodegenerator.mdx

@@ -37,7 +37,9 @@ pip install google-vertex-haystack
 Basic usage:
 
 ````python
-from haystack_integrations.components.generators.google_vertex import VertexAICodeGenerator
+from haystack_integrations.components.generators.google_vertex import (
+    VertexAICodeGenerator,
+)
 
 generator = VertexAICodeGenerator()
 
@@ -45,7 +47,6 @@ result = generator.run(prefix="def to_json(data):")
 
 for answer in result["replies"]:
     print(answer)
-
 ````
 
 You can also set other parameters like the number of output tokens, temperature, stop sequences, and the number of candidates.

docs-website/versioned_docs/version-2.18/pipeline-components/generators/vertexaitextgenerator.mdx

@@ -39,13 +39,14 @@ pip install google-vertex-haystack
 Basic usage:
 
 ````python
-from haystack_integrations.components.generators.google_vertex import VertexAITextGenerator
+from haystack_integrations.components.generators.google_vertex import (
+    VertexAITextGenerator,
+)
 
 generator = VertexAITextGenerator()
 res = generator.run("Tell me a good interview question for a software engineer.")
 
 print(res["replies"][0])
-
 ````
 
 You can also set other parameters like the number of answers generated, temperature to control the randomness, and stop sequences to stop generation. For a full list of possible parameters, see the documentation of [`TextGenerationModel.predict()`](https://cloud.google.com/python/docs/reference/aiplatform/latest/vertexai.language_models.TextGenerationModel#vertexai_language_models_TextGenerationModel_predict).

docs-website/versioned_docs/version-2.18/pipeline-components/retrievers/azureaisearchbm25retriever.mdx

@@ -76,7 +76,6 @@ retriever.run(query="How many languages are spoken around the world today?")
 The below example shows how to use the `AzureAISearchBM25Retriever` in a RAG pipeline. Set your `OPENAI_API_KEY` as an environment variable and then run the following code:
 
 ```python
-
 from haystack_integrations.components.retrievers.azure_ai_search import (
     AzureAISearchBM25Retriever,
 )

docs-website/versioned_docs/version-2.18/pipeline-components/retrievers/elasticsearchbm25retriever.mdx

@@ -87,7 +87,6 @@ retriever.run(query="How many languages are spoken around the world today?")
 Set your `OPENAI_API_KEY` as an environment variable and then run the following code:
 
 ```python
-
 from haystack_integrations.components.retrievers.elasticsearch import (
     ElasticsearchBM25Retriever,
 )

docs-website/versioned_docs/version-2.19/concepts/secret-management.mdx

@@ -138,7 +138,6 @@ new_env_secret = Secret.from_dict(env_secret_dict)
 Both types of secrets can be resolved to their actual values using the `resolve_value` method. This method returns the token or the value of the environment variable.
 
 ```python
-
 ## Resolve the token-based secret
 token_value = api_key_secret.resolve_value()
 

docs-website/versioned_docs/version-2.19/development/tracing.mdx

@@ -66,17 +66,22 @@ To use OpenTelemetry as your tracing backend, follow these steps:
      from opentelemetry.semconv.resource import ResourceAttributes
 
      # Service name is required for most backends
-     resource = Resource(attributes={
-         ResourceAttributes.SERVICE_NAME: "haystack"  # Correct constant
-     })
+     resource = Resource(
+         attributes={
+             ResourceAttributes.SERVICE_NAME: "haystack"  # Correct constant
+         }
+     )
 
      tracer_provider = TracerProvider(resource=resource)
-     processor = BatchSpanProcessor(OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces"))
+     processor = BatchSpanProcessor(
+         OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces")
+     )
      tracer_provider.add_span_processor(processor)
      trace.set_tracer_provider(tracer_provider)
 
      # Tell Haystack to auto-detect the configured tracer
      import haystack.tracing
+
      haystack.tracing.auto_enable_tracing()
 
      # Explicitly tell Haystack to use your tracer
@@ -156,36 +161,40 @@ To use your custom tracing backend with Haystack, follow these steps:
    from haystack.tracing import utils as tracing_utils
    import opentelemetry.trace
 
-   class OpenTelemetrySpan(Span):
-      def __init__(self, span: opentelemetry.trace.Span) -> None:
-          self._span = span
 
-      def set_tag(self, key: str, value: Any) -> None:
-   			 # Tracing backends usually don't support any tag value
-   			 # `coerce_tag_value` forces the value to either be a Python
-   			 # primitive (int, float, boolean, str) or tries to dump it as string.
-          coerced_value = tracing_utils.coerce_tag_value(value)
-          self._span.set_attribute(key, coerced_value)
+   class OpenTelemetrySpan(Span):
+       def __init__(self, span: opentelemetry.trace.Span) -> None:
+           self._span = span
+
+       def set_tag(self, key: str, value: Any) -> None:
+           # Tracing backends usually don't support any tag value
+           # `coerce_tag_value` forces the value to either be a Python
+           # primitive (int, float, boolean, str) or tries to dump it as string.
+           coerced_value = tracing_utils.coerce_tag_value(value)
+           self._span.set_attribute(key, coerced_value)
+
 
    class OpenTelemetryTracer(Tracer):
-      def __init__(self, tracer: opentelemetry.trace.Tracer) -> None:
-          self._tracer = tracer
+       def __init__(self, tracer: opentelemetry.trace.Tracer) -> None:
+           self._tracer = tracer
 
-      @contextlib.contextmanager
-      def trace(self, operation_name: str, tags: Optional[Dict[str, Any]] = None) -> Iterator[Span]:
-          with self._tracer.start_as_current_span(operation_name) as span:
-              span = OpenTelemetrySpan(span)
-              if tags:
-                  span.set_tags(tags)
+       @contextlib.contextmanager
+       def trace(
+           self, operation_name: str, tags: Optional[Dict[str, Any]] = None
+       ) -> Iterator[Span]:
+           with self._tracer.start_as_current_span(operation_name) as span:
+               span = OpenTelemetrySpan(span)
+               if tags:
+                   span.set_tags(tags)
 
-              yield span
+               yield span
 
-      def current_span(self) -> Optional[Span]:
-          current_span = trace.get_current_span()
-          if isinstance(current_span, NonRecordingSpan):
-              return None
+       def current_span(self) -> Optional[Span]:
+           current_span = trace.get_current_span()
+           if isinstance(current_span, NonRecordingSpan):
+               return None
 
-          return OpenTelemetrySpan(current_span)
+           return OpenTelemetrySpan(current_span)
    ```
 
 2. Tell Haystack to use your custom tracer:
@@ -279,12 +288,12 @@ Use [Jaeger](https://www.jaegertracing.io/docs/1.6/getting-started/) as a lightw
    from opentelemetry.sdk.trace.export import BatchSpanProcessor
 
    # Service name is required for most backends
-   resource = Resource(attributes={
-       ResourceAttributes.SERVICE_NAME: "haystack"
-   })
+   resource = Resource(attributes={ResourceAttributes.SERVICE_NAME: "haystack"})
 
    tracer_provider = TracerProvider(resource=resource)
-   processor = BatchSpanProcessor(OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces"))
+   processor = BatchSpanProcessor(
+       OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces")
+   )
    tracer_provider.add_span_processor(processor)
    trace.set_tracer_provider(tracer_provider)
    ```

docs-website/versioned_docs/version-2.19/pipeline-components/converters/imagefiletodocument.mdx

@@ -43,7 +43,6 @@ Optionally, you can provide metadata using the `meta` parameter. This can be a s
 This component is primarily meant to be used in pipelines.
 
