Commit Graph

  • 25b595e125 add suggestions Fabrice Lamant 2025-08-29 14:51:20 +02:00
  • edc8cc1e69 remove sample_rate from GladiaInputParams Fabrice Lamant 2025-08-29 14:00:00 +02:00
  • 633dd69dee feat: add logging for pipecat version and session url Fabrice Lamant 2025-08-29 13:47:16 +02:00
  • 1a1d5a1081 feat: add missing config params Fabrice Lamant 2025-08-29 13:46:44 +02:00
  • c1b8d2acab Merge pull request #2532 from pipecat-ai/aleix/universal-dtmf-support Aleix Conchillo Flaqué 2025-08-28 21:04:13 -07:00
  • ea368e4c5f scripts(dtmf): added generate_dtmf.sh to generate DTMF wav files Aleix Conchillo Flaqué 2025-08-28 16:10:01 -07:00
  • f03deb6ecc DailyTransport: remove send_dtmf() and write_dtmf() Aleix Conchillo Flaqué 2025-08-28 15:37:41 -07:00
  • 0e01ac8ef6 BaseOutputTransport: implement generic write_dtmf() Aleix Conchillo Flaqué 2025-08-28 15:34:14 -07:00
  • 5787743ab3 audio(dtmf): added DTMF audio files and load_dtmf_audio() Aleix Conchillo Flaqué 2025-08-28 15:32:30 -07:00
  • 79be0695dd make sure warnings are always displayed Aleix Conchillo Flaqué 2025-08-28 15:30:23 -07:00
  • a5c5e069ba move pipecat.frames.frames.KeypadEntry to pipecat.audio.dtmf.types.KeypadEntry Aleix Conchillo Flaqué 2025-08-28 15:29:20 -07:00
  • 77c34076f7 Merge pull request #2531 from pipecat-ai/aleix/pipecat-0.0.82 v0.0.82 Aleix Conchillo Flaqué 2025-08-28 13:04:41 -07:00
  • d67cece356 update CHANGELOG for 0.0.82 Aleix Conchillo Flaqué 2025-08-28 11:05:19 -07:00
  • 275c8b59c5 MistralLLMService: fix build_chat_completion_params() Aleix Conchillo Flaqué 2025-08-28 12:03:25 -07:00
  • 5ebcea2a3b scripts(eval): change "result" function call parameter Aleix Conchillo Flaqué 2025-08-28 11:38:34 -07:00
  • 64f2135ddc examples(14f): use default models Aleix Conchillo Flaqué 2025-08-28 11:38:18 -07:00
  • a74231f036 Merge pull request #2515 from pipecat-ai/pk/llm-run-frame kompfner 2025-08-28 10:01:00 -04:00
  • 189749b579 Add LLMRunFrame to trigger an LLM response, replacing context_aggregator.user().get_context_frame() Paul Kompfner 2025-08-26 16:39:23 -04:00
  • 901899aa19 PipelineTask: handle BotInterruptionFrame in PipelineTask aleix/pipelinetask-handle-botinterruption Aleix Conchillo Flaqué 2025-08-27 18:17:29 -07:00
  • 947faf8a39 tests: allow PipelineParams instead of individual arguments Aleix Conchillo Flaqué 2025-08-27 19:01:15 -07:00
  • e384ca949e Merge pull request #2512 from pipecat-ai/aleix/textframe-skip-tts Aleix Conchillo Flaqué 2025-08-27 16:26:03 -07:00
  • eb248fedc1 add skip_tts to LLMFullResponseStartFrame/LLMFullResponseEndFrame Aleix Conchillo Flaqué 2025-08-26 14:47:19 -07:00
  • 16f57be72c LLMConfigureOutputFrame: allow configuring LLM output Aleix Conchillo Flaqué 2025-08-26 14:01:48 -07:00
  • 5803936838 TextFrame: add skip_tts field Aleix Conchillo Flaqué 2025-08-26 12:38:30 -07:00
  • d9837dd1e5 Merge pull request #2527 from pipecat-ai/aleix/daily-python-0.19.8 Aleix Conchillo Flaqué 2025-08-27 16:22:49 -07:00
  • e48c9fc3e2 pyproject: update daily-python to 0.19.8 Aleix Conchillo Flaqué 2025-08-27 15:59:30 -07:00
  • 3c4454a33e Merge pull request #2526 from pipecat-ai/aleix/pipeline-task-wait-for-startframe Aleix Conchillo Flaqué 2025-08-27 15:57:10 -07:00
