diff --git a/CHANGELOG.md b/CHANGELOG.md index b4de8325c..78620da43 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -231,10 +231,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ### Other -- Updated all vision 12-series foundational examples to use function calling to - request for a camera image and also to push `LLMMessagesAppendFrame` with the - retrieved image. For the specific `Moondream` example (`12-describe-video.py`) - we now use a regular LLM and a parallel pipeline with the `MoondreamService`. +- Updated all vision 12-series foundational examples to load images from a file + and push `LLMMessagesAppendFrame` with the loaded image. + +- Added 14-series video examples for different services. These new examples + request an image from the user camera through a function call. ## [0.0.91] - 2025-10-21 diff --git a/examples/foundational/12-describe-image-openai.py b/examples/foundational/12-describe-image-openai.py new file mode 100644 index 000000000..97cb82054 --- /dev/null +++ b/examples/foundational/12-describe-image-openai.py @@ -0,0 +1,141 @@ +# +# Copyright (c) 2024–2025, Daily +# +# SPDX-License-Identifier: BSD 2-Clause License +# + + +import os + +from dotenv import load_dotenv +from loguru import logger +from PIL import Image + +from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams +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.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 +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.openai.llm import OpenAILLMService +from pipecat.transports.base_transport import BaseTransport, TransportParams +from pipecat.transports.daily.transport import DailyParams + +load_dotenv(override=True) + + +# We store functions so objects (e.g. SileroVADAnalyzer) don't get +# instantiated. The function will be called when the desired transport gets +# selected. +transport_params = { + "daily": lambda: DailyParams( + audio_in_enabled=True, + audio_out_enabled=True, + vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)), + turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()), + ), + "webrtc": lambda: TransportParams( + audio_in_enabled=True, + audio_out_enabled=True, + vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)), + turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()), + ), +} + + +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"), + voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady + ) + + llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY")) + + 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 converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way. You are also able to describe images.", + }, + ] + + context = LLMContext(messages) + context_aggregator = LLMContextAggregatorPair(context) + + pipeline = Pipeline( + [ + transport.input(), # Transport user input + stt, # STT + context_aggregator.user(), # User responses + llm, # LLM + tts, # TTS + transport.output(), # Transport bot output + context_aggregator.assistant(), # Assistant spoken responses + ] + ) + + 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") + + if not runner_args.body: + script_dir = os.path.dirname(__file__) + runner_args.body = { + "image_path": os.path.join(script_dir, "assets", "cat.jpg"), + "question": "Describe this image", + } + + image_path = runner_args.body["image_path"] + question = runner_args.body["question"] + + # Kick off the conversation. + image = Image.open(image_path) + message = LLMContext.create_image_message( + image=image.tobytes(), + format="RGB", + size=image.size, + text=question, + ) + messages.append(message) + 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/12a-describe-image-anthropic.py b/examples/foundational/12a-describe-image-anthropic.py new file mode 100644 index 000000000..1690a06bf --- /dev/null +++ b/examples/foundational/12a-describe-image-anthropic.py @@ -0,0 +1,141 @@ +# +# Copyright (c) 2024–2025, Daily +# +# SPDX-License-Identifier: BSD 2-Clause License +# + + +import os + +from dotenv import load_dotenv +from loguru import logger +from PIL import Image + +from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams +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.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 +from pipecat.runner.types import RunnerArguments +from pipecat.runner.utils import create_transport +from pipecat.services.anthropic.llm import AnthropicLLMService +from pipecat.services.cartesia.tts import CartesiaTTSService +from pipecat.services.deepgram.stt import DeepgramSTTService +from pipecat.transports.base_transport import BaseTransport, TransportParams +from pipecat.transports.daily.transport import DailyParams + +load_dotenv(override=True) + + +# We store functions so objects (e.g. SileroVADAnalyzer) don't get +# instantiated. The function will be called when the desired transport gets +# selected. +transport_params = { + "daily": lambda: DailyParams( + audio_in_enabled=True, + audio_out_enabled=True, + vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)), + turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()), + ), + "webrtc": lambda: TransportParams( + audio_in_enabled=True, + audio_out_enabled=True, + vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)), + turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()), + ), +} + + +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"), + voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady + ) + + llm = AnthropicLLMService(api_key=os.getenv("ANTHROPIC_API_KEY")) + + 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 converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way. You are also able to describe images.", + }, + ] + + context = LLMContext(messages) + context_aggregator = LLMContextAggregatorPair(context) + + pipeline = Pipeline( + [ + transport.input(), # Transport user input + stt, # STT + context_aggregator.user(), # User responses + llm, # LLM + tts, # TTS + transport.output(), # Transport bot output + context_aggregator.assistant(), # Assistant spoken responses + ] + ) + + 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") + + if not runner_args.body: + script_dir = os.path.dirname(__file__) + runner_args.body = { + "image_path": os.path.join(script_dir, "assets", "cat.jpg"), + "question": "Describe this image", + } + + image_path = runner_args.body["image_path"] + question = runner_args.body["question"] + + # Kick off the conversation. + image = Image.open(image_path) + message = LLMContext.create_image_message( + image=image.tobytes(), + format="RGB", + size=image.size, + text=question, + ) + messages.append(message) + 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/12b-describe-image-aws.py b/examples/foundational/12b-describe-image-aws.py new file mode 100644 index 000000000..1827c8906 --- /dev/null +++ b/examples/foundational/12b-describe-image-aws.py @@ -0,0 +1,148 @@ +# +# Copyright (c) 2024–2025, Daily +# +# SPDX-License-Identifier: BSD 2-Clause License +# + + +import os + +from dotenv import load_dotenv +from loguru import logger +from PIL import Image + +from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams +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.