llama-stack-haystack 1.0.0__tar.gz

llama_stack_haystack-1.0.0/.gitignore

@@ -0,0 +1,146 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+volumes/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# IDEs
+.vscode
+
+# Docs generation artifacts
+_readme_*.md
+.idea
+
+# macOS
+.DS_Store
+
+# http cache (requests-cache)
+**/http_cache.sqlite
+
+# ruff
+.ruff_cache

llama_stack_haystack-1.0.0/LICENSE.txt

@@ -0,0 +1,73 @@
+Apache License
+Version 2.0, January 2004
+http://www.apache.org/licenses/
+
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+1. Definitions.
+
+"License" shall mean the terms and conditions for use, reproduction, and distribution as defined by Sections 1 through 9 of this document.
+
+"Licensor" shall mean the copyright owner or entity authorized by the copyright owner that is granting the License.
+
+"Legal Entity" shall mean the union of the acting entity and all other entities that control, are controlled by, or are under common control with that entity. For the purposes of this definition, "control" means (i) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares, or (iii) beneficial ownership of such entity.
+
+"You" (or "Your") shall mean an individual or Legal Entity exercising permissions granted by this License.
+
+"Source" form shall mean the preferred form for making modifications, including but not limited to software source code, documentation source, and configuration files.
+
+"Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types.
+
+"Work" shall mean the work of authorship, whether in Source or Object form, made available under the License, as indicated by a copyright notice that is included in or attached to the work (an example is provided in the Appendix below).
+
+"Derivative Works" shall mean any work, whether in Source or Object form, that is based on (or derived from) the Work and for which the editorial revisions, annotations, elaborations, or other modifications represent, as a whole, an original work of authorship. For the purposes of this License, Derivative Works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work and Derivative Works thereof.
+
+"Contribution" shall mean any work of authorship, including the original version of the Work and any modifications or additions to that Work or Derivative Works thereof, that is intentionally submitted to Licensor for inclusion in the Work by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, "submitted" means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Work, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution."
+
+"Contributor" shall mean Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Work.
+
+2. Grant of Copyright License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute the Work and such Derivative Works in Source or Object form.
+
+3. Grant of Patent License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Work, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Work to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Work or a Contribution incorporated within the Work constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for that Work shall terminate as of the date such litigation is filed.
+
+4. Redistribution. You may reproduce and distribute copies of the Work or Derivative Works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions:
+
+     (a) You must give any other recipients of the Work or Derivative Works a copy of this License; and
+
+     (b) You must cause any modified files to carry prominent notices stating that You changed the files; and
+
+     (c) You must retain, in the Source form of any Derivative Works that You distribute, all copyright, patent, trademark, and attribution notices from the Source form of the Work, excluding those notices that do not pertain to any part of the Derivative Works; and
+
+     (d) If the Work includes a "NOTICE" text file as part of its distribution, then any Derivative Works that You distribute must include a readable copy of the attribution notices contained within such NOTICE file, excluding those notices that do not pertain to any part of the Derivative Works, in at least one of the following places: within a NOTICE text file distributed as part of the Derivative Works; within the Source form or documentation, if provided along with the Derivative Works; or, within a display generated by the Derivative Works, if and wherever such third-party notices normally appear. The contents of the NOTICE file are for informational purposes only and do not modify the License. You may add Your own attribution notices within Derivative Works that You distribute, alongside or as an addendum to the NOTICE text from the Work, provided that such additional attribution notices cannot be construed as modifying the License.
+
+     You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such Derivative Works as a whole, provided Your use, reproduction, and distribution of the Work otherwise complies with the conditions stated in this License.
+
+5. Submission of Contributions. Unless You explicitly state otherwise, any Contribution intentionally submitted for inclusion in the Work by You to the Licensor shall be under the terms and conditions of this License, without any additional terms or conditions. Notwithstanding the above, nothing herein shall supersede or modify the terms of any separate license agreement you may have executed with Licensor regarding such Contributions.
+
+6. Trademarks. This License does not grant permission to use the trade names, trademarks, service marks, or product names of the Licensor, except as required for reasonable and customary use in describing the origin of the Work and reproducing the content of the NOTICE file.
+
+7. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Work (and each Contributor provides its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Work and assume any risks associated with Your exercise of permissions under this License.
+
+8. Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Work (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages.
+
+9. Accepting Warranty or Additional Liability. While redistributing the Work or Derivative Works thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability.
+
+END OF TERMS AND CONDITIONS
+
+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]
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.

