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

don't tie UserImageRawFrame with function calls

Browse Source
This commit is contained in:
Aleix Conchillo Flaqué
2025-10-30 12:42:47 -07:00
parent 74fb6e7676
commit ec95618b94
13 changed files with 126 additions and 180 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
src/pipecat/frames/frames.py
View File

@@ -11,7 +11,6 @@ including data frames, system frames, and control frames for audio, video, text,
and LLM processing.
"""
import asyncio
from dataclasses import dataclass, field
from typing import (
TYPE_CHECKING,
@@ -1202,27 +1201,23 @@ class TransportMessageUrgentFrame(OutputTransportMessageUrgentFrame):
class UserImageRequestFrame(SystemFrame):
"""Frame requesting an image from a specific user.
A frame to request an image from the given user. The frame might be
generated by a function call in which case the corresponding fields will be
properly set.
A frame to request an image from the given user. The request might come with
a text that can be later used to describe the requested image.
Parameters:
user_id: Identifier of the user to request image from.
context: Optional context for the image request.
function_name: Name of function that generated this request (if any).
tool_call_id: Tool call ID if generated by function call.
text: An optional text associated to the image request.
add_to_context: Whether the requested image should be added to an LLM context.
video_source: Specific video source to capture from.
"""
user_id: str
context: Optional[Any] = None
function_name: Optional[str] = None
tool_call_id: Optional[str] = None
text: Optional[str] = None
add_to_context: Optional[bool] = None
video_source: Optional[str] = None
request_event: Optional[asyncio.Event] = None
def __str__(self):
return f"{self.name}(user: {self.user_id}, video_source: {self.video_source}, function: {self.function_name}, request: {self.tool_call_id})"
return f"{self.name}(user: {self.user_id}, text: {self.text}, add_to_context: {self.add_to_context}, {self.video_source})"
@dataclass
@@ -1296,33 +1291,17 @@ class UserImageRawFrame(InputImageRawFrame):
Parameters:
user_id: Identifier of the user who provided this image.
request: The original image request frame if this is a response.
text: An optional text associated to this image.
add_to_context: Whether this image should be added to an LLM context.
"""
user_id: str = ""
request: Optional[UserImageRequestFrame] = None
text: Optional[str] = None
add_to_context: Optional[bool] = None
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}, request: {self.request})"
@dataclass
class VisionImageRawFrame(InputImageRawFrame):
"""Raw image input frame to be analyzed by vision services.
This is just an image with an associated text describing how the vision
service should analyze the image.
Parameters:
text: Description of how the vision service should analyze the image.
"""
text: str
def __str__(self):
pts = format_pts(self.pts)
return f"{self.name}(pts: {pts}, source: {self.transport_source}, size: {self.size}, format: {self.format}, text: {self.text})"
return f"{self.name}(pts: {pts}, user: {self.user_id}, source: {self.transport_source}, size: {self.size}, format: {self.format}, text: {self.text}, add_to_context: {self.add_to_context})"
@dataclass