From 39919f78890dfa1765ed45e13462ee0c72ad0a98 Mon Sep 17 00:00:00 2001 From: Arindam200 Date: Sun, 29 Mar 2026 14:35:46 +0530 Subject: [PATCH 1/3] Add NebiusLLMService for Nebius Token Factory Adds an OpenAI-compatible LLM service for Nebius Token Factory, supporting open-source models (Meta Llama, Qwen, DeepSeek) via their OpenAI-compatible REST API at https://api.tokenfactory.nebius.com/v1/. --- README.md | 2 +- pyproject.toml | 1 + src/pipecat/services/nebius/__init__.py | 13 ++++ src/pipecat/services/nebius/llm.py | 97 +++++++++++++++++++++++++ uv.lock | 10 ++- 5 files changed, 120 insertions(+), 3 deletions(-) create mode 100644 src/pipecat/services/nebius/__init__.py create mode 100644 src/pipecat/services/nebius/llm.py diff --git a/README.md b/README.md index 2fa1a45e2..a947f1fbd 100644 --- a/README.md +++ b/README.md @@ -88,7 +88,7 @@ Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.yout | Category | Services | | ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | Speech-to-Text | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Gradium](https://docs.pipecat.ai/server/services/stt/gradium), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [Sarvam](https://docs.pipecat.ai/server/services/stt/sarvam), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper) | -| LLMs | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [Mistral](https://docs.pipecat.ai/server/services/llm/mistral), [Novita](https://docs.pipecat.ai/server/services/llm/novita), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nvidia), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova), [Sarvam](https://docs.pipecat.ai/server/services/llm/sarvam), [Together AI](https://docs.pipecat.ai/server/services/llm/together) | +| LLMs | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [Mistral](https://docs.pipecat.ai/server/services/llm/mistral), [Nebius](https://docs.pipecat.ai/server/services/llm/nebius), [Novita](https://docs.pipecat.ai/server/services/llm/novita), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nvidia), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova), [Sarvam](https://docs.pipecat.ai/server/services/llm/sarvam), [Together AI](https://docs.pipecat.ai/server/services/llm/together) | | Text-to-Speech | [Async](https://docs.pipecat.ai/server/services/tts/asyncai), [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Camb AI](https://docs.pipecat.ai/server/services/tts/camb), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [Gradium](https://docs.pipecat.ai/server/services/tts/gradium), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Hume](https://docs.pipecat.ai/server/services/tts/hume), [Inworld](https://docs.pipecat.ai/server/services/tts/inworld), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [NVIDIA Riva](https://docs.pipecat.ai/server/services/tts/riva), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [Resemble](https://docs.pipecat.ai/server/services/tts/resemble), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [Smallest](https://docs.pipecat.ai/server/services/tts/smallest), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [xAI](https://docs.pipecat.ai/server/services/tts/xai), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) | | Speech-to-Speech | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [Grok Voice Agent](https://docs.pipecat.ai/server/services/s2s/grok), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai), [Ultravox](https://docs.pipecat.ai/server/services/s2s/ultravox), | | Transport | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local | diff --git a/pyproject.toml b/pyproject.toml index f7089ab99..5f08332b4 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -65,6 +65,7 @@ cerebras = [] daily = [ "daily-python~=0.27.0" ] deepgram = [ "deepgram-sdk>=6.1.1,<7", "pipecat-ai[websockets-base]" ] deepseek = [] +nebius = [] elevenlabs = [ "pipecat-ai[websockets-base]" ] fal = [] fireworks = [] diff --git a/src/pipecat/services/nebius/__init__.py b/src/pipecat/services/nebius/__init__.py new file mode 100644 index 000000000..8be606de9 --- /dev/null +++ b/src/pipecat/services/nebius/__init__.py @@ -0,0 +1,13 @@ +# +# Copyright (c) 2024-2026, Daily +# +# SPDX-License-Identifier: BSD 2-Clause License +# + +import sys + +from pipecat.services import DeprecatedModuleProxy + +from .llm import * + +sys.modules[__name__] = DeprecatedModuleProxy(globals(), "nebius", "nebius.llm") diff --git a/src/pipecat/services/nebius/llm.py b/src/pipecat/services/nebius/llm.py new file mode 100644 index 000000000..1efe8df45 --- /dev/null +++ b/src/pipecat/services/nebius/llm.py @@ -0,0 +1,97 @@ +# +# Copyright (c) 2024-2026, Daily +# +# SPDX-License-Identifier: BSD 2-Clause License +# + +"""Nebius Token Factory LLM service implementation using OpenAI-compatible interface.""" + +from dataclasses import dataclass +from typing import Optional + +from loguru import logger + +from pipecat.services.openai.base_llm import BaseOpenAILLMService +from pipecat.services.openai.llm import OpenAILLMService + + +@dataclass +class NebiusLLMSettings(BaseOpenAILLMService.Settings): + """Settings for NebiusLLMService.""" + + pass + + +class NebiusLLMService(OpenAILLMService): + """A service for