llama_stack_haystack-1.0.0/PKG-INFO

@@ -0,0 +1,45 @@
+Metadata-Version: 2.4
+Name: llama-stack-haystack
+Version: 1.0.0
+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
+Project-URL: Source, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/llama-stack
+Author-email: deepset GmbH <info@deepset.ai>
+License-Expression: Apache-2.0
+License-File: LICENSE.txt
+Classifier: Development Status :: 4 - Beta
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Requires-Python: >=3.10
+Requires-Dist: haystack-ai>=2.14
+Requires-Dist: llama-stack
+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)
+
+-----
+
+**Table of Contents**
+
+- [Installation](#installation)
+- [License](#license)
+
+## Installation
+
+```console
+pip install llama-stack-haystack
+```
+
+## License
+
+`llama-stack-haystack` is distributed under the terms of the [Apache-2.0](https://spdx.org/licenses/Apache-2.0.html) license.

llama_stack_haystack-1.0.0/README.md

@@ -0,0 +1,21 @@
+# 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)
+
+-----
+
+**Table of Contents**
+
+- [Installation](#installation)
+- [License](#license)
+
+## Installation
+
+```console
+pip install llama-stack-haystack
+```
+
+## License
+
+`llama-stack-haystack` is distributed under the terms of the [Apache-2.0](https://spdx.org/licenses/Apache-2.0.html) license.

llama_stack_haystack-1.0.0/examples/llama-stack-with-tools.py

@@ -0,0 +1,49 @@
+# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+# This example demonstrates how to use the LlamaStackChatGenerator component
+# with tools.
+# To run this example, you will need to
+# 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.dataclasses import ChatMessage
+from haystack.tools import Tool
+
+from .components.generators.llama_stack.chat.chat_generator import LlamaStackChatGenerator
+
+
+# Define a tool that models can call
+def weather(city: str):
+    """Return mock weather info for the given city."""
+    return f"The weather in {city} is sunny and 32°C"
+
+
+tool_parameters = {"type": "object", "properties": {"city": {"type": "string"}}, "required": ["city"]}
+
+weather_tool = Tool(
+    name="weather",
+    description="Useful for getting the weather in a specific city",
+    parameters=tool_parameters,
+    function=weather,
+)
+
+# Create a tool invoker with the weather tool
+tool_invoker = ToolInvoker(tools=[weather_tool])
+
+client = LlamaStackChatGenerator(
+    model="llama3.2:3b",  # model name varies depending on the inference provider used for the Llama Stack Server.
+    api_base_url="http://localhost:8321/v1/openai/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
+
+# 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

