livekit-plugins-cerebras 1.5.3__tar.gz

livekit_plugins_cerebras-1.5.3/.gitignore

@@ -0,0 +1,179 @@
+**/.vscode
+**/.DS_Store
+
+# 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/
+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/
+cover/
+
+# 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
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .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
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__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
+
+# trunk
+.trunk/
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+
+node_modules
+
+credentials.json
+pyrightconfig.json
+docs/
+
+# Database files
+*.db
+
+
+# Examples for development
+examples/dev/*

livekit_plugins_cerebras-1.5.3/PKG-INFO

@@ -0,0 +1,39 @@
+Metadata-Version: 2.4
+Name: livekit-plugins-cerebras
+Version: 1.5.3
+Summary: Cerebras inference plugin for LiveKit Agents
+Project-URL: Documentation, https://docs.livekit.io
+Project-URL: Website, https://livekit.io/
+Project-URL: Source, https://github.com/livekit/agents
+Author-email: LiveKit <hello@livekit.io>
+License-Expression: Apache-2.0
+Keywords: ai,audio,cerebras,livekit,realtime,video,voice
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Topic :: Multimedia :: Sound/Audio
+Classifier: Topic :: Multimedia :: Video
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10.0
+Requires-Dist: livekit-agents[codecs,openai]>=1.5.3
+Requires-Dist: msgpack-types>=0.7.0
+Requires-Dist: msgpack>=1.0
+Description-Content-Type: text/markdown
+
+# Cerebras plugin for LiveKit Agents
+
+Support for LLM with [Cerebras](https://cerebras.ai/) fast inference.
+
+See [https://docs.livekit.io/agents/integrations/llm/](https://docs.livekit.io/agents/integrations/llm/) for more information.
+
+## Installation
+
+```bash
+pip install livekit-plugins-cerebras
+```
+
+## Pre-requisites
+
+For credentials, you'll need a Cerebras account and API key. Credentials can be passed directly or via `CEREBRAS_API_KEY` environment variable.

livekit_plugins_cerebras-1.5.3/README.md

@@ -0,0 +1,15 @@
+# Cerebras plugin for LiveKit Agents
+
+Support for LLM with [Cerebras](https://cerebras.ai/) fast inference.
+
+See [https://docs.livekit.io/agents/integrations/llm/](https://docs.livekit.io/agents/integrations/llm/) for more information.
+
+## Installation
+
+```bash
+pip install livekit-plugins-cerebras
+```
+
+## Pre-requisites
+
+For credentials, you'll need a Cerebras account and API key. Credentials can be passed directly or via `CEREBRAS_API_KEY` environment variable.

livekit_plugins_cerebras-1.5.3/livekit/plugins/cerebras/__init__.py

@@ -0,0 +1,44 @@
+# Copyright 2026 LiveKit, Inc.
+#
+# 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.
+
+"""Cerebras plugin for LiveKit Agents
+
+Support for LLM with Cerebras fast inference, including payload optimization
+via gzip compression and msgpack encoding.
+"""
+
+from livekit.agents import Plugin
+
+from .llm import LLM
+from .log import logger
+from .version import __version__
+
+__all__ = ["LLM", "__version__"]
+
+
+class CerebrasPlugin(Plugin):
+    def __init__(self) -> None:
+        super().__init__(__name__, __version__, __package__, logger)
+
+
+Plugin.register_plugin(CerebrasPlugin())
+
+# Cleanup docs of unexported modules
+_module = dir()
+NOT_IN_ALL = [m for m in _module if m not in __all__]
+
+__pdoc__ = {}
+
+for n in NOT_IN_ALL:
+    __pdoc__[n] = False