 ```python
-
 from haystack.components.converters.image import ImageFileToDocument
 
 converter = ImageFileToDocument()

docs-website/versioned_docs/version-2.19/pipeline-components/converters/imagefiletoimagecontent.mdx

@@ -41,7 +41,6 @@ This component is often used in query pipelines just before a `ChatPromptBuilder
 ### On its own
 
 ```python
-
 from haystack.components.converters.image import ImageFileToImageContent
 
 converter = ImageFileToImageContent(detail="high", size=(800, 600))

docs-website/versioned_docs/version-2.19/pipeline-components/converters/outputadapter.mdx

@@ -100,7 +100,6 @@ assert result["output_adapter"]["output"] == "Haystack"
 You can also define your own custom filters, which can then be added to an `OutputAdapter` instance through its init method and used in templates. Here’s an example of this approach:
 
 ```python
-
 from haystack import Pipeline, component, Document
 from haystack.components.converters import OutputAdapter
 

docs-website/versioned_docs/version-2.19/pipeline-components/embedders/mistraltextembedder.mdx

@@ -54,7 +54,6 @@ Remember to set the`MISTRAL_API_KEY` as an environment variable first or pass it
 Here is how you can use the component on its own:
 
 ```python
-
 from haystack_integrations.components.embedders.mistral.text_embedder import (
     MistralTextEmbedder,
 )

docs-website/versioned_docs/version-2.19/pipeline-components/generators/anthropicchatgenerator.mdx

@@ -111,18 +111,27 @@ from haystack.dataclasses import ChatMessage
 generation_kwargs = {"extra_headers": {"anthropic-beta": "prompt-caching-2024-07-31"}}
 
 claude_llm = AnthropicChatGenerator(
-    api_key=Secret.from_env_var("ANTHROPIC_API_KEY"), generation_kwargs=generation_kwargs
+    api_key=Secret.from_env_var("ANTHROPIC_API_KEY"),
+    generation_kwargs=generation_kwargs,
 )
 
-system_message = ChatMessage.from_system("Replace with some long text documents, code or instructions")
+system_message = ChatMessage.from_system(
+    "Replace with some long text documents, code or instructions"
+)
 system_message.meta["cache_control"] = {"type": "ephemeral"}
 
-messages = [system_message, ChatMessage.from_user("A query about the long text for example")]
+messages = [
+    system_message,
+    ChatMessage.from_user("A query about the long text for example"),
+]
 result = claude_llm.run(messages)
 
 ## and now invoke again with
 
-messages = [system_message, ChatMessage.from_user("Another query about the long text etc")]
+messages = [
+    system_message,
+    ChatMessage.from_user("Another query about the long text etc"),
+]
 result = claude_llm.run(messages)
 
 ## and so on, either invoking component directly or in the pipeline

docs-website/versioned_docs/version-2.19/pipeline-components/generators/guides-to-generators/choosing-the-right-generator.mdx

@@ -141,7 +141,6 @@ Here are the components that support shared hosted models in Haystack:
   Here is an example using OctoAI and [`OpenAIChatGenerator`](../openaichatgenerator.mdx):
 
 ```python
-
 from haystack.components.generators.chat import OpenAIChatGenerator
 from haystack.utils import Secret
 from haystack.dataclasses import ChatMessage

docs-website/versioned_docs/version-2.19/pipeline-components/generators/vertexaicodegenerator.mdx

@@ -41,7 +41,9 @@ pip install google-vertex-haystack
 Basic usage:
 
 ````python
-from haystack_integrations.components.generators.google_vertex import VertexAICodeGenerator
+from haystack_integrations.components.generators.google_vertex import (
+    VertexAICodeGenerator,
+)
 
 generator = VertexAICodeGenerator()
 
@@ -49,7 +51,6 @@ result = generator.run(prefix="def to_json(data):")
 
 for answer in result["replies"]:
     print(answer)
-
 ````
 
 You can also set other parameters like the number of output tokens, temperature, stop sequences, and the number of candidates.

docs-website/versioned_docs/version-2.19/pipeline-components/generators/vertexaitextgenerator.mdx

@@ -43,13 +43,14 @@ pip install google-vertex-haystack
 Basic usage:
 
 ````python
-from haystack_integrations.components.generators.google_vertex import VertexAITextGenerator
+from haystack_integrations.components.generators.google_vertex import (
+    VertexAITextGenerator,
+)
 
 generator = VertexAITextGenerator()
 res = generator.run("Tell me a good interview question for a software engineer.")
 
 print(res["replies"][0])
-
 ````
 
 You can also set other parameters like the number of answers generated, temperature to control the randomness, and stop sequences to stop generation. For a full list of possible parameters, see the documentation of [`TextGenerationModel.predict()`](https://cloud.google.com/python/docs/reference/aiplatform/latest/vertexai.language_models.TextGenerationModel#vertexai_language_models_TextGenerationModel_predict).

docs-website/versioned_docs/version-2.19/pipeline-components/retrievers/azureaisearchbm25retriever.mdx

@@ -80,7 +80,6 @@ retriever.run(query="How many languages are spoken around the world today?")
 The below example shows how to use the `AzureAISearchBM25Retriever` in a RAG pipeline. Set your `OPENAI_API_KEY` as an environment variable and then run the following code:
 
 ```python
-
 from haystack_integrations.components.retrievers.azure_ai_search import (
     AzureAISearchBM25Retriever,
 )

docs-website/versioned_docs/version-2.19/pipeline-components/retrievers/elasticsearchbm25retriever.mdx

@@ -91,7 +91,6 @@ retriever.run(query="How many languages are spoken around the world today?")
 Set your `OPENAI_API_KEY` as an environment variable and then run the following code:
 
 ```python
-
 from haystack_integrations.components.retrievers.elasticsearch import (
     ElasticsearchBM25Retriever,
 )

docs-website/versioned_docs/version-2.20/concepts/pipelines/pipeline-loops.mdx

@@ -211,14 +211,20 @@ If your pipeline seems stuck or runs longer than expected, here are common cause
 
    ```python
    # Problematic: user input goes directly to a component inside the loop
-   result = pipe.run({
-       "generator": {"prompt": query},  # This input persists and may retrigger the loop
-   })
+   result = pipe.run(
+       {
+           "generator": {
+               "prompt": query
+           },  # This input persists and may retrigger the loop
+       }
+   )
 
    # Better: use an entry-point component outside the loop
-   result = pipe.run({
-       "prompt_builder": {"query": query},  # Entry point feeds into the loop once
-   })
+   result = pipe.run(
+       {
+           "prompt_builder": {"query": query},  # Entry point feeds into the loop once
+       }
+   )
    ```
 
    See [Greedy vs. Lazy Variadic Sockets](#greedy-vs-lazy-variadic-sockets-in-loops) for details on how inputs are consumed.