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 +from pipecat.runner.types import RunnerArguments +from pipecat.runner.utils import create_transport +from pipecat.services.aws.llm import AWSBedrockLLMService +from pipecat.services.cartesia.tts import CartesiaTTSService +from pipecat.services.deepgram.stt import DeepgramSTTService +from pipecat.transports.base_transport import BaseTransport, TransportParams +from pipecat.transports.daily.transport import DailyParams + +load_dotenv(override=True) + + +# We store functions so objects (e.g. SileroVADAnalyzer) don't get +# instantiated. The function will be called when the desired transport gets +# selected. +transport_params = { + "daily": lambda: DailyParams( + audio_in_enabled=True, + audio_out_enabled=True, + vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)), + turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()), + ), + "webrtc": lambda: TransportParams( + audio_in_enabled=True, + audio_out_enabled=True, + vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)), + turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()), + ), +} + + +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"), + voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady + ) + + llm = AWSBedrockLLMService( + aws_region="us-west-2", + model="us.anthropic.claude-3-7-sonnet-20250219-v1:0", + # Note: usually, prefer providing latency="optimized" param. + # Here we can't because AWS Bedrock doesn't support it for Claude 3.7, + # which we need for image input. + params=AWSBedrockLLMService.InputParams(temperature=0.8), + ) + + 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 converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way. You are also able to describe images.", + }, + ] + + context = LLMContext(messages) + context_aggregator = LLMContextAggregatorPair(context) + + pipeline = Pipeline( + [ + transport.input(), # Transport user input + stt, # STT + context_aggregator.user(), # User responses + llm, # LLM + tts, # TTS + transport.output(), # Transport bot output + context_aggregator.assistant(), # Assistant spoken responses + ] + ) + + 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") + + if not runner_args.body: + script_dir = os.path.dirname(__file__) + runner_args.body = { + "image_path": os.path.join(script_dir, "assets", "cat.jpg"), + "question": "Describe this image", + } + + image_path = runner_args.body["image_path"] + question = runner_args.body["question"] + + # Kick off the conversation. + image = Image.open(image_path) + message = LLMContext.create_image_message( + image=image.tobytes(), + format="RGB", + size=image.size, + text=question, + ) + messages.append(message) + 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/12c-describe-image-gemini-flash.py b/examples/foundational/12c-describe-image-gemini-flash.py new file mode 100644 index 000000000..9a36785e8 --- /dev/null +++ b/examples/foundational/12c-describe-image-gemini-flash.py @@ -0,0 +1,141 @@ +# +# Copyright (c) 2024–2025, Daily +# +# SPDX-License-Identifier: BSD 2-Clause License +# + + +import os + +from dotenv import load_dotenv +from loguru import logger +from PIL import Image + +from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams +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.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 +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.google.llm import GoogleLLMService +from pipecat.transports.base_transport import BaseTransport, TransportParams +from pipecat.transports.daily.transport import DailyParams + +load_dotenv(override=True) + + +# We store functions so objects (e.g. SileroVADAnalyzer) don't get +# instantiated. The function will be called when the desired transport gets +# selected. +transport_params = { + "daily": lambda: DailyParams( + audio_in_enabled=True, + audio_out_enabled=True, + vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)), + turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()), + ), + "webrtc": lambda: TransportParams( + audio_in_enabled=True, + audio_out_enabled=True, + vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)), + turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()), + ), +} + + +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"), + voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady + ) + + llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY")) + + 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 converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way. You are also able to describe images.", + }, + ] + + context = LLMContext(messages) + context_aggregator = LLMContextAggregatorPair(context) + + pipeline = Pipeline( + [ + transport.input(), # Transport user input + stt, # STT + context_aggregator.user(), # User responses + llm, # LLM + tts, # TTS + transport.output(), # Transport bot output + context_aggregator.assistant(), # Assistant spoken responses + ] + ) + + 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") + + if not runner_args.body: + script_dir = os.path.dirname(__file__) + runner_args.body = { + "image_path": os.path.join(script_dir, "assets", "cat.jpg"), + "question": "Describe this image", + } + + image_path = runner_args.body["image_path"] + question = runner_args.body["question"] + + # Kick off the conversation. + image = Image.open(image_path) + message = LLMContext.create_image_message( + image=image.tobytes(), + format="RGB", + size=image.size, + text=question, + ) + messages.append(message) + 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/assets/cat.jpg b/examples/foundational/assets/cat.jpg new file mode 100644 index 000000000..700b5fc92 Binary files /dev/null and b/examples/foundational/assets/cat.jpg differ