wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
1,555 Commits 276 Branches 111 Tags
be8ca505cdf609f6af5fffe1027de96d31a99d19
Commit Graph

206 Commits

Author SHA1 Message Date
Mark Backman
be8ca505cd Merge pull request #652 from pipecat-ai/khk/more-gemini 
Gemini new context manager and rewrite to use google data structures internally
 2024-10-24 13:47:38 -04:00
Kwindla Hultman Kramer
e032b0b70a gemini context aggregators 2024-10-23 18:44:09 -07:00
Mattie Ruth
d26751e968 add missing PipelineParams to enable the metrics (#645) 2024-10-23 16:46:46 -04:00
Mark Backman
46927805bc Update GladiaSTTService to use the Gladia V2 API 2024-10-21 07:10:38 -04:00
Mark Backman
1dbf4ff27d Add AssemblyAI STT service 2024-10-20 08:57:57 -04:00
Aleix Conchillo Flaqué
be4bdabdf4 examples: use OpenAILLMContext in all the examples 2024-10-19 18:24:00 -07:00
Aleix Conchillo Flaqué
3502509d3e move SileroVAD processor to processors package 2024-10-18 23:28:29 -07:00
Kwindla Hultman Kramer
07712cdb16 gemini function calling and partial implementation of standard context stuff 2024-10-18 17:14:57 -07:00
Aleix Conchillo Flaqué
4550545528 examples: use EndFrame() when the participant leaves 2024-10-18 11:18:03 -07:00
Aleix Conchillo Flaqué
c9318ecd5c examples: minor fixes 2024-10-17 16:15:09 -07:00
Aleix Conchillo Flaqué
8108423742 transport(livekit): force specifying a vad analyzer 
Don't default to SileroVADAnalyzer(). Also, resample to input sample rate.
 2024-10-17 14:06:43 -07:00
Aleix Conchillo Flaqué
2a37b2459a move vad package to audio.vad 2024-10-17 13:49:16 -07:00
Mark Backman
d1000f2fe4 Merge pull request #606 from pipecat-ai/mb/add-playht-options 
PlayHT: Add websocket TTS service; rename existing service to PlayHTHttpTTSService, upgrade client, add input params
 2024-10-17 16:46:59 -04:00
Mark Backman
da3810f1a2 Add websocket support for PlayHT 2024-10-17 15:41:33 -04:00
Aleix Conchillo Flaqué
e3eea0c02f vad: add support for interruption to SileroVAD processor 2024-10-17 10:48:25 -07:00
Mark Backman
45606e177c Add input options to PlayHT, upgrade to latest PlayHT model 2024-10-17 11:56:12 -04:00
Kwindla Hultman Kramer
280691b1b3 explanatory comment in 19-openai-realtime-beta.py 2024-10-16 14:27:48 -07:00
Kwindla Hultman Kramer
93c9e219ce fix for message handling bug on initialization 2024-10-16 12:40:20 -07:00
Aleix Conchillo Flaqué
edd44cc181 services(openai): rename OpenAILLMServiceRealtimeBeta to OpenAIRealtimeBetaLLMService 2024-10-16 10:20:19 -07:00
Kwindla Hultman Kramer
f7b7f0d680 Merge pull request #541 from pipecat-ai/khk/openai-realtime-beta 
openai realtime beta
 2024-10-14 21:02:06 -07:00
Kwindla Hultman Kramer
40b3e50815 fix system, consecutive same role, and empty message parsing for anthropic 2024-10-14 20:56:42 -07:00
Kwindla Hultman Kramer
6f2a464451 conversation save/load for openai, openai-realtime, and anthropic 2024-10-13 18:12:03 -07:00
Kwindla Hultman Kramer
9e95419301 much cleanup 2024-10-12 21:58:11 -07:00
Kwindla Hultman Kramer
f390ec9608 temp commit; debugging 2024-10-12 21:58:11 -07:00
Kwindla Hultman Kramer
ce8a83efba tools frame support and wip message resetting/loading 2024-10-12 21:58:11 -07:00
Kwindla Hultman Kramer
e5a2bf9564 context management improvements 2024-10-12 21:58:11 -07:00
Kwindla Hultman Kramer
31916ed9fd turn on/off openai vad 2024-10-12 21:58:11 -07:00
Kwindla Hultman Kramer
3a2fbc2b19 send user started/stopped speaking event from openai realtime events 
send user started/stopped speaking event from openai realtime events
 2024-10-12 21:58:11 -07:00
Kwindla Hultman Kramer
40dc546b81 function call fix and user transcription frames 2024-10-12 21:58:11 -07:00
Kwindla Hultman Kramer
7dfac0163b bits of pydantic 2024-10-12 21:58:11 -07:00
Kwindla Hultman Kramer
09a3c2a82d major functionality working (not configurable, occasional timing bugs maybe) 2024-10-12 21:58:11 -07:00
Kwindla Hultman Kramer
c32c65014b definitely broke something in the pipeline 2024-10-12 21:58:11 -07:00
Kwindla Hultman Kramer
b8898e449e lots of debugging statements. multiple function calls broken 2024-10-12 21:58:11 -07:00
Kwindla Hultman Kramer
d1f6d229ca space exploration prompt 2024-10-12 21:58:11 -07:00
Kwindla Hultman Kramer
4fa0318005 configurability via constructor 2024-10-12 21:58:11 -07:00
Kwindla Hultman Kramer
93ebb9d541 working 19-openai-realtime-beta.py example 2024-10-12 21:58:11 -07:00
Kwindla Hultman Kramer
16101c79c5 beginning of realtime impl 2024-10-12 21:58:11 -07:00
Kwindla Hultman Kramer
53451899a7 fix for Deepgram settings not merging 2024-10-11 21:07:39 -07:00
Aleix Conchillo Flaqué
8c01a900cd google: allow using GOOGLE_APPLICATION_CREDENTIALS 2024-10-02 11:56:01 -07:00
Mark Backman
3d642df2b0 Revert aligning voice_id name in TTS service constructor 2024-10-02 11:07:48 -04:00
Mark Backman
28643b453d Update to use LLM, STT, TTS subclasses and remove setter methods 2024-10-01 20:30:27 -04:00
Kwindla Hultman Kramer
92d8b37229 implement vision for openai 2024-09-30 21:49:29 -07:00
Kwindla Hultman Kramer
0d5cb84531 function calling testing and improvements 2024-09-30 20:59:28 -07:00
Kwindla Hultman Kramer
a5c73ec829 handle openai multiple function calls 2024-09-30 16:08:30 -07:00
Kwindla Hultman Kramer
5d63615b1b Merge pull request #528 from pipecat-ai/khk/sentence-splits 
TTS sentence aggregation fix
 2024-09-30 16:07:21 -07:00
Kwindla Hultman Kramer
ed607d5c4b typo fix 2024-09-30 16:05:32 -07:00
Kwindla Hultman Kramer
37da7e44cd whitespace fix 2024-09-30 16:05:32 -07:00
Aleix Conchillo Flaqué
c8995b82e5 all frame processors are asynchrnous 
In this commit we make all frame processors asynchronous, that is, they have an
internal queue and they push frames using a task from that queue.
 2024-09-30 15:11:21 -07:00
Kwindla Hultman Kramer
6b7f924af6 tts sentence aggregation fix 2024-09-30 14:33:08 -07:00
Mark Backman
97cba92fa5 Merge pull request #516 from pipecat-ai/mb/google-tts 
Add Google TTS
 2024-09-30 12:25:16 -04:00