chore: import upstream snapshot with attribution

releasenotes/notes/Add-run_async-for-`OpenAITextEmbedder`-14bb634d74a65847.yaml

@@ -0,0 +1,8 @@
+---
+features:
+  - |
+    Add run_async for `OpenAITextEmbedder`.
+fixes:
+  - |
+    `OpenAITextEmbedder` no longer replaces newlines with spaces in the text to embed. This was only required for the
+    discontinued v1 embedding models.

releasenotes/notes/AnalyzeResult-forward-declaration-5ed1bd9b6dc62c6f.yaml

@@ -0,0 +1,7 @@
+---
+fixes:
+  - |
+    Forward declaration of `AnalyzeResult` type in `AzureOCRDocumentConverter`.
+
+    `AnalyzeResult` is already imported in a lazy import block.
+    The forward declaration avoids issues when `azure-ai-formrecognizer>=3.2.0b2` is not installed.

releasenotes/notes/Merge-AsyncPipeline-into-Pipeline-73c83002fd647297.yaml

@@ -0,0 +1,31 @@
+---
+upgrade:
+  - |
+    ``AsyncPipeline`` has been removed. Its asynchronous capabilities are now part of the single ``Pipeline``
+    class, which provides both a synchronous ``run`` method and the asynchronous ``run_async``,
+    ``run_async_generator``, and ``stream`` methods (mirroring how components expose ``run`` and ``run_async``).
+
+    To migrate, replace ``AsyncPipeline`` with ``Pipeline``:
+
+    .. code-block:: python
+
+        # Before
+        from haystack import AsyncPipeline
+        pipeline = AsyncPipeline()
+        result = await pipeline.run_async(data)
+
+        # After
+        from haystack import Pipeline
+        pipeline = Pipeline()
+        result = await pipeline.run_async(data)
+
+    Serialized pipelines, ``SuperComponent``s, and ``PipelineTool``s are loaded as ``Pipeline`` instances.
+
+    ``Pipeline.run`` runs synchronously and blocks until completion; in an async context use
+    ``await pipeline.run_async(...)``. The former ``AsyncPipeline.run`` was a synchronous wrapper around the
+    concurrent engine, so to preserve that behavior use ``asyncio.run(pipeline.run_async(...))``. Note that
+    ``Pipeline.run`` executes components sequentially and does not accept ``concurrency_limit``.
+
+    Both synchronous and asynchronous runs are traced under a single ``haystack.pipeline.run`` operation
+    name, distinguished by a ``haystack.pipeline.execution_mode`` tag (``sync`` or ``async``). Previously,
+    asynchronous runs used the ``haystack.async_pipeline.run`` operation name.

releasenotes/notes/Restore-Thinc-Ops-state-in-NamedEntityExtractor-spaCy-backend-44be660745d5c3b4.yaml

@@ -0,0 +1,6 @@
+---
+fixes:
+  - |
+    Fixed a bug in ``NamedEntityExtractor`` where the spaCy/Thinc device state was not correctly 
+    restored after execution, potentially affecting the device configuration of other spaCy 
+    components in the same process.

releasenotes/notes/SentenceSplitter-ReDoS-fix-ca91b020cab50bf6.yaml

@@ -0,0 +1,7 @@
+---
+security:
+  - |
+    Made QUOTE_SPANS_RE regex ReDoS-safe. This prevents potential catastrophic backtracking on malicious inputs
+fixes:
+  - |
+    Fixed a potential ReDoS issue in QUOTE_SPANS_RE regex used inside the SentenceSplitter component.

releasenotes/notes/adapt-chat-promp-builder-message-copy-6aa4de39363ffbf2.yaml

@@ -0,0 +1,4 @@
+---
+enhancements:
+  - |
+    Adapts how ChatPromptBuilder creates ChatMessages. Messages are deep copied to ensure all meta fields are copied correctly.

releasenotes/notes/adapt-gpt-generator-bb7f52bd67f6b197.yaml

@@ -0,0 +1,4 @@
+---
+preview:
+  - |
+    Adapt GPTGenerator to use strings for input and output

releasenotes/notes/add-CohereGenerator-ca55e5b8e46df754.yaml

@@ -0,0 +1,4 @@
+---
+preview:
+  - |
+    Add CohereGenerator compatible with Cohere generate endpoint

releasenotes/notes/add-MarkdownToTextDocument-f97ec6c5fb35527d.yaml

@@ -0,0 +1,4 @@
+---
+preview:
+  - |
+    Add MarkdownToTextDocument, a file converter that converts Markdown files into a text Documents.

releasenotes/notes/add-TEI-embedders-8c76593bc25a7219.yaml

@@ -0,0 +1,28 @@
+---
+features:
+  - |
+    Add HuggingFace TEI Embedders - `HuggingFaceTEITextEmbedder` and `HuggingFaceTEIDocumentEmbedder`.
+
+    An example using `HuggingFaceTEITextEmbedder` to embed a string:
+    ```python
+    from haystack.components.embedders import HuggingFaceTEITextEmbedder
+    text_to_embed = "I love pizza!"
+    text_embedder = HuggingFaceTEITextEmbedder(
+        model="BAAI/bge-small-en-v1.5", url="<your-tei-endpoint-url>", token="<your-token>"
+    )
+    print(text_embedder.run(text_to_embed))
+    # {'embedding': [0.017020374536514282, -0.023255806416273117, ...],
+    ```
+
+    An example using `HuggingFaceTEIDocumentEmbedder` to create Document embeddings:
+    ```python
+    from haystack.dataclasses import Document
+    from haystack.components.embedders import HuggingFaceTEIDocumentEmbedder
+    doc = Document(content="I love pizza!")
+    document_embedder = HuggingFaceTEIDocumentEmbedder(
+        model="BAAI/bge-small-en-v1.5", url="<your-tei-endpoint-url>", token="<your-token>"
+    )
+    result = document_embedder.run([doc])
+    print(result["documents"][0].embedding)
+    # [0.017020374536514282, -0.023255806416273117, ...]
+    ```

releasenotes/notes/add-after-tool-hook-d8d0779aaf65ce66.yaml

@@ -0,0 +1,8 @@
+---
+features:
+  - |
+    Added an ``after_tool`` hook point to the ``Agent``. Hooks registered under ``after_tool`` run after tools execute,
+    once their result messages are in ``state.data["messages"]``, and before the exit check and the next LLM call. Use it to
+    rewrite the freshly produced tool-result messages, for example to offload, redact, truncate, or summarize results
+    before the next LLM call sees them. It does not run on the plain-text exit step, where no tools run. Register it
+    like any other hook: ``hooks={"after_tool": [my_hook]}``.

