Commit Graph

  • c1a1d40f9a Refactoring services to use push_error. Filipi Fuchter 2025-11-19 15:54:43 -03:00
  • ede995c563 Merge branch 'main' into filipi/improve_error_handler Filipi Fuchter 2025-11-19 15:42:35 -03:00
  • cc861d6b70 Refactor WebSocket connection code in RimeNonJsonTTSService for improved readability Gokul Js 2025-11-19 22:46:36 +05:30
  • de4e9c54f6 Increase WebSocket max size limit in RimeNonJsonTTSService to enhance data handling capacity Gokul Js 2025-11-19 22:44:50 +05:30
  • 20dd160c1e cleanup vp-minimax-2962 vipyne 2025-11-19 11:10:27 -06:00
  • 2a92e4f856 Update CHANGELOG vipyne 2025-11-19 11:02:13 -06:00
  • 13f1507c06 Update src/pipecat/services/minimax/tts.py Vanessa Pyne 2025-11-05 09:11:55 -06:00
  • ce09c6f6ff minimax updates vipyne 2025-11-04 15:40:38 -06:00
  • 9694d8d687 docs(minimax): add API endpoint comment for west US region minimax 2025-11-04 10:52:13 +08:00
  • 77be2bd013 feat(minimax): comprehensive updates to TTS service minimax 2025-11-04 02:04:25 +08:00
  • da671cd232 Fix whitespace inconsistency in audio flushing method of RimeNonJsonTTSService Gokul Js 2025-11-19 22:19:36 +05:30
  • 1d9696e614 Add audio flushing after sending text in RimeNonJsonTTSService Gokul Js 2025-11-19 22:19:00 +05:30
  • 510f3df6b7 Merge pull request #3091 from pipecat-ai/vp-fix-mcp-examples Vanessa Pyne 2025-11-19 10:35:08 -06:00
  • 68292bd75f rename MCP foundational examples vipyne 2025-11-19 10:34:13 -06:00
  • 42423bff41 update MCP foundational examples vipyne 2025-11-18 19:29:32 -06:00
  • c3d2a25229 Merge pull request #3082 from pipecat-ai/aleix/pipecat-0.0.95 v0.0.95 Aleix Conchillo Flaqué 2025-11-18 21:17:07 -08:00
  • cf1a9c1548 update CHANGELOG for 0.0.95 Aleix Conchillo Flaqué 2025-11-18 10:54:44 -08:00
  • 51ba245e10 scripts(evals): fix EVAL_CONVERSATION/EVAL_WEATHER eval Aleix Conchillo Flaqué 2025-11-18 14:13:34 -08:00
  • 39b4e61837 SimliVideoService: fix connection issue Aleix Conchillo Flaqué 2025-11-18 13:50:47 -08:00
  • ceaf53fdb0 LLMContext: async create_image_message/create_audio_message fixes Aleix Conchillo Flaqué 2025-11-18 12:08:09 -08:00
  • f93276c64f Merge pull request #3090 from pipecat-ai/revert_function_calling_pr Aleix Conchillo Flaqué 2025-11-18 19:40:58 -08:00
  • 62a0f0c0f5 Merge pull request #3070 from ivaaan/hume-timestamps Mark Backman 2025-11-18 19:56:20 -05:00
  • 793aca6b8b Revert "Ensure that the function call results respect the previous LLM context." Filipi Fuchter 2025-11-18 21:38:49 -03:00
  • 1fcaf3a4bf Revert "Searching in both _function_calls_context_messages and context messages when updating the result." Filipi Fuchter 2025-11-18 21:38:49 -03:00
  • afeef94900 Remove unused audio_format parameter from extra settings in RimeNonJsonTTSService Gokul Js 2025-11-19 04:55:14 +05:30
  • 860d9c4f29 Refactor _update_settings method in RimeNonJsonTTSService for improved readability and maintainability Gokul Js 2025-11-19 04:53:27 +05:30
  • 4393191166 Add method to update settings in RimeNonJsonTTSService Gokul Js 2025-11-19 04:53:21 +05:30
  • 600cd18cb7 Ensure to push LLMFullResponseEndFrame if the sentence is empty. filipi/pushing_llm_end_frame Filipi Fuchter 2025-11-18 19:50:14 -03:00
  • 88daad524e Refactor whitespace in RimeNonJsonTTSService to improve code readability Gokul Js 2025-11-19 03:43:49 +05:30
  • 66c58f8155 fix Gokul Js 2025-11-19 03:40:59 +05:30
  • 7bbb5be910 format fix Gokul Js 2025-11-19 03:35:54 +05:30
  • 0dcb65bd56 add run tts methos for rimeNonJsonTTs Gokul Js 2025-11-19 03:34:58 +05:30
  • 2784b0f438 Add RimeNonJsonTTSService for non-JSON WebSocket API support Gokul Js 2025-11-19 03:24:57 +05:30
  • fdf3c8b4cf Refactoring the services to use push_error and push_error_frame Filipi Fuchter 2025-11-18 18:43:30 -03:00
