Mark Backman
7cf099eae7
Merge pull request #2541 from parshvadaftari/user/parshva/update_mem0
...
Update mem0 integration
2025-08-30 05:11:31 -07:00
Mark Backman
d56762262a
Fix docs build errors
2025-08-29 20:24:35 -04:00
Mark Backman
972546b24f
Add IVR navigation ( #2529 )
2025-08-29 20:08:17 -04:00
Aleix Conchillo Flaqué
399f8de6ef
audio(dtmf): use longer tones and longer gaps
2025-08-29 15:10:20 -07:00
parshvadaftari
60c070e077
update mem0 integration for reduced latency and better performance
2025-08-30 02:27:36 +05:30
Aleix Conchillo Flaqué
f03deb6ecc
DailyTransport: remove send_dtmf() and write_dtmf()
2025-08-28 21:01:41 -07:00
Aleix Conchillo Flaqué
0e01ac8ef6
BaseOutputTransport: implement generic write_dtmf()
2025-08-28 21:01:41 -07:00
Aleix Conchillo Flaqué
5787743ab3
audio(dtmf): added DTMF audio files and load_dtmf_audio()
2025-08-28 21:01:41 -07:00
Aleix Conchillo Flaqué
79be0695dd
make sure warnings are always displayed
2025-08-28 17:43:29 -07:00
Aleix Conchillo Flaqué
a5c5e069ba
move pipecat.frames.frames.KeypadEntry to pipecat.audio.dtmf.types.KeypadEntry
2025-08-28 17:43:29 -07:00
Aleix Conchillo Flaqué
275c8b59c5
MistralLLMService: fix build_chat_completion_params()
2025-08-28 12:04:14 -07:00
Paul Kompfner
189749b579
Add LLMRunFrame to trigger an LLM response, replacing context_aggregator.user().get_context_frame()
2025-08-28 09:53:33 -04:00
Aleix Conchillo Flaqué
eb248fedc1
add skip_tts to LLMFullResponseStartFrame/LLMFullResponseEndFrame
2025-08-27 16:23:27 -07:00
Aleix Conchillo Flaqué
16f57be72c
LLMConfigureOutputFrame: allow configuring LLM output
2025-08-27 16:23:27 -07:00
Aleix Conchillo Flaqué
5803936838
TextFrame: add skip_tts field
...
This lets a text frame bypass TTS while still being included in the LLM
context. Useful for cases like structured text that isn’t meant to be spoken but
should still contribute to context.
2025-08-27 16:23:27 -07:00
Aleix Conchillo Flaqué
2a0780e6ef
PipelineTask: wait for StartFrame to reach end of pipeline
...
Fixes #2498
2025-08-27 14:23:09 -07:00
Aleix Conchillo Flaqué
2bdca8d22c
RTVIProcessor: make check sure client version is set
2025-08-27 13:36:11 -07:00
Aleix Conchillo Flaqué
1f5888bcf7
Merge pull request #2517 from pipecat-ai/aleix/unify-get-messages-for-logging
...
unify get_messages_for_logging()
2025-08-27 12:49:36 -07:00
Mark Backman
3d09f9a2af
Merge pull request #2524 from pipecat-ai/mb/cartesia-speed
...
Cartesia: update speed InputParam
2025-08-27 12:47:29 -07:00
Aleix Conchillo Flaqué
cd3563bb16
unify get_messages_for_logging()
...
Some implementations were returing a list and some were returning a JSON
string. They should all return a list and the user would decide if it wants to
transform that into JSON.
2025-08-27 12:45:24 -07:00
Aleix Conchillo Flaqué
2613da1a1f
PipelineTask: increase CANCEL_TIMEOUT_SECS to 20
2025-08-27 11:50:48 -07:00
Aleix Conchillo Flaqué
41d40f9a11
DailyTransport: make sure we have a client before joining/leaving
2025-08-27 11:50:48 -07:00
Aleix Conchillo Flaqué
74af2b6aa4
DailyTransport: fix sending DTMF tones
2025-08-27 11:50:48 -07:00
Mark Backman
f7d9f32b0f
Cartesia: update speed InputParam
2025-08-27 13:34:28 -04:00
Sam Sykes
06f7a92c99
fix to finally statement
2025-08-27 14:43:07 +01:00
Mark Backman
fc3d84dff7
Merge pull request #2501 from pipecat-ai/mb/aws-tts-more-flexible-auth
...
