diff --git a/README.md b/README.md index 1afc7f7a0..f00234cbc 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), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [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), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [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) [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), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [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), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [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 | @@ -98,7 +98,7 @@ Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.yout | Vision & Image | [fal](https://docs.pipecat.ai/server/services/image-generation/fal), [Google Imagen](https://docs.pipecat.ai/server/services/image-generation/google-imagen), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream) | | Audio Processing | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [ai-coustics](https://docs.pipecat.ai/server/utilities/audio/aic-filter) | | Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry) | -| Community | [Browse community integrations →](https://docs.pipecat.ai/server/services/community-integrations) | +| Community | [Browse community integrations →](https://docs.pipecat.ai/server/services/community-integrations) | 📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services) diff --git a/changelog/3978.added.md b/changelog/3978.added.md new file mode 100644 index 000000000..bb80b10c0 --- /dev/null +++ b/changelog/3978.added.md @@ -0,0 +1 @@ +- Added `SarvamLLMService` with support for `sarvam-30b`, `sarvam-30b-16k`, `sarvam-105b` and `sarvam-105b-32k` diff --git a/examples/foundational/07z-interruptible-sarvam-http.py b/examples/foundational/07z-interruptible-sarvam-http.py index f8a806493..09938cf96 100644 --- a/examples/foundational/07z-interruptible-sarvam-http.py +++ b/examples/foundational/07z-interruptible-sarvam-http.py @@ -23,7 +23,7 @@ from pipecat.processors.aggregators.llm_response_universal import ( ) from pipecat.runner.types import RunnerArguments from pipecat.runner.utils import create_transport -from pipecat.services.openai.llm import OpenAILLMService +from pipecat.services.sarvam.llm import SarvamLLMService from pipecat.services.sarvam.stt import SarvamSTTService from pipecat.services.sarvam.tts import SarvamHttpTTSService from pipecat.transcriptions.language import Language @@ -72,9 +72,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): ), ) - llm = OpenAILLMService( - api_key=os.getenv("OPENAI_API_KEY"), - settings=OpenAILLMService.Settings( + llm = SarvamLLMService( + api_key=os.getenv("SARVAM_API_KEY"), + settings=SarvamLLMService.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.", ), ) diff --git a/examples/foundational/07z-interruptible-sarvam.py b/examples/foundational/07z-interruptible-sarvam.py index 5f144f73f..031b82116 100644 --- a/examples/foundational/07z-interruptible-sarvam.py +++ b/examples/foundational/07z-interruptible-sarvam.py @@ -21,7 +21,7 @@ from pipecat.processors.aggregators.llm_response_universal import ( ) from pipecat.runner.types import RunnerArguments from pipecat.runner.utils import create_transport -from pipecat.services.openai.llm import OpenAILLMService +from pipecat.services.sarvam.llm import SarvamLLMService from pipecat.services.sarvam.stt import SarvamSTTService from pipecat.services.sarvam.tts import SarvamTTSService from pipecat.transports.base_transport import BaseTransport, TransportParams @@ -55,20 +55,20 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): stt = SarvamSTTService( api_key=os.getenv("SARVAM_API_KEY"), settings=SarvamSTTService.Settings( - model="saarika:v2.5", + model="saaras:v3", ), ) tts = SarvamTTSService( api_key=os.getenv("SARVAM_API_KEY"), settings=SarvamTTSService.Settings( - model="bulbul:v2", - voice="manisha", + model="bulbul:v3", + voice="shubh", ), ) - llm = OpenAILLMService( - api_key=os.getenv("OPENAI_API_KEY"), - settings=OpenAILLMService.Settings( + llm = SarvamLLMService( + api_key=os.getenv("SARVAM_API_KEY"), + settings=SarvamLLMService.