docs-website/versioned_docs/version-2.20/concepts/secret-management.mdx

@@ -138,7 +138,6 @@ new_env_secret = Secret.from_dict(env_secret_dict)
 Both types of secrets can be resolved to their actual values using the `resolve_value` method. This method returns the token or the value of the environment variable.
 
 ```python
-
 ## Resolve the token-based secret
 token_value = api_key_secret.resolve_value()
 

docs-website/versioned_docs/version-2.20/development/tracing.mdx

@@ -66,17 +66,22 @@ To use OpenTelemetry as your tracing backend, follow these steps:
      from opentelemetry.semconv.resource import ResourceAttributes
 
      # Service name is required for most backends
-     resource = Resource(attributes={
-         ResourceAttributes.SERVICE_NAME: "haystack"  # Correct constant
-     })
+     resource = Resource(
+         attributes={
+             ResourceAttributes.SERVICE_NAME: "haystack"  # Correct constant
+         }
+     )
 
      tracer_provider = TracerProvider(resource=resource)
-     processor = BatchSpanProcessor(OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces"))
+     processor = BatchSpanProcessor(
+         OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces")
+     )
      tracer_provider.add_span_processor(processor)
      trace.set_tracer_provider(tracer_provider)
 
      # Tell Haystack to auto-detect the configured tracer
      import haystack.tracing
+
      haystack.tracing.auto_enable_tracing()
 
      # Explicitly tell Haystack to use your tracer
@@ -153,36 +158,40 @@ To use your custom tracing backend with Haystack, follow these steps:
    from haystack.tracing import utils as tracing_utils
    import opentelemetry.trace
 
-   class OpenTelemetrySpan(Span):
-      def __init__(self, span: opentelemetry.trace.Span) -> None:
-          self._span = span
 
-      def set_tag(self, key: str, value: Any) -> None:
-   			 # Tracing backends usually don't support any tag value
-   			 # `coerce_tag_value` forces the value to either be a Python
-   			 # primitive (int, float, boolean, str) or tries to dump it as string.
-          coerced_value = tracing_utils.coerce_tag_value(value)
-          self._span.set_attribute(key, coerced_value)
+   class OpenTelemetrySpan(Span):
+       def __init__(self, span: opentelemetry.trace.Span) -> None:
+           self._span = span
+
+       def set_tag(self, key: str, value: Any) -> None:
+           # Tracing backends usually don't support any tag value
+           # `coerce_tag_value` forces the value to either be a Python
+           # primitive (int, float, boolean, str) or tries to dump it as string.
+           coerced_value = tracing_utils.coerce_tag_value(value)
+           self._span.set_attribute(key, coerced_value)
+
 
    class OpenTelemetryTracer(Tracer):
-      def __init__(self, tracer: opentelemetry.trace.Tracer) -> None:
-          self._tracer = tracer
+       def __init__(self, tracer: opentelemetry.trace.Tracer) -> None:
+           self._tracer = tracer
 
-      @contextlib.contextmanager
-      def trace(self, operation_name: str, tags: Optional[Dict[str, Any]] = None) -> Iterator[Span]:
-          with self._tracer.start_as_current_span(operation_name) as span:
-              span = OpenTelemetrySpan(span)
-              if tags:
-                  span.set_tags(tags)
+       @contextlib.contextmanager
+       def trace(
+           self, operation_name: str, tags: Optional[Dict[str, Any]] = None
+       ) -> Iterator[Span]:
+           with self._tracer.start_as_current_span(operation_name) as span:
+               span = OpenTelemetrySpan(span)
+               if tags:
+                   span.set_tags(tags)
 
-              yield span
+               yield span
 
-      def current_span(self) -> Optional[Span]:
-          current_span = trace.get_current_span()
-          if isinstance(current_span, NonRecordingSpan):
-              return None
+       def current_span(self) -> Optional[Span]:
+           current_span = trace.get_current_span()
+           if isinstance(current_span, NonRecordingSpan):
+               return None
 
-          return OpenTelemetrySpan(current_span)
+           return OpenTelemetrySpan(current_span)
    ```
 
 2. Tell Haystack to use your custom tracer:
@@ -275,12 +284,12 @@ Use [Jaeger](https://www.jaegertracing.io/docs/1.6/getting-started/) as a lightw
    from opentelemetry.sdk.trace.export import BatchSpanProcessor
 
    # Service name is required for most backends
-   resource = Resource(attributes={
-       ResourceAttributes.SERVICE_NAME: "haystack"
-   })
+   resource = Resource(attributes={ResourceAttributes.SERVICE_NAME: "haystack"})
 
    tracer_provider = TracerProvider(resource=resource)
-   processor = BatchSpanProcessor(OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces"))
+   processor = BatchSpanProcessor(
+       OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces")
+   )
    tracer_provider.add_span_processor(processor)
    trace.set_tracer_provider(tracer_provider)
    ```

docs-website/versioned_docs/version-2.20/pipeline-components/converters/imagefiletodocument.mdx

@@ -43,7 +43,6 @@ Optionally, you can provide metadata using the `meta` parameter. This can be a s
 This component is primarily meant to be used in pipelines.
 
 ```python
-
 from haystack.components.converters.image import ImageFileToDocument
 
 converter = ImageFileToDocument()

docs-website/versioned_docs/version-2.20/pipeline-components/converters/imagefiletoimagecontent.mdx

@@ -41,7 +41,6 @@ This component is often used in query pipelines just before a `ChatPromptBuilder
 ### On its own
 
 ```python
-
 from haystack.components.converters.image import ImageFileToImageContent
 
 converter = ImageFileToImageContent(detail="high", size=(800, 600))

docs-website/versioned_docs/version-2.20/pipeline-components/converters/outputadapter.mdx

@@ -100,7 +100,6 @@ assert result["output_adapter"]["output"] == "Haystack"
 You can also define your own custom filters, which can then be added to an `OutputAdapter` instance through its init method and used in templates. Here’s an example of this approach:
 
 ```python
-
 from haystack import Pipeline, component, Document
 from haystack.components.converters import OutputAdapter
 

docs-website/versioned_docs/version-2.20/pipeline-components/embedders/mistraltextembedder.mdx

@@ -54,7 +54,6 @@ Remember to set the`MISTRAL_API_KEY` as an environment variable first or pass it
 Here is how you can use the component on its own:
 
 ```python
-
 from haystack_integrations.components.embedders.mistral.text_embedder import (
     MistralTextEmbedder,
 )

docs-website/versioned_docs/version-2.20/pipeline-components/generators/anthropicchatgenerator.mdx

@@ -110,18 +110,27 @@ from haystack.dataclasses import ChatMessage
 generation_kwargs = {"extra_headers": {"anthropic-beta": "prompt-caching-2024-07-31"}}
 
 claude_llm = AnthropicChatGenerator(
-    api_key=Secret.from_env_var("ANTHROPIC_API_KEY"), generation_kwargs=generation_kwargs
+    api_key=Secret.from_env_var("ANTHROPIC_API_KEY"),
+    generation_kwargs=generation_kwargs,
 )
 
-system_message = ChatMessage.from_system("Replace with some long text documents, code or instructions")
+system_message = ChatMessage.from_system(
+    "Replace with some long text documents, code or instructions"
+)
 system_message.meta["cache_control"] = {"type": "ephemeral"}
 
-messages = [system_message, ChatMessage.from_user("A query about the long text for example")]
+messages = [
+    system_message,
+    ChatMessage.from_user("A query about the long text for example"),
+]
 result = claude_llm.run(messages)
 
 ## and now invoke again with
 
-messages = [system_message, ChatMessage.from_user("Another query about the long text etc")]
+messages = [
+    system_message,
+    ChatMessage.from_user("Another query about the long text etc"),
+]
 result = claude_llm.run(messages)
 
 ## and so on, either invoking component directly or in the pipeline

docs-website/versioned_docs/version-2.20/pipeline-components/generators/guides-to-generators/choosing-the-right-generator.mdx

@@ -141,7 +141,6 @@ Here are the components that support shared hosted models in Haystack:
   Here is an example using OctoAI and [`OpenAIChatGenerator`](../openaichatgenerator.mdx):
 
 ```python
-
 from haystack.components.generators.chat import OpenAIChatGenerator
 from haystack.utils import Secret
 from haystack.dataclasses import ChatMessage

docs-website/versioned_docs/version-2.20/pipeline-components/retrievers/azureaisearchbm25retriever.mdx

@@ -80,7 +80,6 @@ retriever.run(query="How many languages are spoken around the world today?")
 The below example shows how to use the `AzureAISearchBM25Retriever` in a RAG pipeline. Set your `OPENAI_API_KEY` as an environment variable and then run the following code:
 
 ```python
-
 from haystack_integrations.components.retrievers.azure_ai_search import (
     AzureAISearchBM25Retriever,
 )

docs-website/versioned_docs/version-2.20/pipeline-components/retrievers/elasticsearchbm25retriever.mdx

@@ -91,7 +91,6 @@ retriever.run(query="How many languages are spoken around the world today?")
 Set your `OPENAI_API_KEY` as an environment variable and then run the following code:
 
