Mark Backman
8ead309f8d
38b: Update bundled ONNX smart-turn model
2025-09-16 13:17:14 -04:00
Aleix Conchillo Flaqué
0f2b7bc01b
examples(foundational): fix 19b-openai-realtime-beta-text
2025-09-12 11:03:32 -07:00
Aleix Conchillo Flaqué
2a24061bbb
examples(07ad): remove deprecated user_continuous_stream
2025-09-11 18:50:00 -07:00
Aleix Conchillo Flaqué
8249b014f0
frames: BotInterruptionFrame is deprecated, use InterruptionTaskFrame
2025-09-11 09:01:54 -07:00
Aleix Conchillo Flaqué
9d9f10ae0e
frames: StartInterruptionFrame is deprecated, use InterruptionFrame
2025-09-11 09:01:54 -07:00
marcus-daily
a2e76bcad8
Smart Turn V3 support
2025-09-11 16:04:56 +01:00
kompfner
b31322e38e
Merge pull request #2619 from pipecat-ai/pk/aws-universal-context
...
Expand universal `LLMContext` support to AWS Bedrock
2025-09-11 09:33:08 -04:00
Mark Backman
f4938e0fad
fix: 13 foundational examples now push frames from TranscriptionLogger
2025-09-10 10:40:10 -04:00
Paul Kompfner
fedb8a201f
Update 12d example to use LLMContext, now that AWS Bedrock supports it
2025-09-09 16:24:13 -04:00
Paul Kompfner
75f9914f49
Add support for universal LLMContext to AWS Bedrock LLM service
2025-09-09 15:25:04 -04:00
Paul Kompfner
f4d6715e32
Add foundational example using AWS Bedrock with universal LLMContext
2025-09-09 10:49:51 -04:00
Paul Kompfner
f3a4b416df
Remove VisionImageRawFrame, which was previously being handled directly by the LLM services, and deprecate the associated VisionImageFrameAggregator.
...
Removing `VisionImageRawFrame` lets us simplify LLM services' logic, getting us closer to the idealized architecture where all they care about is handling context frames.
This change is in service of getting us closer to ready to deprecate usage of `OpenAILLMContext` and subclasses in favor of the universal `LLMContext`, at least for the traditional text-to-text LLMs.
Why remove `VisionImageRawFrame` rather than deprecate? It's "internal"—only created by `VisionImageFrameAggregator`—and never intended to be used directly by users (it would be difficult to use directly anyway).
Move the logic that was once in `VisionImageFrameAggregator` directly into the examples. Reasoning:
- If `UserImageRequester` is defined in the examples, it makes sense for `UserImageProcessor` to be too, as it’s the flip side of the same coin, so to speak
- The logic is now pretty trivial
- This kind of one-shot, history-less image-describing pipeline shouldn't be common at all; it's ok for it to live in examples rather than as a dedicated class
- In the short term, this enables us to create `LLMContext`s for services that support it and `OpenAILLMContext`s for services that don't yet (AWS)
This commit also adds missing translation from OpenAI-format image context messages to AWS format. Note that this isn't a wasted effort in the face of the upcoming migration to universal `LLMContext`—this work will be reused as it has to be implemented there too.
2025-09-08 17:00:08 -04:00
Mark Backman
a537382816
Add OpenAIRealtimeLLMService, AzureRealtimeLLMService ( #2596 )
...
* Add OpenAI Realtime module
* Add foundational examples for OpenAI Realtime
* Add deprecation warning to OpenAIRealtimeBetaLLMService
* Add deprecation warning to AzureRealtimeBetaLLMService
* Update Changelog
2025-09-07 09:09:57 -04:00
Filipi Fuchter
5477dfcbea
Improving HeyGen example video quality.