releasenotes/notes/add-agent-hooks-4584408a3a2a2ad4.yaml

@@ -0,0 +1,129 @@
+---
+upgrade:
+  - |
+    ``continue_run`` is now a reserved key in ``Agent.state_schema`` (set by an ``on_exit`` hook to keep the Agent
+    running). Passing it via the ``state_schema`` argument now raises ``ValueError``. Rename any conflicting state
+    key (e.g. ``my_continue_run``) to migrate.
+features:
+  - |
+    Added hooks to the ``Agent``. Pass ``hooks`` as a dictionary mapping a hook point to a list of hooks the Agent runs
+    at that point. Each hook receives the live ``State`` and influences the run by mutating it in place; hooks for a
+    hook point run in list order, and the same hook can be registered under multiple hook points. Valid hook points are:
+    - ``before_llm``: Runs before each chat-generator call.
+    - ``before_tool``: Runs after the model requests tool calls, before any tools run. After these hooks run, the Agent
+      re-reads the current last message from ``state["messages"]``. If that message contains tool calls, those calls are
+      executed. If it does not, no tools run for that step, no tool-based exit condition is triggered, and the Agent
+      loops back to the next LLM call unless ``max_agent_steps`` has been reached.
+    - ``on_exit``: Runs when the Agent is about to stop on an exit condition. An ``on_exit`` hook can keep the Agent
+      running by setting the ``continue_run`` control flag (``state.set("continue_run", True)``), usually alongside a
+      message telling the model what to do next. ``on_exit`` hooks run when the Agent stops on an exit condition, but
+      not when it stops because ``max_agent_steps`` is reached.
+
+    A hook is any object with a ``run(state)`` method (optionally ``run_async(state)``); use the ``@hook`` decorator
+    to build one from a function. This enables patterns such as building run-time system context, retrieving memories,
+    and requiring a tool to be called before finishing.
+
+    The example below registers one hook at each placement to show what each can do:
+
+    .. code-block:: python
+
+        from datetime import datetime, timezone
+        from typing import Annotated
+
+        from haystack.components.agents import Agent
+        from haystack.components.agents.state import State, replace_values
+        from haystack.components.generators.chat import OpenAIChatGenerator
+        from haystack.dataclasses import ChatMessage
+        from haystack.hooks import hook
+        from haystack.tools import tool
+
+
+        @tool
+        def search(query: Annotated[str, "The search query"]) -> str:
+            """Search the web."""
+            # Placeholder: would call a real search API
+            return "Fusion startups reported net-energy-gain milestones this year."
+
+
+        @hook
+        def build_context(state: State) -> None:
+            # before_llm: build run-time system context once, before the first model call.
+            if state.get("step_count") == 0:
+                now = datetime.now(timezone.utc).strftime("%Y-%m-%d %H:%M UTC")
+                system = ChatMessage.from_system(f"You are a research assistant. The current time is {now}.")
+                state.set("messages", [system, *state.data["messages"]], handler_override=replace_values)
+
+
+        @hook
+        def audit_tool_calls(state: State) -> None:
+            # before_tool: see which tools the model is about to run.
+            pending = state.data["messages"][-1].tool_calls
+            print(f"about to run: {[tc.tool_name for tc in pending]}")
+
+
+        @hook
+        def require_search(state: State) -> None:
+            # on_exit: keep going until the agent has actually searched.
+            if state.get("tool_call_counts", {}).get("search", 0) == 0:
+                state.set("messages", [ChatMessage.from_system("Search before answering.")])
+                state.set("continue_run", True)
+
+
+        agent = Agent(
+            chat_generator=OpenAIChatGenerator(model="gpt-5.4-nano"),
+            tools=[search],
+            hooks={
+                "before_llm": [build_context],
+                "before_tool": [audit_tool_calls],
+                "on_exit": [require_search],
+            },
+        )
+
+        result = agent.run(messages=[ChatMessage.from_user("What are the latest developments in fusion energy?")])
+        print(result["last_message"].text)
+
+    Class-based hooks may also implement the optional lifecycle methods ``warm_up`` / ``warm_up_async`` and
+    ``close`` / ``close_async``. The Agent calls them from its own ``warm_up`` / ``warm_up_async`` and
+    ``close`` / ``close_async``, so a hook can defer opening clients or reading credentials until warm-up and release
+    them on close. When a class-based hook should be serializable, store serializable constructor arguments on the hook
+    and rebuild runtime clients from those values. For example, an ``on_exit`` hook can grade the Agent's answer with
+    its own LLM and ask it to improve a weak answer before finishing, warming the judge's client during the Agent's
+    warm-up:
+
+    .. code-block:: python
+
+        from typing import Any
+        from haystack.core.serialization import default_from_dict, default_to_dict
+
+
+        class GradeFinalAnswer:
+            """Grade the Agent's answer with an LLM and ask it to improve a weak answer before finishing."""
+
+            def __init__(self, model: str = "gpt-5.4-nano"):
+                self.model = model
+                self._judge = OpenAIChatGenerator(model=self.model)
+
+            def warm_up(self) -> None:
+                # Warm up the judge's own client during the Agent's warm-up.
+                self._judge.warm_up()
+
+            def run(self, state: State) -> None:
+                answer = state.data["messages"][-1].text or ""
+                verdict = self._judge.run(
+                    messages=[ChatMessage.from_user(f"Reply with only PASS or FAIL. Is this answer complete?\n\n{answer}")]
+                )["replies"][0].text or ""
+                if "FAIL" in verdict.upper():
+                    state.set("messages", [ChatMessage.from_user("Your answer was incomplete. Please improve it.")])
+                    state.set("continue_run", True)
+
+            def to_dict(self) -> dict[str, Any]:
+                return default_to_dict(self, model=self.model)
+
+            @classmethod
+            def from_dict(cls, data: dict[str, Any]) -> "GradeFinalAnswer":
+                return default_from_dict(cls, data)
+
+
+        agent = Agent(chat_generator=OpenAIChatGenerator(model="gpt-5.4-nano"), hooks={"on_exit": [GradeFinalAnswer()]})
+        result = agent.run(messages=[ChatMessage.from_user("Explain how vaccines work.")])
+        print(result["last_message"].text)

releasenotes/notes/add-answerbuilder-2.0-5dd255eeba68041f.yaml

@@ -0,0 +1,4 @@
+---
+preview:
+  - |
+    Add the `AnswerBuilder` component for Haystack 2.0 that creates Answer objects from the string output of Generators.

releasenotes/notes/add-apple-silicon-gpu-acceleration-38bf69781a933b95.yaml

@@ -0,0 +1,4 @@
+---
+enhancements:
+  - |
+    Added support for Apple Silicon GPU acceleration through "mps pytorch", enabling better performance on Apple M1 hardware.

releasenotes/notes/add-apply_filter_policy-function-ae3152e6afe0ca57.yaml

@@ -0,0 +1,4 @@
+---
+enhancements:
+  - |
+    Added the apply_filter_policy function to standardize the application of filter policies across all document store-specific retrievers, allowing for consistent handling of initial and runtime filters based on the chosen policy (replace or merge).

