llama-stack-haystack 1.3.0__tar.gz → 3.0.0__tar.gz

{llama_stack_haystack-1.3.0 → llama_stack_haystack-3.0.0}/CHANGELOG.md

@@ -1,5 +1,33 @@
 # 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)
+
 ## [integrations/llama_stack-v1.2.0] - 2025-10-24
 
 ### 🚀 Features

{llama_stack_haystack-1.3.0 → llama_stack_haystack-3.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: llama-stack-haystack
-Version: 1.3.0
+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
@@ -16,8 +16,8 @@ Classifier: Programming Language :: Python :: 3.13
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Programming Language :: Python :: Implementation :: PyPy
 Requires-Python: >=3.12
-Requires-Dist: haystack-ai>=2.19.0
-Requires-Dist: llama-stack>=0.2.17
+Requires-Dist: haystack-ai>=2.22.0
+Requires-Dist: llama-stack>=0.4.0
 Description-Content-Type: text/markdown
 
 # llama-stack-haystack

{llama_stack_haystack-1.3.0 → 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-1.3.0 → 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>=2.19.0", "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"
@@ -42,8 +42,8 @@ git_describe_command = 'git describe --tags --match="integrations/llama_stack-v[
 installer = "uv"
 dependencies = ["haystack-pydoc-tools", "ruff"]
 [tool.hatch.envs.default.scripts]
-docs = ["pydoc-markdown pydoc/config.yml"]
-fmt = "ruff check --fix {args} && ruff format {args}"
+docs = ["pydoc-markdown pydoc/config_docusaurus.yml"]
+fmt = "ruff check --fix {args}; ruff format {args}"
 fmt-check = "ruff check {args} && ruff format --check {args}"
 
 [tool.hatch.envs.test]
@@ -60,7 +60,7 @@ dependencies = [
 [tool.hatch.envs.test.scripts]
 unit = 'pytest -m "not integration" {args:tests}'
 integration = 'pytest -m "integration" {args:tests}'
-all = 'pytest --reruns 3 --reruns-delay 30 -x {args:tests}'
+all = 'pytest {args:tests}'
 cov-retry = 'pytest --cov=haystack_integrations --reruns 3 --reruns-delay 30 -x {args:tests}'
 
 types = "mypy -p haystack_integrations.components.generators.llama_stack {args}"

{llama_stack_haystack-1.3.0 → llama_stack_haystack-3.0.0}/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 @@ class LlamaStackChatGenerator(OpenAIChatGenerator):
         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,

{llama_stack_haystack-1.3.0 → 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,

llama_stack_haystack-1.3.0/pydoc/config.yml

@@ -1,29 +0,0 @@
-loaders:
-  - type: haystack_pydoc_tools.loaders.CustomPythonLoader
-    search_path: [../src]
-    modules: [
-      "haystack_integrations.components.generators.llama_stack.chat.chat_generator",
-    ]
-    ignore_when_discovered: ["__init__"]
-processors:
-  - type: filter
-    expression:
-    documented_only: true
-    do_not_filter_modules: false
-    skip_empty_modules: true
-  - type: smart
-  - type: crossref
-renderer:
-  type: haystack_pydoc_tools.renderers.ReadmeIntegrationRenderer
-  excerpt: Llama Stack integration for Haystack
-  category_slug: integrations-api
-  title: Llama Stack
-  slug: integrations-llama-stack
-  order: 200
-  markdown:
-    descriptive_class_title: false
-    classdef_code_block: false
-    descriptive_module_title: true
-    add_method_class_prefix: true
-    add_member_class_prefix: false
-    filename: _readme_llama_stack.md