Commit Graph

  • 384814e640 Merge pull request #2456 from a6kme/patch-1 Aleix Conchillo Flaqué 2025-09-11 16:56:25 -07:00
  • ab4364b833 update CHANGELOG and fix formatting Aleix Conchillo Flaqué 2025-09-11 15:34:47 -07:00
  • fafdadad3c Merge pull request #2473 from TheNotary/adds-interim-transcription-frame-support Aleix Conchillo Flaqué 2025-09-11 15:33:38 -07:00
  • 05dc2fa916 updated CHANGELOG.md with GoogleTTSService updates Aleix Conchillo Flaqué 2025-09-11 14:36:21 -07:00
  • 0c30cc6ea6 Merge pull request #2547 from manishkjs/feat/google-tts-voice-cloning Aleix Conchillo Flaqué 2025-09-11 14:32:21 -07:00
  • c26d336e34 Merge pull request #2545 from pipecat-ai/aleix/aws-nova-sonic-pre-load-cue Aleix Conchillo Flaqué 2025-09-11 14:31:26 -07:00
  • 37b6198787 Merge pull request #2635 from pipecat-ai/mb/openai-tts-speed Mark Backman 2025-09-11 14:22:51 -07:00
  • 3c271da94c Merge pull request #2633 from pipecat-ai/pk/uv-readme-updates kompfner 2025-09-11 17:07:41 -04:00
  • be28d3f93b Merge pull request #2637 from pipecat-ai/pk/llm-context-evals-and-bug-fix kompfner 2025-09-11 17:00:07 -04:00
  • d2f210e960 Bundle Smart Turn v3 with Pipecat marcus-daily 2025-09-11 20:03:55 +01:00
  • 57add41971 tests: add unit test for MinWordsInterruptionStrategy Aleix Conchillo Flaqué 2025-09-11 13:00:03 -07:00
  • 74b38b59d6 tests(utils): allow passing PipelineParams to run_test() Aleix Conchillo Flaqué 2025-09-11 12:59:27 -07:00
  • dac58deffc Merge pull request #2636 from pipecat-ai/pk/uv-lock-update-for-smart-turn-v3 kompfner 2025-09-11 14:35:36 -04:00
  • aff11f5121 Fix missing import in llm_response_universal.py Paul Kompfner 2025-09-11 14:33:17 -04:00
  • a4023d3915 Update evals to include examples that exercise the universal LLMContext Paul Kompfner 2025-09-11 14:32:56 -04:00
  • d6543d244d uv.lock update for Smart Turn v3 Paul Kompfner 2025-09-11 14:07:17 -04:00
  • fafcd79870 OpenAITTSService: add speed arg Mark Backman 2025-09-11 13:53:52 -04:00
  • 6a717fbbd1 Updating the README to reflect that: - various dependencies that previously didn't work with Python 3.13 now seem to - ultravox isn't fully supported on macOS Paul Kompfner 2025-09-11 12:27:43 -04:00
  • 9b3f6927c2 Merge pull request #2621 from pipecat-ai/aleix/interruption-task-frame Aleix Conchillo Flaqué 2025-09-11 09:22:35 -07:00
  • 0b21f8a6bd FrameProcessor: add push_interruption_task_frame_and_wait() Aleix Conchillo Flaqué 2025-09-08 19:57:44 -07:00
  • 8249b014f0 frames: BotInterruptionFrame is deprecated, use InterruptionTaskFrame Aleix Conchillo Flaqué 2025-09-08 19:26:28 -07:00
  • 9d9f10ae0e frames: StartInterruptionFrame is deprecated, use InterruptionFrame Aleix Conchillo Flaqué 2025-09-08 19:07:25 -07:00
  • e27b23694d frames: add new TaskFrame Aleix Conchillo Flaqué 2025-09-08 18:55:32 -07:00
  • 66ce5fe6bd Ruff fixes marcus-daily 2025-09-11 15:20:06 +01:00
  • a9b53dc800 Update inference session options marcus-daily 2025-09-11 15:09:14 +01:00
  • 818352a300 Formatting marcus-daily 2025-09-11 15:06:37 +01:00
  • 3e9fc7be19 Update onnxruntime version marcus-daily 2025-09-11 15:05:30 +01:00
