wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
6,073 Commits 276 Branches 111 Tags
75b3ea9c96dfd3233136dd5846bd2527eb845e21
Commit Graph

3460 Commits

Author SHA1 Message Date
dan-ince-aai
d16c36c56d feat: add keyterms_prompt to AssemblyAI service 2025-10-15 14:27:52 +01:00
Mark Backman
8fe3bcd484 Merge pull request #2840 from Rickaym/fix--excess-space-in-elevelabs-word-timestamp-joins 
fix: handle ElevenLabs partial word concatenation across alignment chunks gracefully
 2025-10-15 09:01:05 -04:00
Aleix Conchillo Flaqué
be2858bfbb CartesiaSTTService: inherit from WebsocketSTTService 2025-10-14 14:14:57 -07:00
Pyae Sone Myo
b6b0997553 fix: add support for partial words 2025-10-14 23:06:13 +06:30
Pyae Sone Myo
3b751322d3 fix: add interruption reset for partial word states 2025-10-14 23:04:09 +06:30
Aleix Conchillo Flaqué
d9580f72a9 runner: allow subdirectories in --folder 2025-10-13 18:29:19 -07:00
nbyers-altira
cc66ac14f1 add is_final to segmented func. sig. instead so tracing is consistent 2025-10-13 10:48:41 -04:00
nbyers-altira
9ddec0f8b4 is_final is not part of the segmented _handle_transcription function signature 2025-10-13 10:44:25 -04:00
shreyas-sarvam
9babfe9fd9 refactor: Improve code reability and replace deprecated interruption frames 2025-10-13 08:54:29 +05:30
Pyae Sone Myo
21d8d148b8 fix: handle partial words across alignment chunks gracefully 2025-10-12 22:10:11 +06:30
Aleix Conchillo Flaqué
0473556992 tts: fix RimeHttpTTSService/PiperTTSService 16-bit audio frames alignment 2025-10-10 14:19:22 -07:00
Paul Kompfner
1c25b6fb72 location should not be optional when using Google Vertex. 
Also, update `GoogleVertexLLMService` initialization pattern in the example file.
 2025-10-10 12:58:45 -04:00
Mark Backman
21d610cd30 Docs fixes for 0.0.90 release 2025-10-10 12:43:31 -04:00
Paul Kompfner
523e890c8c Fix deprecation messages pointing users to the new import paths for Gemini Live 2025-10-10 10:30:38 -04:00
kompfner
3c748fe772 Merge pull request #2823 from pipecat-ai/pk/vertex-init-args-fixup 
Move `location` and `project_id` out of `InputParams` in `GoogleVerte…
 2025-10-10 10:18:51 -04:00
kompfner
d293cee372 Merge pull request #2822 from pipecat-ai/pk/make-pause-processing-frames-more-robust 
Make `pause_processing_frames()` and `pause_processing_system_frames(…
 2025-10-10 10:16:27 -04:00
Paul Kompfner
8b62a96878 Improve how we're deprecating location and project_id in GoogleVertexLLMService, allowing user code to (correctly) continue referring to GoogleVertexLLMService.InputParams. 
Also fix the slightly wrong (but so far harmless) pattern of initializing `OpenAILLMService.InputParams()` in the `GoogleVertexLLMService` if `params` wasn't provided—we should be letting the superclass decide what to do if the argument isn't specified.
 2025-10-10 10:12:00 -04:00
Mark Backman
3894d2a4b9 Deprecate LivekitFrameSerializer 2025-10-10 09:51:57 -04:00
Aleix Conchillo Flaqué
1f6b61c0db Merge pull request #2828 from pipecat-ai/aleix/gemini-live-gemini-to-llm 
google: rename google.gemini_live.gemini to google.gemini_live.llm
 2025-10-10 06:42:51 -07:00
Aleix Conchillo Flaqué
8ee28b37cd google: rename google.gemini_live.vertext to google.gemini_live.llm_vertex 2025-10-10 06:41:19 -07:00
Filipi Fuchter
1b3afb5511 Added audio filter KrispVivaFilter using the Krisp VIVA SDK 2025-10-10 09:44:47 -03:00
Aleix Conchillo Flaqué
7cec013666 google: rename google.gemini_live.gemini to google.gemini_live.llm 2025-10-09 22:20:09 -07:00
Aleix Conchillo Flaqué
5679dde70f ai_service: use openai.realtime.events instead of openai_realtime_beta.events 2025-10-09 22:14:46 -07:00
Aleix Conchillo Flaqué
9698b008da deprecate openai_realtime 2025-10-09 22:14:46 -07:00
Aleix Conchillo Flaqué
7b05c9283b move openai.realtime.azure to azure.realtime.llm 2025-10-09 22:14:46 -07:00
Aleix Conchillo Flaqué
303dd2ec35 move openai.realtime.openai to openai.realtime.llm 2025-10-09 22:14:46 -07:00
Aleix Conchillo Flaqué
aa6e81648a move openai_realtime to openai.realtime 2025-10-09 22:14:46 -07:00
Aleix Conchillo Flaqué
2a79b2c853 aws: deprecate aws_nova_sonic 2025-10-09 17:44:29 -07:00
Aleix Conchillo Flaqué
15bf5b1533 aws: move aws_nova_sonic to aws.nova_sonic 2025-10-09 17:35:47 -07:00
Aleix Conchillo Flaqué
9d2ad750b5 Merge pull request #2779 from LucasStringPay/patch-1 
Ignore None value for 'completion_tokens' or similar for Gemini
 2025-10-09 16:55:33 -07:00
Aleix Conchillo Flaqué
59217eae38 runner: add --folder argument to allow file downloads 2025-10-09 16:49:51 -07:00
Aleix Conchillo Flaqué
aeace9b9be google: move gemini_live inside google service 2025-10-09 16:06:42 -07:00
Paul Kompfner
2994640f47 Move location and project_id out of InputParams in GoogleVertexLLMService, making them top-level init args instead. We do this for two reasons: 
- Conceptually, these args comprise project-level setup, akin to credentials, whereas everything in `InputParams` is concerned with model configuration
- Providing a `project_id` when initializing `GoogleVertexLLMService` should not be optional, but prior to the change in this commit it was (erroneously) treated as optional by dint of `InputParams` being optional

