Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

add text delta handle for openai realtime #633

Open
wants to merge 5 commits into
base: main
Choose a base branch
from
Open

add text delta handle for openai realtime #633

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
5d99b08
service(openai_realtime): add text delta handle
nulyang Oct 21, 2024
cb72a61
service(openai_realtime): add text content append
nulyang Oct 21, 2024
737bf3b
service(openai_realtime): fix condition structure
nulyang Oct 28, 2024
c7e7674
Merge branch 'pipecat-ai:main' into feat/openai-realtime-text
nulyang Nov 18, 2024
19904d5
Merge branch 'pipecat-ai:main' into feat/openai-realtime-text
nulyang Dec 31, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions src/pipecat/services/openai_realtime_beta/context.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -139,6 +139,8 @@ def add_assistant_content_item_as_message(self, item):
for content in item.content:
if content.type == "audio":
message["content"].append({"type": "text", "text": content.transcript})
elif content.type == "text":
message["content"].append({"type": "text", "text": content.text})
else:
logger.error(f"Unhandled content type in assistant item: {content.type} - {item}")
self.add_message(message)
Expand Down
6 changes: 6 additions & 0 deletions src/pipecat/services/openai_realtime_beta/openai.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -311,6 +311,8 @@ async def _receive_task_handler(self):
await self._handle_evt_audio_delta(evt)
elif evt.type == "response.audio.done":
await self._handle_evt_audio_done(evt)
elif evt.type == "response.text.delta":
await self._handle_evt_text_delta(evt)
elif evt.type == "conversation.item.created":
await self._handle_evt_conversation_item_created(evt)
elif evt.type == "conversation.item.input_audio_transcription.completed":
Expand Down Expand Up @@ -374,6 +376,10 @@ async def _handle_evt_audio_done(self, evt):
# Don't clear the self._current_audio_response here. We need to wait until we
# receive a BotStoppedSpeakingFrame from the output transport.

async def _handle_evt_text_delta(self, evt):
await self.stop_ttfb_metrics()
await self.push_frame(TextFrame(evt.delta))

async def _handle_evt_conversation_item_created(self, evt):
# This will get sent from the server every time a new "message" is added
# to the server's conversation state, whether we create it via the API
Expand Down
Loading