  • a2e76bcad8 Smart Turn V3 support marcus-daily 2025-08-18 14:54:52 +01:00
  • 8e8e42717b Add to and from phone information to the development runner Mark Backman 2025-09-09 21:29:48 -04:00
  • b31322e38e Merge pull request #2619 from pipecat-ai/pk/aws-universal-context kompfner 2025-09-11 09:33:08 -04:00
  • 6bb3cb2b83 demo: DelayProcessor hush/delayProcessorDemo James Hush 2025-09-11 16:05:08 +08:00
  • 305108be9a [TwilioFrameSerializer]: Add parameter validation Jessie Wei 2025-09-10 23:00:15 +00:00
  • 65ce5d0457 Add SelfClosingTagAggregator, example 45, and unit tests mb/break-time Mark Backman 2025-09-05 21:40:04 -04:00
  • 908325484d Merge pull request #2614 from pipecat-ai/aleix/readme-client-sdks-table Aleix Conchillo Flaqué 2025-09-10 10:21:18 -07:00
  • dd6ff789c7 Merge pull request #2628 from pipecat-ai/mb/fix-13-push-frame Mark Backman 2025-09-10 09:13:04 -07:00
  • f4938e0fad fix: 13 foundational examples now push frames from TranscriptionLogger Mark Backman 2025-09-10 10:40:10 -04:00
  • 2e1f397d17 Support TwilioFrameSerializer region/edge settings to that the call is terminated successfully for regions other than default us1 region Jessie Wei 2025-09-10 14:30:10 +00:00
  • e8f60c7c6f Handle missing rawResponse in transcription messages (#2623) James Hush 2025-09-10 15:03:23 +08:00
  • fedb8a201f Update 12d example to use LLMContext, now that AWS Bedrock supports it Paul Kompfner 2025-09-09 16:24:13 -04:00
  • 8ccd220a60 Add universal LLMContext support to AWSBedrockLLMService.run_inference() Paul Kompfner 2025-09-09 16:00:32 -04:00
  • fe79de8f27 When converting universal LLMContext messages to AWS Bedrock expected format, automatically update non-initial "system"-role messages to "user"-role messages, as we do in other non-OpenAI LLM services Paul Kompfner 2025-09-09 15:50:03 -04:00
  • 176573c342 Add to CHANGELOG AWS Bedrock's support for universal LLMContext Paul Kompfner 2025-09-09 15:31:56 -04:00
  • 75f9914f49 Add support for universal LLMContext to AWS Bedrock LLM service Paul Kompfner 2025-09-09 12:15:56 -04:00
  • f4d6715e32 Add foundational example using AWS Bedrock with universal LLMContext Paul Kompfner 2025-09-09 10:49:51 -04:00
  • 38f6e33f97 Merge pull request #2598 from pipecat-ai/pk/deprecate-vision-image-raw-frame kompfner 2025-09-08 17:13:28 -04:00
  • 1c3e4e34e5 Minor fix to AWS Bedrock console logging to handle image messages in the context Paul Kompfner 2025-09-08 17:10:11 -04:00
  • 623c660027 Remove debugging comment Paul Kompfner 2025-09-08 16:59:24 -04:00
  • a3e65ab3b5 The VisionImageRawFrame removal and corresponding VisionImageFrameAggregator deprecation will now happen in version 0.0.85 Paul Kompfner 2025-09-08 16:58:49 -04:00
  • f3a4b416df Remove VisionImageRawFrame, which was previously being handled directly by the LLM services, and deprecate the associated VisionImageFrameAggregator. Paul Kompfner 2025-09-05 12:28:28 -04:00
  • aa471a4ef5 update CHANGELOG with LiveKitTransport updates Aleix Conchillo Flaqué 2025-09-08 13:53:21 -07:00