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.", ), ) @@ -96,6 +96,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): params=PipelineParams( enable_metrics=True, enable_usage_metrics=True, + allow_interruptions=True, ), ) diff --git a/examples/foundational/14y-function-calling-sarvam.py b/examples/foundational/14y-function-calling-sarvam.py new file mode 100644 index 000000000..fece01a3a --- /dev/null +++ b/examples/foundational/14y-function-calling-sarvam.py @@ -0,0 +1,178 @@ +# +# 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.llm_service import FunctionCallParams +from pipecat.services.sarvam.llm import SarvamLLMService +from pipecat.services.sarvam.stt import SarvamSTTService +from pipecat.services.sarvam.tts import SarvamTTSService +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 = SarvamSTTService( + api_key=os.getenv("SARVAM_API_KEY"), + settings=SarvamSTTService.Settings( + model="saaras:v3", + ), + ) + + tts = SarvamTTSService( + api_key=os.getenv("SARVAM_API_KEY"), + settings=SarvamTTSService.Settings( + model="bulbul:v3", + voice="shubh", + ), + ) + llm = SarvamLLMService( + api_key=os.getenv("SARVAM_API_KEY"), + settings=SarvamLLMService.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": "user", "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/55zzq-update-settings-sarvam-llm.py b/examples/foundational/55zzq-update-settings-sarvam-llm.py new file mode 100644 index 000000000..227adb3cb --- /dev/null +++ b/examples/foundational/55zzq-update-settings-sarvam-llm.py @@ -0,0 +1,137 @@ +# +# Copyright (c) 2024-2026, Daily +# +# SPDX-License-Identifier: BSD 2-Clause License +# + +import asyncio +import os +from typing import Any + +from dotenv import load_dotenv +from loguru import logger + +from pipecat.audio.vad.silero import SileroVADAnalyzer +from pipecat.frames.frames import LLMRunFrame, LLMUpdateSettingsFrame +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.sarvam.llm import SarvamLLMService +from pipecat.services.sarvam.stt import SarvamSTTService +from pipecat.services.sarvam.tts import SarvamTTSService +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) + +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, + ), +} + + +def _require_env(name: str) -> str: + value = os.getenv(name) + if not value: + raise ValueError(f"Environment variable `{name}` is required.") + return value + + +async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): + logger.info("Starting bot") + + stt = SarvamSTTService( + settings=SarvamSTTService.Settings(model="saaras:v3"), + api_key=_require_env("SARVAM_API_KEY"), + ) + + tts = SarvamTTSService( + settings=SarvamTTSService.Settings(model="bulbul:v3"), + api_key=_require_env("SARVAM_API_KEY"), + ) + + llm = SarvamLLMService( + api_key=_require_env("SARVAM_API_KEY"), + settings=SarvamLLMService.Settings(model="sarvam-30b"), + system_instruction=( + "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way." + ), + ) + + context = LLMContext() + 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("Client connected") + context.add_message({"role": "user", "content": "Please introduce yourself to the user."}) + await task.queue_frames([LLMRunFrame()]) + + await asyncio.sleep(10) + logger.info("Updating Sarvam LLM settings: temperature=0.1") + await task.queue_frame( + LLMUpdateSettingsFrame(delta=SarvamLLMService.Settings(temperature=0.1)) + ) + + @transport.event_handler("on_client_disconnected") + async def on_client_disconnected(transport, client): + logger.info("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/scripts/evals/run-release-evals.py b/scripts/evals/run-release-evals.py index 19492ba62..dcb531cd6 100644 --- a/scripts/evals/run-release-evals.py +++ b/scripts/evals/run-release-evals.py @@ -186,6 +186,7 @@ TESTS_14 = [ ("14v-function-calling-openai.py", EVAL_WEATHER), ("14w-function-calling-mistral.py", EVAL_WEATHER), ("14x-function-calling-openpipe.py", EVAL_WEATHER), + ("14y-function-calling-sarvam.py", EVAL_WEATHER), ("14-function-calling-openai-responses.py", EVAL_WEATHER), ("14-function-calling-openai-responses.py", EVAL_WEATHER_AND_RESTAURANT), # Video diff --git a/src/pipecat/services/sarvam/__init__.py b/src/pipecat/services/sarvam/__init__.py index e8af1401e..30d115d3f 100644 --- a/src/pipecat/services/sarvam/__init__.py +++ b/src/pipecat/services/sarvam/__init__.py @@ -4,5 +4,4 @@ # SPDX-License-Identifier: BSD 2-Clause License # - from .tts import * diff --git a/src/pipecat/services/sarvam/llm.py b/src/pipecat/services/sarvam/llm.py new file mode 100644 index 000000000..c1fc6990e --- /dev/null +++ b/src/pipecat/services/sarvam/llm.py @@ -0,0 +1,160 @@ +# +# Copyright (c) 2024-2026, Daily +# +# SPDX-License-Identifier: BSD 2-Clause License +# + +"""Sarvam LLM service implementation using OpenAI-compatible interface.""" + +from dataclasses import dataclass, field +from typing import Literal, Mapping, Optional + +from loguru import logger +from openai import NOT_GIVEN + +from pipecat.adapters.services.open_ai_adapter import OpenAILLMInvocationParams +from pipecat.services.openai.base_llm import OpenAILLMSettings +from