  • 2a0780e6ef PipelineTask: wait for StartFrame to reach end of pipeline Aleix Conchillo Flaqué 2025-08-27 14:06:44 -07:00
  • 5e121346fb Merge pull request #2516 from pipecat-ai/aleix/rtvi-client-version-check Aleix Conchillo Flaqué 2025-08-27 14:02:14 -07:00
  • 2bdca8d22c RTVIProcessor: make check sure client version is set Aleix Conchillo Flaqué 2025-08-26 15:43:15 -07:00
  • 1f5888bcf7 Merge pull request #2517 from pipecat-ai/aleix/unify-get-messages-for-logging Aleix Conchillo Flaqué 2025-08-27 12:49:36 -07:00
  • 3d09f9a2af Merge pull request #2524 from pipecat-ai/mb/cartesia-speed Mark Backman 2025-08-27 12:47:29 -07:00
  • cd3563bb16 unify get_messages_for_logging() Aleix Conchillo Flaqué 2025-08-26 16:20:38 -07:00
  • 3e79ef4118 Merge pull request #2525 from pipecat-ai/aleix/daily-fix-send-dtmf Aleix Conchillo Flaqué 2025-08-27 12:44:27 -07:00
  • 2613da1a1f PipelineTask: increase CANCEL_TIMEOUT_SECS to 20 Aleix Conchillo Flaqué 2025-08-27 11:13:42 -07:00
  • 41d40f9a11 DailyTransport: make sure we have a client before joining/leaving Aleix Conchillo Flaqué 2025-08-27 11:11:15 -07:00
  • 74af2b6aa4 DailyTransport: fix sending DTMF tones Aleix Conchillo Flaqué 2025-08-27 10:41:10 -07:00
  • f7d9f32b0f Cartesia: update speed InputParam Mark Backman 2025-08-27 13:34:28 -04:00
  • 6074af60ef Merge pull request #2521 from pipecat-ai/mb/update-quickstart-pcc-docker Mark Backman 2025-08-27 08:13:31 -07:00
  • 7ef6893c0d Merge pull request #2523 from sam-s10s/fix/connection-none Mark Backman 2025-08-27 08:09:46 -07:00
  • cc5557e051 changelog Sam Sykes 2025-08-27 16:07:31 +01:00
  • 06f7a92c99 fix to finally statement Sam Sykes 2025-08-27 14:43:07 +01:00
  • 61a333ccae Update quickstart to use pcc docker command Mark Backman 2025-08-26 21:29:13 -04:00
  • fc3d84dff7 Merge pull request #2501 from pipecat-ai/mb/aws-tts-more-flexible-auth Mark Backman 2025-08-26 18:05:37 -07:00
  • 86a37d8cea Add changelog entry for SentryMetrics missing import fix Mark Backman 2025-08-26 21:00:16 -04:00
  • 3f66acf9f1 Merge pull request #2520 from geluso/bugfix-missing-asyncio-import Mark Backman 2025-08-26 17:59:25 -07:00
  • facfaa2dd4 AWSBedrockLLMService: Allow setting auth credentials via env vars Mark Backman 2025-08-25 10:53:40 -04:00
  • 8250c381d1 AWSPollyTTSService: allow setting auth credentials through provider chain Mark Backman 2025-08-25 10:53:12 -04:00
  • c6235a34a9 fix: add missing asyncio import to SentryMetrics mb/fix-sentry-asyncio Mark Backman 2025-08-26 20:55:52 -04:00
  • 32f9e48865 add missing import asyncio Steve Geluso 2025-08-26 17:40:11 -07:00
  • 76eef837b6 Removing watchdog from SarvamTTSService. Filipi Fuchter 2025-08-26 18:29:10 -03:00
  • c9aaa463b7 Mentioning the recent SarvamTTSService changes in the changelog. Filipi Fuchter 2025-08-26 18:19:19 -03:00
  • 6d582e41b7 Added Sarvam TTS Websocket Implementation (#2356) pratham-sarvam 2025-08-27 02:40:26 +05:30
  • ca29f62bff Merge pull request #2510 from pipecat-ai/pk/fix-set-tools-types kompfner 2025-08-26 14:12:21 -04:00
  • 0dced68c3c Merge pull request #2511 from pipecat-ai/aleix/end-of-pipline-warning Aleix Conchillo Flaqué 2025-08-26 11:02:26 -07:00