2025-09-05 11:30:01 -03:00
Paul Kompfner
b2e9fd9341
Rename Anthropic enable_prompt_caching_beta parameter to just enable_prompt_caching
2025-09-04 13:03:06 -04:00
Paul Kompfner
5c574eaad9
Add support for universal LLMContext to Anthropic LLM service
2025-09-04 13:03:06 -04:00
Paul Kompfner
2df231143a
Add foundational example using Anthropic with universal LLMContext
2025-09-04 13:03:06 -04:00
Aleix Conchillo Flaqué
f2b50c14d2
Merge pull request #2573 from pipecat-ai/vp-minor-fixes-07s
...
example 07s: minor typo updates
2025-09-04 09:21:32 -07:00
Mark Backman
977a57c8fb
Add 14k (CerebrasLLMService) to release evals
2025-09-03 17:11:38 -04:00
Mark Backman
c64bc5a636
Merge pull request #2576 from joyceerhl/joyce/cerebras-default
...
fix: update default Cerebras model to GPT-OSS-120B
2025-09-03 14:10:28 -07:00
Joyce Er
eba006d39c
Fix nits
2025-09-03 14:07:49 -07:00
Joyce Er
a001f6f193
Switch to GPT-OSS-120B
2025-09-03 14:00:27 -07:00
Mark Backman
052ffe8712
fix: Specify frame direction in 06a push_frame
2025-09-03 15:07:05 -04:00
vipyne
83f64ecd3b
example 07s: minor typo updates
2025-09-03 12:11:07 -05:00
Aleix Conchillo Flaqué
d19170d8b1
Merge pull request #2565 from pipecat-ai/aleix/reorganize-transports
...
transports: reorganize module
2025-09-03 08:52:49 -07:00
Paul Kompfner
f8e13a82cf
Fix Fireworks AI function calling example
2025-09-03 09:07:18 -04:00
Paul Kompfner
2dbd17da4d
Fix Cerebras function calling example
2025-09-03 09:07:18 -04:00
Aleix Conchillo Flaqué
aeb9f1ffca
transports: reorganize module
2025-09-02 17:31:39 -07:00
Aleix Conchillo Flaqué
fdcd14dd21
updated CHANGELOG with AICFilter and fix deprecations
2025-09-02 13:10:10 -07:00
Corvin Jaedicke
8ecece2d9c
Add AIC SDK audio filter
2025-09-02 11:11:29 -07:00
Aleix Conchillo Flaqué
bd7d9346b7
frames: remove StopInterruptionFrame
2025-08-29 16:40:01 -07:00
Aleix Conchillo Flaqué
64f2135ddc
examples(14f): use default models
2025-08-28 11:38:59 -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
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
Paul Kompfner
f1f43fe500
After a rebase, rename foundational examples showing usage of universal context to avoid naming conflict with a recently-added example.
2025-08-26 09:44:15 -04:00
Paul Kompfner
a962459151
Change LLMContextAggregatorPair.create(context) to LLMContextAggregatorPair(context)
2025-08-26 09:44:15 -04:00
Paul Kompfner
688b136141
[WIP] Universal (LLM-agnostic) context machinery to support runtime LLM switching.
...
- Add to Google LLM service support for universal LLM context
2025-08-26 09:44:15 -04:00
Paul Kompfner
809c4c1bc5
[WIP] Universal (LLM-agnostic) context machinery to support runtime LLM switching.
...
- Add to OpenAI LLM service support for universal LLM context
2025-08-26 09:44:15 -04:00
Mark Backman
bd401e8d6f
Rename TTSBuffer to TTSGate
2025-08-22 12:12:17 -04:00
Mark Backman
f0dfab23e7
Cleanup
2025-08-22 12:12:17 -04:00
Mark Backman
fbc907c371
Change path to extensions
2025-08-22 12:12:17 -04:00
Mark Backman
446bb5cddf
Refactor callback to event
2025-08-22 12:12:17 -04:00
Mark Backman
1c1ee94074
Add 44 to evals, update evals to support user speaking first
2025-08-22 12:12:17 -04:00
Mark Backman
ce579d4266
Make on_voicemail_detected callback required, cleanup logging
2025-08-22 12:12:17 -04:00
Mark Backman
5a07b30c7a
Class name changes, add TTSStarted/StoppedFrame to the TTSBuffer
2025-08-22 12:12:17 -04:00
Mark Backman
9da33f3897
Handle multiple user inputs from the user when a voicemail is detected; add a configurable timeout to emitting the callback
2025-08-22 12:12:17 -04:00
Mark Backman
5ca82ec61e
Final docstrings, comments, and cleanup
2025-08-22 12:12:17 -04:00
Mark Backman
238d6bf9ab
Add buffering logic
2025-08-22 12:12:17 -04:00
Mark Backman
90ae85bab2
More updates—added new voicemail module
2025-08-22 12:12:17 -04:00
Mark Backman
29e09b2053
POC demo in progress
2025-08-22 12:12:17 -04:00