pipecat.services.openai.llm import OpenAILLMService +from pipecat.services.sarvam._sdk import sdk_headers +from pipecat.services.settings import NOT_GIVEN as _NOT_GIVEN +from pipecat.services.settings import _NotGiven, is_given + + +@dataclass +class SarvamLLMSettings(OpenAILLMSettings): + """Settings for SarvamLLMService. + + Parameters: + wiki_grounding: Sarvam wiki grounding toggle. + reasoning_effort: Reasoning effort level (low, medium, high). + """ + + wiki_grounding: bool | None | _NotGiven = field(default_factory=lambda: _NOT_GIVEN) + reasoning_effort: Literal["low", "medium", "high"] | None | _NotGiven = field( + default_factory=lambda: _NOT_GIVEN + ) + + +class SarvamLLMService(OpenAILLMService): + """A service for interacting with Sarvam's API using the OpenAI-compatible interface. + + This service extends OpenAILLMService to connect to Sarvam's API endpoint while + maintaining full compatibility with OpenAI's interface and functionality. + """ + + _SUPPORTED_MODELS = frozenset( + {"sarvam-30b", "sarvam-30b-16k", "sarvam-105b", "sarvam-105b-32k"} + ) + Settings = SarvamLLMSettings + _settings: Settings + + def __init__( + self, + *, + api_key: str, + base_url: str = "https://api.sarvam.ai/v1", + settings: Optional[Settings] = None, + default_headers: Optional[Mapping[str, str]] = None, + **kwargs, + ): + """Initialize Sarvam LLM service. + + Args: + api_key: Sarvam API key used for both OpenAI auth and Sarvam subscription header. + base_url: Sarvam OpenAI-compatible base URL. + settings: Runtime-updatable settings. + default_headers: Additional HTTP headers to include in requests. + **kwargs: Additional keyword arguments passed to ``OpenAILLMService``. + """ + # Initialize only Sarvam-specific defaults; inherited defaults are + # provided by the OpenAI base service initialization. + default_settings = self.Settings( + model="sarvam-30b", + wiki_grounding=None, + reasoning_effort=None, + ) + + # Apply settings delta (canonical API, always wins) + if settings is not None: + default_settings.apply_update(settings) + + self._validate_model(default_settings.model) + + super().__init__( + api_key=api_key, + base_url=base_url, + settings=default_settings, + default_headers=default_headers, + **kwargs, + ) + + def create_client( + self, + api_key=None, + base_url=None, + organization=None, + project=None, + default_headers=None, + **kwargs, + ): + """Create OpenAI-compatible client for Sarvam API endpoint. + + Ensures Sarvam auth and SDK identification headers are always attached. + """ + merged_headers = dict(default_headers or {}) + # sdk_headers() carries Pipecat User-Agent and should override caller-provided value. + merged_headers.update(sdk_headers()) + if api_key: + merged_headers["api-subscription-key"] = api_key + + logger.debug(f"Creating Sarvam client with API {base_url}") + return super().create_client( + api_key=api_key, + base_url=base_url, + organization=organization, + project=project, + default_headers=merged_headers, + **kwargs, + ) + + def build_chat_completion_params(self, params_from_context: OpenAILLMInvocationParams) -> dict: + """Build parameters for Sarvam chat completion request. + + Starts from OpenAI-compatible defaults, then removes unsupported + request fields and applies Sarvam-specific options. + """ + self._validate_tool_parameters(params_from_context) + + params = super().build_chat_completion_params(params_from_context) + params.pop("stream_options", None) + params.pop("max_completion_tokens", None) + params.pop("service_tier", None) + + if is_given(self._settings.wiki_grounding) and self._settings.wiki_grounding is not None: + params["wiki_grounding"] = self._settings.wiki_grounding + if ( + is_given(self._settings.reasoning_effort) + and self._settings.reasoning_effort is not None + ): + params["reasoning_effort"] = self._settings.reasoning_effort + + return params + + def _validate_model(self, model: str): + if model not in self._SUPPORTED_MODELS: + allowed = ", ".join(sorted(self._SUPPORTED_MODELS)) + raise ValueError(f"Unsupported Sarvam LLM model '{model}'. Allowed values: {allowed}.") + + def _validate_tool_parameters(self, params_from_context: OpenAILLMInvocationParams): + tools = params_from_context.get("tools", NOT_GIVEN) + tool_choice = params_from_context.get("tool_choice", NOT_GIVEN) + + has_tools = ( + tools is not NOT_GIVEN + and tools is not None + and (not isinstance(tools, list) or len(tools) > 0) + ) + has_tool_choice = tool_choice is not NOT_GIVEN and tool_choice is not None + + if has_tool_choice and not has_tools: + raise ValueError("Sarvam requires non-empty `tools` when `tool_choice` is provided.")