releasenotes/notes/add-async-support-for-HuggingFaceAPIDocumentEmbedder-016bbb1f8964cf3f.yaml

@@ -0,0 +1,5 @@
+---
+features:
+  - |
+    Add `run_async` method to HuggingFaceAPIDocumentEmbedder. This method enriches Documents with embeddings.
+    It supports the same parameters as the `run` method. It returns a coroutine that can be awaited.

releasenotes/notes/add-async-tool-invocation-f0b95da0d1cff332.yaml

@@ -0,0 +1,20 @@
+---
+features:
+  - |
+    Add native async tool invocation. ``Tool`` now accepts an optional ``async_function`` (a coroutine function) alongside the existing ``function`` field.
+    When ``Agent.run_async`` invokes a tool, it now awaits the ``async_function`` of Tool if available.
+
+    ``@tool`` / ``create_tool_from_function`` automatically routes ``async def`` callables to ``async_function``, so simply decorating an ``async def`` produces an async tool:
+
+    .. code-block:: python
+
+        from typing import Annotated
+        from haystack.tools import tool
+
+        @tool
+        async def weather(city: Annotated[str, "The name of the city"]) -> str:
+            """Get the weather for a city."""
+            ...
+
+    ``ComponentTool`` automatically wires an async invoker for components that define ``run_async`` (``__haystack_supports_async__`` is ``True``).
+    ``PipelineTool`` enables the async path when wrapping an ``AsyncPipeline`` and falls back to the threaded sync path when wrapping a regular ``Pipeline``.

releasenotes/notes/add-attributes-to-pipeline-runtime-error-03941943aaf89880.yaml

@@ -0,0 +1,6 @@
+---
+enhancements:
+  - |
+    Added component_name and component_type attributes to PipelineRuntimeError.
+    - Moved error message creation to within PipelineRuntimeError
+    - Created a new subclass of PipelineRuntimeError called PipelineComponentsBlockedError for the specific case where the pipeline cannot run since no components are unblocked.

releasenotes/notes/add-auto-joiners-for-lists-types-b07771e6d8add3da.yaml

@@ -0,0 +1,41 @@
+---
+features:
+  - |
+    Pipelines now natively support connecting multiple outputs directly to a single component input without requiring
+    an explicit Joiner component. This only works when the connected outputs and inputs are of compatible list types,
+    such as ``list[Document]``.
+
+    This simplifies pipeline definitions when multiple components produce compatible outputs.
+    For example, multiple outputs from a ``FileTypeRouter`` can now be connected directly to a single converter or writer, without defining an intermediate ``ListJoiner`` or ``DocumentJoiner``.
+
+    .. code:: python
+        from haystack import Pipeline
+        from haystack.components.converters import HTMLToDocument, TextFileToDocument
+        from haystack.components.routers import FileTypeRouter
+        from haystack.components.writers import DocumentWriter
+        from haystack.dataclasses import ByteStream
+        from haystack.document_stores.in_memory import InMemoryDocumentStore
+
+        sources = [
+            ByteStream.from_string(text="Text file content", mime_type="text/plain", meta={"file_type": "txt"}),
+            ByteStream.from_string(
+                text="\n<html><body>Some content</body></html>\n", mime_type="text/html", meta={"file_type": "html"},
+            ),
+        ]
+
+        doc_store = InMemoryDocumentStore()
+        pipe = Pipeline()
+
+        pipe.add_component("router", FileTypeRouter(mime_types=["text/plain", "text/html"]))
+        pipe.add_component("txt_converter", TextFileToDocument())
+        pipe.add_component("html_converter", HTMLToDocument())
+        pipe.add_component("writer", DocumentWriter(doc_store))
+
+        pipe.connect("router.text/plain", "txt_converter.sources")
+        pipe.connect("router.text/html", "html_converter.sources")
+        # The DocumentWriter accepts documents from both converters without needing a DocumentJoiner
+        pipe.connect("txt_converter.documents", "writer.documents")
+        pipe.connect("html_converter.documents", "writer.documents")
+
+        result = pipe.run({"router": {"sources": sources}})
+        # result["writer"]["documents_written"] == 2

releasenotes/notes/add-azure-embedder-exception-handler-c10ea46fb536de3b.yaml

@@ -0,0 +1,5 @@
+---
+enhancements:
+  - |
+    Improved AzureDocumentEmbedder to handle embedding generation failures gracefully.
+    Errors are logged, and processing continues with the remaining batches.

releasenotes/notes/add-azure-embedders-fd5f4fbcab0e1c48.yaml

@@ -0,0 +1,5 @@
+---
+features:
+  - |
+    Adds AzureOpenAIDocumentEmbedder and AzureOpenAITextEmbedder as new embedders. These embedders are very similar to
+    their OpenAI counterparts, but they use the Azure API instead of the OpenAI API.

releasenotes/notes/add-azure-generators-a30c786204b22e48.yaml

@@ -0,0 +1,4 @@
+---
+features:
+  - |
+    Adds support for Azure OpenAI models with AzureOpenAIGenerator and AzureOpenAIChatGenerator components.

releasenotes/notes/add-azure-kwargs-6a5ab1358ef7f44c.yaml

@@ -0,0 +1,6 @@
+---
+enhancements:
+  - |
+    Expose default_headers to pass custom headers to Azure API including APIM subscription key.
+  - |
+    Add optional azure_kwargs dictionary parameter to pass in parameters undefined in Haystack but supported by AzureOpenAI.

releasenotes/notes/add-azure-responses-api-1b2c990a060b09f5.yaml

@@ -0,0 +1,24 @@
+---
+features:
+  - |
+    Added the `AzureOpenAIResponsesChatGenerator`, a new component that integrates Azure OpenAI's Responses API into Haystack.
+    This unlocks several advanced capabilities from the Responses API:
+    - Allowing retrieval of concise summaries of the model's reasoning process.
+    - Allowing the use of native OpenAI or MCP tool formats, along with Haystack Tool objects and Toolset instances.
+
+    Example with reasoning and web search tool:
+    ```python
+    from haystack.components.generators.chat import AzureOpenAIResponsesChatGenerator
+    from haystack.dataclasses import ChatMessage
+
+    chat_generator = AzureOpenAIResponsesChatGenerator(
+        azure_endpoint="https://example-resource.azure.openai.com/",
+        azure_deployment="gpt-5-mini",
+        generation_kwargs={"reasoning": {"effort": "low", "summary": "auto"}},
+    )
+
+    response = chat_generator.run(
+        messages=[ChatMessage.from_user("What's Natural Language Processing?")]
+    )
+    print(response["replies"][0].text)
+    ```

releasenotes/notes/add-azure_ocr_doc_converter-935130b3b243d236.yaml

@@ -0,0 +1,4 @@
+---
+preview:
+  - |
+    Add AzureOCRDocumentConverter to convert files of different types using Azure's Document Intelligence Service.

