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

updated ImageFrame and added URLImageFrame and UserImageFrame

Browse Source
This commit is contained in:
Aleix Conchillo Flaqué
2024-04-08 23:10:10 -07:00
parent 96950ca6df
commit 319b8e7816
16 changed files with 97 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
examples/foundational/05a-local-sync-speech-and-text.py
View File

@@ -5,7 +5,7 @@ import tkinter as tk
import os
from dailyai.pipeline.aggregators import LLMFullResponseAggregator
from dailyai.pipeline.frames import AudioFrame, ImageFrame, LLMMessagesFrame, TextFrame
from dailyai.pipeline.frames import AudioFrame, URLImageFrame, LLMMessagesFrame, TextFrame
from dailyai.services.open_ai_services import OpenAILLMService
from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
from dailyai.services.fal_ai_services import FalImageGenService
@@ -94,6 +94,7 @@ async def main():
"text": image_description,
"image_url": image_data[0],
"image": image_data[1],
"image_size": image_data[2],
"audio": audio,
}
@@ -117,7 +118,7 @@ async def main():
if data:
await transport.send_queue.put(
[
ImageFrame(data["image_url"], data["image"]),
URLImageFrame(data["image_url"], data["image"], data["image_size"]),
AudioFrame(data["audio"]),
]
)

4
examples/foundational/06a-image-sync.py
View File

@@ -35,9 +35,9 @@ class ImageSyncAggregator(AIService):
self._waiting_image_bytes = self._waiting_image.tobytes()
async def process_frame(self, frame: Frame) -> AsyncGenerator[Frame, None]:
yield ImageFrame(None, self._speaking_image_bytes)
yield ImageFrame(self._speaking_image_bytes, (1024, 1024))
yield frame
yield ImageFrame(None, self._waiting_image_bytes)
yield ImageFrame(self._waiting_image_bytes, (1024, 1024))
async def main(room_url: str, token):

4
examples/foundational/08-bots-arguing.py
View File

@@ -122,7 +122,7 @@ async def main(room_url: str):
)
await transport.send_queue.put(
[
ImageFrame(None, image_data1[1]),
ImageFrame(image_data1[1], image_data1[2]),
AudioFrame(audio1),
]
)
@@ -134,7 +134,7 @@ async def main(room_url: str):
)
await transport.send_queue.put(
[
ImageFrame(None, image_data2[1]),
ImageFrame(image_data2[1], image_data2[2]),
AudioFrame(audio2),
]
)

2
examples/foundational/10-wake-word.py
View File

@@ -55,7 +55,7 @@ for file in image_files:
sprites[file] = img.tobytes()
# When the bot isn't talking, show a static image of the cat listening
quiet_frame = ImageFrame("", sprites["sc-listen-1.png"])
quiet_frame = ImageFrame(sprites["sc-listen-1.png"], (720, 1280))
# When the bot is talking, build an animation from two sprites
talking_list = [sprites["sc-default.png"], sprites["sc-talk.png"]]
talking = [random.choice(talking_list) for x in range(30)]