 ```python
-
 from haystack_integrations.components.retrievers.elasticsearch import (
     ElasticsearchBM25Retriever,
 )

docs-website/versioned_docs/version-2.21/concepts/pipelines/pipeline-loops.mdx

@@ -211,14 +211,20 @@ If your pipeline seems stuck or runs longer than expected, here are common cause
 
    ```python
    # Problematic: user input goes directly to a component inside the loop
-   result = pipe.run({
-       "generator": {"prompt": query},  # This input persists and may retrigger the loop
-   })
+   result = pipe.run(
+       {
+           "generator": {
+               "prompt": query
+           },  # This input persists and may retrigger the loop
+       }
+   )
 
    # Better: use an entry-point component outside the loop
-   result = pipe.run({
-       "prompt_builder": {"query": query},  # Entry point feeds into the loop once
-   })
+   result = pipe.run(
+       {
+           "prompt_builder": {"query": query},  # Entry point feeds into the loop once
+       }
+   )
    ```
 
    See [Greedy vs. Lazy Variadic Sockets](#greedy-vs-lazy-variadic-sockets-in-loops) for details on how inputs are consumed.

docs-website/versioned_docs/version-2.21/concepts/secret-management.mdx

@@ -138,7 +138,6 @@ new_env_secret = Secret.from_dict(env_secret_dict)
 Both types of secrets can be resolved to their actual values using the `resolve_value` method. This method returns the token or the value of the environment variable.
 
 ```python
-
 ## Resolve the token-based secret
 token_value = api_key_secret.resolve_value()
 

docs-website/versioned_docs/version-2.21/development/tracing.mdx

@@ -66,17 +66,22 @@ To use OpenTelemetry as your tracing backend, follow these steps:
      from opentelemetry.semconv.resource import ResourceAttributes
 
      # Service name is required for most backends
-     resource = Resource(attributes={
-         ResourceAttributes.SERVICE_NAME: "haystack"  # Correct constant
-     })
+     resource = Resource(
+         attributes={
+             ResourceAttributes.SERVICE_NAME: "haystack"  # Correct constant
+         }
+     )
 
      tracer_provider = TracerProvider(resource=resource)
-     processor = BatchSpanProcessor(OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces"))
+     processor = BatchSpanProcessor(
+         OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces")
+     )
      tracer_provider.add_span_processor(processor)
      trace.set_tracer_provider(tracer_provider)
 
      # Tell Haystack to auto-detect the configured tracer
      import haystack.tracing
+
      haystack.tracing.auto_enable_tracing()
 
      # Explicitly tell Haystack to use your tracer
@@ -153,36 +158,40 @@ To use your custom tracing backend with Haystack, follow these steps:
    from haystack.tracing import utils as tracing_utils
    import opentelemetry.trace
 
-   class OpenTelemetrySpan(Span):
-      def __init__(self, span: opentelemetry.trace.Span) -> None:
-          self._span = span
 
-      def set_tag(self, key: str, value: Any) -> None:
-   			 # Tracing backends usually don't support any tag value
-   			 # `coerce_tag_value` forces the value to either be a Python
-   			 # primitive (int, float, boolean, str) or tries to dump it as string.
-          coerced_value = tracing_utils.coerce_tag_value(value)
-          self._span.set_attribute(key, coerced_value)
+   class OpenTelemetrySpan(Span):
+       def __init__(self, span: opentelemetry.trace.Span) -> None:
+           self._span = span
+
+       def set_tag(self, key: str, value: Any) -> None:
+           # Tracing backends usually don't support any tag value
+           # `coerce_tag_value` forces the value to either be a Python
+           # primitive (int, float, boolean, str) or tries to dump it as string.
+           coerced_value = tracing_utils.coerce_tag_value(value)
+           self._span.set_attribute(key, coerced_value)
+
 
    class OpenTelemetryTracer(Tracer):
-      def __init__(self, tracer: opentelemetry.trace.Tracer) -> None:
-          self._tracer = tracer
+       def __init__(self, tracer: opentelemetry.trace.Tracer) -> None:
+           self._tracer = tracer
 
-      @contextlib.contextmanager
-      def trace(self, operation_name: str, tags: Optional[Dict[str, Any]] = None) -> Iterator[Span]:
-          with self._tracer.start_as_current_span(operation_name) as span:
-              span = OpenTelemetrySpan(span)
-              if tags:
-                  span.set_tags(tags)
+       @contextlib.contextmanager
+       def trace(
+           self, operation_name: str, tags: Optional[Dict[str, Any]] = None
+       ) -> Iterator[Span]:
+           with self._tracer.start_as_current_span(operation_name) as span:
+               span = OpenTelemetrySpan(span)
+               if tags:
+                   span.set_tags(tags)
 
-              yield span
+               yield span
 
-      def current_span(self) -> Optional[Span]:
-          current_span = trace.get_current_span()
-          if isinstance(current_span, NonRecordingSpan):
-              return None
+       def current_span(self) -> Optional[Span]:
+           current_span = trace.get_current_span()
+           if isinstance(current_span, NonRecordingSpan):
+               return None
 
-          return OpenTelemetrySpan(current_span)
+           return OpenTelemetrySpan(current_span)
    ```
 
 2. Tell Haystack to use your custom tracer:
@@ -275,12 +284,12 @@ Use [Jaeger](https://www.jaegertracing.io/docs/1.6/getting-started/) as a lightw
    from opentelemetry.sdk.trace.export import BatchSpanProcessor
 
    # Service name is required for most backends
-   resource = Resource(attributes={
-       ResourceAttributes.SERVICE_NAME: "haystack"
-   })
+   resource = Resource(attributes={ResourceAttributes.SERVICE_NAME: "haystack"})
 
    tracer_provider = TracerProvider(resource=resource)
-   processor = BatchSpanProcessor(OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces"))
+   processor = BatchSpanProcessor(
+       OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces")
+   )
    tracer_provider.add_span_processor(processor)
    trace.set_tracer_provider(tracer_provider)
    ```

docs-website/versioned_docs/version-2.21/pipeline-components/converters/imagefiletodocument.mdx

@@ -43,7 +43,6 @@ Optionally, you can provide metadata using the `meta` parameter. This can be a s
 This component is primarily meant to be used in pipelines.
 
 ```python
-
 from haystack.components.converters.image import ImageFileToDocument
 
 converter = ImageFileToDocument()

docs-website/versioned_docs/version-2.21/pipeline-components/converters/imagefiletoimagecontent.mdx

@@ -41,7 +41,6 @@ This component is often used in query pipelines just before a `ChatPromptBuilder
 ### On its own
 
 ```python
-
 from haystack.components.converters.image import ImageFileToImageContent
 
 converter = ImageFileToImageContent(detail="high", size=(800, 600))

docs-website/versioned_docs/version-2.21/pipeline-components/converters/outputadapter.mdx

@@ -100,7 +100,6 @@ assert result["output_adapter"]["output"] == "Haystack"
 You can also define your own custom filters, which can then be added to an `OutputAdapter` instance through its init method and used in templates. Here’s an example of this approach:
 
 ```python
-
 from haystack import Pipeline, component, Document
 from haystack.components.converters import OutputAdapter
 

docs-website/versioned_docs/version-2.21/pipeline-components/embedders/mistraltextembedder.mdx