releasenotes/notes/add-bare-type-validation-a4720bc66ccaf5ef.yaml

@@ -0,0 +1,4 @@
+---
+features:
+  - |
+    Treat bare types (e.g., List, Dict) as generic types with Any arguments during type compatibility checks.

releasenotes/notes/add-batch_size_faiss_init-5e97c1fb9409f873.yaml

@@ -0,0 +1,5 @@
+---
+enhancements:
+  - |
+    Add batch_size to the __init__ method of FAISS Document Store. This works as the default value for all methods of
+    FAISS Document Store that support batch_size.

releasenotes/notes/add-blob-type-2a9476a39841f54d.yaml

@@ -0,0 +1,5 @@
+---
+preview:
+  - |
+    Add ByteStream type to send binary raw data across components
+    in a pipeline.

releasenotes/notes/add-branch-joiner-037298459ca74077.yaml

@@ -0,0 +1,14 @@
+---
+highlights: >
+    The `Multiplexer` component proved to be hard to explain and to understand. After reviewing its use cases, the documentation
+    was rewritten and the component was renamed to `BranchJoiner` to better explain its functionalities.
+upgrade:
+  - |
+    `BranchJoiner` has the very same interface as `Multiplexer`. To upgrade your code, just rename any occurrence
+    of `Multiplexer` to `BranchJoiner` and ajdust the imports accordingly.
+features:
+  - |
+    Add `BranchJoiner` to eventually replace `Multiplexer`
+deprecations:
+  - |
+    `Mulitplexer` is now deprecated.

releasenotes/notes/add-bytestream-guess-mime-type-e973262fa75f2982.yaml

@@ -0,0 +1,4 @@
+---
+enhancements:
+  - |
+    Add `guess_mime_type` parameter to `Bytestream.from_file_path()`

releasenotes/notes/add-bytestream-support-metadata-router-1ee5149745894f42.yaml

@@ -0,0 +1,4 @@
+---
+features:
+  - Add support for ByteStream objects in MetadataRouter.
+    It can now be used to route `list[Documents]` or `list[ByteStream]` based on metadata.

releasenotes/notes/add-calculate-metrics-metricsresults-03bf27ce8b16cff5.yaml

@@ -0,0 +1,6 @@
+---
+features:
+  - |
+    Adds `calculate_metrics()` function to EvaluationResult for computation of evaluation metrics.
+    Adds `Metric` class to store list of available metrics.
+    Adds `MetricsResult` class to store the metric values computed during the evaluation.

releasenotes/notes/add-callable-type-compatibility-a3746cd0cfd8fc10.yaml

@@ -0,0 +1,4 @@
+---
+features:
+  - |
+    Add compatibility for Callable types.

releasenotes/notes/add-chat-message-c456e4603529ae85.yaml

@@ -0,0 +1,5 @@
+---
+preview:
+  - |
+    Introduce ChatMessage data class to facilitate structured handling and processing of message content
+    within LLM chat interactions.

releasenotes/notes/add-chat-message-name-field-a8ae96fb9ff13f7b.yaml

@@ -0,0 +1,6 @@
+---
+fixes:
+  - |
+    In the `ChatMessage.to_openai_dict_format` utility method,
+    include the `name` field in the returned dictionary, if present.
+    Previously, the `name` field was erroneously skipped.

releasenotes/notes/add-chatpromptbuilder-19acd18a6486909d.yaml

@@ -0,0 +1,7 @@
+---
+enhancements:
+  - |
+    `ChatPromptBuilder` now supports changing its template at runtime. This allows you to define a default template and then change it based on your needs at runtime.
+deprecations:
+  - |
+    `DynamicChatPromptBuilder` has been deprecated as `ChatPromptBuilder` fully covers its functionality. Use `ChatPromptBuilder` instead.

releasenotes/notes/add-component-info-dataclass-be115dee2fa50abd.yaml

@@ -0,0 +1,7 @@
+---
+features:
+  - |
+    - Add a `ComponentInfo` dataclass to the `haystack.dataclasses` module.
+    This dataclass is used to store information about the component. We pass it to `StreamingChunk` so we can tell from which component a stream is coming from.
+
+    - Pass the `component_info` to the `StreamingChunk` in the `OpenAIChatGenerator`, `AzureOpenAIChatGenerator`, `HuggingFaceAPIChatGenerator` and `HuggingFaceLocalChatGenerator`.

releasenotes/notes/add-component-tool-ffe9f9911ea055a6.yaml

@@ -0,0 +1,38 @@
+---
+highlights: |
+   Introduced ComponentTool, a powerful addition to the Haystack tooling architecture that enables any Haystack component to be used as a tool by LLMs.
+   ComponentTool bridges the gap between Haystack's component ecosystem and LLM tool/function calling capabilities, allowing LLMs to
+   directly interact with components like web search, document processing, or any custom user component. ComponentTool handles
+   all the complexity of schema generation and type conversion, making it easy to expose component functionality to LLMs.
+
+features:
+ - |
+   Introduced the ComponentTool, a new tool that wraps Haystack components allowing them to be utilized as tools for LLMs (various ChatGenerators).
+   This ComponentTool supports automatic tool schema generation, input type conversion, and offering support for components with run methods that have input types:
+   - Basic types (str, int, float, bool, dict)
+   - Dataclasses (both simple and nested structures)
+   - Lists of basic types (e.g., List[str])
+   - Lists of dataclasses (e.g., List[Document])
+   - Parameters with mixed types (e.g., List[Document], str etc.)
+
+   Example usage:
+   ```python
+   from haystack.components.websearch import SerperDevWebSearch
+   from haystack.tools import ComponentTool
+   from haystack.utils import Secret
+
+   # Create a SerperDev search component
+   search = SerperDevWebSearch(
+       api_key=Secret.from_token("your-api-key"),
+       top_k=3
+   )
+
+   # Create a tool from the component
+   tool = ComponentTool(
+       component=search,
+       name="web_search",  # Optional: defaults to "serper_dev_web_search"
+       description="Search the web for current information"  # Optional: defaults to component docstring
+   )
+
+   # You can now use the tool now in a pipeline, see docs for more examples
+   ```

releasenotes/notes/add-csv-converter-5c0d52f180d498f5.yaml

@@ -0,0 +1,4 @@
+---
+features:
+  - |
+    Add a CSV to Document converter component. Loads the file as bytes object. Adds the loaded string as a new document that can be used for further processing by the Document Splitter.

