llama-stack-haystack 2.0.0__tar.gz → 3.0.1__tar.gz

{llama_stack_haystack-2.0.0 → llama_stack_haystack-3.0.1}/CHANGELOG.md

@@ -1,11 +1,36 @@
 # Changelog
 
+## [integrations/llama_stack-v3.0.0] - 2026-02-03
+
+### 🐛 Bug Fixes
+
+- *(llama_stack)* Support llama-stack>=0.4.0 (#2805)
+
+
+## [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-3.0.1}/LICENSE.txt

@@ -58,7 +58,7 @@ APPENDIX: How to apply the Apache License to your work.
 
 To apply the Apache License to your work, attach the following boilerplate notice, with the fields enclosed by brackets "[]" replaced with your own identifying information. (Don't include the brackets!)  The text should be enclosed in the appropriate comment syntax for the file format. We also recommend that a file or class name and description of purpose be included on the same "printed page" as the copyright notice for easier identification within third-party archives.
 
-Copyright [yyyy] [name of copyright owner]
+Copyright 2023-present deepset GmbH
 
 Licensed under the Apache License, Version 2.0 (the "License");
 you may not use this file except in compliance with the License.

{llama_stack_haystack-2.0.0 → llama_stack_haystack-3.0.1}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.5
 Name: llama-stack-haystack
-Version: 2.0.0
+Version: 3.0.1
 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
@@ -13,17 +13,19 @@ Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Programming Language :: Python :: 3.15
 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
 
 [![PyPI - Version](https://img.shields.io/pypi/v/llama-stack-haystack.svg)](https://pypi.org/project/llama-stack-haystack)
-[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/llama-haystack.svg)](https://pypi.org/project/llama-stack-haystack)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/llama-stack-haystack.svg)](https://pypi.org/project/llama-stack-haystack)
 
 - [Integration page](https://haystack.deepset.ai/integrations/llama_stack)
 - [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/llama_stack/CHANGELOG.md)
@@ -34,4 +36,4 @@ Description-Content-Type: text/markdown
 
 Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).
 
-To run integration tests locally, you need to run Ollama and the Llama Stack Server. Refer to the [workflow file](https://github.com/deepset-ai/haystack-core-integrations/blob/main/.github/workflows/llama_stack.yml) for more details.
+To run integration tests locally, you need to run Ollama and the Llama Stack Server. Refer to the [workflow file](https://github.com/deepset-ai/haystack-core-integrations/blob/main/.github/workflows/llama_stack.yml) for more details.

{llama_stack_haystack-2.0.0 → llama_stack_haystack-3.0.1}/README.md

@@ -1,7 +1,7 @@
 # llama-stack-haystack
 
 [![PyPI - Version](https://img.shields.io/pypi/v/llama-stack-haystack.svg)](https://pypi.org/project/llama-stack-haystack)
-[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/llama-haystack.svg)](https://pypi.org/project/llama-stack-haystack)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/llama-stack-haystack.svg)](https://pypi.org/project/llama-stack-haystack)
 
 - [Integration page](https://haystack.deepset.ai/integrations/llama_stack)
 - [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/llama_stack/CHANGELOG.md)
@@ -12,4 +12,4 @@
 
 Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).
 
-To run integration tests locally, you need to run Ollama and the Llama Stack Server. Refer to the [workflow file](https://github.com/deepset-ai/haystack-core-integrations/blob/main/.github/workflows/llama_stack.yml) for more details.
+To run integration tests locally, you need to run Ollama and the Llama Stack Server. Refer to the [workflow file](https://github.com/deepset-ai/haystack-core-integrations/blob/main/.github/workflows/llama_stack.yml) for more details.

{llama_stack_haystack-2.0.0 → llama_stack_haystack-3.0.1}/examples/llama-stack-with-tools.py

@@ -8,11 +8,11 @@
 # set up Llama Stack Server through an inference provider and have a model available.
 # For a quick start on how to setup server with Ollama, see [Llama Stack docs](https://llama-stack.readthedocs.io/en/latest/getting_started/index.html).
 