Support additional authentication mechanisms for AWS services
2025-08-26 18:05:37 -07:00
Mark Backman
facfaa2dd4
AWSBedrockLLMService: Allow setting auth credentials via env vars
2025-08-26 20:59:12 -04:00
Mark Backman
8250c381d1
AWSPollyTTSService: allow setting auth credentials through provider chain
2025-08-26 20:58:02 -04:00
Steve Geluso
32f9e48865
add missing import asyncio
2025-08-26 17:40:11 -07:00
Filipi Fuchter
76eef837b6
Removing watchdog from SarvamTTSService.
2025-08-26 18:44:58 -03:00
pratham-sarvam
6d582e41b7
Added Sarvam TTS Websocket Implementation ( #2356 )
...
* Added Sarvam TTS Websocket Implementation
* Addressed some of the comments on PR
* added change voice logic
* added changes from main
* pushing text frames and added flush audio
* updated docs string for better docs
* Addressed comments and added some improvements
* pushed optional args down
* removed new line
* made aiohttp session mandatory in http service
* added push frame and removed unused function
* removed pong message
* added disconnecting logic
---------
Co-authored-by: vinayak-sarvam <vinayak@sarvam.ai >
2025-08-26 18:10:26 -03:00
kompfner
ca29f62bff
Merge pull request #2510 from pipecat-ai/pk/fix-set-tools-types
...
Update types for tools in `LLMSetToolsFrame` and `LLMContextAggregato…
2025-08-26 14:12:21 -04:00
Aleix Conchillo Flaqué
8ab81d289a
PipelineTask: warn if CancelFrame doesn't reach the end
2025-08-26 10:36:33 -07:00
Paul Kompfner
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`.
2025-08-26 11:32:21 -04:00
Paul Kompfner
dcb4949e20
Move ServiceSwitcherFrame and ManuallySwitchServiceFrame to frames.py
2025-08-26 09:47:37 -04:00
Paul Kompfner
71de0da570
ServiceSwitchers are now controlled using frames rather than with direct method calls
2025-08-26 09:44:15 -04:00
Paul Kompfner
b40c8bb81d
Refactor LLMSwitcher into a base ServiceSwitcher and an LLMSwitcher that subclasses it
2025-08-26 09:44:15 -04:00
Paul Kompfner
43f1b59b86
Convert LLM generate_summary() methods to the more generic run_inference()
2025-08-26 09:44:15 -04:00
Paul Kompfner
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.
2025-08-26 09:44:15 -04:00
Paul Kompfner
04a50df3d5
Add LLMSwitcher, with LLMSwitcherStrategyManual as the first supported switching strategy
2025-08-26 09:44:15 -04:00
Paul Kompfner
8c0edffaff
Fix bug in AWS Bedrock conversation summarization. It was using an out-of-date pattern (the _client property no longer exists)
2025-08-26 09:44:15 -04:00
Paul Kompfner
fe6063fdbe
Introduce an affordance to LLMService for generating a summary of a conversation directly (i.e. without going through the pipeline).
...
This abstraction will allow us to update Pipecat Flows to avoid reaching into LLM service internals to generate summaries.
In addition to being a helpful refactor to remove a fragile part of Pipecat Flows, this change helps set the stage for supporting the upcoming `LLMSwitcher`, where the “active” LLM will only be determined at runtime—today, Pipecat Flows needs to know ahead of time what type of LLM it’s working with, to load an LLM-specific “adapter” that does the work of generating summaries, among other things.
2025-08-26 09:44:15 -04:00
Paul Kompfner
195146adb2
Bump deprecation warning version, as this commit is not expected to ship until version 0.0.82.
2025-08-26 09:44:15 -04:00
Paul Kompfner
cab9e18cc9
Port recent change to LLMAssistantContextAggregator to universal LLMAssistantAggregator
2025-08-26 09:44:15 -04:00
Paul Kompfner
baef688e4e
Port recent changes to LLMUserContextAggregator to universal LLMUserAggregator
2025-08-26 09:44:15 -04:00
Paul Kompfner
73b63f8d35
Remove unnecessary import
2025-08-26 09:44:15 -04:00
Paul Kompfner
0c14b33e92
Deprecate GoogleLLMOpenAIBetaService
2025-08-26 09:44:15 -04:00
Paul Kompfner
09beaccaf0
Assorted minor improvements after code review
2025-08-26 09:44:15 -04:00
Paul Kompfner
40557a1aae
Remove TODO comment
2025-08-26 09:44:15 -04:00
Paul Kompfner
ecc4cc4a79
Add support for universal LLMContext to RTVIObserver
2025-08-26 09:44:15 -04:00