releasenotes/notes/add-current-date-promptbuilder-ff60c846f5a70dc6.yaml

@@ -0,0 +1,16 @@
+---
+enhancements:
+  - |
+    Allow the ability to add the current date inside a template in `PromptBuilder` using the following syntax:
+
+    - `{% now 'UTC' %}`: Get the current date for the UTC timezone.
+
+    - `{% now 'America/Chicago' + 'hours=2' %}`: Add two hours to the current date in the Chicago timezone.
+
+    - `{% now 'Europe/Berlin' - 'weeks=2' %}`: Subtract two weeks from the current date in the Berlin timezone.
+
+    - `{% now 'Pacific/Fiji' + 'hours=2', '%H' %}`: Display only the number of hours after adding two hours to the Fiji timezone.
+
+    - `{% now 'Etc/GMT-4', '%I:%M %p' %}`: Change the date format to AM/PM for the GMT-4 timezone.
+
+    Note that if no date format is provided, the default will be `%Y-%m-%d %H:%M:%S`. Please refer to [list of tz database](https://en.wikipedia.org/wiki/List_of_tz_database_time_zones) for a list of timezones.

releasenotes/notes/add-custom-converter-hook-to-pypdf-cc7c333a6e7fc5f7.yaml

@@ -0,0 +1,4 @@
+---
+preview:
+  - |
+    Add callable hook to PyPDFToDocument to enable easier customization of pdf to Document conversion.

releasenotes/notes/add-custom-filters-to-conditional-router-631eba8bab3c2ae7.yaml

@@ -0,0 +1,6 @@
+---
+features:
+  - |
+    Added custom filters support to ConditionalRouter. Users can now pass in
+    one or more custom Jinja2 filter callables and be able to access those
+    filters when defining condition expressions in routes.

releasenotes/notes/add-dalle-image-generator-495aa11823e11a60.yaml

@@ -0,0 +1,12 @@
+---
+features:
+  - |
+    We've added a new **DALLEImageGenerator** component, bringing image generation with OpenAI's DALL-E to the Haystack
+
+    - **Easy to Use**: Just a few lines of code to get started:
+        ```python
+        from haystack.components.generators import DALLEImageGenerator
+        image_generator = DALLEImageGenerator()
+        response = image_generator.run("Show me a picture of a black cat.")
+        print(response)
+        ```

releasenotes/notes/add-dataframe-to-legacy-fields-0f2c9abc00c67aa5.yaml

@@ -0,0 +1,6 @@
+---
+fixes:
+  - |
+    Add dataframe to legacy fields for the Document dataclass.
+    This fixes a bug where Document.from_dict() in haystack-ai>=2.11.0 could not properly deserialize a Document 
+    dictionary obtained with document.to_dict(flatten=False) in haystack-ai<=2.10.0.

releasenotes/notes/add-default-headers-azure-embedders-6ffd24ec1502c5e4.yaml

@@ -0,0 +1,4 @@
+---
+enhancements:
+  - |
+    Added `default_headers` parameter to `AzureOpenAIDocumentEmbedder` and `AzureOpenAITextEmbedder`.

releasenotes/notes/add-default-value-to-input-socket-2e62116fc4be5214.yaml

@@ -0,0 +1,5 @@
+---
+enhancements:
+  - |
+    Add a field called `default_value` to the `InputSocket` dataclass.
+    Derive `is_mandatory` value from the presence of `default_value`.

releasenotes/notes/add-deprecation-warning-context-relevance-937df7e807ac1a8d.yaml

@@ -0,0 +1,4 @@
+---
+deprecations:
+  - |
+    The output of the ContextRelevanceEvaluator will change in Haystack 2.4.0. Contexts will be scored as a whole instead of individual statements and only the relevant sentences will be returned. A score of 1 is now returned if a relevant sentence is found, and 0 otherwise.

releasenotes/notes/add-dimensions-parameter-azureopeaniembedders-ef48fcc7c064b45c.yaml

@@ -0,0 +1,4 @@
+---
+enhancements:
+  - |
+    add dimensions parameter to Azure OpenAI Embedders (AzureOpenAITextEmbedder and AzureOpenAIDocumentEmbedder) to fully support new embedding models like text-embedding-3-small, text-embedding-3-large and upcoming ones

releasenotes/notes/add-dimensions-parameter-to-OpenAI-Embedders-to-fully-support-the-new-models-1393cc235e457733.yaml

@@ -0,0 +1,4 @@
+---
+enhancements:
+  - |
+    add dimensions parameter to OpenAI Embedders to fully support new embedding models like text-embedding-3-small, text-embedding-3-large and upcoming ones

releasenotes/notes/add-distribution-based-rank-fusion-mode-JoinDocuments-6fca30b82fd535ce.yaml

@@ -0,0 +1,6 @@
+---
+features:
+  - |
+    Added a new mode in JoinDocuments,
+    Distribution-based rank fusion as
+    [the article](https://medium.com/plain-simple-software/distribution-based-score-fusion-dbsf-a-new-approach-to-vector-search-ranking-f87c37488b18)

releasenotes/notes/add-diversity-ranker-6ecee21134eda673.yaml

@@ -0,0 +1,6 @@
+---
+features:
+  - |
+    Add `SentenceTransformersDiversityRanker`.
+    The Diversity Ranker orders documents in such a way as to maximize the overall diversity of the given documents.
+    The ranker leverages sentence-transformer models to calculate semantic embeddings for each document and the query.

releasenotes/notes/add-document-comparison-field-to-ndcg-evaluator-f9abbbd556f49c04.yaml

@@ -0,0 +1,16 @@
+upgrade:
+  - |
+    ``DocumentNDCGEvaluator`` now matches documents by their ``content`` field
+    by default instead of their auto-generated ``id``. Previously, ground
+    truth and retrieved documents were matched only if they had identical
+    ``id`` values, which rarely happened in practice since IDs are generated
+    independently for each Document instance. As a result, NDCG scores
+    computed with this evaluator may change for existing pipelines. To keep
+    the previous ``id``-based matching behavior, pass
+    ``document_comparison_field="id"`` when constructing the evaluator.
+enhancements:
+  - |
+    Added ``document_comparison_field`` parameter to ``DocumentNDCGEvaluator``,
+    consistent with ``DocumentMAPEvaluator``, ``DocumentMRREvaluator``, and
+    ``DocumentRecallEvaluator``. Users can now match documents by ``"content"``,
+    ``"id"``, or any ``"meta.<key>"`` field when calculating NDCG scores.

releasenotes/notes/add-document-writer-number-of-documents-written-2c57f3a5d6ae2131.yaml

@@ -0,0 +1,4 @@
+---
+enhancements:
+  - |
+    Document writer returns the number of documents written.

releasenotes/notes/add-docx-file-to-document-47b603755a00fbe6.yaml

@@ -0,0 +1,6 @@
+---
+highlights: >
+    Adding the `DocxToDocument` component to convert Docx files to Documents.
+features:
+  - |
+    Adding the `DocxToDocument` component inside the `converters` category. It uses the `python-docx` library to convert Docx files to haystack Documents.

