Aleix Conchillo Flaqué
0a9daa2f56
task: avoid canceling tasks more than once
2025-01-27 14:42:23 -08:00
Aleix Conchillo Flaqué
e48c0e52ef
transports(daily): avoid canceling task more than once
2025-01-27 14:42:23 -08:00
Aleix Conchillo Flaqué
6bca8396d3
utils: error if we try to cancel the same task multiple times
2025-01-27 14:42:23 -08:00
Aleix Conchillo Flaqué
c2d8a45a07
runner: warn about remaining dangling tasks
2025-01-27 14:42:23 -08:00
Aleix Conchillo Flaqué
80a7f1b1e7
runner: improve signal handler task cancellation
2025-01-27 14:42:23 -08:00
Aleix Conchillo Flaqué
aff6e24560
pipeline: fix pipeline cleanup
2025-01-27 14:42:23 -08:00
Aleix Conchillo Flaqué
cb93f6b368
utils: store created tasks and add current_tasks()
2025-01-27 14:42:23 -08:00
Aleix Conchillo Flaqué
ff0bcec33a
transports: improve task naming
2025-01-27 14:42:23 -08:00
Aleix Conchillo Flaqué
5885fcc230
add id and name properties
2025-01-27 14:42:23 -08:00
Aleix Conchillo Flaqué
57b186cde8
base_transport: add name and id fields
2025-01-27 14:42:23 -08:00
Aleix Conchillo Flaqué
d1a3f404a5
improve task creation and cancellation
...
If a FrameProcessor needs to create a task it should use
FrameProcessor.create_task() and FrameProcessor.cancel_task(). This gives
Pipecat more control over all the tasks that are created in Pipecat.
Both functions internally use the utils module: utils.create_task() and
utils.cancel_task() which should also be used outside of FrameProcessors. That
is, unless strictly necessary, we should avoid using asyncio.create_task().
2025-01-27 14:42:23 -08:00
Mark Backman
9e9822f17d
Use inspect.signature to determine which callback to use
2025-01-27 10:24:58 -05:00
Mark Backman
5f9671e2ca
Added retry functionality and a new callback to the UserIdleProcessor
2025-01-27 10:24:57 -05:00
Mark Backman
aac8961ae5
Merge pull request #1078 from pipecat-ai/mb/improve-error-handling-truncate-audio
...
Add better error handling for OpenAIRealtimeBetaLLMService truncate errors
2025-01-27 08:54:39 -05:00
Mark Backman
3e9a6b6262
Merge pull request #1095 from pipecat-ai/mb/elevenlabs-lang-codes
2025-01-26 12:21:28 -05:00
Mark Backman
fb3097560f
Remove eleven_multilinguagal_v2 from language code list
2025-01-26 07:17:38 -05:00
vengadanathan srinivasan
7a0cfc8d3d
Adding hindi danda symbol as end of sentence marker
2025-01-25 14:55:51 +05:30
Mark Backman
abf0d0d053
Improve token parameter construction using DailyMeetingTokenProperties
2025-01-24 17:22:31 -05:00
Mark Backman
1acdf7aff7
Fix expiry_time type validation in get_token REST API helper
2025-01-24 17:21:50 -05:00
Filipi Fuchter
655d56f634
Fixing pydantic validation when creating meeting token.
2025-01-24 19:15:56 -03:00
Filipi Fuchter
07c84b733b
Sending Search Response to RTVI
2025-01-24 18:59:46 -03:00
Filipi da Silva Fuchter
7c52736ff6
Merge pull request #1030 from pipecat-ai/gemini_grounding_metadata
...
Introduce support for extracting and processing grounding metadata from GoogleLLMService.