llama_stack_haystack-1.0.0/pydoc/config.yml

@@ -0,0 +1,29 @@
+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

llama_stack_haystack-1.0.0/pyproject.toml

@@ -0,0 +1,156 @@
+[build-system]
+requires = ["hatchling", "hatch-vcs"]
+build-backend = "hatchling.build"
+
+[project]
+name = "llama-stack-haystack"
+dynamic = ["version"]
+description = 'Use Llama Stack framework for text generation'
+readme = "README.md"
+requires-python = ">=3.10"
+license = "Apache-2.0"
+keywords = []
+authors = [{ name = "deepset GmbH", email = "info@deepset.ai" }]
+classifiers = [
+  "License :: OSI Approved :: Apache Software License",
+  "Development Status :: 4 - Beta",
+  "Programming Language :: Python",
+  "Programming Language :: Python :: 3.10", # python 3.9 is not supported by llama-stack
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
+  "Programming Language :: Python :: Implementation :: CPython",
+  "Programming Language :: Python :: Implementation :: PyPy",
+]
+dependencies = ["haystack-ai>=2.14", "llama-stack"]
+
+[project.urls]
+Documentation = "https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/llama-stack#readme"
+Issues = "https://github.com/deepset-ai/haystack-core-integrations/issues"
+Source = "https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/llama-stack"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/haystack_integrations"]
+
+[tool.hatch.version]
+source = "vcs"
+tag-pattern = 'integrations\/llama_stack-v(?P<version>.*)'
+
+[tool.hatch.version.raw-options]
+root = "../.."
+git_describe_command = 'git describe --tags --match="integrations/llama_stack-v[0-9]*"'
+
+[tool.hatch.envs.default]
+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}"
+fmt-check = "ruff check {args} && ruff format --check {args}"
+
+[tool.hatch.envs.test]
+dependencies = [
+    "pytest",
+    "pytest-asyncio",
+    "pytest-cov",
+    "pytest-rerunfailures",
+    "mypy",
+    "pip",
+    "pytz"
+]
+
+[tool.hatch.envs.test.scripts]
+unit = 'pytest -m "not integration" {args:tests}'
+integration = 'pytest -m "integration" {args:tests}'
+all = 'pytest {args:tests}'
+cov-retry = 'all --cov=haystack_integrations --reruns 3 --reruns-delay 30 -x'
+
+types = "mypy -p haystack_integrations.components.generators.llama_stack {args}"
+
+[tool.mypy]
+install_types = true
+non_interactive = true
+check_untyped_defs = true
+disallow_incomplete_defs = true
+
+
+[tool.ruff]
+target-version = "py38"
+line-length = 120
+
+[tool.ruff.lint]
+select = [
+  "A",
+  "ARG",
+  "B",
+  "C",
+  "DTZ",
+  "E",
+  "EM",
+  "F",
+  "I",
+  "ICN",
+  "ISC",
+  "N",
+  "PLC",
+  "PLE",
+  "PLR",
+  "PLW",
+  "Q",
+  "RUF",
+  "S",
+  "T",
+  "TID",
+  "UP",
+  "W",
+  "YTT",
+]
+ignore = [
+  # Allow non-abstract empty methods in abstract base classes
+  "B027",
+  # Ignore checks for possible passwords
+  "S105",
+  "S106",
+  "S107",
+  # Ignore complexity
+  "C901",
+  "PLR0911",
+  "PLR0912",
+  "PLR0913",
+  "PLR0915",
+  # Misc
+  "B008",
+  "S101",
+]
+unfixable = [
+  # Don't touch unused imports
+  "F401",
+]
+
+[tool.ruff.lint.isort]
+known-first-party = ["haystack_integrations"]
+
+[tool.ruff.lint.flake8-tidy-imports]
+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"]
+
+[tool.coverage.run]
+source = ["haystack_integrations"]
+branch = true
+parallel = false
+
+
+[tool.coverage.report]
+omit = ["*/tests/*", "*/__init__.py"]
+show_missing = true
+exclude_lines = ["no cov", "if __name__ == .__main__.:", "if TYPE_CHECKING:"]
+
+[tool.pytest.ini_options]
+addopts = "--strict-markers"
+markers = [
+  "integration: integration tests",
+]
+log_cli = true

llama_stack_haystack-1.0.0/src/haystack_integrations/components/generators/llama_stack/__init__.py

@@ -0,0 +1,3 @@
+from .chat.chat_generator import LlamaStackChatGenerator
+
+__all__ = ["LlamaStackChatGenerator"]

llama_stack_haystack-1.0.0/src/haystack_integrations/components/generators/llama_stack/chat/chat_generator.py