releasenotes/notes/add-dynamic-per-message-templating-908468226c5e3d45.yaml

@@ -0,0 +1,4 @@
+---
+preview:
+  - |
+    Adds `ChatMessage` templating in `PromptBuilder`

releasenotes/notes/add-dynamic-prompt-builder-e61c4b11405b8d80.yaml

@@ -0,0 +1,5 @@
+---
+preview:
+  - |
+    Add `DynamicPromptBuilder` to dynamically generate prompts from either a list of ChatMessage instances or a string
+    template, leveraging Jinja2 templating for flexible and efficient prompt construction.

releasenotes/notes/add-enable-streaming-passthrough-and-fix-sede-toolinvoker-bc2e906ddcff0e0d.yaml

@@ -0,0 +1,7 @@
+---
+features:
+  - |
+    Added the `enable_streaming_callback_passthrough` to the `ToolInovker` init, run and run_async methods. If set to True the ToolInvoker will try and pass the `streaming_callback` function to a tool's invoke method only if the tool's invoke method has `streaming_callback` in its signature.
+fixes:
+  - |
+    Fixed the `to_dict` and `from_dict` of `ToolInvoker` to properly serialize the `streaming_callback` init parameter.

releasenotes/notes/add-encode-kwargs-sentence-transformers-f4d885f6c5b1706f.yaml

@@ -0,0 +1,6 @@
+---
+enhancements:
+  - |
+    Enhanced `SentenceTransformersDocumentEmbedder` and `SentenceTransformersTextEmbedder` to accept
+    an additional parameter, which is passed directly to the underlying `SentenceTransformer.encode` method
+    for greater flexibility in embedding customization.

releasenotes/notes/add-encoding-format-to-openai-embedder-create-kwargs-eed6d0f858fd3808.yaml

@@ -0,0 +1,4 @@
+---
+fixes:
+  - |
+    Add encoding format keyword argument to OpenAI client when creating embeddings.

releasenotes/notes/add-enum-serialization-support-0ff44d00e9474e93.yaml

@@ -0,0 +1,4 @@
+---
+features:
+  - |
+    Updated our serialization and deserialization of PipelineSnapshots to work with python Enum classes.

releasenotes/notes/add-error-message-component-run-failure-b956852263d41c3c.yaml

@@ -0,0 +1,4 @@
+---
+enhancements:
+  - |
+    Improved error handling for component `run` failures by raising a runtime error that includes the component's name and type.

releasenotes/notes/add-eval-and-evaluation-result-5e9ac742e323bda8.yaml

@@ -0,0 +1,4 @@
+preview:
+  - |
+    Add eval function for evaluation of components and Pipelines.
+    Adds EvaluationResult to store results of evaluation.

releasenotes/notes/add-exact-match-a7df21717238b771.yaml

@@ -0,0 +1,8 @@
+---
+features:
+  - |
+    Adds support for the Exact Match metric to `EvaluationResult.calculate_metrics(...)`:
+    ```python
+    from haystack.evaluation.metrics import Metric
+    exact_match_metric = eval_result.calculate_metrics(Metric.EM, output_key="answers")
+    ```

releasenotes/notes/add-excel-to-document-converter-1920c9f9902ddf17.yaml

@@ -0,0 +1,4 @@
+---
+features:
+  - |
+    Add XLSXToDocument converter that loads an Excel file using Pandas + openpyxl and by default converts each sheet into a separate Document in a CSV format.

releasenotes/notes/add-extra-field-to-toolcall-541e1aa06dd4e12d.yaml

@@ -0,0 +1,4 @@
+---
+features:
+  - |
+    Add an `extra` field to `ToolCall` and `ToolCallDelta` to store provider-specific information.

releasenotes/notes/add-f1-d54cc900bec753f7.yaml

@@ -0,0 +1,8 @@
+---
+features:
+  - |
+    Adds support for the F1 metric to `EvaluationResult.calculate_metrics(...)`:
+    ```python
+    from haystack.evaluation.metrics import Metric
+    f1_metric = eval_result.calculate_metrics(Metric.F1, output_key="answers")
+    ```

releasenotes/notes/add-failsafe-for-LLM-based-evaluators-34cdc183ab545315.yaml

@@ -0,0 +1,5 @@
+---
+enhancements:
+  - |
+    If an LLM-based evaluator (e.g., `Faithfulness` or `ContextRelevance`) is initialised with `raise_on_failure=False`, and if a call to an LLM fails or an LLM outputs an invalid JSON, the score of the sample is set to `NaN` instead of raising an exception.
+    The user is notified with a warning indicating the number of requests that failed.

releasenotes/notes/add-fallback-chat-generator-ffe557ca01fcdaca.yaml

@@ -0,0 +1,6 @@
+---
+highlights: >
+  Introduced `FallbackChatGenerator` that tries multiple chat providers one by one, improving reliability in production and making sure you get answers even when some provider fails.
+features:
+  - |
+    Added `FallbackChatGenerator` that automatically retries different chat generators and returns first successful response with detailed information about which providers were tried.

releasenotes/notes/add-file-extension-classifier-preview-40f31c27bbd7cff9.yaml

@@ -0,0 +1,4 @@
+---
+preview:
+  - |
+    Adds FileExtensionClassifier to preview components.

releasenotes/notes/add-filter-retriever-8901af26144d1a17.yaml

@@ -0,0 +1,5 @@
+---
+features:
+  - |
+    Add FilterRetriever.
+    It retrieves documents that match the provided (either at init or runtime) filters.

releasenotes/notes/add-finish-reason-field-streaming-chunk-89828ec09c6e6385.yaml

@@ -0,0 +1,6 @@
+---
+features:
+  - |
+    Added dedicated `finish_reason` field to `StreamingChunk` class to improve type safety and enable sophisticated streaming UI logic. The field uses a `FinishReason` type alias with standard values: "stop", "length", "tool_calls", "content_filter", plus Haystack-specific value "tool_call_results" (used by ToolInvoker to indicate tool execution completion).
+  - |
+    Updated `ToolInvoker` component to use the new `finish_reason` field when streaming tool results. The component now sets `finish_reason="tool_call_results"` in the final streaming chunk to indicate that tool execution has completed, while maintaining backward compatibility by also setting the value in `meta["finish_reason"]`.

releasenotes/notes/add-fully-qualified-type-to-trace-c227a9ca328daded.yaml

@@ -0,0 +1,8 @@
+---
+enhancements:
+  - |
+    Added ``haystack.component.fully_qualified_type`` field to component tracing output.
+    This new field provides the full module path and class name (e.g.,
+    ``haystack.components.generators.chat.openai.OpenAIChatGenerator``) alongside the
+    existing ``haystack.component.type`` field that only contains the class name.
+    This enables dynamic component loading and better tooling integration.

releasenotes/notes/add-generation-kwargs-to-agent-9600a6c1e6bc069b.yaml

@@ -0,0 +1,4 @@
+---
+enhancements:
+  - |
+    Adds `generation_kwargs` to the `Agent` component, allowing for more fine-grained control at run-time over the chat generation.