@@ -54,7 +54,6 @@ Remember to set the`MISTRAL_API_KEY` as an environment variable first or pass it
 Here is how you can use the component on its own:
 
 ```python
-
 from haystack_integrations.components.embedders.mistral.text_embedder import (
     MistralTextEmbedder,
 )

docs-website/versioned_docs/version-2.21/pipeline-components/generators/anthropicchatgenerator.mdx

@@ -110,18 +110,27 @@ from haystack.dataclasses import ChatMessage
 generation_kwargs = {"extra_headers": {"anthropic-beta": "prompt-caching-2024-07-31"}}
 
 claude_llm = AnthropicChatGenerator(
-    api_key=Secret.from_env_var("ANTHROPIC_API_KEY"), generation_kwargs=generation_kwargs
+    api_key=Secret.from_env_var("ANTHROPIC_API_KEY"),
+    generation_kwargs=generation_kwargs,
 )
 
-system_message = ChatMessage.from_system("Replace with some long text documents, code or instructions")
+system_message = ChatMessage.from_system(
+    "Replace with some long text documents, code or instructions"
+)
 system_message.meta["cache_control"] = {"type": "ephemeral"}
 
-messages = [system_message, ChatMessage.from_user("A query about the long text for example")]
+messages = [
+    system_message,
+    ChatMessage.from_user("A query about the long text for example"),
+]
 result = claude_llm.run(messages)
 
 ## and now invoke again with
 
-messages = [system_message, ChatMessage.from_user("Another query about the long text etc")]
+messages = [
+    system_message,
+    ChatMessage.from_user("Another query about the long text etc"),
+]
 result = claude_llm.run(messages)
 
 ## and so on, either invoking component directly or in the pipeline

docs-website/versioned_docs/version-2.21/pipeline-components/generators/guides-to-generators/choosing-the-right-generator.mdx

@@ -141,7 +141,6 @@ Here are the components that support shared hosted models in Haystack:
   Here is an example using OctoAI and [`OpenAIChatGenerator`](../openaichatgenerator.mdx):
 
 ```python
-
 from haystack.components.generators.chat import OpenAIChatGenerator
 from haystack.utils import Secret
 from haystack.dataclasses import ChatMessage

docs-website/versioned_docs/version-2.21/pipeline-components/retrievers/azureaisearchbm25retriever.mdx

@@ -80,7 +80,6 @@ retriever.run(query="How many languages are spoken around the world today?")
 The below example shows how to use the `AzureAISearchBM25Retriever` in a RAG pipeline. Set your `OPENAI_API_KEY` as an environment variable and then run the following code:
 
 ```python
-
 from haystack_integrations.components.retrievers.azure_ai_search import (
     AzureAISearchBM25Retriever,
 )

docs-website/versioned_docs/version-2.21/pipeline-components/retrievers/elasticsearchbm25retriever.mdx

@@ -91,7 +91,6 @@ retriever.run(query="How many languages are spoken around the world today?")
 Set your `OPENAI_API_KEY` as an environment variable and then run the following code:
 
 ```python
-
 from haystack_integrations.components.retrievers.elasticsearch import (
     ElasticsearchBM25Retriever,
 )

docs-website/versioned_docs/version-2.22/concepts/pipelines/pipeline-loops.mdx

@@ -211,14 +211,20 @@ If your pipeline seems stuck or runs longer than expected, here are common cause
 
    ```python
    # Problematic: user input goes directly to a component inside the loop
-   result = pipe.run({
-       "generator": {"prompt": query},  # This input persists and may retrigger the loop
-   })
+   result = pipe.run(
+       {
+           "generator": {
+               "prompt": query
+           },  # This input persists and may retrigger the loop
+       }
+   )
 
    # Better: use an entry-point component outside the loop
-   result = pipe.run({
-       "prompt_builder": {"query": query},  # Entry point feeds into the loop once
-   })
+   result = pipe.run(
+       {
+           "prompt_builder": {"query": query},  # Entry point feeds into the loop once
+       }
+   )
    ```
 
    See [Greedy vs. Lazy Variadic Sockets](#greedy-vs-lazy-variadic-sockets-in-loops) for details on how inputs are consumed.

docs-website/versioned_docs/version-2.22/concepts/secret-management.mdx

@@ -138,7 +138,6 @@ new_env_secret = Secret.from_dict(env_secret_dict)
 Both types of secrets can be resolved to their actual values using the `resolve_value` method. This method returns the token or the value of the environment variable.
 
 ```python
-
 ## Resolve the token-based secret
 token_value = api_key_secret.resolve_value()
 

docs-website/versioned_docs/version-2.22/development/tracing.mdx

@@ -66,17 +66,22 @@ To use OpenTelemetry as your tracing backend, follow these steps:
      from opentelemetry.semconv.resource import ResourceAttributes
 
      # Service name is required for most backends
-     resource = Resource(attributes={
-         ResourceAttributes.SERVICE_NAME: "haystack"  # Correct constant
-     })
+     resource = Resource(
+         attributes={
+             ResourceAttributes.SERVICE_NAME: "haystack"  # Correct constant
+         }
+     )
 
      tracer_provider = TracerProvider(resource=resource)
-     processor = BatchSpanProcessor(OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces"))
+     processor = BatchSpanProcessor(
+         OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces")
+     )
      tracer_provider.add_span_processor(processor)
      trace.set_tracer_provider(tracer_provider)
 
      # Tell Haystack to auto-detect the configured tracer
      import haystack.tracing
+
      haystack.tracing.auto_enable_tracing()
 
      # Explicitly tell Haystack to use your tracer
@@ -153,36 +158,40 @@ To use your custom tracing backend with Haystack, follow these steps:
    from haystack.tracing import utils as tracing_utils
    import opentelemetry.trace
 
-   class OpenTelemetrySpan(Span):
-      def __init__(self, span: opentelemetry.trace.Span) -> None:
-          self._span = span
 
-      def set_tag(self, key: str, value: Any) -> None:
-   			 # Tracing backends usually don't support any tag value
-   			 # `coerce_tag_value` forces the value to either be a Python
-   			 # primitive (int, float, boolean, str) or tries to dump it as string.
-          coerced_value = tracing_utils.coerce_tag_value(value)
-          self._span.set_attribute(key, coerced_value)
+   class OpenTelemetrySpan(Span):
+       def __init__(self, span: opentelemetry.trace.Span) -> None:
+           self._span = span
+
+       def set_tag(self, key: str, value: Any) -> None:
+           # Tracing backends usually don't support any tag value
+           # `coerce_tag_value` forces the value to either be a Python
+           # primitive (int, float, boolean, str) or tries to dump it as string.
+           coerced_value = tracing_utils.coerce_tag_value(value)
+           self._span.set_attribute(key, coerced_value)
+
 
    class OpenTelemetryTracer(Tracer):
-      def __init__(self, tracer: opentelemetry.trace.Tracer) -> None:
-          self._tracer = tracer
+       def __init__(self, tracer: opentelemetry.trace.Tracer) -> None:
+           self._tracer = tracer
 
-      @contextlib.contextmanager
-      def trace(self, operation_name: str, tags: Optional[Dict[str, Any]] = None) -> Iterator[Span]:
-          with self._tracer.start_as_current_span(operation_name) as span:
-              span = OpenTelemetrySpan(span)
-              if tags:
-                  span.set_tags(tags)
+       @contextlib.contextmanager
+       def trace(
+           self, operation_name: str, tags: Optional[Dict[str, Any]] = None
+       ) -> Iterator[Span]:
+           with self._tracer.start_as_current_span(operation_name) as span:
+               span = OpenTelemetrySpan(span)
+               if tags:
+                   span.set_tags(tags)
 
-              yield span
+               yield span
 
-      def current_span(self) -> Optional[Span]:
-          current_span = trace.get_current_span()
-          if isinstance(current_span, NonRecordingSpan):
-              return None
+       def current_span(self) -> Optional[Span]:
+           current_span = trace.get_current_span()
+           if isinstance(current_span, NonRecordingSpan):
+               return None
 
-          return OpenTelemetrySpan(current_span)
+           return OpenTelemetrySpan(current_span)
    ```
 
 2. Tell Haystack to use your custom tracer:
@@ -275,12 +284,12 @@ Use [Jaeger](https://www.jaegertracing.io/docs/1.6/getting-started/) as a lightw
    from opentelemetry.sdk.trace.export import BatchSpanProcessor
 
    # Service name is required for most backends
-   resource = Resource(attributes={
-       ResourceAttributes.SERVICE_NAME: "haystack"
-   })
+   resource = Resource(attributes={ResourceAttributes.SERVICE_NAME: "haystack"})
 
    tracer_provider = TracerProvider(resource=resource)
-   processor = BatchSpanProcessor(OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces"))
+   processor = BatchSpanProcessor(
+       OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces")
+   )
    tracer_provider.add_span_processor(processor)
    trace.set_tracer_provider(tracer_provider)
    ```

docs-website/versioned_docs/version-2.22/pipeline-components/converters/imagefiletodocument.mdx

@@ -43,7 +43,6 @@ Optionally, you can provide metadata using the `meta` parameter. This can be a s
 This component is primarily meant to be used in pipelines.
 
