wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #3430 from pipecat-ai/pk/request-image-frame-fixes

Browse Source 
Fix request_image_frame and usage
This commit is contained in:
kompfner
2026-01-13 15:36:44 -05:00
committed by GitHub
parent b8e48dee7f 21534f7d83
commit f6d09e1574
13 changed files with 199 additions and 101 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
changelog/3430.fixed.md Normal file
View File

@@ -0,0 +1 @@
- Fixed `request_image_frame` (for backwards compatibility) and restored function-call–related fields in `UserImageRequestFrame` and `UserImageRawFrame`, preventing a case where adding a non-LLM message to the context could trigger duplicate LLM inferences (on image arrival and on function-call result), potentially causing an infinite inference loop.

16
examples/foundational/14d-function-calling-anthropic-video.py
View File

@@ -14,7 +14,7 @@ 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, UserImageRequestFrame
from pipecat.frames.frames import LLMRunFrame, TTSSpeakFrame, UserImageRequestFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -55,9 +55,15 @@ async def fetch_user_image(params: FunctionCallParams):
logger.debug(f"Requesting image with user_id={user_id}, question={question}")
# Request a user image frame and indicate that it should be added to the
# context.
# context. Also associate it to the function call.
await params.llm.push_frame(
UserImageRequestFrame(user_id=user_id, text=question, append_to_context=True),
UserImageRequestFrame(
user_id=user_id,
text=question,
append_to_context=True,
function_name=params.function_name,
tool_call_id=params.tool_call_id,
),
FrameDirection.UPSTREAM,
)
@@ -101,6 +107,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = AnthropicLLMService(api_key=os.getenv("ANTHROPIC_API_KEY"))
llm.register_function("fetch_user_image", fetch_user_image)
@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."))
fetch_image_function = FunctionSchema(
name="fetch_user_image",
description="Called when the user requests a description of their camera feed",

16
examples/foundational/14d-function-calling-aws-video.py
View File

@@ -14,7 +14,7 @@ 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, UserImageRequestFrame
from pipecat.frames.frames import LLMRunFrame, TTSSpeakFrame, UserImageRequestFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -55,9 +55,15 @@ async def fetch_user_image(params: FunctionCallParams):
logger.debug(f"Requesting image with user_id={user_id}, question={question}")
# Request a user image frame and indicate that it should be added to the
# context.
# context. Also associate it to the function call.
await params.llm.push_frame(
UserImageRequestFrame(user_id=user_id, text=question, append_to_context=True),
UserImageRequestFrame(
user_id=user_id,
text=question,
append_to_context=True,
function_name=params.function_name,
tool_call_id=params.tool_call_id,
),
FrameDirection.UPSTREAM,
)
@@ -108,6 +114,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
llm.register_function("fetch_user_image", fetch_user_image)
@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."))
fetch_image_function = FunctionSchema(
name="fetch_user_image",
description="Called when the user requests a description of their camera feed",

16
examples/foundational/14d-function-calling-gemini-flash-video.py
View File

@@ -14,7 +14,7 @@ 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, UserImageRequestFrame
from pipecat.frames.frames import LLMRunFrame, TTSSpeakFrame, UserImageRequestFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -55,9 +55,15 @@ async def fetch_user_image(params: FunctionCallParams):
logger.debug(f"Requesting image with user_id={user_id}, question={question}")
# Request a user image frame and indicate that it should be added to the
# context.
# context. Also associate it to the function call.
await params.llm.push_frame(
UserImageRequestFrame(user_id=user_id, text=question, append_to_context=True),
UserImageRequestFrame(
user_id=user_id,
text=question,
append_to_context=True,
function_name=params.function_name,
tool_call_id=params.tool_call_id,
),
FrameDirection.UPSTREAM,
)
@@ -101,6 +107,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))
llm.register_function("fetch_user_image", fetch_user_image)
@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."))
fetch_image_function = FunctionSchema(
name="fetch_user_image",
description="Called when the user requests a description of their camera feed",