releasenotes/notes/add-getmetadata-async-methods-and-tests-3ff2601b692697cb.yaml

@@ -0,0 +1,7 @@
+---
+enhancements:
+  - |
+    Add async variants of metadata methods to ``InMemoryDocumentStore``:
+    ``get_metadata_fields_info_async()``, ``get_metadata_field_min_max_async()``, and
+    ``get_metadata_field_unique_values_async()``. These rely on the store's thread-pool executor,
+    consistent with the existing async method pattern.

releasenotes/notes/add-haystack-experimental-dependency-96ff02e71bc2af13.yaml

@@ -0,0 +1,4 @@
+---
+features:
+ - |
+   Added haystack-experimental to the project's dependencies to enable automatic use of cutting-edge features from Haystack. Users can now access components from haystack-experimental by simply importing them from haystack_experimental instead of haystack. For more information, visit https://github.com/deepset-ai/haystack-experimental.

releasenotes/notes/add-hf-free-tier-checks-99384060139d5d30.yaml

@@ -0,0 +1,7 @@
+---
+fixes:
+  - |
+    Resolves a bug where the HuggingFaceTGIGenerator and HuggingFaceTGIChatGenerator encountered issues if provided
+    with valid models that were not available on the HuggingFace inference API rate-limited tier. The fix, detailed
+    in [GitHub issue #6816](https://github.com/deepset-ai/haystack/issues/6816) and its GitHub PR, ensures these
+    components now correctly handle model availability, eliminating previous limitations.

releasenotes/notes/add-hitl-e8ee5222e897d7a8.yaml

@@ -0,0 +1,32 @@
+---
+features:
+  - |
+    Added support for human confirmation on ``Agent`` tool calls.
+    You can now configure per-tool confirmation strategies when building an ``Agent``, including always requiring confirmation,
+    never requiring it, or requesting confirmation only on first use.
+    The confirmation experience is customizable through different UI strategies, allowing fine-grained control over how and when users approve tool executions.
+
+    .. code-block:: python
+
+        agent = Agent(
+            chat_generator=OpenAIChatGenerator(model="gpt-4.1"),
+            tools=[balance_tool, addition_tool, phone_tool],
+            system_prompt=(
+                "You are a helpful financial assistant. "
+                "Use the provided tool to get bank balances when needed."
+            ),
+            confirmation_strategies={
+                balance_tool.name: BlockingConfirmationStrategy(
+                    confirmation_policy=AlwaysAskPolicy(),
+                    confirmation_ui=RichConsoleUI(console=cons),
+                ),
+                addition_tool.name: BlockingConfirmationStrategy(
+                    confirmation_policy=NeverAskPolicy(),
+                    confirmation_ui=SimpleConsoleUI(),
+                ),
+                phone_tool.name: BlockingConfirmationStrategy(
+                    confirmation_policy=AskOncePolicy(),
+                    confirmation_ui=SimpleConsoleUI(),
+                ),
+            },
+        )

releasenotes/notes/add-html-to-document-21fe38b244388f4d.yaml

@@ -0,0 +1,4 @@
+---
+preview:
+  - |
+    Adds HTMLToDocument component to convert HTML to a Document.

releasenotes/notes/add-hugging-face-chat-local-5fe7a88e24fde11b.yaml

@@ -0,0 +1,19 @@
+---
+features:
+  - |
+    Introducing the HuggingFaceLocalChatGenerator, a new chat-based generator designed for leveraging chat models from
+    Hugging Face's (HF) model hub. Users can now perform inference with chat-based models in a local runtime, utilizing
+    familiar HF generation parameters, stop words, and even employing custom chat templates for custom message formatting.
+    This component also supports streaming responses and is optimized for compatibility with a variety of devices.
+
+    Here is an example of how to use the HuggingFaceLocalChatGenerator:
+
+    ```python
+    from haystack.components.generators.chat import HuggingFaceLocalChatGenerator
+    from haystack.dataclasses import ChatMessage
+
+    generator = HuggingFaceLocalChatGenerator(model="HuggingFaceH4/zephyr-7b-beta")
+    generator.warm_up()
+    messages = [ChatMessage.from_user("What's Natural Language Processing? Be brief.")]
+    print(generator.run(messages))
+    ```

releasenotes/notes/add-huggingface-api-text-embeddings-inference-to-component-rankers-0e3f54e523e42141.yaml

@@ -0,0 +1,5 @@
+---
+features:
+  - |
+    Added new `HuggingFaceTEIRanker` component to enable reranking with Text Embeddings Inference (TEI) API.
+    This component supports both self-hosted Text Embeddings Inference services and Hugging Face Inference Endpoints.

releasenotes/notes/add-huggingface-tgi-chat-c63f4879a5d81342.yaml

@@ -0,0 +1,5 @@
+---
+preview:
+  - |
+    Adds `HuggingFaceTGIChatGenerator` for text and chat generation. This components support remote inferencing for
+    Hugging Face LLMs via text-generation-inference (TGI) protocol.

releasenotes/notes/add-huggingface-tgi-generator-9d7eed86f5246ea9.yaml

@@ -0,0 +1,5 @@
+---
+preview:
+  - |
+    Adds `HuggingFaceTGIGenerator` for text generation. This components support remote inferencing for
+    Hugging Face LLMs via text-generation-inference (TGI) protocol.

releasenotes/notes/add-hyperlink-extraction-pptx-xlsx-a3b9f1c2d4e5f6a7.yaml

@@ -0,0 +1,13 @@
+---
+features:
+  - |
+    Added ``link_format`` parameter to ``PPTXToDocument`` and ``XLSXToDocument`` converters,
+    allowing extraction of hyperlink addresses from PPTX and XLSX files.
+
+    Supported formats:
+
+    - ``"markdown"``: ``[text](url)``
+    - ``"plain"``: ``text (url)``
+    - ``"none"`` (default): Only text is extracted, link addresses are ignored.
+
+    This follows the same pattern already available in ``DOCXToDocument``.

releasenotes/notes/add-image-support-huggingface-api-chat-generator-9671.yaml

@@ -0,0 +1,6 @@
+---
+enhancements:
+  - |
+    Added multimodal support to `HuggingFaceAPIChatGenerator` to enable vision-language model (VLM) usage with images and text.
+    Users can now send both text and images to VLM models through Hugging Face APIs. The implementation follows the HF VLM API format
+    specification and maintains full backward compatibility with text-only messages.

releasenotes/notes/add-indexing-ready-made-pipeline-85c1da2f8f910f9d.yaml

@@ -0,0 +1,4 @@
+---
+features:
+  - |
+    Add a indexing `build_indexing_pipeline` utility function

releasenotes/notes/add-inf-mode-reader-e6eb79920e73c956.yaml

@@ -0,0 +1,4 @@
+---
+enhancements:
+  - |
+    Adds inference mode to model call of the ExtractiveReader. This prevents gradients from being calculated during inference time in pytorch.