 ```python
-
 from haystack.components.converters.image import ImageFileToDocument
 
 converter = ImageFileToDocument()

docs-website/versioned_docs/version-2.22/pipeline-components/converters/imagefiletoimagecontent.mdx

@@ -41,7 +41,6 @@ This component is often used in query pipelines just before a `ChatPromptBuilder
 ### On its own
 
 ```python
-
 from haystack.components.converters.image import ImageFileToImageContent
 
 converter = ImageFileToImageContent(detail="high", size=(800, 600))

docs-website/versioned_docs/version-2.22/pipeline-components/converters/outputadapter.mdx

@@ -100,7 +100,6 @@ assert result["output_adapter"]["output"] == "Haystack"
 You can also define your own custom filters, which can then be added to an `OutputAdapter` instance through its init method and used in templates. Here’s an example of this approach:
 
 ```python
-
 from haystack import Pipeline, component, Document
 from haystack.components.converters import OutputAdapter
 

docs-website/versioned_docs/version-2.22/pipeline-components/embedders/mistraltextembedder.mdx

@@ -54,7 +54,6 @@ Remember to set the`MISTRAL_API_KEY` as an environment variable first or pass it
 Here is how you can use the component on its own:
 
 ```python
-
 from haystack_integrations.components.embedders.mistral.text_embedder import (
     MistralTextEmbedder,
 )

docs-website/versioned_docs/version-2.22/pipeline-components/generators/anthropicchatgenerator.mdx

@@ -110,18 +110,27 @@ from haystack.dataclasses import ChatMessage
 generation_kwargs = {"extra_headers": {"anthropic-beta": "prompt-caching-2024-07-31"}}
 
 claude_llm = AnthropicChatGenerator(
-    api_key=Secret.from_env_var("ANTHROPIC_API_KEY"), generation_kwargs=generation_kwargs
+    api_key=Secret.from_env_var("ANTHROPIC_API_KEY"),
+    generation_kwargs=generation_kwargs,
 )
 
-system_message = ChatMessage.from_system("Replace with some long text documents, code or instructions")
+system_message = ChatMessage.from_system(
+    "Replace with some long text documents, code or instructions"
+)
 system_message.meta["cache_control"] = {"type": "ephemeral"}
 
-messages = [system_message, ChatMessage.from_user("A query about the long text for example")]
+messages = [
+    system_message,
+    ChatMessage.from_user("A query about the long text for example"),
+]
 result = claude_llm.run(messages)
 
 ## and now invoke again with
 
-messages = [system_message, ChatMessage.from_user("Another query about the long text etc")]
+messages = [
+    system_message,
+    ChatMessage.from_user("Another query about the long text etc"),
+]
 result = claude_llm.run(messages)
 
 ## and so on, either invoking component directly or in the pipeline

docs-website/versioned_docs/version-2.22/pipeline-components/generators/guides-to-generators/choosing-the-right-generator.mdx

@@ -141,7 +141,6 @@ Here are the components that support shared hosted models in Haystack:
   Here is an example using OctoAI and [`OpenAIChatGenerator`](../openaichatgenerator.mdx):
 
 ```python
-
 from haystack.components.generators.chat import OpenAIChatGenerator
 from haystack.utils import Secret
 from haystack.dataclasses import ChatMessage

docs-website/versioned_docs/version-2.22/pipeline-components/preprocessors/embeddingbaseddocumentsplitter.mdx

@@ -36,7 +36,6 @@ This component is inspired by [5 Levels of Text Splitting](https://github.com/Fu
 ### On its own
 
 ```python
-
 from haystack import Document
 from haystack.components.embedders import SentenceTransformersDocumentEmbedder
 from haystack.components.preprocessors import EmbeddingBasedDocumentSplitter

docs-website/versioned_docs/version-2.22/pipeline-components/retrievers/azureaisearchbm25retriever.mdx

@@ -80,7 +80,6 @@ retriever.run(query="How many languages are spoken around the world today?")
 The below example shows how to use the `AzureAISearchBM25Retriever` in a RAG pipeline. Set your `OPENAI_API_KEY` as an environment variable and then run the following code:
 
 ```python
-
 from haystack_integrations.components.retrievers.azure_ai_search import (
     AzureAISearchBM25Retriever,
 )

docs-website/versioned_docs/version-2.22/pipeline-components/retrievers/elasticsearchbm25retriever.mdx

@@ -91,7 +91,6 @@ retriever.run(query="How many languages are spoken around the world today?")
 Set your `OPENAI_API_KEY` as an environment variable and then run the following code:
 
 ```python
-
 from haystack_integrations.components.retrievers.elasticsearch import (
     ElasticsearchBM25Retriever,
 )

docs-website/versioned_docs/version-2.23/concepts/pipelines/pipeline-loops.mdx

@@ -211,14 +211,20 @@ If your pipeline seems stuck or runs longer than expected, here are common cause
 
    ```python
    # Problematic: user input goes directly to a component inside the loop
-   result = pipe.run({
-       "generator": {"prompt": query},  # This input persists and may retrigger the loop
-   })
+   result = pipe.run(
+       {
+           "generator": {
+               "prompt": query
+           },  # This input persists and may retrigger the loop
+       }
+   )
 
    # Better: use an entry-point component outside the loop
-   result = pipe.run({
-       "prompt_builder": {"query": query},  # Entry point feeds into the loop once
-   })
+   result = pipe.run(
+       {
+           "prompt_builder": {"query": query},  # Entry point feeds into the loop once
+       }
+   )
    ```
 
    See [Greedy vs. Lazy Variadic Sockets](#greedy-vs-lazy-variadic-sockets-in-loops) for details on how inputs are consumed.

docs-website/versioned_docs/version-2.23/concepts/secret-management.mdx

@@ -138,7 +138,6 @@ new_env_secret = Secret.from_dict(env_secret_dict)
 Both types of secrets can be resolved to their actual values using the `resolve_value` method. This method returns the token or the value of the environment variable.
 