15
examples/foundational/14d-function-calling-moondream-video.py
View File

@@ -20,6 +20,7 @@ from pipecat.frames.frames import (
LLMFullResponseStartFrame,
LLMRunFrame,
TextFrame,
TTSSpeakFrame,
UserImageRequestFrame,
)
from pipecat.pipeline.parallel_pipeline import ParallelPipeline
@@ -64,9 +65,15 @@ async def fetch_user_image(params: FunctionCallParams):
# Request a user image frame. In this case, we don't want the requested
# image to be added to the context because we will process it with
# Moondream.
# Moondream. Also associate it to the function call.
await params.llm.push_frame(
UserImageRequestFrame(user_id=user_id, text=question, append_to_context=False),
UserImageRequestFrame(
user_id=user_id,
text=question,
append_to_context=False,
function_name=params.function_name,
tool_call_id=params.tool_call_id,
),
FrameDirection.UPSTREAM,
)
@@ -130,6 +137,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
llm.register_function("fetch_user_image", fetch_user_image)
@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."))
fetch_image_function = FunctionSchema(
name="fetch_user_image",
description="Called when the user requests a description of their camera feed",

16
examples/foundational/14d-function-calling-openai-video.py
View File

@@ -15,7 +15,7 @@ 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, UserImageRequestFrame
from pipecat.frames.frames import LLMRunFrame, TTSSpeakFrame, UserImageRequestFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -56,9 +56,15 @@ async def fetch_user_image(params: FunctionCallParams):
logger.debug(f"Requesting image with user_id={user_id}, question={question}")
# Request a user image frame and indicate that it should be added to the
# context.
# context. Also associate it to the function call.
await params.llm.push_frame(
UserImageRequestFrame(user_id=user_id, text=question, append_to_context=True),
UserImageRequestFrame(
user_id=user_id,
text=question,
append_to_context=True,
function_name=params.function_name,
tool_call_id=params.tool_call_id,
),
FrameDirection.UPSTREAM,
)
@@ -101,6 +107,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
llm.register_function("fetch_user_image", fetch_user_image)
@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."))
fetch_image_function = FunctionSchema(
name="fetch_user_image",
description="Called when the user requests a description of their camera feed",

