Commit Graph

5051 Commits

Author SHA1 Message Date
Mark Backman
be6ea0dbf6 Code review feedback 2025-08-11 21:17:04 -04:00
Mark Backman
c4506523ab Refactor PlayHTHttpTTSService to use aiohttp 2025-08-11 19:58:25 -04:00
Aleix Conchillo Flaqué
07f104199c Merge pull request #2415 from pipecat-ai/aleix/moondream-2025-01-09
MoondreamService: update to revision 2025-01-09
2025-08-11 15:10:35 -07:00
Aleix Conchillo Flaqué
bc1949b4bf MoondreamService: update to revision 2025-01-09 2025-08-11 14:54:04 -07:00
Aleix Conchillo Flaqué
2035dd8b39 Merge pull request #2403 from pipecat-ai/aleix/system-frame-queue-priority-fix
FrameProcessor: fix system frame higher priorty and use a PriortyQueue
2025-08-11 13:57:57 -07:00
Aleix Conchillo Flaqué
24c8189327 Merge pull request #2405 from pipecat-ai/aleix/frame-processor-direct-mode
FrameProcessor: introduce direct mode
2025-08-11 13:57:34 -07:00
Mark Backman
998ac32627 Merge pull request #2413 from captaincaius/fix-stt-mute-filter-vad-frames-20250810
Add VADUserStartSpeakingFrame VADUserStopSpeakingFrame to STTMuteFilter (fix #2412)
2025-08-11 13:54:34 -07:00
Aleix Conchillo Flaqué
50645c1c4f README: recommend python 3.11-3.12
Python 3.11 has significant performance improvements compared to 3.10 which
makes Pipecat's asyncio heavy use  specially better.
2025-08-11 13:53:08 -07:00
Aleix Conchillo Flaqué
8ce29ee8f2 FrameProcessor: fix system frame higher priorty and use a PriortyQueue 2025-08-11 13:53:08 -07:00
Captain Caius
7b8aeef4cc update changelog 2025-08-11 12:45:54 -07:00
Aleix Conchillo Flaqué
6a24457f0e FrameProcessor: introduce direct mode
Direct mode avoids creating internal queues and tasks and processes frames right
away. This might be useful for some very simple processors.
2025-08-11 09:26:31 -07:00
Aleix Conchillo Flaqué
2c01c2b5b3 Merge pull request #2404 from pipecat-ai/aleix/examples-22-simplify-main-pipeline
examples(foundational): update 22 series with simple main pipelines
2025-08-11 09:14:39 -07:00
Aleix Conchillo Flaqué
1c2e114fa2 examples(foundational): update 22 series with simple main pipelines 2025-08-11 09:13:09 -07:00
Filipi da Silva Fuchter
0f137e36c2 Merge pull request #2399 from pipecat-ai/filipi/heygen_latency
Improving the latency of the `HeyGenVideoService`.
2025-08-11 09:13:10 -03:00
Filipi Fuchter
b7f12a96f1 Improving the latency of the HeyGenVideoService. 2025-08-11 09:11:17 -03:00
Filipi da Silva Fuchter
3331f71e17 Merge pull request #2398 from pipecat-ai/filipi/ttfb_metrics_video_services
Added TTFB metrics for `HeyGenVideoService` and `TavusVideoService`.