 ```python
-
 ## Resolve the token-based secret
 token_value = api_key_secret.resolve_value()
 

docs-website/versioned_docs/version-2.23/development/tracing.mdx

@@ -66,17 +66,22 @@ To use OpenTelemetry as your tracing backend, follow these steps:
      from opentelemetry.semconv.resource import ResourceAttributes
 
      # Service name is required for most backends
-     resource = Resource(attributes={
-         ResourceAttributes.SERVICE_NAME: "haystack"  # Correct constant
-     })
+     resource = Resource(
+         attributes={
+             ResourceAttributes.SERVICE_NAME: "haystack"  # Correct constant
+         }
+     )
 
      tracer_provider = TracerProvider(resource=resource)
-     processor = BatchSpanProcessor(OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces"))
+     processor = BatchSpanProcessor(
+         OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces")
+     )
      tracer_provider.add_span_processor(processor)
      trace.set_tracer_provider(tracer_provider)
 
      # Tell Haystack to auto-detect the configured tracer
      import haystack.tracing
+
      haystack.tracing.auto_enable_tracing()
 
      # Explicitly tell Haystack to use your tracer
@@ -153,36 +158,40 @@ To use your custom tracing backend with Haystack, follow these steps:
    from haystack.tracing import utils as tracing_utils
    import opentelemetry.trace
 
-   class OpenTelemetrySpan(Span):
-      def __init__(self, span: opentelemetry.trace.Span) -> None:
-          self._span = span
 
-      def set_tag(self, key: str, value: Any) -> None:
-   			 # Tracing backends usually don't support any tag value
-   			 # `coerce_tag_value` forces the value to either be a Python
-   			 # primitive (int, float, boolean, str) or tries to dump it as string.
-          coerced_value = tracing_utils.coerce_tag_value(value)
-          self._span.set_attribute(key, coerced_value)
+   class OpenTelemetrySpan(Span):
+       def __init__(self, span: opentelemetry.trace.Span) -> None:
+           self._span = span
+
+       def set_tag(self, key: str, value: Any) -> None:
+           # Tracing backends usually don't support any tag value
+           # `coerce_tag_value` forces the value to either be a Python
+           # primitive (int, float, boolean, str) or tries to dump it as string.
+           coerced_value = tracing_utils.coerce_tag_value(value)
+           self._span.set_attribute(key, coerced_value)
+
 
    class OpenTelemetryTracer(Tracer):
-      def __init__(self, tracer: opentelemetry.trace.Tracer) -> None:
-          self._tracer = tracer
+       def __init__(self, tracer: opentelemetry.trace.Tracer) -> None:
+           self._tracer = tracer
 
-      @contextlib.contextmanager
-      def trace(self, operation_name: str, tags: Optional[Dict[str, Any]] = None) -> Iterator[Span]:
-          with self._tracer.start_as_current_span(operation_name) as span:
-              span = OpenTelemetrySpan(span)
-              if tags:
-                  span.set_tags(tags)
+       @contextlib.contextmanager
+       def trace(
+           self, operation_name: str, tags: Optional[Dict[str, Any]] = None
+       ) -> Iterator[Span]:
+           with self._tracer.start_as_current_span(operation_name) as span:
+               span = OpenTelemetrySpan(span)
+               if tags:
+                   span.set_tags(tags)
 
-              yield span
+               yield span
 
-      def current_span(self) -> Optional[Span]:
-          current_span = trace.get_current_span()
-          if isinstance(current_span, NonRecordingSpan):
-              return None
+       def current_span(self) -> Optional[Span]:
+           current_span = trace.get_current_span()
+           if isinstance(current_span, NonRecordingSpan):
+               return None
 
-          return OpenTelemetrySpan(current_span)
+           return OpenTelemetrySpan(current_span)
    ```
 
 2. Tell Haystack to use your custom tracer:
@@ -275,12 +284,12 @@ Use [Jaeger](https://www.jaegertracing.io/docs/1.6/getting-started/) as a lightw
    from opentelemetry.sdk.trace.export import BatchSpanProcessor
 
    # Service name is required for most backends
-   resource = Resource(attributes={
-       ResourceAttributes.SERVICE_NAME: "haystack"
-   })
+   resource = Resource(attributes={ResourceAttributes.SERVICE_NAME: "haystack"})
 
    tracer_provider = TracerProvider(resource=resource)
-   processor = BatchSpanProcessor(OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces"))
+   processor = BatchSpanProcessor(
+       OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces")
+   )
    tracer_provider.add_span_processor(processor)
    trace.set_tracer_provider(tracer_provider)
    ```

docs-website/versioned_docs/version-2.23/pipeline-components/converters/imagefiletodocument.mdx

@@ -43,7 +43,6 @@ Optionally, you can provide metadata using the `meta` parameter. This can be a s
 This component is primarily meant to be used in pipelines.
 
 ```python
-
 from haystack.components.converters.image import ImageFileToDocument
 
 converter = ImageFileToDocument()

docs-website/versioned_docs/version-2.23/pipeline-components/converters/imagefiletoimagecontent.mdx

@@ -41,7 +41,6 @@ This component is often used in query pipelines just before a `ChatPromptBuilder
 ### On its own
 
 ```python
-
 from haystack.components.converters.image import ImageFileToImageContent
 
 converter = ImageFileToImageContent(detail="high", size=(800, 600))

docs-website/versioned_docs/version-2.23/pipeline-components/converters/outputadapter.mdx

@@ -100,7 +100,6 @@ assert result["output_adapter"]["output"] == "Haystack"
 You can also define your own custom filters, which can then be added to an `OutputAdapter` instance through its init method and used in templates. Here’s an example of this approach:
 
 ```python
-
 from haystack import Pipeline, component, Document
 from haystack.components.converters import OutputAdapter
 

docs-website/versioned_docs/version-2.23/pipeline-components/embedders/mistraltextembedder.mdx

@@ -54,7 +54,6 @@ Remember to set the`MISTRAL_API_KEY` as an environment variable first or pass it
 Here is how you can use the component on its own:
 
 ```python
-
 from haystack_integrations.components.embedders.mistral.text_embedder import (
     MistralTextEmbedder,
 )

docs-website/versioned_docs/version-2.23/pipeline-components/generators/anthropicchatgenerator.mdx

@@ -110,18 +110,27 @@ from haystack.dataclasses import ChatMessage
 generation_kwargs = {"extra_headers": {"anthropic-beta": "prompt-caching-2024-07-31"}}
 
 claude_llm = AnthropicChatGenerator(
-    api_key=Secret.from_env_var("ANTHROPIC_API_KEY"), generation_kwargs=generation_kwargs
+    api_key=Secret.from_env_var("ANTHROPIC_API_KEY"),
+    generation_kwargs=generation_kwargs,
 )
 
-system_message = ChatMessage.from_system("Replace with some long text documents, code or instructions")
+system_message = ChatMessage.from_system(
+    "Replace with some long text documents, code or instructions"
+)
 system_message.meta["cache_control"] = {"type": "ephemeral"}
 
-messages = [system_message, ChatMessage.from_user("A query about the long text for example")]
+messages = [
+    system_message,
+    ChatMessage.from_user("A query about the long text for example"),
+]
 result = claude_llm.run(messages)
 
 ## and now invoke again with
 
-messages = [system_message, ChatMessage.from_user("Another query about the long text etc")]
+messages = [
+    system_message,
+    ChatMessage.from_user("Another query about the long text etc"),
+]
 result = claude_llm.run(messages)
 
 ## and so on, either invoking component directly or in the pipeline

docs-website/versioned_docs/version-2.23/pipeline-components/generators/guides-to-generators/choosing-the-right-generator.mdx

@@ -141,7 +141,6 @@ Here are the components that support shared hosted models in Haystack:
   Here is an example using OctoAI and [`OpenAIChatGenerator`](../openaichatgenerator.mdx):
 
 ```python
-
 from haystack.components.generators.chat import OpenAIChatGenerator
 from haystack.utils import Secret
 from haystack.dataclasses import ChatMessage

docs-website/versioned_docs/version-2.23/pipeline-components/preprocessors/embeddingbaseddocumentsplitter.mdx

@@ -36,7 +36,6 @@ This component is inspired by [5 Levels of Text Splitting](https://github.com/Fu
 ### On its own
 
