Merge pull request #34 from pipecat-ai/mb/update-voice-ui-kit-0.8.0

Update voice-ui-kit to 0.8.0

Author: markbackman

CHANGELOG.md

@@ -5,6 +5,13 @@ All notable changes to **SmallWebRTC Prebuilt** will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [2.3.0] - 2026-02-25
+
+### Changed
+
+- Update to `voice-ui-kit` 0.8.0, which adds support for function call status
+  information in the ConversationPanel.
+
 ## [2.2.0] - 2026-02-13
 
 ### Changed
@@ -19,7 +26,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Changed
 
-- Update to voice-ui-kit 0.7.1, which introduces support for the
+- Update to `voice-ui-kit` 0.7.1, which introduces support for the
   `bot-output` event. Now the conversation panel displays text optimally for
   configured TTS service.
 

client/package-lock.json

@@ -26,7 +26,7 @@
     "@pipecat-ai/client-react": "^1.1.0",
     "@pipecat-ai/small-webrtc-transport": "^1.9.0",
     "@pipecat-ai/daily-transport": "^1.6.0",
-    "@pipecat-ai/voice-ui-kit": "^0.7.1",
+    "@pipecat-ai/voice-ui-kit": "^0.8.0",
     "react": "^19.1.0",
     "react-dom": "^19.1.0"
   }

client/package.json

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "pipecat-ai-small-webrtc-prebuilt"
-version = "2.2.0"
+version = "2.3.0"
 description = "A simple, ready-to-use client for testing the SmallWebRTCTransport."
 license = { text = "BSD 2-Clause License" }
 readme = "README.md"

pyproject.toml

@@ -4,14 +4,17 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
+import asyncio
 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.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
-from pipecat.frames.frames import LLMRunFrame
+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
@@ -20,18 +23,29 @@
     LLMContextAggregatorPair,
     LLMUserAggregatorParams,
 )
+from pipecat.processors.frameworks.rtvi import RTVIFunctionCallReportLevel, RTVIObserverParams
 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.deepgram.tts import DeepgramTTSService
+from pipecat.services.llm_service import FunctionCallParams
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
 from pipecat.turns.user_turn_strategies import UserTurnStrategies
 
 load_dotenv(override=True)
 
+
+async def fetch_weather_from_api(params: FunctionCallParams):
+    await asyncio.sleep(1)
+    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 = {
@@ -51,26 +65,56 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         api_key=os.getenv("CARTESIA_API_KEY"),
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
-    # tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
 
     llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
+    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])
+
     messages = [
         {
             "role": "system",
             "content": "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(messages)
+    context = LLMContext(messages, tools)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(
-            user_turn_strategies=UserTurnStrategies(
-                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
-            ),
-            vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        ),
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
     )
 
     pipeline = Pipeline(
@@ -92,6 +136,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_usage_metrics=True,
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+        rtvi_observer_params=RTVIObserverParams(
+            function_call_report_level={"*": RTVIFunctionCallReportLevel.FULL}
+        ),
     )
 
     @task.rtvi.event_handler("on_client_ready")

test/bot-cascade.py

@@ -4,7 +4,7 @@ version = "0.1.0"
 description = "Quickstart example for building voice AI bots with Pipecat"
 requires-python = ">=3.10"
 dependencies = [
-    "pipecat-ai[google,openai,cartesia,deepgram,silero,webrtc,runner,local-smart-turn-v3]>=0.0.101",
+    "pipecat-ai[google,openai,cartesia,deepgram,silero,webrtc,runner]>=0.0.103",
     "pipecat-ai-small-webrtc-prebuilt"
 ]