interacting with Nebius Token Factory's API using the OpenAI-compatible interface. + + This service extends OpenAILLMService to connect to Nebius Token Factory's API endpoint + while maintaining full compatibility with OpenAI's interface and functionality. + + Nebius Token Factory provides access to open-source models including Meta Llama, + Qwen, and DeepSeek variants through an OpenAI-compatible REST API. + + Set the ``NEBIUS_API_KEY`` environment variable or pass ``api_key`` directly. + + Example:: + + service = NebiusLLMService( + api_key="your-nebius-api-key", + settings=NebiusLLMService.Settings( + model="meta-llama/Meta-Llama-3.1-70B-Instruct", + ), + ) + """ + + Settings = NebiusLLMSettings + _settings: Settings + + def __init__( + self, + *, + api_key: str, + base_url: str = "https://api.tokenfactory.nebius.com/v1/", + model: Optional[str] = None, + settings: Optional[Settings] = None, + **kwargs, + ): + """Initialize the Nebius Token Factory LLM service. + + Args: + api_key: The API key for accessing Nebius Token Factory's API. + base_url: The base URL for the Nebius API. Defaults to + ``"https://api.tokenfactory.nebius.com/v1/"``. + model: The model identifier to use. Defaults to + ``"meta-llama/Meta-Llama-3.1-8B-Instruct"``. + + .. deprecated:: 0.0.109 + Use ``settings=NebiusLLMService.Settings(model=...)`` instead. + + settings: Runtime-updatable settings. When provided alongside deprecated + parameters, ``settings`` values take precedence. + **kwargs: Additional keyword arguments passed to OpenAILLMService. + """ + default_settings = self.Settings(model="meta-llama/Meta-Llama-3.1-8B-Instruct") + + if model is not None: + self._warn_init_param_moved_to_settings("model", "model") + default_settings.model = model + + if settings is not None: + default_settings.apply_update(settings) + + super().__init__(api_key=api_key, base_url=base_url, settings=default_settings, **kwargs) + + def create_client(self, api_key=None, base_url=None, **kwargs): + """Create OpenAI-compatible client for Nebius Token Factory API endpoint. + + Args: + api_key: The API key for authentication. If None, uses instance default. + base_url: The base URL for the API. If None, uses instance default. + **kwargs: Additional keyword arguments for client configuration. + + Returns: + An OpenAI-compatible client configured for Nebius Token Factory's API. + """ + logger.debug(f"Creating Nebius client with api {base_url}") + return super().create_client(api_key, base_url, **kwargs) diff --git a/uv.lock b/uv.lock index 94de6927e..735c68b4f 100644 --- a/uv.lock +++ b/uv.lock @@ -1,5 +1,5 @@ version = 1 -revision = 3 +revision = 2 requires-python = ">=3.10" resolution-markers = [ "python_full_version >= '3.14'", @@ -2169,6 +2169,7 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/38/3f/9859f655d11901e7b2996c6e3d33e0caa9a1d4572c3bc61ed0faa64b2f4c/greenlet-3.3.2-cp310-cp310-macosx_11_0_universal2.whl", hash = "sha256:9bc885b89709d901859cf95179ec9f6bb67a3d2bb1f0e88456461bd4b7f8fd0d", size = 277747, upload-time = "2026-02-20T20:16:21.325Z" }, { url = "https://files.pythonhosted.org/packages/fb/07/cb284a8b5c6498dbd7cba35d31380bb123d7dceaa7907f606c8ff5993cbf/greenlet-3.3.2-cp310-cp310-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b568183cf65b94919be4438dc28416b234b678c608cafac8874dfeeb2a9bbe13", size = 579202, upload-time = "2026-02-20T20:47:28.955Z" }, { url = "https://files.pythonhosted.org/packages/ed/45/67922992b3a152f726163b19f890a85129a992f39607a2a53155de3448b8/greenlet-3.3.2-cp310-cp310-manylinux_2_24_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:527fec58dc9f90efd594b9b700662ed3fb2493c2122067ac9c740d98080a620e", size = 590620, upload-time = "2026-02-20T20:55:55.581Z" }, + { url = "https://files.pythonhosted.org/packages/03/5f/6e2a7d80c353587751ef3d44bb947f0565ec008a2e0927821c007e96d3a7/greenlet-3.3.2-cp310-cp310-manylinux_2_24_s390x.manylinux_2_28_s390x.whl", hash = "sha256:508c7f01f1791fbc8e011bd508f6794cb95397fdb198a46cb6635eb5b78d85a7", size = 602132, upload-time = "2026-02-20T21:02:43.261Z" }, { url = "https://files.pythonhosted.org/packages/ad/55/9f1ebb5a825215fadcc0f7d5073f6e79e3007e3282b14b22d6aba7ca6cb8/greenlet-3.3.2-cp310-cp310-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ad0c8917dd42a819fe77e6bdfcb84e3379c0de956469301d9fd36427a1ca501f", size = 591729, upload-time = "2026-02-20T20:20:58.395Z" }, { url = "https://files.pythonhosted.org/packages/24/b4/21f5455773d37f94b866eb3cf5caed88d6cea6dd2c6e1f9c34f463cba3ec/greenlet-3.3.2-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:97245cc10e5515dbc8c3104b2928f7f02b6813002770cfaffaf9a6e0fc2b94ef", size = 1551946, upload-time = "2026-02-20T20:49:31.102Z" }, { url = "https://files.pythonhosted.org/packages/00/68/91f061a926abead128fe1a87f0b453ccf07368666bd59ffa46016627a930/greenlet-3.3.2-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:8c1fdd7d1b309ff0da81d60a9688a8bd044ac4e18b250320a96fc68d31c209ca", size = 1618494, upload-time = "2026-02-20T20:21:06.541Z" }, @@ -2176,6 +2177,7 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/f3/47/16400cb42d18d7a6bb46f0626852c1718612e35dcb0dffa16bbaffdf5dd2/greenlet-3.3.2-cp311-cp311-macosx_11_0_universal2.whl", hash = "sha256:c56692189a7d1c7606cb794be0a8381470d95c57ce5be03fb3d0ef57c7853b86", size = 278890, upload-time = "2026-02-20T20:19:39.263Z" }, { url = "https://files.pythonhosted.org/packages/a3/90/42762b77a5b6aa96cd8c0e80612663d39211e8ae8a6cd47c7f1249a66262/greenlet-3.3.2-cp311-cp311-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1ebd458fa8285960f382841da585e02201b53a5ec2bac6b156fc623b5ce4499f", size = 581120, upload-time = "2026-02-20T20:47:30.161Z" }, { url = "https://files.pythonhosted.org/packages/bf/6f/f3d64f4fa0a9c7b5c5b3c810ff1df614540d5aa7d519261b53fba55d4df9/greenlet-3.3.2-cp311-cp311-manylinux_2_24_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:a443358b33c4ec7b05b79a7c8b466f5d275025e750298be7340f8fc63dff2a55", size = 594363, upload-time = "2026-02-20T20:55:56.965Z" }, + { url = "https://files.pythonhosted.org/packages/9c/8b/1430a04657735a3f23116c2e0d5eb10220928846e4537a938a41b350bed6/greenlet-3.3.2-cp311-cp311-manylinux_2_24_s390x.manylinux_2_28_s390x.whl", hash = "sha256:4375a58e49522698d3e70cc0b801c19433021b5c37686f7ce9c65b0d5c8677d2", size = 605046, upload-time = "2026-02-20T21:02:45.234Z" }, { url = "https://files.pythonhosted.org/packages/72/83/3e06a52aca8128bdd4dcd67e932b809e76a96ab8c232a8b025b2850264c5/greenlet-3.3.2-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:8e2cd90d413acbf5e77ae41e5d3c9b3ac1d011a756d7284d7f3f2b806bbd6358", size = 594156, upload-time = "2026-02-20T20:20:59.955Z" }, { url = "https://files.pythonhosted.org/packages/70/79/0de5e62b873e08fe3cef7dbe84e5c4bc0e8ed0c7ff131bccb8405cd107c8/greenlet-3.3.2-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:442b6057453c8cb29b4fb36a2ac689382fc71112273726e2423f7f17dc73bf99", size = 1554649, upload-time = "2026-02-20T20:49:32.293Z" }, { url = "https://files.pythonhosted.org/packages/5a/00/32d30dee8389dc36d42170a9c66217757289e2afb0de59a3565260f38373/greenlet-3.3.2-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:45abe8eb6339518180d5a7fa47fa01945414d7cca5ecb745346fc6a87d2750be", size = 1619472, upload-time = "2026-02-20T20:21:07.966Z" }, @@ -2184,6 +2186,7 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/ea/ab/1608e5a7578e62113506740b88066bf09888322a311cff602105e619bd87/greenlet-3.3.2-cp312-cp312-macosx_11_0_universal2.whl", hash = "sha256:ac8d61d4343b799d1e526db579833d72f23759c71e07181c2d2944e429eb09cd", size = 280358, upload-time = "2026-02-20T20:17:43.971Z" }, { url = "https://files.pythonhosted.org/packages/a5/23/0eae412a4ade4e6623ff7626e38998cb9b11e9ff1ebacaa021e4e108ec15/greenlet-3.3.2-cp312-cp312-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:3ceec72030dae6ac0c8ed7591b96b70410a8be370b6a477b1dbc072856ad02bd", size = 601217, upload-time = "2026-02-20T20:47:31.462Z" }, { url = "https://files.pythonhosted.org/packages/f8/16/5b1678a9c07098ecb9ab2dd159fafaf12e963293e61ee8d10ecb55273e5e/greenlet-3.3.2-cp312-cp312-manylinux_2_24_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:a2a5be83a45ce6188c045bcc44b0ee037d6a518978de9a5d97438548b953a1ac", size = 611792, upload-time = "2026-02-20T20:55:58.423Z" }, + { url = "https://files.pythonhosted.org/packages/5c/c5/cc09412a29e43406eba18d61c70baa936e299bc27e074e2be3806ed29098/greenlet-3.3.2-cp312-cp312-manylinux_2_24_s390x.manylinux_2_28_s390x.whl", hash = "sha256:ae9e21c84035c490506c17002f5c8ab25f980205c3e61ddb3a2a2a2e6c411fcb", size = 626250, upload-time = "2026-02-20T21:02:46.596Z" }, { url = "https://files.pythonhosted.org/packages/50/1f/5155f55bd71cabd03765a4aac9ac446be129895271f73872c36ebd4b04b6/greenlet-3.3.2-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:43e99d1749147ac21dde49b99c9abffcbc1e2d55c67501465ef0930d6e78e070", size = 613875, upload-time = "2026-02-20T20:21:01.102Z" }, { url = "https://files.pythonhosted.org/packages/fc/dd/845f249c3fcd69e32df80cdab059b4be8b766ef5830a3d0aa9d6cad55beb/greenlet-3.3.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:4c956a19350e2c37f2c48b336a3afb4bff120b36076d9d7fb68cb44e05d95b79", size = 1571467, upload-time = "2026-02-20T20:49:33.495Z" }, { url = "https://files.pythonhosted.org/packages/2a/50/2649fe21fcc2b56659a452868e695634722a6655ba245d9f77f5656010bf/greenlet-3.3.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:6c6f8ba97d17a1e7d664151284cb3315fc5f8353e75221ed4324f84eb162b395", size = 1640001, upload-time = "2026-02-20T20:21:09.154Z" }, @@ -2192,6 +2195,7 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/ac/48/f8b875fa7dea7dd9b33245e37f065af59df6a25af2f9561efa8d822fde51/greenlet-3.3.2-cp313-cp313-macosx_11_0_universal2.whl", hash = "sha256:aa6ac98bdfd716a749b84d4034486863fd81c3abde9aa3cf8eff9127981a4ae4", size = 279120, upload-time = "2026-02-20T20:19:01.9Z" }, { url = "https://files.pythonhosted.org/packages/49/8d/9771d03e7a8b1ee456511961e1b97a6d77ae1dea4a34a5b98eee706689d3/greenlet-3.3.2-cp313-cp313-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ab0c7e7901a00bc0a7284907273dc165b32e0d109a6713babd04471327ff7986", size = 603238, upload-time = "2026-02-20T20:47:32.873Z" }, { url = "https://files.pythonhosted.org/packages/59/0e/4223c2bbb63cd5c97f28ffb2a8aee71bdfb30b323c35d409450f51b91e3e/greenlet-3.3.2-cp313-cp313-manylinux_2_24_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:d248d8c23c67d2291ffd47af766e2a3aa9fa1c6703155c099feb11f526c63a92", size = 614219, upload-time = "2026-02-20T20:55:59.817Z" }, + { url = "https://files.pythonhosted.org/packages/94/2b/4d012a69759ac9d77210b8bfb128bc621125f5b20fc398bce3940d036b1c/greenlet-3.3.2-cp313-cp313-manylinux_2_24_s390x.manylinux_2_28_s390x.whl", hash = "sha256:ccd21bb86944ca9be6d967cf7691e658e43417782bce90b5d2faeda0ff78a7dd", size = 628268, upload-time = "2026-02-20T21:02:48.024Z" }, { url = "https://files.pythonhosted.org/packages/7a/34/259b28ea7a2a0c904b11cd36c79b8cef8019b26ee5dbe24e73b469dea347/greenlet-3.3.2-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:b6997d360a4e6a4e936c0f9625b1c20416b8a0ea18a8e19cabbefc712e7397ab", size = 616774, upload-time = "2026-02-20T20:21:02.454Z" }, { url = "https://files.pythonhosted.org/packages/0a/03/996c2d1689d486a6e199cb0f1cf9e4aa940c500e01bdf201299d7d61fa69/greenlet-3.3.2-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:64970c33a50551c7c50491671265d8954046cb6e8e2999aacdd60e439b70418a", size = 1571277, upload-time = "2026-02-20T20:49:34.795Z" }, { url = "https://files.pythonhosted.org/packages/d9/c4/2570fc07f34a39f2caf0bf9f24b0a1a0a47bc2e8e465b2c2424821389dfc/greenlet-3.3.2-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:1a9172f5bf6bd88e6ba5a84e0a68afeac9dc7b6b412b245dd64f52d83c81e55b", size = 1640455, upload-time = "2026-02-20T20:21:10.261Z" }, @@ -2200,6 +2204,7 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/3f/ae/8bffcbd373b57a5992cd077cbe8858fff39110480a9d50697091faea6f39/greenlet-3.3.2-cp314-cp314-macosx_11_0_universal2.whl", hash = "sha256:8d1658d7291f9859beed69a776c10822a0a799bc4bfe1bd4272bb60e62507dab", size = 279650, upload-time = "2026-02-20T20:18:00.783Z" }, { url = "https://files.pythonhosted.org/packages/d1/c0/45f93f348fa49abf32ac8439938726c480bd96b2a3c6f4d949ec0124b69f/greenlet-3.3.2-cp314-cp314-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:18cb1b7337bca281915b3c5d5ae19f4e76d35e1df80f4ad3c1a7be91fadf1082", size = 650295, upload-time = "2026-02-20T20:47:34.036Z" }, { url = "https://files.pythonhosted.org/packages/b3/de/dd7589b3f2b8372069ab3e4763ea5329940fc7ad9dcd3e272a37516d7c9b/greenlet-3.3.2-cp314-cp314-manylinux_2_24_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:c2e47408e8ce1c6f1ceea0dffcdf6ebb85cc09e55c7af407c99f1112016e45e9", size = 662163, upload-time = "2026-02-20T20:56:01.295Z" }, + { url = "https://files.pythonhosted.org/packages/cd/ac/85804f74f1ccea31ba518dcc8ee6f14c79f73fe36fa1beba38930806df09/greenlet-3.3.2-cp314-cp314-manylinux_2_24_s390x.manylinux_2_28_s390x.whl", hash = "sha256:e3cb43ce200f59483eb82949bf1835a99cf43d7571e900d7c8d5c62cdf25d2f9", size = 675371, upload-time = "2026-02-20T21:02:49.664Z" }, { url = "https://files.pythonhosted.org/packages/d2/d8/09bfa816572a4d83bccd6750df1926f79158b1c36c5f73786e26dbe4ee38/greenlet-3.3.2-cp314-cp314-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:63d10328839d1973e5ba35e98cccbca71b232b14051fd957b6f8b6e8e80d0506", size = 664160, upload-time = "2026-02-20T20:21:04.015Z" }, { url = "https://files.pythonhosted.org/packages/48/cf/56832f0c8255d27f6c35d41b5ec91168d74ec721d85f01a12131eec6b93c/greenlet-3.3.2-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:8e4ab3cfb02993c8cc248ea73d7dae6cec0253e9afa311c9b37e603ca9fad2ce", size = 1619181, upload-time = "2026-02-20T20:49:36.052Z" }, { url = "https://files.pythonhosted.org/packages/0a/23/b90b60a4aabb4cec0796e55f25ffbfb579a907c3898cd2905c8918acaa16/greenlet-3.3.2-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:94ad81f0fd3c0c0681a018a976e5c2bd2ca2d9d94895f23e7bb1af4e8af4e2d5", size = 1687713, upload-time = "2026-02-20T20:21:11.684Z" }, @@ -2208,6 +2213,7 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/98/6d/8f2ef704e614bcf58ed43cfb8d87afa1c285e98194ab2cfad351bf04f81e/greenlet-3.3.2-cp314-cp314t-macosx_11_0_universal2.whl", hash = "sha256:e26e72bec7ab387ac80caa7496e0f908ff954f31065b0ffc1f8ecb1338b11b54", size = 286617, upload-time = "2026-02-20T20:19:29.856Z" }, { url = "https://files.pythonhosted.org/packages/5e/0d/93894161d307c6ea237a43988f27eba0947b360b99ac5239ad3fe09f0b47/greenlet-3.3.2-cp314-cp314t-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:8b466dff7a4ffda6ca975979bab80bdadde979e29fc947ac3be4451428d8b0e4", size = 655189, upload-time = "2026-02-20T20:47:35.742Z" }, { url = "https://files.pythonhosted.org/packages/f5/2c/d2d506ebd8abcb57386ec4f7ba20f4030cbe56eae541bc6fd6ef399c0b41/greenlet-3.3.2-cp314-cp314t-manylinux_2_24_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:b8bddc5b73c9720bea487b3bffdb1840fe4e3656fba3bd40aa1489e9f37877ff", size = 658225, upload-time = "2026-02-20T20:56:02.527Z" }, + { url = "https://files.pythonhosted.org/packages/d1/67/8197b7e7e602150938049d8e7f30de1660cfb87e4c8ee349b42b67bdb2e1/greenlet-3.3.2-cp314-cp314t-manylinux_2_24_s390x.manylinux_2_28_s390x.whl", hash = "sha256:59b3e2c40f6706b05a9cd299c836c6aa2378cabe25d021acd80f13abf81181cf", size = 666581, upload-time = "2026-02-20T21:02:51.526Z" }, { url = "https://files.pythonhosted.org/packages/8e/30/3a09155fbf728673a1dea713572d2d31159f824a37c22da82127056c44e4/greenlet-3.3.2-cp314-cp314t-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:b26b0f4428b871a751968285a1ac9648944cea09807177ac639b030bddebcea4", size = 657907, upload-time = "2026-02-20T20:21:05.259Z" }, { url = "https://files.pythonhosted.org/packages/f3/fd/d05a4b7acd0154ed758797f0a43b4c0962a843bedfe980115e842c5b2d08/greenlet-3.3.2-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:1fb39a11ee2e4d94be9a76671482be9398560955c9e568550de0224e41104727", size = 1618857, upload-time = "2026-02-20T20:49:37.309Z" }, { url = "https://files.pythonhosted.org/packages/6f/e1/50ee92a5db521de8f35075b5eff060dd43d39ebd46c2181a2042f7070385/greenlet-3.3.2-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:20154044d9085151bc309e7689d6f7ba10027f8f5a8c0676ad398b951913d89e", size = 1680010, upload-time = "2026-02-20T20:21:13.427Z" }, @@ -4990,7 +4996,7 @@ requires-dist = [ { name = "wait-for2", marker = "python_full_version < '3.12'", specifier = ">=0.4.1,<1" }, { name = "websockets", marker = "extra == 'websockets-base'", specifier = ">=13.1,<16.0" }, ] -provides-extras = ["aic", "anthropic", "assemblyai", "asyncai", "aws", "aws-nova-sonic", "azure", "cartesia", "camb", "cerebras", "daily", "deepgram", "deepseek", "elevenlabs", "fal", "fireworks", "fish", "gladia", "google", "gradium", "grok", "groq", "gstreamer", "heygen", "hume", "inworld", "koala", "kokoro", "krisp", "langchain", "lemonslice", "livekit", "lmnt", "local", "local-smart-turn", "mcp", "mem0", "mistral", "mlx-whisper", "moondream", "neuphonic", "noisereduce", "novita", "nvidia", "openai", "rnnoise", "openpipe", "openrouter", "perplexity", "piper", "qwen", "remote-smart-turn", "resembleai", "rime", "riva", "runner", "sagemaker", "sambanova", "sarvam", "sentry", "silero", "simli", "smallest", "soniox", "soundfile", "speechmatics", "strands", "tavus", "together", "tracing", "ultravox", "webrtc", "websocket", "websockets-base", "whisper", "xai"] +provides-extras = ["aic", "anthropic", "assemblyai", "asyncai", "aws", "aws-nova-sonic", "azure", "cartesia", "camb", "cerebras", "daily", "deepgram", "deepseek", "nebius", "elevenlabs", "fal", "fireworks", "fish", "gladia", "google", "gradium", "grok", "groq", "gstreamer", "heygen", "hume", "inworld", "koala", "kokoro", "krisp", "langchain", "lemonslice", "livekit", "lmnt", "local", "local-smart-turn", "mcp", "mem0", "mistral", "mlx-whisper", "moondream", "neuphonic", "noisereduce", "novita", "nvidia", "openai", "rnnoise", "openpipe", "openrouter", "perplexity", "piper", "qwen", "remote-smart-turn", "resembleai", "rime", "riva", "runner", "sagemaker", "sambanova", "sarvam", "sentry", "silero", "simli", "smallest", "soniox", "soundfile", "speechmatics", "strands", "tavus", "together", "tracing", "ultravox", "webrtc", "websocket", "websockets-base", "whisper", "xai"] [package.metadata.requires-dev] dev = [ From 63254fe337986ae9060fa33db2007eaeec7fb1aa Mon Sep 17 00:00:00 2001 From: Mark Backman Date: Sun, 29 Mar 2026 08:50:01 -0400 Subject: [PATCH 2/3] Add NebiusLLMService with developer role and tool support fixes - Add Nebius LLM service wrapping OpenAI-compatible Token Factory API - Set supports_developer_role = False (Nebius rejects developer role) - Default to openai/gpt-oss-120b model (supports function calling) - Add Nebius function-calling example and env.example entry - Fix Sarvam developer role support - Update examples to use developer role for intro messages --- env.example | 3 + .../07z-interruptible-sarvam-http.py | 2 +- .../foundational/07z-interruptible-sarvam.py | 4 +- examples/foundational/14-function-calling.py | 3 + ...enai.py => 14b-function-calling-openai.py} | 0 .../14c-function-calling-together.py | 3 + .../14v-function-calling-nebius.py | 175 ++++++++++++++++++ .../14y-function-calling-sarvam.py | 4 +- scripts/evals/run-release-evals.py | 7 +- src/pipecat/services/nebius/__init__.py | 13 -- src/pipecat/services/nebius/llm.py | 51 ++--- src/pipecat/services/sarvam/llm.py | 4 + 12 files changed, 216 insertions(+), 53 deletions(-) rename examples/foundational/{14v-function-calling-openai.py => 14b-function-calling-openai.py} (100%) create mode 100644 examples/foundational/14v-function-calling-nebius.py diff --git a/env.example b/env.example index 3723fbf26..183fd23ba 100644 --- a/env.example +++ b/env.example @@ -121,6 +121,9 @@ MINIMAX_GROUP_ID=... # Mistral MISTRAL_API_KEY=... +# Nebius +NEBIUS_API_KEY=... + # Neuphonic NEUPHONIC_API_KEY=... diff --git a/examples/foundational/07z-interruptible-sarvam-http.py b/examples/foundational/07z-interruptible-sarvam-http.py index 09938cf96..bca27e051 100644 --- a/examples/foundational/07z-interruptible-sarvam-http.py +++ b/examples/foundational/07z-interruptible-sarvam-http.py @@ -111,7 +111,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): logger.info(f"Client connected") # Kick off the conversation. context.add_message( - {"role": "user", "content": "Please introduce yourself to the user."} + {"role": "developer", "content": "Please introduce yourself to the user."} ) await task.queue_frames([LLMRunFrame()]) diff --git a/examples/foundational/07z-interruptible-sarvam.py b/examples/foundational/07z-interruptible-sarvam.py index 031b82116..bd007d89e 100644 --- a/examples/foundational/07z-interruptible-sarvam.py +++ b/examples/foundational/07z-interruptible-sarvam.py @@ -104,7 +104,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): async def on_client_connected(transport, client): logger.info(f"Client connected") # Kick off the conversation. - context.add_message({"role": "user", "content": "Please introduce yourself to the user."