  • d55133a44f Merge pull request #2604 from alexyzhou/feature/livekit_video_and_bug_fix Aleix Conchillo Flaqué 2025-09-08 13:51:14 -07:00
  • 0f1cf81691 README: update clients' table Aleix Conchillo Flaqué 2025-09-08 11:38:16 -07:00
  • ac4d335799 Merge pull request #2613 from pipecat-ai/pk/mistral-message-fixups kompfner 2025-09-08 13:59:54 -04:00
  • e65385c151 Tweak the Mistral-specific context messages fixup logic to handle the (mostly academic) possibility of a "tool" message appearing at the end Paul Kompfner 2025-09-08 13:55:09 -04:00
  • 0bb7df7a6b Remove stray debugging message Paul Kompfner 2025-09-08 13:38:26 -04:00
  • daee1ddf3b Apply additional fixups to context messages to meet Mistral-specific requirements Paul Kompfner 2025-09-08 11:23:25 -04:00
  • d1f72c1c0b Added usage metrics Adithya Suresh 2025-09-08 14:44:25 +10:00
  • 1cccb97ccf Merge pull request #2608 from pipecat-ai/aleix/deprecate-noisereducefilter Aleix Conchillo Flaqué 2025-09-07 20:54:09 -07:00
  • d7794abf21 audio(filters): deprecate NoisereduceFilter Aleix Conchillo Flaqué 2025-09-06 19:31:38 -07:00
  • 6a6a63a532 Merge pull request #2607 from pipecat-ai/aleix/scripts-evals-improve-eval-prompt Aleix Conchillo Flaqué 2025-09-07 20:49:43 -07:00
  • 6edb6fed41 Merge pull request #2606 from pipecat-ai/mb/quickstart-lockfile Mark Backman 2025-09-07 06:10:14 -07:00
  • a537382816 Add OpenAIRealtimeLLMService, AzureRealtimeLLMService (#2596) Mark Backman 2025-09-07 06:09:57 -07:00
  • 46deaada70 scripts(evals): allow user to talk and only eval when needed Aleix Conchillo Flaqué 2025-09-06 19:19:08 -07:00
  • 7366b1aee0 adds missing InterimTranscriptionFrame import TheNotary 2025-09-06 14:40:19 -05:00
  • dbc52bc6b0 Remove uv.lock from quickstart Mark Backman 2025-09-06 11:13:50 -04:00
  • d6432589f6 fix: fix format and lint by ruff Alex Zhou 2025-09-06 10:50:47 +08:00
  • 13b73d4406 feat: Add support for pipecat video stream; fix the bug of duplicate participants when connecting; fix the bug of RTVI messages sent via livekit messages; Alex Zhou 2025-09-06 10:41:33 +08:00
  • 85d8282f7e Merge pull request #2602 from pipecat-ai/aleix/pipecat-0.0.84 v0.0.84 Aleix Conchillo Flaqué 2025-09-05 19:35:26 -07:00
  • 070690ec64 update CHANGELOG for 0.0.84 Aleix Conchillo Flaqué 2025-09-05 18:22:50 -07:00
  • b9c96fd623 Merge pull request #2601 from pipecat-ai/aleix/daily-python-0.19.9 Aleix Conchillo Flaqué 2025-09-05 18:21:49 -07:00
  • f8b2ab6331 pyproject: update daily-python to 0.19.9 Aleix Conchillo Flaqué 2025-09-05 18:11:06 -07:00
  • ea3f7e3c34 Merge pull request #2600 from pipecat-ai/mb/livekit-dtmf Mark Backman 2025-09-05 15:25:32 -07:00
  • 2f44f88b08 LiveKitTransport: Add support to send DTMF Mark Backman 2025-09-05 18:11:27 -04:00
  • 25747a001b Merge pull request #2599 from pipecat-ai/mb/fix-daily-dtmf Mark Backman 2025-09-05 15:20:05 -07:00
  • fbe4338440 DTMF: Add support for native DTMF implementation where available Mark Backman 2025-09-05 17:50:24 -04:00
  • 64b4c65728 Merge pull request #2595 from pipecat-ai/filipi/heygen_quality Filipi da Silva Fuchter 2025-09-05 17:19:25 -03:00