livekit_plugins_cerebras-1.5.3/livekit/plugins/cerebras/llm.py

@@ -0,0 +1,189 @@
+# Copyright 2026 LiveKit, Inc.
+#
+# 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.
+
+from __future__ import annotations
+
+import gzip
+import json
+import os
+from typing import Any
+
+import httpx
+import msgpack
+import openai
+from openai._models import FinalRequestOptions
+from openai._utils import is_mapping
+from openai.types import ReasoningEffort
+
+from livekit.agents.llm import ToolChoice
+from livekit.agents.types import (
+    NOT_GIVEN,
+    NotGivenOr,
+)
+from livekit.agents.utils import is_given
+from livekit.plugins.openai import LLM as OpenAILLM
+
+from .models import CerebrasChatModels
+
+
+class _CerebrasClient(openai.AsyncClient):
+    """AsyncClient subclass that compresses request payloads via msgpack and/or gzip.
+
+    Overrides _build_request() to serialize json_data directly to the target
+    format, avoiding a JSON->dict->msgpack round-trip when msgpack is enabled.
+
+    See https://inference-docs.cerebras.ai/payload-optimization
+    """
+
+    def __init__(
+        self,
+        *,
+        use_msgpack: bool = False,
+        use_gzip: bool = True,
+        **kwargs: Any,
+    ) -> None:
+        super().__init__(**kwargs)
+        self._use_msgpack = use_msgpack
+        self._use_gzip = use_gzip
+
+    def _build_request(
+        self,
+        options: FinalRequestOptions,
+        *,
+        retries_taken: int = 0,
+    ) -> httpx.Request:
+        if not (self._use_msgpack or self._use_gzip):
+            return super()._build_request(options, retries_taken=retries_taken)
+
+        json_data = options.json_data
+        if json_data is not None:
+            # merge extra_json (same logic as base class)
+            if options.extra_json is not None:
+                if is_mapping(json_data):
+                    json_data = {**json_data, **options.extra_json}
+
+            if self._use_msgpack:
+                body = msgpack.packb(json_data)
+                content_type = "application/vnd.msgpack"
+            else:
+                body = json.dumps(json_data, separators=(",", ":"), ensure_ascii=False).encode()
+                content_type = "application/json"
+
+            if self._use_gzip:
+                body = gzip.compress(body, compresslevel=5)
+
+            # bypass openapi_dumps() by switching to the content path
+            options.json_data = None
+            options.extra_json = None
+            options.content = body
+
+            existing = (
+                dict(options.headers) if is_given(options.headers) and options.headers else {}
+            )
+            overrides: dict[str, str] = {"Content-Type": content_type}
+            if self._use_gzip:
+                overrides["Content-Encoding"] = "gzip"
+            options.headers = existing | overrides
+
+        return super()._build_request(options, retries_taken=retries_taken)
+
+
+class LLM(OpenAILLM):
+    def __init__(
+        self,
+        *,
+        model: str | CerebrasChatModels = "llama3.1-8b",
+        api_key: NotGivenOr[str] = NOT_GIVEN,
+        base_url: NotGivenOr[str] = "https://api.cerebras.ai/v1",
+        client: openai.AsyncClient | None = None,
+        user: NotGivenOr[str] = NOT_GIVEN,
+        temperature: NotGivenOr[float] = NOT_GIVEN,
+        parallel_tool_calls: NotGivenOr[bool] = NOT_GIVEN,
+        tool_choice: NotGivenOr[ToolChoice] = NOT_GIVEN,
+        reasoning_effort: NotGivenOr[ReasoningEffort] = NOT_GIVEN,
+        safety_identifier: NotGivenOr[str] = NOT_GIVEN,
+        prompt_cache_key: NotGivenOr[str] = NOT_GIVEN,
+        top_p: NotGivenOr[float] = NOT_GIVEN,
+        timeout: httpx.Timeout | None = None,
+        max_retries: NotGivenOr[int] = NOT_GIVEN,
+        gzip_compression: bool = True,
+        msgpack_encoding: bool = True,
+    ):
+        """
+        Create a new instance of Cerebras LLM.
+
+        ``api_key`` must be set to your Cerebras API key, either using the argument or by setting
+        the ``CEREBRAS_API_KEY`` environmental variable.
+
+        When ``gzip_compression`` is True (default), request payloads are gzip-compressed,
+        which can reduce TTFT for requests with large prompts.
+
+        When ``msgpack_encoding`` is True (default), request payloads are encoded with msgpack
+        binary format instead of JSON.
+        """
+
+        cerebras_api_key = _get_api_key(api_key)
+
+        created_client = False
+        if client is None and (gzip_compression or msgpack_encoding):
+            client = _CerebrasClient(
+                use_msgpack=msgpack_encoding,
+                use_gzip=gzip_compression,
+                api_key=cerebras_api_key,
+                base_url=base_url if is_given(base_url) else None,
+                max_retries=max_retries if is_given(max_retries) else 0,
+                http_client=httpx.AsyncClient(
+                    timeout=timeout
+                    if timeout
+                    else httpx.Timeout(connect=15.0, read=5.0, write=5.0, pool=5.0),
+                    follow_redirects=True,
+                    limits=httpx.Limits(
+                        max_connections=50,
+                        max_keepalive_connections=50,
+                        keepalive_expiry=120,
+                    ),
+                ),
+            )
+            created_client = True
+
+        super().__init__(
+            model=model,
+            api_key=cerebras_api_key,
+            base_url=base_url,
+            client=client,
+            user=user,
+            temperature=temperature,
+            parallel_tool_calls=parallel_tool_calls,
+            tool_choice=tool_choice,
+            reasoning_effort=reasoning_effort,
+            safety_identifier=safety_identifier,
+            prompt_cache_key=prompt_cache_key,
+            top_p=top_p,
+            timeout=timeout,
+            max_retries=max_retries,
+            _strict_tool_schema=False,
+        )
+
+        if created_client:
+            self._owns_client = True
+
+
+def _get_api_key(key: NotGivenOr[str]) -> str:
+    cerebras_api_key = key if is_given(key) else os.environ.get("CEREBRAS_API_KEY")
+    if not cerebras_api_key:
+        raise ValueError(
+            "CEREBRAS_API_KEY is required, either as argument or set "
+            "CEREBRAS_API_KEY environmental variable"
+        )
+    return cerebras_api_key

