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

Merge pull request #836 from pipecat-ai/aleix/moondream-studypal-fixes

Browse Source 
examples: fixes for moondream-chatbot and studypal
This commit is contained in:
Aleix Conchillo Flaqué
2024-12-11 11:16:09 -08:00
committed by GitHub
parent cff9bb6068 42f5ec20f6
commit 6089d4255c
2 changed files with 9 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
examples/moondream-chatbot/bot.py
View File

@@ -13,13 +13,13 @@ from PIL import Image
from pipecat.audio.vad.silero import SileroVADAnalyzer from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import ( from pipecat.frames.frames import (
BotStartedSpeakingFrame,
BotStoppedSpeakingFrame,
ImageRawFrame, ImageRawFrame,
OutputImageRawFrame, OutputImageRawFrame,
SpriteFrame, SpriteFrame,
Frame, Frame,
LLMMessagesFrame, LLMMessagesFrame,
TTSAudioRawFrame,
TTSStoppedFrame,
TextFrame, TextFrame,
UserImageRawFrame, UserImageRawFrame,
UserImageRequestFrame, UserImageRequestFrame,
@@ -83,14 +83,15 @@ class TalkingAnimation(FrameProcessor):
async def process_frame(self, frame: Frame, direction: FrameDirection): async def process_frame(self, frame: Frame, direction: FrameDirection):
await super().process_frame(frame, direction) await super().process_frame(frame, direction)
if isinstance(frame, TTSAudioRawFrame): if isinstance(frame, BotStartedSpeakingFrame):
if not self._is_talking: if not self._is_talking:
await self.push_frame(talking_frame) await self.push_frame(talking_frame)
self._is_talking = True self._is_talking = True
elif isinstance(frame, TTSStoppedFrame): elif isinstance(frame, BotStoppedSpeakingFrame):
await self.push_frame(quiet_frame) await self.push_frame(quiet_frame)
self._is_talking = False self._is_talking = False
await self.push_frame(frame)
await self.push_frame(frame, direction)
class UserImageRequester(FrameProcessor): class UserImageRequester(FrameProcessor):
@@ -126,7 +127,7 @@ class TextFilterProcessor(FrameProcessor):
if frame.text != self.text: if frame.text != self.text:
await self.push_frame(frame) await self.push_frame(frame)
else: else:
await self.push_frame(frame) await self.push_frame(frame, direction)
class ImageFilterProcessor(FrameProcessor): class ImageFilterProcessor(FrameProcessor):
@@ -134,7 +135,7 @@ class ImageFilterProcessor(FrameProcessor):
await super().process_frame(frame, direction) await super().process_frame(frame, direction)
if not isinstance(frame, ImageRawFrame): if not isinstance(frame, ImageRawFrame):
await self.push_frame(frame) await self.push_frame(frame, direction)
async def main(): async def main():

4
examples/studypal/studypal.py
View File

@@ -128,9 +128,7 @@ async def main():
api_key=os.getenv("CARTESIA_API_KEY"), api_key=os.getenv("CARTESIA_API_KEY"),
voice_id=os.getenv("CARTESIA_VOICE_ID", "4d2fd738-3b3d-4368-957a-bb4805275bd9"), voice_id=os.getenv("CARTESIA_VOICE_ID", "4d2fd738-3b3d-4368-957a-bb4805275bd9"),
# British Narration Lady: 4d2fd738-3b3d-4368-957a-bb4805275bd9 # British Narration Lady: 4d2fd738-3b3d-4368-957a-bb4805275bd9
params=CartesiaTTSService.InputParams( sample_rate=44100,
sample_rate=44100,
),
) )
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o-mini") llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o-mini")