Merge pull request #3981 from dhruvladia-sarvam/feat/sarvam-llm-integration

Sarvam LLM Integration

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)
 

changelog/3978.added.md

@@ -0,0 +1 @@
+- Added `SarvamLLMService` with support for `sarvam-30b`, `sarvam-30b-16k`, `sarvam-105b` and `sarvam-105b-32k`

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(
+        llm = SarvamLLMService(
-            api_key=os.getenv("OPENAI_API_KEY"),
+            api_key=os.getenv("SARVAM_API_KEY"),
-            settings=OpenAILLMService.Settings(
+            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.",
             ),
         )

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",
+            model="bulbul:v3",
-            voice="manisha",
+            voice="shubh",
         ),
     )
-    llm = OpenAILLMService(
+    llm = SarvamLLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
+        api_key=os.getenv("SARVAM_API_KEY"),
-        settings=OpenAILLMService.Settings(
+        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,
         ),
     )
 

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()

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()

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

src/pipecat/services/sarvam/__init__.py

@@ -4,5 +4,4 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-
 from .tts import *

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.")