This improvement was discussed [in this comment](https://github.com/pipecat-ai/pipecat/pull/2795#discussion_r2408279142).
 2025-10-09 16:53:21 -04:00
Paul Kompfner
10069719e4 Make pause_processing_frames() and pause_processing_system_frames() more robust in FrameProcessor. 
To understand this fix, let's look exclusively at `pause_processing_frames()` (`pause_processing_system_frames()` works the same way).

`pause_processing_frames()` works by setting a `__should_block_frames` flag, which is then read each time through the loop in the long-running `__process_frame_task_handler`. if `__should_block_frames` is `True`, it pauses processing frames until it's resumed.

Prior to this fix, the check for `__should_block_frames` was before `await self.__process_queue.get()`. The problem is that a lot of the time spent in the loop is waiting for a frame from the process queue. So if `pause_processing_frames()` is set at any time other than within `process_frame()` itself, it actually won't have an effect by the next frame, only on the frame *after* the next, which is later than intended.

Because thus far in the Pipecat codebase we've only ever called `pause_processing_frames()` and `pause_processing_system_frames()` from within `process_frame()`, this change should have no behavioral effect. But it will be helpful if we ever need to call it from anywhere else. I noticed this issue while developing a feature that did exactly that (though I later abandoned that code).
 2025-10-09 15:57:31 -04:00
Paul Kompfner
f2d9063984 Renames: remove "multimodal" from Gemini Live types 2025-10-09 10:58:36 -04:00
shreyas-sarvam
7c1e2793c5 feat: Add support for bulbul:v3 and bulbul:v3-beta 2025-10-09 18:26:22 +05:30
Paul Kompfner
2699f0c2a6 Fix tool calls when using Gemini Live + Vertex AI 2025-10-08 21:03:07 -04:00
Paul Kompfner
a14fb20d15 Fix Gemini Live w/Vertex AI not being able to handle an empty list provided for "function_declarations" 2025-10-08 21:03:07 -04:00
Paul Kompfner
728361a6a7 Add GeminiVertexMultimodalLiveLLMService 2025-10-08 21:03:01 -04:00
Paul Kompfner
cf90071926 Format fix 2025-10-08 17:19:46 -04:00
Paul Kompfner
a666327d70 Implement ending GeminiMultimodalLiveLLMService gracefully (i.e. after the bot is finished) 2025-10-08 17:13:04 -04:00
Paul Kompfner
7da37a0d1f Pull _connection_established_threshold and _max_consecutive_failures into file-level constants 2025-10-08 17:04:05 -04:00
Paul Kompfner
7efb22a323 Add (relatively spartan) reconnection logic to GeminiMultimodalLiveLLMService, leveraging the Gemini Live session resumption mechanism 2025-10-08 16:53:21 -04:00
Paul Kompfner
402e019ae2 Make a bit of code clearer 2025-10-08 16:45:55 -04:00
Paul Kompfner
f09e4e238b Fix some mishandling of enum values 2025-10-08 16:45:55 -04:00
Paul Kompfner
2921162b3b Add deprecation warning around importing StartSensitivity and EndSensitivity from pipecat.services.gemini_multimodal_live.events 2025-10-08 16:45:55 -04:00
Paul Kompfner
ac1582c906 Let users directly use google-genai types rather than aliased re-exported types 2025-10-08 16:45:55 -04:00
Paul Kompfner
e4b01a5844 Bumping deprecation version of GeminiMultimodalLiveLLMService's base_url arg 2025-10-08 16:45:55 -04:00
Paul Kompfner
d19e6111c3 Bumping deprecation version of GeminiMultimodalLiveLLMService's base_url arg 2025-10-08 16:45:55 -04:00
Paul Kompfner
8a6d504a7e Add enable_affective_dialog and proactivity settings to GeminiMultimodalLiveLLMService 2025-10-08 16:45:55 -04:00