@@ -0,0 +1,168 @@
+# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from typing import Any, Dict, List, Optional, Union
+
+from haystack import component, default_from_dict, default_to_dict, logging
+from haystack.components.generators.chat import OpenAIChatGenerator
+from haystack.dataclasses import StreamingCallbackT
+from haystack.tools import Tool, Toolset, deserialize_tools_or_toolset_inplace, serialize_tools_or_toolset
+from haystack.utils import deserialize_callable, serialize_callable
+from haystack.utils.auth import Secret
+
+logger = logging.getLogger(__name__)
+
+
+@component
+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).
+
+    Users can pass any text generation parameters valid for the OpenAI chat completion API
+    directly to this component using the `generation_kwargs`
+    parameter in `__init__` or the `generation_kwargs` parameter in `run` method.
+
+    This component uses the `ChatMessage` format for structuring both input and output,
+    ensuring coherent and contextually relevant responses in chat-based text generation scenarios.
+    Details on the `ChatMessage` format can be found in the
+    [Haystack docs](https://docs.haystack.deepset.ai/docs/chatmessage)
+
+    Usage example:
+    You need to setup Llama Stack Server before running this example 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).
+
+    ```python
+    from haystack_integrations.components.generators.llama_stack import LlamaStackChatGenerator
+    from haystack.dataclasses import ChatMessage
+
+    messages = [ChatMessage.from_user("What's Natural Language Processing?")]
+
+    client = LlamaStackChatGenerator(model="llama3.2:3b")
+    response = client.run(messages)
+    print(response)
+
+    >>{'replies': [ChatMessage(_content=[TextContent(text='Natural Language Processing (NLP)
+    is a branch of artificial intelligence
+    >>that focuses on enabling computers to understand, interpret, and generate human language in a way that is
+    >>meaningful and useful.')], _role=<ChatRole.ASSISTANT: 'assistant'>, _name=None,
+    >>_meta={'model': 'llama3.2:3b', 'index': 0, 'finish_reason': 'stop',
+    >>'usage': {'prompt_tokens': 15, 'completion_tokens': 36, 'total_tokens': 51}})]}
+    """
+
+    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[Union[List[Tool], Toolset]] = None,
+        tools_strict: bool = False,
+        max_retries: Optional[int] = None,
+        http_client_kwargs: Optional[Dict[str, Any]] = 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.
+
+        :param model:
+            The name of the model to use for chat completion.
+            This depends on the inference provider used for the Llama Stack Server.
+        :param streaming_callback:
+            A callback function that is called when a new token is received from the stream.
+            The callback function accepts StreamingChunk as an argument.
+        :param api_base_url:
+            The Llama Stack API base url. If not specified, the localhost is used with the default port 8321.
+        :param organization: Your organization ID, defaults to `None`.
+        :param generation_kwargs:
+            Other parameters to use for the model. These parameters are all sent directly to
+            the Llama Stack endpoint. See [Llama Stack API docs](https://llama-stack.readthedocs.io/) for more details.
+            Some of the supported parameters:
+            - `max_tokens`: The maximum number of tokens the output text can have.
+            - `temperature`: What sampling temperature to use. Higher values mean the model will take more risks.
+                Try 0.9 for more creative applications and 0 (argmax sampling) for ones with a well-defined answer.
+            - `top_p`: An alternative to sampling with temperature, called nucleus sampling, where the model
+                considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens
+                comprising the top 10% probability mass are considered.
+            - `stream`: Whether to stream back partial progress. If set, tokens will be sent as data-only server-sent
+                events as they become available, with the stream terminated by a data: [DONE] message.
+            - `safe_prompt`: Whether to inject a safety prompt before all conversations.
+            - `random_seed`: The seed to use for random sampling.
+        :param timeout:
+            Timeout for client calls using OpenAI API. If not set, it defaults to either the
+            `OPENAI_TIMEOUT` environment variable, or 30 seconds.
+        :param tools:
+            A list of tools or a Toolset for which the model can prepare calls. This parameter can accept either a
+            list of `Tool` objects or a `Toolset` instance.
+        :param tools_strict:
+            Whether to enable strict schema adherence for tool calls. If set to `True`, the model will follow exactly
+            the schema provided in the `parameters` field of the tool definition, but this may increase latency.
