llama-stack-haystack 2.0.0__tar.gz → 3.0.0__tar.gz

{llama_stack_haystack-2.0.0 → llama_stack_haystack-3.0.0}/CHANGELOG.md

@@ -1,11 +1,29 @@
 # Changelog
 
+## [integrations/llama_stack-v2.0.0] - 2026-01-12
+
+
+### ⚙️ CI
+
+- Add reruns when running nightly tests if tests fail (#2584)
+
+### 🧹 Chores
+
+- Remove Readme API CI workflow and configs (#2573)
+- Make fmt command more forgiving (#2671)
+- Pin llama-stack; X|Y typing (#2715)
+
 ## [integrations/llama_stack-v1.3.0] - 2025-11-23
 
 ### 🚀 Features
 
 - Support structured outputs in `LlamaStackChatGenerator` (#2535)
 
+### ⚙️ CI
+
+- Change pytest command (#2475)
+- Add pytest reruns to nightly tests for flaky tests (#2486)
+
 ### 🌀 Miscellaneous
 
 - Enhancement: Adopt PEP 585 type hinting (part 4) (#2527)

{llama_stack_haystack-2.0.0 → llama_stack_haystack-3.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: llama-stack-haystack
-Version: 2.0.0
+Version: 3.0.0
 Summary: Use Llama Stack framework for text generation
 Project-URL: Documentation, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/llama-stack#readme
 Project-URL: Issues, https://github.com/deepset-ai/haystack-core-integrations/issues
@@ -17,7 +17,7 @@ Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Programming Language :: Python :: Implementation :: PyPy
 Requires-Python: >=3.12
 Requires-Dist: haystack-ai>=2.22.0
-Requires-Dist: llama-stack<0.4.0,>=0.2.17
+Requires-Dist: llama-stack>=0.4.0
 Description-Content-Type: text/markdown
 
 # llama-stack-haystack

{llama_stack_haystack-2.0.0 → llama_stack_haystack-3.0.0}/examples/llama-stack-with-tools.py

@@ -35,7 +35,7 @@ tool_invoker = ToolInvoker(tools=[weather_tool])
 
 client = LlamaStackChatGenerator(
     model="ollama/llama3.2:3b",  # model depends on the inference provider used for the Llama Stack Server.
-    api_base_url="http://localhost:8321/v1/openai/v1",
+    api_base_url="http://localhost:8321/v1",
 )
 messages = [ChatMessage.from_user("What's the weather in Tokyo?")]
 

{llama_stack_haystack-2.0.0 → llama_stack_haystack-3.0.0}/pyproject.toml

@@ -20,7 +20,7 @@ classifiers = [
   "Programming Language :: Python :: Implementation :: CPython",
   "Programming Language :: Python :: Implementation :: PyPy",
 ]
-dependencies = ["haystack-ai>=2.22.0", "llama-stack>=0.2.17,<0.4.0"]
+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"

{llama_stack_haystack-2.0.0 → llama_stack_haystack-3.0.0}/src/haystack_integrations/components/generators/llama_stack/chat/chat_generator.py

@@ -59,7 +59,7 @@ class LlamaStackChatGenerator(OpenAIChatGenerator):
         self,
         *,
         model: str,
-        api_base_url: str = "http://localhost:8321/v1/openai/v1",
+        api_base_url: str = "http://localhost:8321/v1",
         organization: str | None = None,
         streaming_callback: StreamingCallbackT | None = None,
         generation_kwargs: dict[str, Any] | None = None,

{llama_stack_haystack-2.0.0 → llama_stack_haystack-3.0.0}/tests/test_llama_stack_chat_generator.py

@@ -105,7 +105,7 @@ class TestLlamaStackChatGenerator:
     def test_init_default(self):
         component = LlamaStackChatGenerator(model="ollama/llama3.2:3b")
         assert component.model == "ollama/llama3.2:3b"
-        assert component.api_base_url == "http://localhost:8321/v1/openai/v1"
+        assert component.api_base_url == "http://localhost:8321/v1"
         assert component.streaming_callback is None
         assert not component.generation_kwargs
 
@@ -134,7 +134,7 @@ class TestLlamaStackChatGenerator:
         expected_params = {
             "model": "ollama/llama3.2:3b",
             "streaming_callback": None,
-            "api_base_url": "http://localhost:8321/v1/openai/v1",
+            "api_base_url": "http://localhost:8321/v1",
             "generation_kwargs": {},
             "timeout": None,
             "max_retries": None,