  • 50bef86d33 Refactoring the services to use push_error and push_error_frame Filipi Fuchter 2025-11-18 18:22:45 -03:00
  • 79f43ece74 Creating push_error_frame Filipi Fuchter 2025-11-18 18:20:52 -03:00
  • 08b2365244 Starting to refactor how we are handling the errors. Filipi Fuchter 2025-11-18 17:50:47 -03:00
  • 6484855139 fix changelog ivaaan 2025-11-18 21:47:46 +01:00
  • 771469b834 fix changelog ivaaan 2025-11-18 21:39:29 +01:00
  • a60618b0ca Merge pull request #3080 from pipecat-ai/pk/assistant-aggregator-handles-mixed-includes-inter-frame-spaces-text kompfner 2025-11-18 15:24:27 -05:00
  • 3d21faaac2 LLMAssistantAggregator now properly aggregates text that might be a mix of includes_inter_frame_spaces=True and includes_inter_frame_spaces=False frames Paul Kompfner 2025-11-18 11:55:36 -05:00
  • f325eeb95b rm TranscriptProcessor 2 ivaaan 2025-11-18 20:41:10 +01:00
  • 4c3fd42b1c fix changelog ivaaan 2025-11-18 20:36:45 +01:00
  • c2309efd7e rm TranscriptProcessor ivaaan 2025-11-18 20:32:27 +01:00
  • 4ae1819645 Update src/pipecat/services/hume/tts.py Ivan A 2025-11-18 20:30:44 +01:00
  • a38f208135 Update examples/foundational/07ae-interruptible-hume.py Ivan A 2025-11-18 20:30:28 +01:00
  • d1eb837890 Merge pull request #3081 from pipecat-ai/mb/fix-30-tts-text-frame-log Mark Backman 2025-11-18 14:10:56 -05:00
  • 153201542b Fix foundational 30 example to output TTSTextFrames synced to audio Mark Backman 2025-11-18 13:29:06 -05:00
  • 9137e50043 Merge pull request #3053 from pipecat-ai/filipi/function_calls Filipi da Silva Fuchter 2025-11-18 14:59:01 -03:00
  • 8dbe119a73 Merge branch 'main' into hume-timestamps Ivan A 2025-11-18 18:38:24 +01:00
  • 26f96d0be8 upd example ivaaan 2025-11-18 18:31:38 +01:00
  • 9944e6faf0 upd service based on Mark's suggestions ivaaan 2025-11-18 18:25:53 +01:00
  • c1573c1f76 Merge pull request #3078 from pipecat-ai/aleix/llm-context-create-image-audio-async Aleix Conchillo Flaqué 2025-11-18 09:06:51 -08:00
  • 9f45ad4d2e LLMContext: create_image_message/create_audio_message are now async Aleix Conchillo Flaqué 2025-11-18 08:38:45 -08:00
  • 40ed9a7e25 Improve SimpleTextAggregator to handle multi-sentence chunks mb/impmrove-simple-text-aggregator Mark Backman 2025-11-14 09:08:57 -05:00
  • fccc91e923 Searching in both _function_calls_context_messages and context messages when updating the result. Filipi Fuchter 2025-11-18 11:50:28 -03:00
  • a510b276e6 Ensure that the function call results respect the previous LLM context. Filipi Fuchter 2025-11-18 11:37:57 -03:00
  • 6481094638 Merge pull request #3058 from pipecat-ai/mb/add-camera-screen-support-smallwebrtc Mark Backman 2025-11-18 09:22:36 -05:00
  • 3132e12265 Add camera and screen capture support to dev runner for SmallWebRTC Mark Backman 2025-11-14 10:48:52 -05:00
  • 12af3f79d0 Merge pull request #3060 from pipecat-ai/aleix/consumer-queue-frames Aleix Conchillo Flaqué 2025-11-18 00:54:18 -08:00
  • 4835617b16 ConsumerProcessor: queue frames internally instead of pushing them Aleix Conchillo Flaqué 2025-11-14 15:20:01 -08:00
  • 9283108240 Merge pull request #3073 from pipecat-ai/aleix/base-text-filter-only-filter Aleix Conchillo Flaqué 2025-11-17 23:29:26 -08:00
  • 515eaeeb1a Merge pull request #3074 from pipecat-ai/pk/tweak-moondream-example kompfner 2025-11-17 16:52:18 -05:00
  • 5095fc6a64 Update Moondream example so that Moondream service output makes it into the context, even if the TTS service is disabled Paul Kompfner 2025-11-17 15:16:19 -05:00
  • 7eedb33d50 BaseTextFilter: only require subclasses to implement filter() Aleix Conchillo Flaqué 2025-11-17 11:19:04 -08:00
  • 47f78df497 Merge pull request #3071 from pipecat-ai/filipi/small_webrtc_custom_data Filipi da Silva Fuchter 2025-11-17 15:50:11 -03:00
  • 74154b26a2 Mentioning the SmallWebRTCTransport fix in the readme. Filipi Fuchter 2025-11-17 15:39:07 -03:00