65
examples/foundational/14e-function-calling-google.py
View File

@@ -5,7 +5,6 @@
#
import asyncio
import os
from dotenv import load_dotenv
@@ -16,7 +15,7 @@ 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, TTSSpeakFrame
from pipecat.frames.frames import LLMRunFrame, TTSSpeakFrame, UserImageRequestFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -25,6 +24,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
LLMContextAggregatorPair,
LLMUserAggregatorParams,
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import (
create_transport,
@@ -43,10 +43,6 @@ from pipecat.turns.user_turn_strategies import UserTurnStrategies
load_dotenv(override=True)
# Global variable to store the client ID
client_id = ""
async def get_weather(params: FunctionCallParams):
location = params.arguments["location"]
await params.result_callback(f"The weather in {location} is currently 72 degrees and sunny.")
@@ -57,24 +53,35 @@ async def fetch_restaurant_recommendation(params: FunctionCallParams):
async def get_image(params: FunctionCallParams):
"""Fetch the user image and push it to the LLM.
When called, this function pushes a UserImageRequestFrame upstream to the
transport. As a result, the transport will request the user image and push a
UserImageRawFrame downstream which will be added to the context by the LLM
assistant aggregator.
"""
user_id = params.arguments["user_id"]
question = params.arguments["question"]
logger.debug(f"Requesting image with user_id={client_id}, question={question}")
logger.debug(f"Requesting image with user_id={user_id}, question={question}")
# Request the image frame
await params.llm.request_image_frame(
user_id=client_id,
function_name=params.function_name,
tool_call_id=params.tool_call_id,
text_content=question,
# Request a user image frame and indicate that it should be added to the
# context. Also associate it to the function call.
await params.llm.push_frame(
UserImageRequestFrame(
user_id=user_id,
text=question,
append_to_context=True,
function_name=params.function_name,
tool_call_id=params.tool_call_id,
),
FrameDirection.UPSTREAM,
)
# Wait a short time for the frame to be processed
await asyncio.sleep(0.5)
await params.result_callback(None)
# Return a result to complete the function call
await params.result_callback(
f"I've captured an image from your camera and I'm analyzing what you asked about: {question}"
)
# Instead of None, it's possible to also provide a tool call answer to
# tell the LLM that we are grabbing the image to analyze.
# await params.result_callback({"result": "Image is being captured."})
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
@@ -144,14 +151,18 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
get_image_function = FunctionSchema(
name="get_image",
description="Get an image from the video stream.",
description="Called when the user requests a description of their camera feed",
properties={
"user_id": {
"type": "string",
"description": "The ID of the user to grab the image from",
},
"question": {
"type": "string",
"description": "The question that the user is asking about the image.",
}
"description": "The question that the user is asking about the image",
},
},
required=["question"],
required=["user_id", "question"],
)
tools = ToolsSchema(standard_tools=[weather_function, get_image_function, restaurant_function])
@@ -175,7 +186,6 @@ indicate you should use the get_image tool are:
"""
messages = [
{"role": "system", "content": system_prompt},
{"role": "user", "content": "Say hello."},
]
context = LLMContext(messages, tools)
@@ -215,10 +225,15 @@ indicate you should use the get_image tool are:
await maybe_capture_participant_camera(transport, client)
global client_id
client_id = get_transport_client_id(transport, client)
# Kick off the conversation.
messages.append(
{
"role": "system",
"content": f"Please introduce yourself to the user. Use '{client_id}' as the user ID during function calls.",
}
)
await task.queue_frames([LLMRunFrame()])
@transport.event_handler("on_client_disconnected")

51
examples/foundational/20d-persistent-context-gemini.py
View File

@@ -17,7 +17,7 @@ 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, UserImageRequestFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -26,6 +26,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
LLMContextAggregatorPair,
LLMUserAggregatorParams,
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import (
create_transport,
@@ -46,9 +47,6 @@ load_dotenv(override=True)
BASE_FILENAME = "/tmp/pipecat_conversation_"
# Global variable to store the client ID
client_id = ""
async def fetch_weather_from_api(params: FunctionCallParams):
temperature = 75 if params.arguments["format"] == "fahrenheit" else 24
@@ -63,17 +61,29 @@ async def fetch_weather_from_api(params: FunctionCallParams):
async def get_image(params: FunctionCallParams):
user_id = params.arguments["user_id"]
question = params.arguments["question"]
logger.debug(f"Requesting image with user_id={client_id}, question={question}")
logger.debug(f"Requesting image with user_id={user_id}, question={question}")
# Request the image frame
await params.llm.request_image_frame(
user_id=client_id,
function_name=params.function_name,
tool_call_id=params.tool_call_id,
text_content=question,
# Request a user image frame and indicate that it should be added to the
# context. Also associate it to the function call.
await params.llm.push_frame(
UserImageRequestFrame(
user_id=user_id,
text=question,
append_to_context=True,
function_name=params.function_name,
tool_call_id=params.tool_call_id,
),
FrameDirection.UPSTREAM,
)
await params.result_callback(None)
# Instead of None, it's possible to also provide a tool call answer to
# tell the LLM that we are grabbing the image to analyze.
# await params.result_callback({"result": "Image is being captured."})
async def get_saved_conversation_filenames(params: FunctionCallParams):
# Construct the full pattern including the BASE_FILENAME
@@ -207,14 +217,18 @@ load_conversation_function = FunctionSchema(
get_image_function = FunctionSchema(
name="get_image",
description="Get and image from the camera or video stream.",
description="Called when the user requests a description of their camera feed",
properties={
"user_id": {
"type": "string",
"description": "The ID of the user to grab the image from",
},
"question": {
"type": "string",
"description": "The question to to use when running inference on the acquired image.",
"description": "The question that the user is asking about the image",
},
},
required=["question"],
required=["user_id", "question"],
)
tools = ToolsSchema(
@@ -257,7 +271,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
)
llm = GoogleLLMService(model="gemini-2.0-flash-001", api_key=os.getenv("GOOGLE_API_KEY"))
llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))
# you can either register a single function for all function calls, or specific functions
# llm.register_function(None, fetch_weather_from_api)
@@ -304,10 +318,15 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
await maybe_capture_participant_camera(transport, client)
global client_id
client_id = get_transport_client_id(transport, client)
# Kick off the conversation.
messages.append(
{
"role": "system",
"content": f"Please introduce yourself to the user. Use '{client_id}' as the user ID during function calls.",
}
)
await task.queue_frames([LLMRunFrame()])
@transport.event_handler("on_client_disconnected")

