chore!: support X|Y typing and llama-stack>=0.4.0

Author: anakin87

integrations/llama_stack/pyproject.toml

@@ -20,7 +20,7 @@ classifiers = [
   "Programming Language :: Python :: Implementation :: CPython",
   "Programming Language :: Python :: Implementation :: PyPy",
 ]
-dependencies = ["haystack-ai>=2.19.0", "llama-stack>=0.2.17"]
+dependencies = ["haystack-ai>=2.22.0", "llama-stack>=0.4.0"]
 
 [project.urls]
 Documentation = "https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/llama-stack#readme"

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

@@ -2,7 +2,7 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 
-from typing import Any, Optional
+from typing import Any
 
 from haystack import component, default_from_dict, default_to_dict, logging
 from haystack.components.generators.chat import OpenAIChatGenerator
@@ -59,15 +59,15 @@ def __init__(
         self,
         *,
         model: str,
-        api_base_url: str = "http://localhost:8321/v1/openai/v1",
-        organization: Optional[str] = None,
-        streaming_callback: Optional[StreamingCallbackT] = None,
-        generation_kwargs: Optional[dict[str, Any]] = None,
-        timeout: Optional[int] = None,
-        tools: Optional[ToolsType] = None,
+        api_base_url: str = "http://localhost:8321/v1",
+        organization: str | None = None,
+        streaming_callback: StreamingCallbackT | None = None,
+        generation_kwargs: dict[str, Any] | None = None,
+        timeout: int | None = None,
+        tools: ToolsType | None = None,
         tools_strict: bool = False,
-        max_retries: Optional[int] = None,
-        http_client_kwargs: Optional[dict[str, Any]] = None,
+        max_retries: int | None = None,
+        http_client_kwargs: dict[str, Any] | None = None,
     ):
         """
         Creates an instance of LlamaStackChatGenerator. To use this chat generator,