  • 0c3c26b7b8 Passing the custom request_data to the SmallWebRTCRunnerArguments body. Filipi Fuchter 2025-11-17 15:20:09 -03:00
  • 64417ef4ff Merge pull request #3061 from pipecat-ai/pk/greatly-simplify-inter-frame-spaces-logic kompfner 2025-11-17 10:47:56 -05:00
  • f3b254e335 D'oh! My TTS "inter-frame-spaces" logic was *way* overcomplicated (and fundamentally mistaken, though it happened to work) Paul Kompfner 2025-11-14 21:39:18 -05:00
  • f27119a712 Merge pull request #3069 from pipecat-ai/filipi/fix_riva Filipi da Silva Fuchter 2025-11-17 11:48:15 -03:00
  • 2a51d0f1e5 add changelog ivaaan 2025-11-17 15:20:06 +01:00
  • 9156e21727 fix formatting ivaaan 2025-11-17 14:00:03 +01:00
  • a5145be16e Merge pull request #3038 from pipecat-ai/filipi/flux_improvements Filipi da Silva Fuchter 2025-11-17 09:57:43 -03:00
  • b104a59b10 Mentioning the Deepgram Flux improvements in the changelog. Filipi Fuchter 2025-11-17 09:54:39 -03:00
  • 04dbbabc03 Introduced a minimum confidence parameter in DeepgramFluxSTTService to avoid generating transcriptions below a defined threshold. Filipi Fuchter 2025-11-17 09:54:30 -03:00
  • 19cc0177b8 Refactored DeepgramFluxSTTService to automatically reconnect if sending a message fails. Filipi Fuchter 2025-11-17 09:54:20 -03:00
  • 77cd106795 Extracted the logic for retrying connections, and create a new send_with_retry method inside WebSocketService. Filipi Fuchter 2025-11-17 09:54:08 -03:00
  • 71869a116d fix errors ivaaan 2025-11-17 13:51:04 +01:00
  • 2f2bde9856 add timestamps to example ivaaan 2025-11-17 13:40:03 +01:00
  • 7de8838deb add word-level timestamp support to Hume service ivaaan 2025-11-17 13:25:12 +01:00
  • 9bf88bbf14 Fixing RivaTTSService error handler. Filipi Fuchter 2025-11-17 07:43:30 -03:00
  • 1b28fc8e8e Fix: Ensure EndFrame propagates through AIService before stop() hush/endFrameTTS James Hush 2025-11-17 11:09:42 +01:00
  • d9dcf277cd pass through session request data correctly jpt/smallwebrtc-requestdata-fix Jon Taylor 2025-11-16 04:30:26 +00:00
  • e8640d84ae test fix now that we send an aggregated text frame for non word-by-word tts services bot-output mattie ruth backman 2025-11-14 17:13:08 -05:00
  • 35ff44b799 Merge pull request #3059 from pipecat-ai/mb/remove-llm-tracing-fallback Mark Backman 2025-11-14 14:07:40 -05:00
  • 23e4e29999 CHANGELOG fixes mattie ruth backman 2025-11-14 13:57:49 -05:00
  • 713b488bb6 Final PR Feedback changes mattie ruth backman 2025-11-14 13:51:31 -05:00
  • 71b87fd420 add transformers to initialization args mattie ruth backman 2025-11-13 15:43:37 -05:00
  • 3f269f9834 Add backwards compatibility for add_pattern_pair mattie ruth backman 2025-11-13 12:53:56 -05:00
  • 4c698777f3 PR Feedback mattie ruth backman 2025-11-13 12:44:10 -05:00
  • 5ca04ad741 CHANGELOG updates mattie ruth backman 2025-11-12 11:36:13 -05:00
  • 9a3902a82c Introducing a new processor: LLMTextProcessor mattie ruth backman 2025-11-12 10:54:04 -05:00
  • 8ab0c92681 Rename AggregatedLLMTextFrame to AggregatedTextFrame and made built-in types an enum mattie ruth backman 2025-11-07 10:32:54 -05:00
  • 124f147a37 CHANGELOG improvements mattie ruth backman 2025-11-05 14:26:23 -05:00
  • ed808a9246 Fix new test and str version of PatternMatch mattie ruth backman 2025-11-05 14:44:58 -05:00
  • e9de9daf8c Update PatternPairAggregator patterns to replace pattern_id with type to simplify the API mattie ruth backman 2025-11-04 16:22:34 -05:00
  • 82b9c4f0b6 various PR Review fixes: mattie ruth backman 2025-11-04 09:13:45 -05:00
  • 5dfe20be91 Update Changelog mattie ruth backman 2025-10-31 15:34:48 -04:00
  • 0d2c5286fa Support customization over the way the assistant aggregator aggregates LLMTextFrames when tts_skip is on mattie ruth backman 2025-10-30 16:58:47 -04:00