26
src/pipecat/frames/frames.py
View File

@@ -1461,29 +1461,29 @@ class UserImageRequestFrame(SystemFrame):
text: An optional text associated to the image request.
append_to_context: Whether the requested image should be appended to the LLM context.
video_source: Specific video source to capture from.
function_name: Name of function that generated this request (if any).
tool_call_id: Tool call ID if generated by function call (if any).
context: [DEPRECATED] Optional context for the image request.
function_name: [DEPRECATED] Name of function that generated this request (if any).
tool_call_id: [DEPRECATED] Tool call ID if generated by function call.
"""
user_id: str
text: Optional[str] = None
append_to_context: Optional[bool] = None
video_source: Optional[str] = None
context: Optional[Any] = None
function_name: Optional[str] = None
tool_call_id: Optional[str] = None
context: Optional[Any] = None
def __post_init__(self):
super().__post_init__()
if self.context or self.function_name or self.tool_call_id:
if self.context:
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"`UserImageRequestFrame` fields `context`, `function_name` and `tool_call_id` are deprecated.",
"`UserImageRequestFrame` field `context` is deprecated.",
DeprecationWarning,
stacklevel=2,
)
@@ -1565,7 +1565,7 @@ class UserImageRawFrame(InputImageRawFrame):
user_id: Identifier of the user who provided this image.
text: An optional text associated to this image.
append_to_context: Whether the requested image should be appended to the LLM context.
request: [DEPRECATED] The original image request frame if this is a response.
request: The original image request frame if this is a response.
"""
user_id: str = ""
@@ -1573,20 +1573,6 @@ class UserImageRawFrame(InputImageRawFrame):
append_to_context: Optional[bool] = None
request: Optional[UserImageRequestFrame] = None
def __post_init__(self):
super().__post_init__()
if self.request:
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"`UserImageRawFrame` field `request` is deprecated.",
DeprecationWarning,
stacklevel=2,
)
def __str__(self):
pts = format_pts(self.pts)
return f"{self.name}(pts: {pts}, user: {self.user_id}, source: {self.transport_source}, size: {self.size}, format: {self.format}, text: {self.text}, append_to_context: {self.append_to_context})"