}) + context.add_message( + {"role": "developer", "content": "Please introduce yourself to the user."} + ) await task.queue_frames([LLMRunFrame()]) # Optionally, you can wait for 30 seconds and then change the voice. diff --git a/examples/foundational/14-function-calling.py b/examples/foundational/14-function-calling.py index 5001d5dad..085937da9 100644 --- a/examples/foundational/14-function-calling.py +++ b/examples/foundational/14-function-calling.py @@ -148,6 +148,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): async def on_client_connected(transport, client): logger.info(f"Client connected") # Kick off the conversation. + context.add_message( + {"role": "developer", "content": "Please introduce yourself to the user."} + ) await task.queue_frames([LLMRunFrame()]) @transport.event_handler("on_client_disconnected") diff --git a/examples/foundational/14v-function-calling-openai.py b/examples/foundational/14b-function-calling-openai.py similarity index 100% rename from examples/foundational/14v-function-calling-openai.py rename to examples/foundational/14b-function-calling-openai.py diff --git a/examples/foundational/14c-function-calling-together.py b/examples/foundational/14c-function-calling-together.py index 927c30bbd..78da7fbe9 100644 --- a/examples/foundational/14c-function-calling-together.py +++ b/examples/foundational/14c-function-calling-together.py @@ -131,6 +131,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): async def on_client_connected(transport, client): logger.info(f"Client connected") # Kick off the conversation. + context.add_message( + {"role": "developer", "content": "Please introduce yourself to the user."} + ) await task.queue_frames([LLMRunFrame()]) @transport.event_handler("on_client_disconnected") diff --git a/examples/foundational/14v-function-calling-nebius.py b/examples/foundational/14v-function-calling-nebius.py new file mode 100644 index 000000000..4fe9a378a --- /dev/null +++ b/examples/foundational/14v-function-calling-nebius.py @@ -0,0 +1,175 @@ +# +# Copyright (c) 2024-2026, Daily +# +# SPDX-License-Identifier: BSD 2-Clause License +# + +import os + +from dotenv import load_dotenv +from loguru import logger + +from pipecat.adapters.schemas.function_schema import FunctionSchema +from pipecat.adapters.schemas.tools_schema import ToolsSchema +from pipecat.audio.vad.silero import SileroVADAnalyzer +from pipecat.frames.frames import LLMRunFrame, TTSSpeakFrame +from pipecat.pipeline.pipeline import Pipeline +from pipecat.pipeline.runner import PipelineRunner +from pipecat.pipeline.task import PipelineParams, PipelineTask +from pipecat.processors.aggregators.llm_context import LLMContext +from pipecat.processors.aggregators.llm_response_universal import ( + LLMContextAggregatorPair, + LLMUserAggregatorParams, +) +from pipecat.runner.types import RunnerArguments +from pipecat.runner.utils import create_transport +from pipecat.services.cartesia.tts import CartesiaTTSService +from pipecat.services.deepgram.stt import DeepgramSTTService +from pipecat.services.llm_service import FunctionCallParams +from pipecat.services.nebius.llm import NebiusLLMService +from pipecat.transports.base_transport import BaseTransport, TransportParams +from pipecat.transports.daily.transport import DailyParams +from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams + +load_dotenv(override=True) + + +async def fetch_weather_from_api(params: FunctionCallParams): + await params.result_callback({"conditions": "nice", "temperature": "75"}) + + +async def fetch_restaurant_recommendation(params: FunctionCallParams): + await params.result_callback({"name": "The Golden Dragon"}) + + +# We use lambdas to defer transport parameter creation until the transport +# type is selected at runtime. +transport_params = { + "daily": lambda: DailyParams( + audio_in_enabled=True, + audio_out_enabled=True, + ), + "twilio": lambda: FastAPIWebsocketParams( + audio_in_enabled=True, + audio_out_enabled=True, + ), + "webrtc": lambda: TransportParams( + audio_in_enabled=True, + audio_out_enabled=True, + ), +} + + +async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): + logger.info(f"Starting bot") + + stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY")) + + tts = CartesiaTTSService( + api_key=os.getenv("CARTESIA_API_KEY"), + settings=CartesiaTTSService.Settings( + voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady + ), + ) + + llm = NebiusLLMService( + api_key=os.getenv("NEBIUS_API_KEY"), + settings=NebiusLLMService.Settings( + system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.", + ), + ) + + # You can also register a function_name of None to get all functions + # sent to the same callback with an additional function_name parameter. + llm.register_function("get_current_weather", fetch_weather_from_api) + llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation) + + @llm.event_handler("on_function_calls_started") + async def on_function_calls_started(service, function_calls): + await