livekit_plugins_cerebras-1.5.3/livekit/plugins/cerebras/log.py

@@ -0,0 +1,3 @@
+import logging
+
+logger = logging.getLogger("livekit.plugins.cerebras")

livekit_plugins_cerebras-1.5.3/livekit/plugins/cerebras/models.py

@@ -0,0 +1,13 @@
+from typing import Literal
+
+CerebrasChatModels = Literal[
+    "llama3.1-8b",
+    "llama-3.3-70b",
+    "llama-4-scout-17b-16e-instruct",
+    "llama-4-maverick-17b-128e-instruct",
+    "qwen-3-32b",
+    "qwen-3-235b-a22b-instruct-2507",
+    "qwen-3-235b-a22b-thinking-2507",
+    "qwen-3-coder-480b",
+    "gpt-oss-120b",
+]

livekit_plugins_cerebras-1.5.3/livekit/plugins/cerebras/version.py

@@ -0,0 +1,15 @@
+# Copyright 2026 LiveKit, Inc.
+#
+# 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.
+
+__version__ = "1.5.3"

livekit_plugins_cerebras-1.5.3/pyproject.toml

@@ -0,0 +1,46 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "livekit-plugins-cerebras"
+dynamic = ["version"]
+description = "Cerebras inference plugin for LiveKit Agents"
+readme = "README.md"
+license = "Apache-2.0"
+requires-python = ">=3.10.0"
+authors = [{ name = "LiveKit", email = "hello@livekit.io" }]
+keywords = ["voice", "ai", "realtime", "audio", "video", "livekit", "cerebras"]
+classifiers = [
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: Apache Software License",
+    "Topic :: Multimedia :: Sound/Audio",
+    "Topic :: Multimedia :: Video",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3 :: Only",
+]
+dependencies = [
+    "livekit-agents[codecs, openai]>=1.5.3",
+    "msgpack>=1.0",
+    "msgpack-types>=0.7.0",
+]
+
+[project.urls]
+Documentation = "https://docs.livekit.io"
+Website = "https://livekit.io/"
+Source = "https://github.com/livekit/agents"
+
+[tool.hatch.version]
+path = "livekit/plugins/cerebras/version.py"
+
+[tool.hatch.build.targets.wheel]
+packages = ["livekit"]
+
+[tool.hatch.build.targets.sdist]
+include = ["/livekit"]
+
+[tool.uv]
+exclude-newer = "7 days"
+exclude-newer-package = { livekit = "0 days", livekit-agents = "0 days" }