add release notes for 2.5

content/release-notes/2.5.0.md

@@ -0,0 +1,42 @@
+---
+title: Haystack 2.5.0
+description: Release notes for Haystack 2.5.0
+toc: True
+date: 2024-09-04
+last_updated:  2024-09-04
+tags: ["Release Notes"]
+link: https://github.com/deepset-ai/haystack/releases/tag/v2.5.0
+---
+
+### ⬆️ Upgrade Notes
+
+-   Removed `ChatMessage.to_openai_format` method. Use `haystack.components.generators.openai_utils._convert_message_to_openai_format` instead.
+-   Removed unused `debug` parameter from `Pipeline.run` method.
+-   Removed deprecated `SentenceWindowRetrieval`. Use `SentenceWindowRetriever` instead.
+
+### 🚀 New Features
+
+-   Extended core component machinery to support an optional asynchronous `async_run` method in components. If it's present, it should have the same parameters (and output types) as the run method and must be implemented as a coroutine.
+- Added the unsafe argument to enable behavior that could lead to remote code execution in `ConditionalRouter` and `OutputAdapter`. By default, unsafe behavior is disabled, and users must explicitly set `unsafe=True` to enable it. When unsafe is enabled, types such as `ChatMessage`, `Document`, and `Answer` can be used as output types. We recommend enabling unsafe behavior only when the Jinja template source is trusted. For more information, see the documentation for [`ConditionalRouter`](https://docs.haystack.deepset.ai/docs/conditionalrouter#unsafe-behaviour) and [`OutputAdapter`](https://docs.haystack.deepset.ai/docs/outputadapter#unsafe-behaviour).
+- 
+
+### ⚡️ Enhancement Notes
+
+-   Adapts how `ChatPromptBuilder` creates `ChatMessages`. Messages are deep copied to ensure all meta fields are copied correctly.
+-   The parameter, `min_top_k`, has been added to the `TopPSampler`. This parameter sets the minimum number of documents to be returned when the top-p sampling algorithm selects fewer documents than desired. Documents with the next highest scores are added to meet the minimum. This is useful when guaranteeing a set number of documents to pass through while still allowing the Top-P algorithm to determine if more documents should be sent based on scores.
+-   Introduced a utility function to deserialize a generic Document Store from the `init_parameters` of a serialized component.
+-   Refactor `deserialize_document_store_in_init_parameters` to clarify that the function operates in place and does not return a value.
+-   The `SentenceWindowRetriever` has now an extra output key containing all the documents belonging to the context window.
+
+### ⚠️ Deprecation Notes
+
+- The default model for `OpenAIGenerator` and `OpenAIChatGenerator`, previously 'gpt-3.5-turbo', will be replaced by 'gpt-4o-mini'.
+
+### 🐛 Bug Fixes
+
+-   Fixed an issue where page breaks were not being extracted from DOCX files.
+-   Used a forward reference for the `Paragraph` class in the `DOCXToDocument` converter to prevent import errors.
+-   The metadata produced by `DOCXToDocument` component is now JSON serializable. Previously, it contained `datetime` objects automatically extracted from DOCX files, which are not JSON serializable. These `datetime` objects are now converted to strings.
+-   Starting from `haystack-ai==2.4.0`, Haystack is compatible with `sentence-transformers>=3.0.0`; earlier versions of `sentence-transformers` are not supported. We have updated the test dependencies and LazyImport messages to reflect this change.
+-   For components that support multiple Document Stores, prioritize using the specific `from_dict` class method for deserialization when available. Otherwise, fall back to the generic `default_from_dict` method. This impacts the following generic components: `CacheChecker`, `DocumentWriter`, `FilterRetriever`, and `SentenceWindowRetriever`.
+