releasenotes/notes/add-keep-columns-to-EvalRunResult-comparative-be3e15ce45de3e0b.yaml

@@ -0,0 +1,5 @@
+---
+
+enhancements:
+  - |
+    Added a new parameter to `EvaluationRunResult.comparative_individual_scores_report()` to specify columns to keep in the comparative DataFrame.

releasenotes/notes/add-keep-id-to-document-cleaner-2a9854b5f195bb78.yaml

@@ -0,0 +1,4 @@
+---
+enhancements:
+  - |
+    The `DocumentCleaner` class has the optional attribute `keep_id` that if set to True it keeps the document ids unchanged after cleanup.

releasenotes/notes/add-link-content-fetcher-145915976f38e1e0.yaml

@@ -0,0 +1,5 @@
+---
+preview:
+  - |
+    Introduced the LinkContentFetcher in Haystack 2.0. This component fetches content from specified
+    URLs and converts them into ByteStream objects for further processing in Haystack pipelines.

releasenotes/notes/add-list-joiner-4f0ea84e195fa461.yaml

@@ -0,0 +1,4 @@
+---
+features:
+  - |
+    Added a new component `ListJoiner` which joins lists of values from different components to a single list.

releasenotes/notes/add-llm-chat-generator-component-e50c6f7659a31253.yaml

@@ -0,0 +1,26 @@
+---
+features:
+  - |
+    Added a new ``LLM`` component (``haystack.components.generators.chat.LLM``) that provides a simplified
+    interface for text generation powered by a large language model. The ``LLM`` component is a streamlined
+    version of the ``Agent`` that focuses solely on single-turn text generation without tool usage.
+    It supports system prompts, templated user prompts with required variables, streaming callbacks,
+    and both synchronous (``run``) and asynchronous (``run_async``) execution.
+
+    Usage example:
+    .. code:: python
+      from haystack.components.generators.chat import LLM
+      from haystack.components.generators.chat import OpenAIChatGenerator
+      from haystack.dataclasses import ChatMessage
+
+      llm = LLM(
+          chat_generator=OpenAIChatGenerator(),
+          system_prompt="You are a helpful translation assistant.",
+          user_prompt=\"\"\"{% message role="user"%}
+      Summarize the following document: {{ document }}
+      {% endmessage %}\"\"\",
+          required_variables=["document"],
+      )
+
+      result = llm.run(document="The weather is lovely today and the sun is shining. ")
+      print(result["last_message"].text)

releasenotes/notes/add-llm-doc-content-extractor-482b09a21a8b0609.yaml

@@ -0,0 +1,5 @@
+---
+features:
+  - |
+    Added the LLMDocumentContentExtractor which extracts textual content from image-based documents using a vision-enabled LLM.
+    This is good for creating a textual representation of an image which can be used when only text-based retrieval is available.

releasenotes/notes/add-llm-ranker-d68d1cd607ed7b39.yaml

@@ -0,0 +1,5 @@
+features:
+  - |
+    Added ``LLMRanker``, a new ranker component that uses a ``ChatGenerator`` and ``PromptBuilder`` to rerank
+    documents based on JSON-formatted LLM output. ``LLMRanker`` supports configurable prompts, optional custom
+    chat generators, runtime ``top_k`` overrides, and serialization.

releasenotes/notes/add-logprobs-openai-fb2194d0f2a16898.yaml

@@ -0,0 +1,4 @@
+---
+features:
+  - |
+    If logprobs are enabled in the generation kwargs, return logprobs in ChatMessage.meta for `OpenAIChatGenerator` and `OpenAIResponsesChatGenerator`.

releasenotes/notes/add-logs-empty-files-pdf-f28a14e52984c1ea.yaml

@@ -0,0 +1,7 @@
+---
+features:
+  - |
+    Add warning logs to the PDFMinerToDocument and PyPDFToDocument to indicate when a processed PDF file has no content.
+    This can happen if the PDF file is a scanned image.
+    Also added an explicit check and warning message to the DocumentSplitter that warns the user that empty Documents are skipped.
+    This behavior was already occurring, but now its clearer through logs that this is happening.

releasenotes/notes/add-lost-in-the-middle-ranker-6ad7dda754fad5a9.yaml

@@ -0,0 +1,18 @@
+---
+prelude: >
+    We're excited to introduce a new ranker to Haystack - LostInTheMiddleRanker.
+    It reorders documents based on the "Lost in the Middle" order, a strategy that
+    places the most relevant paragraphs at the beginning or end of the context,
+    while less relevant paragraphs are positioned in the middle. This ranker,
+    based on the research paper "Lost in the Middle: How Language Models Use Long
+    Contexts" by Liu et al., can be leveraged in Retrieval-Augmented Generation
+    (RAG) pipelines.
+features:
+  - |
+    The LostInTheMiddleRanker can be used like other rankers in Haystack. After
+    initializing LostInTheMiddleRanker with the desired parameters, it can be
+    used to rank/reorder a list of documents based on the "Lost in the Middle"
+    order - the most relevant documents are located at the top and bottom of
+    the returned list, while the least relevant documents are found in the
+    middle. We advise that you use this ranker in combination with other rankers,
+    and to place it towards the end of the pipeline.

releasenotes/notes/add-lost-in-the-middle-ranker-976f2e9bf83c3c68.yaml

@@ -0,0 +1,8 @@
+---
+
+features:
+  - |
+    Add LostInTheMiddleRanker.
+    It reorders documents based on the "Lost in the Middle" order, a strategy that
+    places the most relevant paragraphs at the beginning or end of the context,
+    while less relevant paragraphs are positioned in the middle.

releasenotes/notes/add-markdown-file-type-router-support-39a607faa5c1436f.yaml

@@ -0,0 +1,4 @@
+---
+enhancements:
+  - |
+    Adds markdown mimetype support to the file type router i.e. `FileTypeRouter` class.

releasenotes/notes/add-maximum-margin-relevance-ranker-9d6d71c6a408c6d1.yaml

@@ -0,0 +1,4 @@
+---
+enhancements:
+  - |
+    Added the Maximum Margin Relevance (MMR) strategy to the `SentenceTransformersDiversityRanker`. MMR scores are calculated for each document based on their relevance to the query and diversity from already selected documents.

releasenotes/notes/add-md-header-splitter-df5c024a6ddd2718.yaml

@@ -0,0 +1,8 @@
+---
+features:
+  - |
+    Introduced the ``MarkdownHeaderSplitter`` component:
+      - Splits documents into chunks at Markdown headers (``#``, ``##``, etc.), preserving header hierarchy as metadata.
+      - Supports secondary splitting (by word, passage, period, or line) for further chunking after header-based splitting using Haystack's ``DocumentSplitter``.
+      - Preserves and propagates metadata such as parent headers and page numbers.
+      - Handles edge cases such as documents with no headers, empty content, and non-text documents.