 ```python
-
 from haystack import Document
 from haystack.components.embedders import SentenceTransformersDocumentEmbedder
 from haystack.components.preprocessors import EmbeddingBasedDocumentSplitter

docs-website/versioned_docs/version-2.23/pipeline-components/retrievers/azureaisearchbm25retriever.mdx

@@ -80,7 +80,6 @@ retriever.run(query="How many languages are spoken around the world today?")
 The below example shows how to use the `AzureAISearchBM25Retriever` in a RAG pipeline. Set your `OPENAI_API_KEY` as an environment variable and then run the following code:
 
 ```python
-
 from haystack_integrations.components.retrievers.azure_ai_search import (
     AzureAISearchBM25Retriever,
 )

docs-website/versioned_docs/version-2.23/pipeline-components/retrievers/elasticsearchbm25retriever.mdx

@@ -91,7 +91,6 @@ retriever.run(query="How many languages are spoken around the world today?")
 Set your `OPENAI_API_KEY` as an environment variable and then run the following code:
 
 ```python
-
 from haystack_integrations.components.retrievers.elasticsearch import (
     ElasticsearchBM25Retriever,
 )

docs-website/versioned_docs/version-2.23/tools/tool.mdx

@@ -131,9 +131,7 @@ By default, a tool's return value is converted to a string using a default handl
 You can use `outputs_to_string` to customize this behavior using one of two formats:
 1. **Single output format**: Use `source`, `handler`, and/or `raw_result` at the root level.
     ```python
-    {
-        "source": "docs", "handler": format_documents, "raw_result": False
-    }
+    {"source": "docs", "handler": format_documents, "raw_result": False}
     ```
     - `source`: (Optional) Specifies the key to extract from the tool's output dictionary. If omitted, the entire result is passed to the handler.
     - `handler`: (Optional) A function that takes the output (or the extracted source value) and returns the final result.
@@ -145,7 +143,7 @@ You can use `outputs_to_string` to customize this behavior using one of two form
     ```python
     {
         "formatted_docs": {"source": "docs", "handler": format_documents},
-        "summary": {"source": "summary_text", "handler": str.upper}
+        "summary": {"source": "summary_text", "handler": str.upper},
     }
     ```
     Each entry defines a `source` key and can optionally include a `handler`. The individual outputs are processed,

docs-website/versioned_docs/version-2.24/concepts/pipelines/pipeline-loops.mdx

@@ -211,14 +211,20 @@ If your pipeline seems stuck or runs longer than expected, here are common cause
 
    ```python
    # Problematic: user input goes directly to a component inside the loop
-   result = pipe.run({
-       "generator": {"prompt": query},  # This input persists and may retrigger the loop
-   })
+   result = pipe.run(
+       {
+           "generator": {
+               "prompt": query
+           },  # This input persists and may retrigger the loop
+       }
+   )
 
    # Better: use an entry-point component outside the loop
-   result = pipe.run({
-       "prompt_builder": {"query": query},  # Entry point feeds into the loop once
-   })
+   result = pipe.run(
+       {
+           "prompt_builder": {"query": query},  # Entry point feeds into the loop once
+       }
+   )
    ```
 
    See [Greedy vs. Lazy Variadic Sockets](#greedy-vs-lazy-variadic-sockets-in-loops) for details on how inputs are consumed.

docs-website/versioned_docs/version-2.24/development/tracing.mdx

@@ -66,17 +66,22 @@ To use OpenTelemetry as your tracing backend, follow these steps:
      from opentelemetry.semconv.resource import ResourceAttributes
 
      # Service name is required for most backends
-     resource = Resource(attributes={
-         ResourceAttributes.SERVICE_NAME: "haystack"  # Correct constant
-     })
+     resource = Resource(
+         attributes={
+             ResourceAttributes.SERVICE_NAME: "haystack"  # Correct constant
+         }
+     )
 
      tracer_provider = TracerProvider(resource=resource)
-     processor = BatchSpanProcessor(OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces"))
+     processor = BatchSpanProcessor(
+         OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces")
+     )
      tracer_provider.add_span_processor(processor)
      trace.set_tracer_provider(tracer_provider)
 
      # Tell Haystack to auto-detect the configured tracer
      import haystack.tracing
+
      haystack.tracing.auto_enable_tracing()
 
      # Explicitly tell Haystack to use your tracer
@@ -153,36 +158,40 @@ To use your custom tracing backend with Haystack, follow these steps:
    from haystack.tracing import utils as tracing_utils
    import opentelemetry.trace
 
-   class OpenTelemetrySpan(Span):
-      def __init__(self, span: opentelemetry.trace.Span) -> None:
-          self._span = span
 
-      def set_tag(self, key: str, value: Any) -> None:
-   			 # Tracing backends usually don't support any tag value
-   			 # `coerce_tag_value` forces the value to either be a Python
-   			 # primitive (int, float, boolean, str) or tries to dump it as string.
-          coerced_value = tracing_utils.coerce_tag_value(value)
-          self._span.set_attribute(key, coerced_value)
+   class OpenTelemetrySpan(Span):
+       def __init__(self, span: opentelemetry.trace.Span) -> None:
+           self._span = span
+
+       def set_tag(self, key: str, value: Any) -> None:
+           # Tracing backends usually don't support any tag value
+           # `coerce_tag_value` forces the value to either be a Python
+           # primitive (int, float, boolean, str) or tries to dump it as string.
+           coerced_value = tracing_utils.coerce_tag_value(value)
+           self._span.set_attribute(key, coerced_value)
+
 
    class OpenTelemetryTracer(Tracer):
-      def __init__(self, tracer: opentelemetry.trace.Tracer) -> None:
-          self._tracer = tracer
+       def __init__(self, tracer: opentelemetry.trace.Tracer) -> None:
+           self._tracer = tracer
 
-      @contextlib.contextmanager
-      def trace(self, operation_name: str, tags: Optional[Dict[str, Any]] = None) -> Iterator[Span]:
-          with self._tracer.start_as_current_span(operation_name) as span:
-              span = OpenTelemetrySpan(span)
-              if tags:
-                  span.set_tags(tags)
+       @contextlib.contextmanager
+       def trace(
+           self, operation_name: str, tags: Optional[Dict[str, Any]] = None
+       ) -> Iterator[Span]:
+           with self._tracer.start_as_current_span(operation_name) as span:
+               span = OpenTelemetrySpan(span)
+               if tags:
+                   span.set_tags(tags)
 
-              yield span
+               yield span
 
-      def current_span(self) -> Optional[Span]:
-          current_span = trace.get_current_span()
-          if isinstance(current_span, NonRecordingSpan):
-              return None
+       def current_span(self) -> Optional[Span]:
+           current_span = trace.get_current_span()
+           if isinstance(current_span, NonRecordingSpan):
+               return None
 
-          return OpenTelemetrySpan(current_span)
+           return OpenTelemetrySpan(current_span)
    ```
 
 2. Tell Haystack to use your custom tracer:
@@ -275,12 +284,12 @@ Use [Jaeger](https://www.jaegertracing.io/docs/1.6/getting-started/) as a lightw
    from opentelemetry.sdk.trace.export import BatchSpanProcessor
 
    # Service name is required for most backends
-   resource = Resource(attributes={
-       ResourceAttributes.SERVICE_NAME: "haystack"
-   })
+   resource = Resource(attributes={ResourceAttributes.SERVICE_NAME: "haystack"})
 
    tracer_provider = TracerProvider(resource=resource)
-   processor = BatchSpanProcessor(OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces"))
+   processor = BatchSpanProcessor(
+       OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces")
+   )
    tracer_provider.add_span_processor(processor)
    trace.set_tracer_provider(tracer_provider)
    ```