-from haystack.components.tools import ToolInvoker
+from haystack.components.agents import Agent
 from haystack.dataclasses import ChatMessage
 from haystack.tools import Tool
 
-from .components.generators.llama_stack.chat.chat_generator import LlamaStackChatGenerator
+from haystack_integrations.components.generators.llama_stack import LlamaStackChatGenerator
 
 
 # Define a tool that models can call
@@ -30,20 +30,14 @@ weather_tool = Tool(
     function=weather,
 )
 
-# Create a tool invoker with the weather tool
-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?")]
-
-response = client.run(messages=messages, tools=[weather_tool])["replies"]
 
-print(f"assistant messages: {response[0]}\n")  # noqa: T201
+# The Agent calls the tool and feeds the result back to the model
+agent = Agent(chat_generator=client, tools=[weather_tool])
+result = agent.run(messages=[ChatMessage.from_user("What's the weather in Tokyo?")])
 
-# If the assistant message contains a tool call, run the tool invoker
-if response[0].tool_calls:
-    tool_messages = tool_invoker.run(messages=response)["tool_messages"]
-    print(f"tool messages: {tool_messages}")  # noqa: T201
+print(f"messages: {result['messages']}\n")
+print(f"assistant final answer: {result['last_message'].text}")

llama_stack_haystack-3.0.1/pydoc/config_docusaurus.yml

@@ -0,0 +1,13 @@
+loaders:
+  - modules:
+      - haystack_integrations.components.generators.llama_stack.chat.chat_generator
+    search_path: [../src]
+processors:
+  - type: filter
+    documented_only: true
+    skip_empty_modules: true
+renderer:
+  description: Llama Stack integration for Haystack
+  id: integrations-llama-stack
+  filename: llama_stack.md
+  title: Llama Stack

{llama_stack_haystack-2.0.0 → llama_stack_haystack-3.0.1}/pyproject.toml

@@ -17,10 +17,12 @@ classifiers = [
   "Programming Language :: Python",
   "Programming Language :: Python :: 3.12", # minimum supported version by llama-stack
   "Programming Language :: Python :: 3.13",
+  "Programming Language :: Python :: 3.14",
+  "Programming Language :: Python :: 3.15",
   "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"
@@ -42,7 +44,7 @@ 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_docusaurus.yml"]
+docs = ["haystack-pydoc pydoc/config_docusaurus.yml"]
 fmt = "ruff check --fix {args}; ruff format {args}"
 fmt-check = "ruff check {args} && ruff format --check {args}"
 
@@ -61,7 +63,8 @@ dependencies = [
 unit = 'pytest -m "not integration" {args:tests}'
 integration = 'pytest -m "integration" {args:tests}'
 all = 'pytest {args:tests}'
-cov-retry = 'pytest --cov=haystack_integrations --reruns 3 --reruns-delay 30 -x {args:tests}'
+unit-cov-retry = 'pytest --cov=haystack_integrations --reruns 3 --reruns-delay 30 -x -m "not integration" {args:tests}'
+integration-cov-append-retry = 'pytest --cov=haystack_integrations --cov-append --reruns 3 --reruns-delay 30 -x -m "integration" {args:tests}'
 
 types = "mypy -p haystack_integrations.components.generators.llama_stack {args}"
 
@@ -73,15 +76,22 @@ disallow_incomplete_defs = true
 
 
 [tool.ruff]
-target-version = "py39"
 line-length = 120
 
 [tool.ruff.lint]
 select = [
   "A",
+  "ANN",
   "ARG",
   "B",
   "C",
+  "D102",   # Missing docstring in public method
+  "D103",   # Missing docstring in public function
+  "D205",   # 1 blank line required between summary line and description
+  "D209",   # Closing triple quotes go to new line
+  "D213",   # summary lines must be positioned on the second physical line of the docstring
+  "D417",   # Missing argument descriptions in the docstring
+  "D419",   # Docstring is empty
   "DTZ",
   "E",
   "EM",
@@ -116,9 +126,12 @@ ignore = [
   "PLR0912",
   "PLR0913",
   "PLR0915",
+  "PLR0917",
   # Misc
   "B008",
   "S101",
+  # Allow `Any` - used legitimately for dynamic types and SDK boundaries
+  "ANN401",
 ]
 unfixable = [
   # Don't touch unused imports
@@ -133,11 +146,14 @@ ban-relative-imports = "parents"
 
