Aleix Conchillo Flaqué
a43c102fc8
Merge pull request #1064 from jcbjoe/jg/additional_dtmf_frames
...
Added: Additional DTMF frames
2025-01-31 18:25:08 -08:00
Aleix Conchillo Flaqué
41d60a14cc
introduce TaskManager and PipelineRunner event loop
2025-01-30 13:10:36 -08:00
Aleix Conchillo Flaqué
3a688840fc
frames: added metadata field to Frame class
2025-01-29 09:53:21 -08:00
Joe Garlick
b72504f1cb
Added: Additional DTMF frames
2025-01-22 13:47:23 +00:00
Aleix Conchillo Flaqué
e9162ae467
Merge pull request #1004 from Fluentsai/feature/dtmf_input
...
Twilio serializer reading dtmf websocket messages
2025-01-17 18:14:46 -08:00
Aleix Conchillo Flaqué
ff8aa68942
introduce heartbeat frames
2025-01-16 19:31:13 -08:00
Maxim Makatchev
c5edbf4b75
Made InputDTMFFrame a DataFrame and moved up to data frames
2025-01-17 12:27:04 +09:00
Maxim Makatchev
dcf317f2fa
Twilio serializer reading dtmf websocket messages and generating InputDTMFFrame containing the corresponding value of KeypadEntry
2025-01-16 17:43:12 +09:00
Aleix Conchillo Flaqué
c8da531402
pipeline(task): add support for pipeline frame observers
2025-01-15 17:43:59 -08:00
Aleix Conchillo Flaqué
2d0f3341c3
frames: add LLMTextFrame and TTSTextFrame
...
This is to distinguish what type of service has generated the TextFrames.
2025-01-15 17:43:59 -08:00
Mark Backman
8c0ecb89de
Refactor for new on_context_updated callback and new frame properties
2025-01-13 17:20:41 -05:00
Mark Backman
874b8bb136
Allow for an override of running a completion after a function call completes, OpenAI
2025-01-13 09:48:43 -05:00
Aleix Conchillo Flaqué
95e69597f3
update copyright keeping original year (2024)
2025-01-12 11:34:00 -08:00
Mark Backman
a1377b7f1a
Merge pull request #924 from xtreme-sameer-vohra/patch-1
...
Update frames.py
2025-01-06 14:13:10 -05:00
Mark Backman
4667624b60
Update copyright to 2025
2025-01-06 10:19:37 -05:00
Sameer Vohra
d07ba80572
Update frames.py
...
fix minor typo in docs
2025-01-05 22:57:54 -05:00
Mark Backman
1117c21483
Refactor TranscriptProcessor into user and assistant processors
2024-12-17 22:34:22 -05:00
Mark Backman
1f8a217cd1
Code review changes
2024-12-17 22:34:02 -05:00
Mark Backman
dd2703317a
Add timestamp frames and include timestamps in the transcription event and frame
2024-12-17 22:31:15 -05:00
Mark Backman
55879bf365
Add TranscriptionProcessor
2024-12-17 22:31:15 -05:00
Aleix Conchillo Flaqué
5b5125b74c
frames: transcriptions should be TextFrames as before
2024-12-11 10:42:38 -08:00
Aleix Conchillo Flaqué
3d4620cf95
frames: FunctionCallResultFrame should be a DataFrame as before
2024-12-06 11:54:50 -08:00
Aleix Conchillo Flaqué
13c27eaa1d
frames: fix AudioRawFrame mixin
2024-12-04 13:25:37 -08:00
Aleix Conchillo Flaqué
52cefaa9d6
frames: remove AppFrame
2024-12-03 14:30:15 -08:00
Aleix Conchillo Flaqué
42658ecd92
frames: use mixins for audio and image data
2024-12-03 14:30:15 -08:00
Aleix Conchillo Flaqué
a5c7b02a73
frames: input frames are now system frames
...
Input frames from a transport should be processed fast and there's no need for
them to be queued internally in each element.