72
src/pipecat/processors/aggregators/llm_response_universal.py
View File

@@ -641,6 +641,7 @@ class LLMAssistantAggregator(LLMContextAggregator):
self._started = 0
self._function_calls_in_progress: Dict[str, Optional[FunctionCallInProgressFrame]] = {}
self._function_calls_image_results: Dict[str, UserImageRawFrame] = {}
self._context_updated_tasks: Set[asyncio.Task] = set()
self._assistant_turn_start_timestamp = ""
@@ -820,6 +821,15 @@ class LLMAssistantAggregator(LLMContextAggregator):
run_llm = False
# Append any images that were generated by function calls.
if frame.tool_call_id in self._function_calls_image_results:
image_frame = self._function_calls_image_results[frame.tool_call_id]
del self._function_calls_image_results[frame.tool_call_id]
# If an image frame has been added to the context, let's run inference.
run_llm = await self._maybe_append_image_to_context(image_frame)
# Run inference if the function call result requires it.
if frame.result:
if properties and properties.run_llm is not None:
@@ -856,31 +866,24 @@ class LLMAssistantAggregator(LLMContextAggregator):
self._update_function_call_result(frame.function_name, frame.tool_call_id, "CANCELLED")
del self._function_calls_in_progress[frame.tool_call_id]
def _update_function_call_result(self, function_name: str, tool_call_id: str, result: Any):
for message in self._context.get_messages():
if (
not isinstance(message, LLMSpecificMessage)
and message["role"] == "tool"
and message["tool_call_id"]
and message["tool_call_id"] == tool_call_id
):
message["content"] = result
async def _handle_user_image_frame(self, frame: UserImageRawFrame):
if not frame.append_to_context:
return
image_appended = False
logger.debug(f"{self} Appending UserImageRawFrame to LLM context (size: {frame.size})")
# Check if this image is a result of a function call if so, let's cache.
# TODO(aleix): The function call might have already been executed
# because FunctionCallResultFrame was just faster, in that case we just
# push the context frame now.
if (
frame.request
and frame.request.tool_call_id
and frame.request.tool_call_id in self._function_calls_in_progress
):
self._function_calls_image_results[frame.request.tool_call_id] = frame
else:
image_appended = await self._maybe_append_image_to_context(frame)
await self._context.add_image_frame_message(
format=frame.format,
size=frame.size,
image=frame.image,
text=frame.text,
)
await self._trigger_assistant_turn_stopped()
await self.push_context_frame(FrameDirection.UPSTREAM)
if image_appended:
await self.push_context_frame(FrameDirection.UPSTREAM)
async def _handle_assistant_image_frame(self, frame: AssistantImageRawFrame):
logger.debug(f"{self} Appending AssistantImageRawFrame to LLM context (size: {frame.size})")
@@ -970,6 +973,31 @@ class LLMAssistantAggregator(LLMContextAggregator):
await self._call_event_handler("on_assistant_thought", message)
async def _maybe_append_image_to_context(self, frame: UserImageRawFrame) -> bool:
if not frame.append_to_context:
return False
logger.debug(f"{self} Appending UserImageRawFrame to LLM context (size: {frame.size})")
await self._context.add_image_frame_message(
format=frame.format,
size=frame.size,
image=frame.image,
text=frame.text,
)
return True
def _update_function_call_result(self, function_name: str, tool_call_id: str, result: Any):
for message in self._context.get_messages():
if (
not isinstance(message, LLMSpecificMessage)
and message["role"] == "tool"
and message["tool_call_id"]
and message["tool_call_id"] == tool_call_id
):
message["content"] = result
def _context_updated_task_finished(self, task: asyncio.Task):
self._context_updated_tasks.discard(task)

3
src/pipecat/services/llm_service.py
View File

@@ -519,9 +519,10 @@ class LLMService(AIService):
UserImageRequestFrame(
user_id=user_id,
text=text_content,
# Deprecated fields below.
append_to_context=True,
function_name=function_name,
tool_call_id=tool_call_id,
# Deprecated fields below.
context=text_content,
),
FrameDirection.UPSTREAM,

2
src/pipecat/transports/daily/transport.py
View File

@@ -27,7 +27,6 @@ from pipecat.frames.frames import (
CancelFrame,
ControlFrame,
EndFrame,
ErrorFrame,
Frame,
InputAudioRawFrame,
InputTransportMessageFrame,
@@ -1844,7 +1843,6 @@ class DailyInputTransport(BaseInputTransport):
format=video_frame.color_format,
text=request_frame.text if request_frame else None,
append_to_context=request_frame.append_to_context if request_frame else None,
# Deprecated fields below.
request=request_frame,
)
frame.transport_source = video_source

1
src/pipecat/transports/smallwebrtc/transport.py
View File

@@ -680,7 +680,6 @@ class SmallWebRTCInputTransport(BaseInputTransport):
format=video_frame.format,
text=request_text,
append_to_context=add_to_context,
# Deprecated fields below.
request=request_frame,
)
image_frame.transport_source = video_source