+        :param max_retries:
+            Maximum number of retries to contact OpenAI after an internal error.
+            If not set, it defaults to either the `OPENAI_MAX_RETRIES` environment variable, or set to 5.
+        :param http_client_kwargs:
+            A dictionary of keyword arguments to configure a custom `httpx.Client`or `httpx.AsyncClient`.
+            For more information, see the [HTTPX documentation](https://www.python-httpx.org/api/#client).
+
+        """
+
+        # Use placeholder key for a Llama Stack server running locally
+        api_key = Secret.from_token("placeholder-api-key")
+
+        super(LlamaStackChatGenerator, self).__init__(  # noqa: UP008
+            model=model,
+            api_key=api_key,
+            streaming_callback=streaming_callback,
+            api_base_url=api_base_url,
+            organization=organization,
+            generation_kwargs=generation_kwargs,
+            timeout=timeout,
+            tools=tools,
+            tools_strict=tools_strict,
+            max_retries=max_retries,
+            http_client_kwargs=http_client_kwargs,
+        )
+
+    def to_dict(self) -> Dict[str, Any]:
+        """
+        Serialize this component to a dictionary.
+
+        :returns:
+            The serialized component as a dictionary.
+        """
+        callback_name = serialize_callable(self.streaming_callback) if self.streaming_callback else None
+        return default_to_dict(
+            self,
+            model=self.model,
+            streaming_callback=callback_name,
+            api_base_url=self.api_base_url,
+            organization=self.organization,
+            generation_kwargs=self.generation_kwargs,
+            timeout=self.timeout,
+            max_retries=self.max_retries,
+            tools=serialize_tools_or_toolset(self.tools),
+            tools_strict=self.tools_strict,
+            http_client_kwargs=self.http_client_kwargs,
+        )
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "LlamaStackChatGenerator":
+        """
+        Deserialize this component from a dictionary.
+
+        :param data: The dictionary representation of this component.
+        :returns:
+            The deserialized component instance.
+        """
+        deserialize_tools_or_toolset_inplace(data["init_parameters"], key="tools")
+        init_params = data.get("init_parameters", {})
+        serialized_callback_handler = init_params.get("streaming_callback")
+        if serialized_callback_handler:
+            data["init_parameters"]["streaming_callback"] = deserialize_callable(serialized_callback_handler)
+        return default_from_dict(cls, data)

llama_stack_haystack-1.0.0/tests/__init__.py

@@ -0,0 +1,3 @@
+# SPDX-FileCopyrightText: 2024-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0

llama_stack_haystack-1.0.0/tests/test_llama_stack_chat_generator.py

@@ -0,0 +1,300 @@
+from datetime import datetime
+from unittest.mock import patch
+
+import pytest
+import pytz
+from haystack.components.generators.utils import print_streaming_chunk
+from haystack.dataclasses import ChatMessage, ChatRole, StreamingChunk, ToolCall
+from haystack.tools import Tool
+from openai.types.chat import ChatCompletion, ChatCompletionMessage
+from openai.types.chat.chat_completion import Choice
+
+from haystack_integrations.components.generators.llama_stack.chat.chat_generator import LlamaStackChatGenerator
+
+
+@pytest.fixture
+def chat_messages():
+    return [
+        ChatMessage.from_system("You are a helpful assistant"),
+        ChatMessage.from_user("What's the capital of France"),
+    ]
+
+
+def weather(city: str):
+    """Get weather for a given city."""
+    return f"The weather in {city} is sunny and 32°C"
+
+
+@pytest.fixture
+def tools():
+    tool_parameters = {"type": "object", "properties": {"city": {"type": "string"}}, "required": ["city"]}
+    tool = Tool(
+        name="weather",
+        description="useful to determine the weather in a given location",
+        parameters=tool_parameters,
+        function=weather,
+    )
+
+    return [tool]
+
+
+@pytest.fixture
+def mock_chat_completion():
+    """
+    Mock the OpenAI API completion response and reuse it for tests
+    """
+    with patch("openai.resources.chat.completions.Completions.create") as mock_chat_completion_create:
+        completion = ChatCompletion(
+            id="foo",
+            model="llama3.2:3b",
+            object="chat.completion",
+            choices=[
+                Choice(
+                    finish_reason="stop",
+                    logprobs=None,
+                    index=0,
+                    message=ChatCompletionMessage(content="Hello world!", role="assistant"),
+                )
+            ],
+            created=int(datetime.now(tz=pytz.timezone("UTC")).timestamp()),
+            usage={"prompt_tokens": 57, "completion_tokens": 40, "total_tokens": 97},
+        )
+
