Aleix Conchillo Flaqué
f0cbdc4e68
LLMService: add on_function_calls_started event
2025-05-31 13:57:52 -07:00
Aleix Conchillo Flaqué
40b52cadde
LLMService: s/FunctionCallLLM/FunctionCallFromLLM/ s/FunctionCallRunner/FunctionCallRunnerItem/
2025-05-31 13:57:52 -07:00
Aleix Conchillo Flaqué
04bf85ddfe
LLMService: allow executing tasks sequentially and in parallel
2025-05-31 13:57:52 -07:00
Aleix Conchillo Flaqué
4809684a13
LLMService: cancel function calls on interruptions by default
2025-05-31 13:57:50 -07:00
Aleix Conchillo Flaqué
1eb50ad88f
LLMService: pass LLM function calls all at once
2025-05-31 13:57:36 -07:00
Aleix Conchillo Flaqué
52569bcdb2
LLMService: don't allow running functions concurrently for now
2025-05-31 13:57:36 -07:00
Aleix Conchillo Flaqué
a50a407415
LLMService: run function calls sequentially
2025-05-31 13:57:35 -07:00
Mark Backman
43719ec737
Update CHANGELOG
2025-05-30 21:36:39 -04:00
Mark Backman
8602557985
Refactor Gemini tracing to more closely match OpenAI Realtime, add TTFB metrics
2025-05-30 21:36:00 -04:00
Mark Backman
dd1f7d0875
Add tracking to OpenAI Realtime
2025-05-30 21:36:00 -04:00
Mark Backman
ec39e794d3
_handle_transcription
2025-05-30 21:36:00 -04:00
Mark Backman
7b1a937d4c
Add tracing for Gemini Live
2025-05-30 21:36:00 -04:00
Mark Backman
7a4efc6212
Code review feedback
2025-05-30 21:09:15 -04:00
Brian Mathiyakom
2eb2c5a413
Use disconnect() because close() doesn't exist
...
SmallWebRTCConnection doesn't have a `close()`. There's a `_close()` but I assume that's private due to its naming. The closest function that uses `_close()` is `disconnect()`. I assume then, that the intended resource freeing function call should be to `disconnect()`.
2025-05-30 17:14:53 -07:00
getchannel
8070e156d8
Add groundingMetadata events.py
2025-05-30 18:07:09 -04:00
getchannel
43c6f1f5cd
Add groundingMetadata and logging gemini.py
2025-05-30 18:01:15 -04:00
Mark Backman
2d609a0bde
Update LLmUserContextAggregator to conditionally push_aggregation
2025-05-30 16:48:42 -04:00
Mark Backman
6bc4b4a17f
Update BaseInputTransport to not push StartInterruptionFrame when InterruptionConfig is set and bot is speaking
2025-05-30 16:48:42 -04:00
Mark Backman
b489e52080
Add InterruptionConfig
2025-05-30 16:15:20 -04:00
getchannel
7263d11ee4
update correct upload endpoint file_api.py
2025-05-30 13:41:55 -04:00
getchannel
40c7e3c52c
Update gemini.py
2025-05-30 12:19:40 -04:00
Aleix Conchillo Flaqué
a8aaeec52b
Merge pull request #1926 from pipecat-ai/aleix/pause-base-input-transport
...
handle StopFrame in base input transport and stop pushing frames
2025-05-30 08:27:20 -07:00
Mark Backman
ad7eec181e
Merge pull request #1923 from philipp-eisen/philipp/fix-ttfb_ms-implementation
...
Fix implementation of ttfb_ms metric
2025-05-30 11:03:42 -04:00
Aleix Conchillo Flaqué
b33897ffb9
SmallWebRTCTransport: don't initialize if a second StartFrame is received
2025-05-30 07:51:51 -07:00
Aleix Conchillo Flaqué
1c3d3f2f4b
WebsocketClientTransport: don't initialize if a second StartFrame is received
2025-05-30 07:51:51 -07:00
Aleix Conchillo Flaqué
9a5a1edb6b
WebsocketServerTransport: don't initialize if a second StartFrame is received
2025-05-30 07:51:51 -07:00
Aleix Conchillo Flaqué
f2eb869b02
FastAPIWebsocketTransport: don't initialize if a second StartFrame is received
2025-05-30 07:51:51 -07:00
Aleix Conchillo Flaqué
0c7e3cfcb2
LiveKitTransport: don't initialize if a second StartFrame is received
2025-05-30 07:51:51 -07:00
Aleix Conchillo Flaqué
24e19db29e
TavusTransport: don't initialize if a second StartFrame is received
2025-05-30 07:51:51 -07:00
Aleix Conchillo Flaqué
cad271068e
BaseInputTransport: handle StopFrame and pause pushing frames
2025-05-30 07:51:49 -07:00
Philipp Eisen
3425293115
Ensure correct formatting
2025-05-30 15:41:45 +02:00
Philipp Eisen
b712e6b9aa
Switch ttfb metric to use seconds instead
2025-05-30 11:13:26 +02:00
Martin Schweiger
b3652e6527
set vad_force_turn_endpoint to True by default
2025-05-30 17:07:54 +08:00
Philipp Eisen
bc97f397ef
Switch to using float instead of int, but keep ms
2025-05-30 10:27:20 +02:00
Martin Schweiger
e5da3f6e68
add tracing
2025-05-30 10:55:19 +08:00
Martin Schweiger
8400539acf
set formatted_finals true by default
2025-05-30 10:40:01 +08:00
Martin Schweiger
b5eac8dfed
add message to TranscriptionFrame result
2025-05-30 10:39:07 +08:00
Martin Schweiger
ba312b5591
Merge branch 'main' into m-ods/assemblyai-universal-streaming
2025-05-30 10:29:49 +08:00
Martin Schweiger
f23572b318
Merge branch 'main' into m-ods/assemblyai-universal-streaming
2025-05-30 10:11:02 +08:00
Martin Schweiger
db838634e7
fix: double finals bug
2025-05-30 10:00:31 +08:00
Martin Schweiger
7f2e848a5c
use FrameProcessor class methods
2025-05-30 09:40:46 +08:00
Martin Schweiger
096e854d50
remove .dict()
2025-05-30 09:31:20 +08:00
Martin Schweiger
3ffe8b3155
remove parse_obj
2025-05-30 09:29:51 +08:00
Mark Backman
a471f49b61
Merge pull request #1889 from pipecat-ai/mb/add-dtmf-aggregator
...
Add DTMFAggregator
2025-05-29 17:13:28 -04:00
Mark Backman
4d2a02f318
Refactor to create task on StartFrame, also cleanup
2025-05-29 17:10:54 -04:00
Mark Backman
0bec7db03b
Emit a BotInterruptionFrame when the first keypress of a sequence is received
2025-05-29 17:07:18 -04:00
Mark Backman
74827f983f
Add tests, improve frame timing
2025-05-29 17:07:18 -04:00
Mark Backman
0ed46f457e
Add DTMFAggregator
2025-05-29 17:07:17 -04:00
Aleix Conchillo Flaqué
36b731be73
Merge pull request #1915 from pipecat-ai/aleix/uvloop-event-loop
...
use uvloop as the new event loop on Linux and macOS
2025-05-29 14:06:44 -07:00
Aleix Conchillo Flaqué
62fbdd4e81
Merge pull request #1922 from pipecat-ai/aleix/output-transport-cleanup
...
output transports cleanup
2025-05-29 14:06:17 -07:00