  • 8ab81d289a PipelineTask: warn if CancelFrame doesn't reach the end Aleix Conchillo Flaqué 2025-08-25 19:46:19 -07:00
  • f457d00760 Update types for tools in LLMSetToolsFrame and LLMContextAggregator.set_tools(), for two reason: 1. ToolsSchema has been supported in LLMSetToolsFrame for a while but wasn't properly reflected in these type hints 2. The new universal LLMContext expects tools to be either a ToolsSchema or NOT_GIVEN. Paul Kompfner 2025-08-26 11:13:24 -04:00
  • f5118c4412 Merge pull request #2440 from pipecat-ai/pk/prototype-llm-failover-attempt-4 kompfner 2025-08-26 09:55:03 -04:00
  • a79fe40162 Fix a typo in the CHANGELOG Paul Kompfner 2025-08-26 09:51:48 -04:00
  • dcb4949e20 Move ServiceSwitcherFrame and ManuallySwitchServiceFrame to frames.py Paul Kompfner 2025-08-26 09:43:47 -04:00
  • 8b543e558d Add CHANGELOG entry describing LLMService.run_inference() Paul Kompfner 2025-08-25 15:06:26 -04:00
  • 8181962236 Add CHANGELOG entry describing LLM switcher Paul Kompfner 2025-08-25 15:03:38 -04:00
  • 98dc891640 Move CHANGELOG log entry from 0.0.81 to Unreleased Paul Kompfner 2025-08-25 14:51:37 -04:00
  • 71de0da570 ServiceSwitchers are now controlled using frames rather than with direct method calls Paul Kompfner 2025-08-25 14:45:04 -04:00
  • b40c8bb81d Refactor LLMSwitcher into a base ServiceSwitcher and an LLMSwitcher that subclasses it Paul Kompfner 2025-08-25 13:55:23 -04:00
  • 43f1b59b86 Convert LLM generate_summary() methods to the more generic run_inference() Paul Kompfner 2025-08-25 12:20:16 -04:00
  • a0a2bb3aa4 In GeminiLLMAdapter, when translating from the universal LLMContext format, only pull out the first "system" message as the system instruction, and convert subsequent ones into "user" messages. This is a more correct thing to do than simply drop subsequent "system" messages, especially when potentially sharing a context between multiple LLMs. Paul Kompfner 2025-08-21 16:56:32 -04:00
  • 04a50df3d5 Add LLMSwitcher, with LLMSwitcherStrategyManual as the first supported switching strategy Paul Kompfner 2025-08-21 12:49:25 -04:00
  • 8c0edffaff Fix bug in AWS Bedrock conversation summarization. It was using an out-of-date pattern (the _client property no longer exists) Paul Kompfner 2025-08-20 16:20:33 -04:00
  • fe6063fdbe Introduce an affordance to LLMService for generating a summary of a conversation directly (i.e. without going through the pipeline). Paul Kompfner 2025-08-20 15:01:59 -04:00
  • 195146adb2 Bump deprecation warning version, as this commit is not expected to ship until version 0.0.82. Paul Kompfner 2025-08-25 10:11:02 -04:00
  • cab9e18cc9 Port recent change to LLMAssistantContextAggregator to universal LLMAssistantAggregator Paul Kompfner 2025-08-22 12:21:17 -04:00
  • baef688e4e Port recent changes to LLMUserContextAggregator to universal LLMUserAggregator Paul Kompfner 2025-08-22 11:42:05 -04:00
  • f1f43fe500 After a rebase, rename foundational examples showing usage of universal context to avoid naming conflict with a recently-added example. Paul Kompfner 2025-08-22 11:36:29 -04:00
  • 73b63f8d35 Remove unnecessary import Paul Kompfner 2025-08-20 13:30:00 -04:00
  • 0c14b33e92 Deprecate GoogleLLMOpenAIBetaService Paul Kompfner 2025-08-20 11:08:15 -04:00