tts.queue_frame(TTSSpeakFrame("Let me check on that.")) + + weather_function = FunctionSchema( + name="get_current_weather", + description="Get the current weather", + properties={ + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA", + }, + "format": { + "type": "string", + "enum": ["celsius", "fahrenheit"], + "description": "The temperature unit to use. Infer this from the user's location.", + }, + }, + required=["location", "format"], + ) + restaurant_function = FunctionSchema( + name="get_restaurant_recommendation", + description="Get a restaurant recommendation", + properties={ + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA", + }, + }, + required=["location"], + ) + tools = ToolsSchema(standard_tools=[weather_function, restaurant_function]) + + context = LLMContext(tools=tools) + user_aggregator, assistant_aggregator = LLMContextAggregatorPair( + context, + user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()), + ) + + pipeline = Pipeline( + [ + transport.input(), + stt, + user_aggregator, + llm, + tts, + transport.output(), + assistant_aggregator, + ] + ) + + task = PipelineTask( + pipeline, + params=PipelineParams( + enable_metrics=True, + enable_usage_metrics=True, + ), + idle_timeout_secs=runner_args.pipeline_idle_timeout_secs, + ) + + @transport.event_handler("on_client_connected") + async def on_client_connected(transport, client): + logger.info(f"Client connected") + # Kick off the conversation. + context.add_message( + {"role": "developer", "content": "Please introduce yourself to the user."} + ) + await task.queue_frames([LLMRunFrame()]) + + @transport.event_handler("on_client_disconnected") + async def on_client_disconnected(transport, client): + logger.info(f"Client disconnected") + await task.cancel() + + runner = PipelineRunner(handle_sigint=runner_args.handle_sigint) + + await runner.run(task) + + +async def bot(runner_args: RunnerArguments): + """Main bot entry point compatible with Pipecat Cloud.""" + transport = await create_transport(runner_args, transport_params) + await run_bot(transport, runner_args) + + +if __name__ == "__main__": + from pipecat.runner.run import main + + main() diff --git a/examples/foundational/14y-function-calling-sarvam.py b/examples/foundational/14y-function-calling-sarvam.py index fece01a3a..bd3fa42fb 100644 --- a/examples/foundational/14y-function-calling-sarvam.py +++ b/examples/foundational/14y-function-calling-sarvam.py @@ -153,7 +153,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): async def on_client_connected(transport, client): logger.info(f"Client connected") # Kick off the conversation. - context.add_message({"role": "user", "content": "Please introduce yourself to the user."}) + context.add_message( + {"role": "developer", "content": "Please introduce yourself to the user."} + ) await task.queue_frames([LLMRunFrame()]) @transport.event_handler("on_client_disconnected") diff --git a/scripts/evals/run-release-evals.py b/scripts/evals/run-release-evals.py index 9632b5eae..c51409b7c 100644 --- a/scripts/evals/run-release-evals.py +++ b/scripts/evals/run-release-evals.py @@ -169,8 +169,11 @@ TESTS_12 = [ TESTS_14 = [ ("14-function-calling.py", EVAL_WEATHER), ("14-function-calling.py", EVAL_WEATHER_AND_RESTAURANT), + ("14-function-calling-openai-responses.py", EVAL_WEATHER), + ("14-function-calling-openai-responses.py", EVAL_WEATHER_AND_RESTAURANT), ("14a-function-calling-anthropic.py", EVAL_WEATHER), ("14a-function-calling-anthropic.py", EVAL_WEATHER_AND_RESTAURANT), + ("14b-function-calling-openai.py", EVAL_WEATHER), ("14e-function-calling-google.py", EVAL_WEATHER), ("14e-function-calling-google.py", EVAL_WEATHER_AND_RESTAURANT), ("14f-function-calling-groq.py", EVAL_WEATHER), @@ -186,13 +189,11 @@ TESTS_14 = [ ("14r-function-calling-aws.py", EVAL_WEATHER), ("14s-function-calling-sambanova.py", EVAL_WEATHER), ("14r-function-calling-aws.py", EVAL_WEATHER_AND_RESTAURANT), - ("14v-function-calling-openai.py", EVAL_WEATHER), + ("14v-function-calling-nebius.py", EVAL_WEATHER), ("14w-function-calling-mistral.py", EVAL_WEATHER), ("14x-function-calling-openpipe.py", EVAL_WEATHER), ("14y-function-calling-sarvam.py", EVAL_WEATHER), ("14z-function-calling-novita.py", EVAL_WEATHER), - ("14-function-calling-openai-responses.py", EVAL_WEATHER), - ("14-function-calling-openai-responses.py", EVAL_WEATHER_AND_RESTAURANT), # Video ("14d-function-calling-anthropic-video.py", EVAL_VISION_CAMERA), ("14d-function-calling-aws-video.py", EVAL_VISION_CAMERA), diff --git a/src/pipecat/services/nebius/__init__.py b/src/pipecat/services/nebius/__init__.py index 8be606de9..e69de29bb 100644 --- a/src/pipecat/services/nebius/__init__.py +++ b/src/pipecat/services/nebius/__init__.py @@ -1,13 +0,0 @@ -# -# Copyright (c) 2024-2026, Daily -# -# SPDX-License-Identifier: BSD 2-Clause License -# - -import sys - -from pipecat.services import DeprecatedModuleProxy - -from .llm import * - -sys.modules[__name__] = DeprecatedModuleProxy(globals(), "nebius", "nebius.llm") diff --git a/src/pipecat/services/nebius/llm.py b/src/pipecat/services/nebius/llm.py index 1efe8df45..aa26e776f 100644 --- a/src/pipecat/services/nebius/llm.py +++ b/src/pipecat/services/nebius/llm.py @@ -4,7 +4,7 @@ # SPDX-License-Identifier: BSD 2-Clause License # -"""Nebius Token Factory LLM service implementation using OpenAI-compatible interface.""" +"""Nebius LLM service implementation using OpenAI-compatible interface.""" from dataclasses import dataclass from typing import Optional @@ -23,26 +23,16 @@ class NebiusLLMSettings(BaseOpenAILLMService.Settings): class NebiusLLMService(OpenAILLMService): - """A service for interacting with Nebius Token Factory's API using the OpenAI-compatible interface. + """A service for interacting with Nebius's API using the OpenAI-compatible interface. - This service extends OpenAILLMService to connect to Nebius Token Factory's API endpoint - while maintaining full compatibility with OpenAI's interface and functionality. - - Nebius Token Factory provides access to open-source models including Meta Llama, - Qwen, and DeepSeek variants through an OpenAI-compatible REST API. - - Set the ``NEBIUS_API_KEY`` environment variable or pass ``api_key`` directly. - - Example:: - - service = NebiusLLMService( - api_key="your-nebius-api-key", - settings=NebiusLLMService.Settings( - model="meta-llama/Meta-Llama-3.1-70B-Instruct", - ), - ) + This service extends OpenAILLMService to connect to Nebius's API endpoint while + maintaining full compatibility with OpenAI's interface and functionality. """ + # Nebius doesn't support the "developer" message role. + # This value is used by BaseOpenAILLMService when calling the adapter. + supports_developer_role = False + Settings = NebiusLLMSettings _settings: Settings @@ -51,39 +41,32 @@ class NebiusLLMService(OpenAILLMService): *, api_key: str, base_url: str = "https://api.tokenfactory.nebius.com/v1/", - model: Optional[str] = None, settings: Optional[Settings] = None, **kwargs, ): - """Initialize the Nebius Token Factory LLM service. + """Initialize the Nebius LLM service. Args: - api_key: The API key for accessing Nebius Token Factory's API. + api_key: The API key for accessing Nebius's API. base_url: The base URL for the Nebius API. Defaults to ``"https://api.tokenfactory.nebius.com/v1/"``. - model: The model identifier to use. Defaults to - ``"meta-llama/Meta-Llama-3.1-8B-Instruct"``. - - .. deprecated:: 0.0.109 - Use ``settings=NebiusLLMService.Settings(model=...)`` instead. - settings: Runtime-updatable settings. When provided alongside deprecated parameters, ``settings`` values take precedence. **kwargs: Additional keyword arguments passed to OpenAILLMService. """ - default_settings = self.Settings(model="meta-llama/Meta-Llama-3.1-8B-Instruct") - - if model is not None: - self._warn_init_param_moved_to_settings("model", "model") - default_settings.model = model + # Initialize default_settings with hardcoded defaults + default_settings = self.Settings( + model="openai/gpt-oss-120b", + ) + # Apply settings delta (canonical API, always wins) if settings is not None: default_settings.apply_update(settings) super().__init__(api_key=api_key, base_url=base_url, settings=default_settings, **kwargs) def create_client(self, api_key=None, base_url=None, **kwargs): - """Create OpenAI-compatible client for Nebius Token Factory API endpoint. + """Create OpenAI-compatible client for Nebius API endpoint. Args: api_key: The API key for authentication. If None, uses instance default. @@ -91,7 +74,7 @@ class NebiusLLMService(OpenAILLMService): **kwargs: Additional keyword arguments for client configuration. Returns: - An OpenAI-compatible client configured for Nebius Token Factory's API. + An OpenAI-compatible client configured for Nebius's API. """ logger.debug(f"Creating Nebius client with api {base_url}") return super().create_client(api_key, base_url, **kwargs) diff --git a/src/pipecat/services/sarvam/llm.py b/src/pipecat/services/sarvam/llm.py index c1fc6990e..ce353ff2b 100644 --- a/src/pipecat/services/sarvam/llm.py +++ b/src/pipecat/services/sarvam/llm.py @@ -42,6 +42,10 @@ class SarvamLLMService(OpenAILLMService): maintaining full compatibility with OpenAI's interface and functionality. """ + # Sarvam doesn't support the "developer" message role. + # This value is used by BaseOpenAILLMService when calling the adapter. + supports_developer_role = False + _SUPPORTED_MODELS = frozenset( {"sarvam-30b", "sarvam-30b-16k", "sarvam-105b", "sarvam-105b-32k"} ) From a3aeafcb2dc2c4172a3c81fa661e443f735ea982 Mon Sep 17 00:00:00 2001 From: Mark Backman Date: Sun, 29 Mar 2026 08:55:52 -0400 Subject: [PATCH 3/3] Alphabetize nebius entry in pyproject.toml extras --- pyproject.toml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pyproject.toml b/pyproject.toml index 5f08332b4..4893e48f5 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -65,7 +65,6 @@ cerebras = [] daily = [ "daily-python~=0.27.0" ] deepgram = [ "deepgram-sdk>=6.1.1,<7", "pipecat-ai[websockets-base]" ] deepseek = [] -nebius = [] elevenlabs = [ "pipecat-ai[websockets-base]" ] fal = [] fireworks = [] @@ -93,6 +92,7 @@ mem0 = [ "mem0ai>=1.0.8,<2" ] mistral = [] mlx-whisper = [ "mlx-whisper~=0.4.2" ] moondream = [ "accelerate~=1.10.0", "einops~=0.8.0", "pyvips[binary]~=3.0.0", "timm~=1.0.13", "transformers>=4.48.0,<6" ] +nebius = [] neuphonic = [ "pipecat-ai[websockets-base]" ] noisereduce = [ "noisereduce~=3.0.3" ] novita = []