  • 29442969a9 Merge pull request #2597 from pipecat-ai/pk/fix-anthropic-tool-less-usage kompfner 2025-09-05 15:30:29 -04:00
  • dc2e1d4ad3 Fix Anthropic tool-less usage Paul Kompfner 2025-09-05 11:47:31 -04:00
  • 5477dfcbea Improving HeyGen example video quality. Filipi Fuchter 2025-09-05 11:30:01 -03:00
  • 516f0e08ab Merge pull request #2590 from pipecat-ai/pk/gemini-multimodal-live-doesnt-support-llm-context kompfner 2025-09-05 09:22:33 -04:00
  • 5959637ff3 Clean up imports hush/hedgeLLM James Hush 2025-09-05 17:14:01 +08:00
  • f9bfadbc6d Clean up code James Hush 2025-09-05 17:05:03 +08:00
  • 4966ca3655 This seems to work James Hush 2025-09-05 16:59:37 +08:00
  • 6a11707604 Save changes James Hush 2025-09-05 16:55:09 +08:00
  • 604b710ee9 Fix lint James Hush 2025-09-05 16:14:49 +08:00
  • c439d7981f example: hedge llms James Hush 2025-09-05 16:13:46 +08:00
  • 246f9f3325 Raise an error when attempting to use Gemini Multimodal Live with universal LLMContext. This is exactly the same error we already have for the other s2s models, AWS Nova Sonic and OpenAI Realtime, it was just missing from this service. Paul Kompfner 2025-09-04 16:47:08 -04:00
  • 4699ee8d86 docs: add docstring for voice_cloning_key and update CHANGELOG Manish Kumar 2025-09-04 22:45:51 +05:30
  • 3d850e8cc5 Merge pull request #2574 from pipecat-ai/pk/expand-universal-llm-context-support-to-anthropic kompfner 2025-09-04 13:09:44 -04:00
  • 6e734a37f9 Fix a bug in AWSBedrockLLMService.run_inference(); it was expecting the wrong format for the system instruction Paul Kompfner 2025-09-04 12:59:39 -04:00
  • f72ca2fd7d Remove unnecessary system_instruction argument from run_inference() methods Paul Kompfner 2025-09-04 12:31:33 -04:00
  • 0826d72f74 Add deprecation warning for using enable_prompt_caching_beta param Paul Kompfner 2025-09-04 11:47:07 -04:00
  • ba5ebfa0ec Fixed subtle CHANGELOG conflict after release of 0.0.83: universal LLMContext support for Anthropic didn't make that release. Also, some automatic Prettier fixes. Paul Kompfner 2025-09-04 10:02:49 -04:00
  • dc3412b2df Bump a deprecation to 0.0.84, as 0.0.83 just shipped Paul Kompfner 2025-09-04 09:54:55 -04:00
  • b2e9fd9341 Rename Anthropic enable_prompt_caching_beta parameter to just enable_prompt_caching Paul Kompfner 2025-09-04 09:49:15 -04:00
  • c11b207c97 Add Anthropic to CHANGELOG list of services newly supporting runtime LLM switching Paul Kompfner 2025-09-04 09:18:53 -04:00
  • d6205027cf Trivial cleanup Paul Kompfner 2025-09-03 22:45:48 -04:00
  • 986160c077 Fix a bug where the Anthropic adapter's merge-consecutive-messages-with-the-same-role logic was unintentionally affecting the source LLMContext's messages, resulting in more and more duplication of text with each inference Paul Kompfner 2025-09-03 22:44:08 -04:00
  • b56ff86fee Minor refactor of AnthropicLLMAdapter cache-control-marker-adding logic (without really changing its behavior) Paul Kompfner 2025-09-03 22:15:02 -04:00
  • 5c574eaad9 Add support for universal LLMContext to Anthropic LLM service Paul Kompfner 2025-09-03 10:58:41 -04:00