 [tool.ruff.lint.per-file-ignores]
 # Tests can use magic values, assertions, and relative imports
-"tests/**/*" = ["PLR2004", "S101", "TID252", "E501", "F841"]
+"tests/**/*" = ["D", "PLR2004", "S101", "TID252", "ANN", "E501", "F841"]
+# Examples can print their output and don't need type annotations
+"examples/**/*" = ["T201", "ANN"]
 
 [tool.coverage.run]
 source = ["haystack_integrations"]
 branch = true
+relative_files = true
 parallel = false
 
 

{llama_stack_haystack-2.0.0 → llama_stack_haystack-3.0.1}/src/haystack_integrations/components/generators/llama_stack/chat/chat_generator.py

@@ -20,6 +20,7 @@ logger = logging.getLogger(__name__)
 class LlamaStackChatGenerator(OpenAIChatGenerator):
     """
     Enables text generation using Llama Stack framework.
+
     Llama Stack Server supports multiple inference providers, including Ollama, Together,
     and vLLM and other cloud providers.
     For a complete list of inference providers, see [Llama Stack docs](https://llama-stack.readthedocs.io/en/latest/providers/inference/index.html).
@@ -59,7 +60,7 @@ 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,
@@ -68,10 +69,12 @@ class LlamaStackChatGenerator(OpenAIChatGenerator):
         tools_strict: bool = False,
         max_retries: int | None = None,
         http_client_kwargs: dict[str, Any] | None = None,
-    ):
+    ) -> None:
         """
-        Creates an instance of LlamaStackChatGenerator. To use this chat generator,
-        you need to setup Llama Stack Server with an inference provider and have a model available.
+        Creates an instance of LlamaStackChatGenerator.
+
+        To use this chat generator, you need to setup Llama Stack Server with an inference provider and have a model
+        available.
 
         :param model:
             The name of the model to use for chat completion.

{llama_stack_haystack-2.0.0 → llama_stack_haystack-3.0.1}/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,
@@ -492,6 +492,6 @@ class TestLlamaStackChatGenerator:
         assert len(results["replies"]) == 1
         message: ChatMessage = results["replies"][0]
         msg = json.loads(message.text)
-        assert "Marketing Summit" in msg["event_name"]
+        assert "marketing summit" in msg["event_name"].lower()
         assert isinstance(msg["event_date"], str)
         assert isinstance(msg["event_location"], str)

llama_stack_haystack-2.0.0/pydoc/config_docusaurus.yml

@@ -1,28 +0,0 @@
-loaders:
-- ignore_when_discovered:
-  - __init__
-  modules:
-  - haystack_integrations.components.generators.llama_stack.chat.chat_generator
-  search_path:
-  - ../src
-  type: haystack_pydoc_tools.loaders.CustomPythonLoader
-processors:
-- do_not_filter_modules: false
-  documented_only: true
-  expression: null
-  skip_empty_modules: true
-  type: filter
-- type: smart
-- type: crossref
-renderer:
-  description: Llama Stack integration for Haystack
-  id: integrations-llama-stack
-  markdown:
-    add_member_class_prefix: false
-    add_method_class_prefix: true
-    classdef_code_block: false
-    descriptive_class_title: false
-    descriptive_module_title: true
-    filename: llama_stack.md
-  title: Llama Stack
-  type: haystack_pydoc_tools.renderers.DocusaurusRenderer