2024-12-03 14:30:15 -08:00
Mark Backman
33108f5798
Code review feedback
2024-11-14 17:05:08 -05:00
Mark Backman
5fe679039c
Add STTMuteProcessor to un/mute the STT
2024-11-14 13:35:02 -05:00
Aleix Conchillo Flaqué
abc8ede3d7
introduce audio filters
2024-11-04 15:37:08 -08:00
Aleix Conchillo Flaqué
81c476dd4c
introduce output transport audio mixers
2024-11-03 11:13:02 -08:00
Aleix Conchillo Flaqué
2a37b2459a
move vad package to audio.vad
2024-10-17 13:49:16 -07:00
Aleix Conchillo Flaqué
f0d89e57ad
frames: some frames need to be SystemFrames
...
We want to process user and bot started/stopped speaking frames as fast as
possible. If we queue them they might be processed too late.
2024-10-15 14:37:56 -07:00
Aleix Conchillo Flaqué
a28a5e954a
add TransportMessageSystemFrame
2024-10-06 16:50:12 -07:00
Mark Backman
28643b453d
Update to use LLM, STT, TTS subclasses and remove setter methods
2024-10-01 20:30:27 -04:00
Mark Backman
88cca7bf68
Consolidate service UpdateSettingsFrame into a single ServiceUpdateSettingsFrame
2024-10-01 11:01:04 -04:00
Mark Backman
a397b859fe
Add support for gender and google_style inputs to Google TTS
2024-10-01 10:39:45 -04:00
Kwindla Hultman Kramer
a5c73ec829
handle openai multiple function calls
2024-09-30 16:08:30 -07:00
Mark Backman
d7555609fd
Add TTS update settings options
2024-09-30 12:50:40 -04:00
Mark Backman
44a349386c
Consolidate update frames classes into a single UpdateSettingsFrame class
2024-09-30 12:50:39 -04:00
Aleix Conchillo Flaqué
ee3786fe15
frames: add EndTaskFrame and CancelTaskFrame
2024-09-24 19:10:22 -07:00
Aleix Conchillo Flaqué
31b5667cee
frames: log text with [] so we can distinguish spaces better
2024-09-24 13:10:40 -07:00
Aleix Conchillo Flaqué
eeb8338dce
introduce Ruff formatting
2024-09-23 09:53:37 -07:00
Mark Backman
9e27a8aad0
Add control frames for LLM param updates
2024-09-21 00:02:58 -04:00
Aleix Conchillo Flaqué
14acf05a26
Merge pull request #480 from pipecat-ai/aleix/input-output-frames
...
introduce input/output audio and image frames
2024-09-20 14:44:37 -07:00
Aleix Conchillo Flaqué
7e39d9ad3d
introduce input/output audio and image frames
...
We now distinguish between input and output audio and image frames. We introduce
`InputAudioRawFrame`, `OutputAudioRawFrame`, `InputImageRawFrame` and
`OutputImageRawFrame` (and other subclasses of those). The input frames usually
come from an input transport and are meant to be processed inside the pipeline
to generate new frames. However, the input frames will not be sent through an
output transport. The output frames can also be processed by any frame processor
in the pipeline and they are allowed to be sent by the output transport.
2024-09-19 23:11:03 -07:00
mattie ruth backman
a4edb3dab1
Cleanup on aisle METRICS. Note: See below, this is a breaking change
...
1. Fleshed out MetricsFrames and broke it into a proper set of types
2. Add model_name as a property to the AIService so that it can be
automatically included in metrics and also remove that
overhead from all the various services themselves
Breaking change!
Because of the types improvements, the MetricsFrame type has
changed. Each frame will have a list of metrics simlilar to before
except each item in the list will only contain one type of metric:
"ttfb", "tokens", "characters", or "processing". Previously these
fields would be in every entry but set to None if they didn't apply.
While this changes internal handling of the MetricsFrame, it does NOT
break the RTVI/daily messaging of metrics. That format remains the same.
Also. Remember to use model_name for accessing a service's current
model and set_model_name for setting it.
2024-09-19 21:30:34 -04:00
mattie ruth backman
50b45ac2da
get the test infrastructure running again
...
disable broken tests for now
2024-09-19 20:58:17 -04:00
Aleix Conchillo Flaqué
f078d156de
frames: StartFrame is now a SystemFrame
2024-09-19 01:31:12 -07:00
Aleix Conchillo Flaqué
cb36a71381
fix some linting
2024-09-13 09:56:12 -07:00
Aleix Conchillo Flaqué
72f231b327
frames: add a presentation timestamp (pts) to each frame
2024-09-12 00:31:48 -07:00