2025-08-11 09:09:27 -03:00
Filipi Fuchter
55d200e2d1 Added TTFB metrics for HeyGenVideoService and TavusVideoService. 2025-08-11 09:07:21 -03:00
Captain Caius
3fae00e067 Add VADUserStartSpeakingFrame VADUserStopSpeakingFrame to STTMuteFilter 2025-08-10 19:35:04 -07:00
Mark Backman
78cdefd191 Merge pull request #2410 from smokyabdulrahman/issue-2373
Support endpoint_id for AzureSTTService
2025-08-10 16:43:29 -07:00
Abdulrahman Alrahma
fc67cc3302 Support endpoint_id for AzureSTTService 2025-08-10 22:24:47 +01:00
Aleix Conchillo Flaqué
241ab19228 update uv.lock with numba dependency 2025-08-08 15:12:55 -07:00
Mark Backman
c08e8ec8fb Merge pull request #2391 from pipecat-ai/mb/readme-local-dev
Update README with local dev setup for contributors
2025-08-08 11:15:58 -07:00
Mark Backman
eb9bc9644e Merge pull request #2400 from pipecat-ai/mb/pin-numba-0.61.2
fix: pin numba to >=0.61.2
2025-08-08 11:15:22 -07:00
Mark Backman
3a306dae90 fix: pin numba to >=0.61.2 2025-08-08 10:52:47 -04:00
Mark Backman
c42cc8254f Update README with local dev setup for contributors 2025-08-07 22:07:35 -04:00
Aleix Conchillo Flaqué
a8e21f7d5d Merge pull request #2395 from pipecat-ai/aleix/examples-15-inherit-parallel-pipeline
examples(foundational): move 15/15a logic into its own processor
2025-08-07 17:59:28 -07:00
Aleix Conchillo Flaqué
c6ef8de578 scripts(evals): fix 14v-function-calling-openai.py 2025-08-07 17:57:47 -07:00
Aleix Conchillo Flaqué
fc571fba42 examples(foundational): move 15/15a logic into its own processor 2025-08-07 17:57:47 -07:00
Mark Backman
0502ee2b5a Merge pull request #2394 from pipecat-ai/mb/uv-lock
Update uv.lock
v0.0.79
2025-08-07 15:25:38 -07:00
Mark Backman
9ec047094b Update uv.lock 2025-08-07 18:24:47 -04:00
Mark Backman
d991c106c8 Merge pull request #2393 from pipecat-ai/mb/openai-dep
fix: pin openai package upper bound to <=1.99.1
2025-08-07 15:19:05 -07:00
Mark Backman
312fb23c89 fix: pin openai package upper bound to <=1.99.1 2025-08-07 18:00:25 -04:00
Aleix Conchillo Flaqué
4d7f21d44e Merge pull request #2392 from pipecat-ai/aleix/avoid-using-tts-say
deprecate TTSService.say() method
2025-08-07 13:55:49 -07:00
Aleix Conchillo Flaqué
ec25d0a7c9 examples(foundational): fix 20a-persistent-context-openai 2025-08-07 13:48:32 -07:00
Aleix Conchillo Flaqué
2b8218deaa examples(foundational): use TTSSpeakFrame instead of TTSService.say() 2025-08-07 13:48:32 -07:00
Aleix Conchillo Flaqué
11119430cd TTSService: deprecate say() method 2025-08-07 13:48:32 -07:00
kompfner
9ca79232c1 Merge pull request #2380 from pipecat-ai/pk/deprecate-llm-messages-frame
Deprecate `LLMMessagesFrame`, `LLMUserResponseAggregator`, and `LLMAssistantResponseAggregator`
2025-08-07 15:13:01 -04:00
Paul Kompfner
9ea06c33f7 Bump deprecation version of LLMMessagesFrame, LLMUserResponseAggregator, and LLMAssistantResponseAggregator (the deprecation slipped past the 0.0.78 release) 2025-08-07 14:56:50 -04:00
Paul Kompfner
30a1dd202e Move deprecation of LLMMessagesFrame, LLMUserResponseAggregator, and LLMAssistantResponseAggregator into the next release in the changelog 2025-08-07 14:55:11 -04:00
Paul Kompfner
809ab0b7b6 Improve printed deprecation warning 2025-08-07 14:45:35 -04:00
Paul Kompfner
2b5db9c562 Remove redundant deprecation warning in docstring 2025-08-07 14:45:35 -04:00
Paul Kompfner
b4a886b59f Remove redundant deprecation warning in docstring 2025-08-07 14:45:35 -04:00
Paul Kompfner
07eb00722b Fix langchain unit test 2025-08-07 14:45:35 -04:00
Paul Kompfner
96652b8fba Add new deprecations to changelog 2025-08-07 14:45:30 -04:00
Paul Kompfner
df1fcf0c68 Remove unused import 2025-08-07 14:43:37 -04:00
Paul Kompfner
711f740d9e Update UserResponseAggregator to avoid using the now-deprecated LLMUserResponseAggregator 2025-08-07 14:43:37 -04:00
Paul Kompfner
a0bda98c20 Update langchain to avoid using the now-deprecated LLMMessagesFrame, LLMUserResponseAggregator, and LLMAssistantResponseAggregator 2025-08-07 14:43:37 -04:00
Paul Kompfner
1c1bae35ab Mention deprecation in docstring for LLMMessagesFrame 2025-08-07 14:43:37 -04:00
Paul Kompfner
56c52c2cf2 Deprecate LLMUserResponseAggregator and LLMAssistantResponseAggregator, which depend on the now-deprecated LLMMessagesFrame. 2025-08-07 14:43:37 -04:00
Paul Kompfner
740aee1a1a Fix an issue in AnthropicLLMContext where we would never initialize turns_above_cache_threshold if we were upgrading from an OpenAILLMContext.
I noticed this when working on 22c-natural-conversation-mixed-llms.py
2025-08-07 14:43:37 -04:00