+        mock_chat_completion_create.return_value = completion
+        yield mock_chat_completion_create
+
+
+class TestLlamaStackChatGenerator:
+    def test_init_default(self):
+        component = LlamaStackChatGenerator(model="llama3.2:3b")
+        assert component.model == "llama3.2:3b"
+        assert component.api_base_url == "http://localhost:8321/v1/openai/v1"
+        assert component.streaming_callback is None
+        assert not component.generation_kwargs
+
+    def test_init_with_parameters(self):
+        component = LlamaStackChatGenerator(
+            model="llama3.2:3b",
+            streaming_callback=print_streaming_chunk,
+            api_base_url="test-base-url",
+            generation_kwargs={"max_tokens": 10, "some_test_param": "test-params"},
+        )
+        assert component.model == "llama3.2:3b"
+        assert component.streaming_callback is print_streaming_chunk
+        assert component.generation_kwargs == {"max_tokens": 10, "some_test_param": "test-params"}
+
+    def test_to_dict_default(
+        self,
+    ):
+        component = LlamaStackChatGenerator(model="llama3.2:3b")
+        data = component.to_dict()
+
+        assert (
+            data["type"]
+            == "haystack_integrations.components.generators.llama_stack.chat.chat_generator.LlamaStackChatGenerator"
+        )
+
+        expected_params = {
+            "model": "llama3.2:3b",
+            "streaming_callback": None,
+            "api_base_url": "http://localhost:8321/v1/openai/v1",
+            "generation_kwargs": {},
+            "timeout": None,
+            "max_retries": None,
+            "tools": None,
+            "http_client_kwargs": None,
+            "tools_strict": False,
+        }
+
+        for key, value in expected_params.items():
+            assert data["init_parameters"][key] == value
+
+    def test_to_dict_with_parameters(
+        self,
+    ):
+        component = LlamaStackChatGenerator(
+            model="llama3.2:3b",
+            streaming_callback=print_streaming_chunk,
+            api_base_url="test-base-url",
+            generation_kwargs={"max_tokens": 10, "some_test_param": "test-params"},
+            timeout=10,
+            max_retries=10,
+            tools=None,
+            http_client_kwargs={"proxy": "http://localhost:8080"},
+            tools_strict=True,
+        )
+        data = component.to_dict()
+
+        assert (
+            data["type"]
+            == "haystack_integrations.components.generators.llama_stack.chat.chat_generator.LlamaStackChatGenerator"
+        )
+
+        expected_params = {
+            "model": "llama3.2:3b",
+            "api_base_url": "test-base-url",
+            "streaming_callback": "haystack.components.generators.utils.print_streaming_chunk",
+            "generation_kwargs": {"max_tokens": 10, "some_test_param": "test-params"},
+            "timeout": 10,
+            "max_retries": 10,
+            "tools": None,
+            "http_client_kwargs": {"proxy": "http://localhost:8080"},
+            "tools_strict": True,
+        }
+
+        for key, value in expected_params.items():
+            assert data["init_parameters"][key] == value
+
+    def test_from_dict(
+        self,
+    ):
+        data = {
+            "type": (
+                "haystack_integrations.components.generators.llama_stack.chat.chat_generator.LlamaStackChatGenerator"
+            ),
+            "init_parameters": {
+                "model": "llama3.2:3b",
+                "api_base_url": "test-base-url",
+                "streaming_callback": "haystack.components.generators.utils.print_streaming_chunk",
+                "generation_kwargs": {"max_tokens": 10, "some_test_param": "test-params"},
+                "timeout": 10,
+                "max_retries": 10,
+                "tools": None,
+                "http_client_kwargs": {"proxy": "http://localhost:8080"},
+                "tools_strict": False,
+            },
+        }
+        component = LlamaStackChatGenerator.from_dict(data)
+        assert component.model == "llama3.2:3b"
+        assert component.streaming_callback is print_streaming_chunk
+        assert component.api_base_url == "test-base-url"
+        assert component.generation_kwargs == {"max_tokens": 10, "some_test_param": "test-params"}
+        assert component.http_client_kwargs == {"proxy": "http://localhost:8080"}
+        assert component.tools is None
+        assert component.timeout == 10
+        assert component.max_retries == 10
+        assert not component.tools_strict
+
+    def test_run(self, chat_messages, mock_chat_completion):  # noqa: ARG002
+        component = LlamaStackChatGenerator(model="llama3.2:3b")
+        response = component.run(chat_messages)
+
+        # check that the component returns the correct ChatMessage response
+        assert isinstance(response, dict)
+        assert "replies" in response
+        assert isinstance(response["replies"], list)
+        assert len(response["replies"]) == 1