2025-01-24 15:41:54 -03:00
Mark Backman
48ce751602
Merge pull request #1075 from Vaibhav159/vl_add_daily_meeting_token_v2
...
adding models to DailyRestHelper
2025-01-24 13:21:52 -05:00
Vaibhav159
1f1e2dac2b
wrapping things up
2025-01-24 23:44:23 +05:30
Vaibhav159
71c2dc3d05
minor typing change
2025-01-24 23:38:44 +05:30
Vaibhav159
ef02ece662
doc string
2025-01-24 22:47:40 +05:30
Vaibhav159
d5818fad5b
addressing comments
2025-01-24 22:46:54 +05:30
Rafal Skorski
9c22bd8df1
Improving read me and encoding support
2025-01-24 16:44:11 +01:00
Vaibhav159
c5faac1cf8
adding RecordingsBucketConfig
2025-01-24 15:14:20 +05:30
Vaibhav159
6ab2404a98
adding more properties to daily room
2025-01-24 09:10:25 +05:30
Eric Deng
2c81dc1f06
Update cartesia.py to use the new model pointer sonic instead of sonic-english
...
We are now using `sonic` as a pointer to the latest stable release (https://docs.cartesia.ai/build-with-sonic/models#continuous-updates ). sonic-english will forever point to `sonic-2024-10-19`, which is already out of date.
2025-01-23 15:47:07 -08:00
Mark Backman
53251dcb88
Add better error handling for OpenAIRealtimeBetaLLMService truncate errors
2025-01-23 14:25:08 -05:00
Vaibhav159
ef511d580d
adding missing audio buffer fix
2025-01-23 23:17:49 +05:30
Vaibhav159
5957ddb038
adding missing audio buffer fix
2025-01-23 23:17:18 +05:30
Vaibhav159
799c2d14b8
adding meeting token v2 func
2025-01-23 21:40:42 +05:30
Rafal Skorski
8eef21db6e
Adding telnyx serializer
2025-01-23 15:39:46 +01:00
Mark Backman
fc6aa6eae8
Merge pull request #1060 from chhao01/patch-1
...
[bug]TypeError: object of type 'NoneType' has no len()
2025-01-22 19:14:35 -05:00
Mark Backman
7167719761
Emit a transcription callback when receiving a CancelFrame, update examples accordingly
2025-01-22 14:56:29 -05:00
Mark Backman
e1430be9f9
Code review fixes
2025-01-22 14:56:29 -05:00
Mark Backman
2a60d54830
Update the AssistantTranscriptProcessor to use TTSTextFrames in place of OpenAILLMContextFrames
2025-01-22 14:56:00 -05:00
Aleix Conchillo Flaqué
b3c99887dc
Merge pull request #1068 from Canonical-AI-Inc/import-fix
...
Fixing missing import
2025-01-22 11:37:49 -08:00
Mark Backman
38ad75cc17
Merge pull request #1065 from pipecat-ai/mb/fix-openai_realtime-function-calling
...
OpenAIRealtimeBetaLLMService: Fixed an error in function calling
2025-01-22 14:37:01 -05:00
Adrian Cowham
2debac314c
fixing missing import
2025-01-22 11:06:53 -08:00
Mark Backman
0ba60c9e28
Merge pull request #975 from imsakg/main
...
fix(gemini): prevent non-audio modality processing
2025-01-22 09:03:18 -05:00
Mark Backman
5ca5fbd825
OpenAIRealtimeBetaLLMService: Fixed an error in function calling
2025-01-22 08:54:03 -05:00
Joe Garlick
b72504f1cb
Added: Additional DTMF frames
2025-01-22 13:47:23 +00:00
Cheng Hao
7e8fc2e7e2
[bug]TypeError: object of type 'NoneType' has no len()
...
Sometimes the chunk.choices is None, and I got exception like:
```
TypeError: object of type 'NoneType' has no len()
```
2025-01-22 15:31:27 +08:00
Aleix Conchillo Flaqué
f89b9ec23f
Merge pull request #1057 from pipecat-ai/aleix/replace-resampy-soxr
...
improve audio resampling by switching from resampy to soxr
2025-01-21 17:52:49 -08:00
Mark Backman
20d5824e56
Merge pull request #1058 from pipecat-ai/mb/fix-trace-log
2025-01-21 20:44:50 -05:00
Aleix Conchillo Flaqué
cacd6ba3fa
improve audio resampling by switching from resampy to soxr
2025-01-21 17:40:17 -08:00