  • 09beaccaf0 Assorted minor improvements after code review Paul Kompfner 2025-08-20 10:24:43 -04:00
  • 40557a1aae Remove TODO comment Paul Kompfner 2025-08-20 10:01:37 -04:00
  • ecc4cc4a79 Add support for universal LLMContext to RTVIObserver Paul Kompfner 2025-08-19 16:24:21 -04:00
  • 37be8805f4 ruff Paul Kompfner 2025-08-19 14:47:03 -04:00
  • 93c7e64995 Add missing PERPLEXITY_API_KEY in env.example Paul Kompfner 2025-08-19 13:08:17 -04:00
  • 9de2bd61a9 Add supports_universal_context for OpenAILLMService subclasses so that we can gradually roll out support for universal LLMContext in a controlled manner. Paul Kompfner 2025-08-19 13:07:56 -04:00
  • 566af71862 Add CHANGELOG entry for the universal LLMContext machinery Paul Kompfner 2025-08-19 11:14:15 -04:00
  • 12064bd6e6 Add a bit of helpful info in an error message Paul Kompfner 2025-08-19 10:45:12 -04:00
  • a962459151 Change LLMContextAggregatorPair.create(context) to LLMContextAggregatorPair(context) Paul Kompfner 2025-08-18 16:03:26 -04:00
  • 8fc76a29bc Raise errors when trying to use universal LLMContext with LLM services that don't yet support it Paul Kompfner 2025-08-18 11:08:40 -04:00
  • e3019261a5 Fix classes that subclass BaseLLMAdapter by adding placeholder stuff until support for universal LLMContext machinery comes to all LLM services Paul Kompfner 2025-08-18 10:18:09 -04:00
  • fa1f6f1c51 In LLMContext, normalize an empty provided ToolsSchema to NOT_GIVEN Paul Kompfner 2025-08-15 17:35:19 -04:00
  • 337f00c16c Minor fix: add a type annotation Paul Kompfner 2025-08-15 17:07:24 -04:00
  • d50922cdcd Update Google adapter to handle possibility of system message in standard format being provided as a list of text parts rather than just a string. Paul Kompfner 2025-08-15 16:56:44 -04:00
  • 47f5ca6265 Update Gemini adapter to be able to handle LLMSpecificMessages containing Google-formatted messages Paul Kompfner 2025-08-15 16:21:07 -04:00
  • 2eddb6ffda [WIP] Universal (LLM-agnostic) context machinery to support runtime LLM switching. Paul Kompfner 2025-08-14 14:46:53 -04:00
  • 560a6f2247 [WIP] Universal (LLM-agnostic) context machinery to support runtime LLM switching. Paul Kompfner 2025-08-14 12:06:26 -04:00
  • 59ecb19000 [WIP] Universal (LLM-agnostic) context machinery to support runtime LLM switching. Paul Kompfner 2025-08-14 09:31:32 -04:00
  • cfb094b3c8 [WIP] Universal (LLM-agnostic) context machinery to support runtime LLM switching. Paul Kompfner 2025-08-13 21:56:59 -04:00
  • 1f7e8e001b [WIP] Universal (LLM-agnostic) context machinery to support runtime LLM switching. Paul Kompfner 2025-08-13 15:45:09 -04:00
  • 688b136141 [WIP] Universal (LLM-agnostic) context machinery to support runtime LLM switching. Paul Kompfner 2025-08-13 11:41:46 -04:00
  • 809c4c1bc5 [WIP] Universal (LLM-agnostic) context machinery to support runtime LLM switching. Paul Kompfner 2025-08-13 11:27:21 -04:00
  • 81ca5e6601 [WIP] Universal (LLM-agnostic) context machinery to support runtime LLM switching. Paul Kompfner 2025-08-12 14:40:56 -04:00
  • ebc49d2252 [WIP] Universal (LLM-agnostic) context machinery to support runtime LLM switching. Paul Kompfner 2025-08-12 14:39:01 -04:00