+        assert [isinstance(reply, ChatMessage) for reply in response["replies"]]
+
+    def test_run_with_params(self, chat_messages, mock_chat_completion):
+        component = LlamaStackChatGenerator(
+            model="llama3.2:3b",
+            generation_kwargs={"max_tokens": 10, "temperature": 0.5},
+        )
+        response = component.run(chat_messages)
+
+        # check that the component calls the OpenAI API with the correct parameters
+        # for LlamaStack
+        _, kwargs = mock_chat_completion.call_args
+        assert kwargs["max_tokens"] == 10
+        assert kwargs["temperature"] == 0.5
+        # check that the component returns the correct response
+        assert isinstance(response, dict)
+        assert "replies" in response
+        assert isinstance(response["replies"], list)
+        assert len(response["replies"]) == 1
+        assert [isinstance(reply, ChatMessage) for reply in response["replies"]]
+
+    @pytest.mark.integration
+    def test_live_run(self):
+        chat_messages = [ChatMessage.from_user("What's the capital of France")]
+        component = LlamaStackChatGenerator(model="llama3.2:3b")
+        results = component.run(chat_messages)
+        assert len(results["replies"]) == 1
+        message: ChatMessage = results["replies"][0]
+        assert "Paris" in message.text
+        assert "llama3.2:3b" in message.meta["model"]
+        assert message.meta["finish_reason"] == "stop"
+
+    @pytest.mark.integration
+    def test_live_run_streaming(self):
+        class Callback:
+            def __init__(self):
+                self.responses = ""
+                self.counter = 0
+
+            def __call__(self, chunk: StreamingChunk) -> None:
+                self.counter += 1
+                self.responses += chunk.content if chunk.content else ""
+
+        callback = Callback()
+        component = LlamaStackChatGenerator(model="llama3.2:3b", streaming_callback=callback)
+        results = component.run([ChatMessage.from_user("What's the capital of France?")])
+
+        assert len(results["replies"]) == 1
+        message: ChatMessage = results["replies"][0]
+        assert "Paris" in message.text
+
+        assert "llama3.2:3b" in message.meta["model"]
+        assert message.meta["finish_reason"] == "stop"
+
+        assert callback.counter > 1
+        assert "Paris" in callback.responses
+
+    @pytest.mark.integration
+    def test_live_run_with_tools(self, tools):
+        chat_messages = [ChatMessage.from_user("What's the weather like in Paris?")]
+        component = LlamaStackChatGenerator(model="llama3.2:3b", tools=tools)
+        results = component.run(chat_messages)
+        assert len(results["replies"]) == 1
+        message = results["replies"][0]
+        assert message.text == ""
+
+        assert message.tool_calls
+        tool_call = message.tool_call
+        assert isinstance(tool_call, ToolCall)
+        assert tool_call.tool_name == "weather"
+        assert tool_call.arguments == {"city": "Paris"}
+        assert message.meta["finish_reason"] == "tool_calls"
+
+    @pytest.mark.integration
+    def test_live_run_with_tools_and_response(self, tools):
+        """
+        Integration test that the LlamaStackChatGenerator component can run with tools and get a response.
+        """
+        initial_messages = [ChatMessage.from_user("What's the weather like in Paris?")]
+        component = LlamaStackChatGenerator(model="llama3.2:3b", tools=tools)
+        results = component.run(messages=initial_messages, generation_kwargs={"tool_choice": "auto"})
+
+        assert len(results["replies"]) > 0, "No replies received"
+
+        # Find the message with tool calls
+        tool_message = None
+        for message in results["replies"]:
+            if message.tool_call:
+                tool_message = message
+                break
+
+        assert tool_message is not None, "No message with tool call found"
+        assert isinstance(tool_message, ChatMessage), "Tool message is not a ChatMessage instance"
+        assert ChatMessage.is_from(tool_message, ChatRole.ASSISTANT), "Tool message is not from the assistant"
+
+        tool_call = tool_message.tool_call
+        assert tool_call.id, "Tool call does not contain value for 'id' key"
+        assert tool_call.tool_name == "weather"
+        assert tool_call.arguments == {"city": "Paris"}
+        assert tool_message.meta["finish_reason"] == "tool_calls"
+
+        new_messages = [
+            initial_messages[0],
+            tool_message,
+            ChatMessage.from_tool(tool_result="22° C", origin=tool_call),
+        ]
+        # Pass the tool result to the model to get the final response
+        results = component.run(new_messages)
+
+        assert len(results["replies"]) == 1
+        final_message = results["replies"][0]
+        assert not final_message.tool_call
+        assert len(final_message.text) > 0
+        assert "paris" in final_message.text.lower()