Commit Graph

148 Commits

Author SHA1 Message Date
Yousif
09aa168840 Merge branch 'pipecat-ai:main' into mcp-http-gemini-support 2025-07-01 23:54:42 -07:00
Pete
9c9d4b35a4 remove audio_transcriber from gemini.py
unecessary import removed.
2025-07-01 20:36:54 -04:00
getchannel
2ee935f784 Update gemini.py 2025-07-01 20:31:58 -04:00
getchannel
0e60385871 add FileAPI to gemini.py 2025-07-01 20:14:31 -04:00
vipyne
c7cbfe7a4f remove grounding metadata commits 2025-07-01 17:21:38 -05:00
vipyne
79e51051c7 New lint rules and remove unused example file 2025-07-01 16:27:25 -05:00
Pete
a63d0da528 Update gemini.py 2025-07-01 16:27:25 -05:00
getchannel
44d3bd30fa Add groundingMetadata and logging gemini.py 2025-07-01 16:27:25 -05:00
getchannel
bd7ca94196 Update gemini.py 2025-07-01 16:27:25 -05:00
getchannel
d45a07b5e5 add FileAPI to gemini.py 2025-07-01 16:27:25 -05:00
Yousif Astarabadi
58675f4d5a renamed clean schema to alternate schema 2025-07-01 11:50:12 -07:00
Pete
a297e4208e Merge branch 'main' into groundingMetadata 2025-06-30 19:48:55 -04:00
Mark Backman
0ecfa827e6 Improve docstrings for services and processors (#2087) 2025-06-28 13:39:45 -04:00
Yousif Astarabadi
86c26fd64c moved needs_mcp_clean_schema to LLMService 2025-06-26 20:09:12 -07:00
Mark Backman
01040ddcdd Merge pull request #2071 from pipecat-ai/mb/services-docstrings-update
Add/update docstrings to LLM services
2025-06-26 14:42:32 -04:00
Aleix Conchillo Flaqué
3de4f22d34 utils(asyncio): simplify watchdog helpers 2025-06-26 09:40:42 -07:00
Mark Backman
d123cd4b2b Update GeminiMultimodalLiveLLMService docstrings 2025-06-26 11:47:30 -04:00
Aleix Conchillo Flaqué
b860e94582 move things to new utils.asyncio package 2025-06-26 08:24:25 -07:00
Aleix Conchillo Flaqué
357934a644 watchdog timers are disabled by default use enable_watchdog_timers 2025-06-25 15:55:16 -07:00
Aleix Conchillo Flaqué
eb5ecab104 no need to call start_watchdog() only reset_watchdog() 2025-06-25 11:12:32 -07:00
Pete
1cf0b35ac1 Merge branch 'main' into groundingMetadata 2025-06-24 22:00:16 -04:00
Aleix Conchillo Flaqué
076a8938f0 add start_watchdog/reset_watchdog to tasks 2025-06-24 11:56:20 -07:00
Pete
e3fe040017 Update gemini.py 2025-06-21 14:43:15 -04:00
Pete
ae5e3e2dc4 Merge branch 'main' into groundingMetadata 2025-06-21 12:16:32 -04:00
Pete
8d55e13750 remove audio_transcriber from gemini.py
unecessary import removed.
2025-06-10 11:22:16 -04:00
Pete
737e8e79c9 Merge branch 'main' into groundingMetadata 2025-06-10 11:12:35 -04:00
Pete
4d977fede0 Merge branch 'main' into main 2025-06-10 11:07:59 -04:00
Mark Backman
31d084eb78 Reverting Gemini Live model back to gemini-2.0-flash-live-001 2025-06-02 13:29:05 -04:00
Aleix Conchillo Flaqué
40b52cadde LLMService: s/FunctionCallLLM/FunctionCallFromLLM/ s/FunctionCallRunner/FunctionCallRunnerItem/ 2025-05-31 13:57:52 -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
a50a407415 LLMService: run function calls sequentially 2025-05-31 13:57:35 -07:00
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
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
getchannel
43c6f1f5cd Add groundingMetadata and logging gemini.py 2025-05-30 18:01:15 -04:00
getchannel
40c7e3c52c Update gemini.py 2025-05-30 12:19:40 -04:00
Aleix Conchillo Flaqué
d203789490 add STT result field to TranscriptionFrame/InterimTranscriptionFrame 2025-05-29 11:21:44 -07:00
Mark Backman
ee143d5b3a Update GeminiMultimodalLiveLLMService to use Gemini 2.5 Flash Native Audio Dialog model 2025-05-22 18:13:41 -04:00
Aleix Conchillo Flaqué
a09bd648af avoid mutable default constructor values 2025-05-20 11:59:28 -07:00
Mark Backman
144ea36c81 Fix: Make LLMTokenUsage more robust 2025-05-18 07:41:16 -04:00
Mark Backman
fac6f526f7 Add comments and docstrings 2025-05-16 10:54:50 -04:00
Mark Backman
2f78d74ce6 Change Gemini Live to use Gemini provided usage metrics 2025-05-16 10:53:01 -04:00
Mark Backman
d3942dda52 Gemini Live to transcribe user audio 2025-05-16 10:53:01 -04:00
getchannel
cd4a893c65 add FileAPI to gemini.py 2025-05-09 10:50:27 -04:00
Mark Backman
8250736f5e Merge pull request #1708 from pipecat-ai/mb/gemini-user-context
Push GeminiMultimodalLiveLLMService TranscriptionFrame Upstream, remo…
2025-05-02 13:10:27 -04:00
Mark Backman
96d40903a9 Only send TTSStoppedFrame from Gemini when in AUDIO mode, only send one LLMFullResponseEndFrame 2025-05-02 10:18:53 -04:00
Mark Backman
38e2d37674 Restore TEXT modalities support to GeminiMultimodalLiveLLMService 2025-05-02 07:36:12 -04:00
Mark Backman
76d198151c Push GeminiMultimodalLiveLLMService TranscriptionFrame Upstream, remove direct context addition 2025-05-01 15:41:04 -04:00
Mark Backman
a1e1255f16 Strip newlines from generated user transcript 2025-04-30 18:27:46 -04:00
Mark Backman
c4f758725e Ignore TranscriptionFrames too 2025-04-30 18:22:43 -04:00