wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
2,486 Commits 276 Branches 111 Tags
95f0dbf3f3f4dc4f2011c4a33962985ec00d739a
Commit Graph

359 Commits

Author SHA1 Message Date
Aleix Conchillo Flaqué
bb9a2560c3 Merge pull request #1118 from pipecat-ai/aleix/task-manager 
introduce TaskManager
 2025-01-31 10:24:52 -08:00
chadbailey59
a17243bc1e More Storybot updates (#1116) 
* initial changes for gemini storybot

* storybot updates for gemini

* more storybot updates

* interim interruptible commit

* cleanup

* cleanup

* cleanup

* first draft

* wip

* more storybot fixes

* more storybot updates WIP

* committing before changing the image prompting strategy

* wip

* prompt updating

* cleanup

* cleanup

* cleanup

* readme cleanup

* fixup
 2025-01-30 20:13:18 -06:00
Aleix Conchillo Flaqué
0131d0a531 examples: make sure unhandled frames are always pushed 2025-01-30 13:15:49 -08:00
Aleix Conchillo Flaqué
642affb2fe add missing super().process_frame() calls 2025-01-30 13:15:17 -08:00
Aleix Conchillo Flaqué
41d60a14cc introduce TaskManager and PipelineRunner event loop 2025-01-30 13:10:36 -08:00
Aleix Conchillo Flaqué
3fe2124314 examples: use task.cancel() when participant leaves or disconnects 2025-01-28 15:46:20 -08:00
Aleix Conchillo Flaqué
cca241a2b7 examples(22c): fix cancel_task call 2025-01-27 14:42:23 -08:00
Aleix Conchillo Flaqué
737e4fa3bd gemini(multimodal live): connect on StartFrame 2025-01-27 14:42:23 -08:00
Aleix Conchillo Flaqué
6cc01bc5b0 examples: update 14 series with TTSSpeakFrame 2025-01-27 14:42:23 -08:00
Aleix Conchillo Flaqué
d1a3f404a5 improve task creation and cancellation 
If a FrameProcessor needs to create a task it should use
FrameProcessor.create_task() and FrameProcessor.cancel_task(). This gives
Pipecat more control over all the tasks that are created in Pipecat.

Both functions internally use the utils module: utils.create_task() and
utils.cancel_task() which should also be used outside of FrameProcessors. That
is, unless strictly necessary, we should avoid using asyncio.create_task().
 2025-01-27 14:42:23 -08:00
Mark Backman
5f9671e2ca Added retry functionality and a new callback to the UserIdleProcessor 2025-01-27 10:24:57 -05:00
Mark Backman
0672530d6b Fix foundational example 6a to switch images when the bot is speaking 2025-01-25 08:40:42 -05:00
Mark Backman
96b90abda6 Merge pull request #1082 from pipecat-ai/mb/update-function-calling-examples 
Update function calling examples to push a TextFrame in the start_cal…
 2025-01-24 17:21:13 -05:00
Filipi da Silva Fuchter
7c52736ff6 Merge pull request #1030 from pipecat-ai/gemini_grounding_metadata 
Introduce support for extracting and processing grounding metadata from GoogleLLMService.
 2025-01-24 15:41:54 -03:00
Mark Backman
dbea86baae Update function calling examples to push a TextFrame in the start_callback 2025-01-24 10:21:08 -05:00
Mark Backman
7167719761 Emit a transcription callback when receiving a CancelFrame, update examples accordingly 2025-01-22 14:56:29 -05:00
Mark Backman
31c77d8e35 Update examples for the updated TranscriptProcessor 2025-01-22 14:56:00 -05:00
Filipi Fuchter
9b61633aa0 Introduce support for extracting and processing grounding metadata from Google LLM responses. 2025-01-20 11:28:12 -03:00
Aleix Conchillo Flaqué
4f883ee31f Merge pull request #1023 from pipecat-ai/aleix/introduce-heartbeat-frames 
introduce heartbeat frames
 2025-01-17 10:31:07 -08:00
Aleix Conchillo Flaqué
2503f76107 examples: add 31-heartbeats.py 2025-01-16 19:31:13 -08:00
Mark Backman
532fd31fd7 Add a second observer to the 30-observer.py example 2025-01-16 19:46:18 -05:00
Mark Backman
07cb8b7a89 Extend the example to include BotStartedSpeakingFrame and BotStoppedSpeakingFrame 2025-01-16 19:24:01 -05:00
Mark Backman
b9b02845a3 Add foundational example 30 to show how to use an Observer 2025-01-16 16:37:32 -05:00
Aleix Conchillo Flaqué
9dacbbbbf4 fix ruff formatting 2025-01-15 13:02:13 -08:00
sahil suman
7339cc7197 Merge remote-tracking branch 'origin/main' into openrouter-integration 2025-01-15 02:52:19 +05:30
sahil suman
62e9e6bc5a changed the file name. 
Signed-off-by: sahil suman <sahilsuman933@gmail.com>
 2025-01-15 02:21:58 +05:30
sahil suman
4d307d26d8 made the required changes. 
Signed-off-by: sahil suman <sahilsuman933@gmail.com>
 2025-01-15 02:19:05 +05:30
sahil suman
11381a536f added example for function calling and made the required changes. 
Signed-off-by: sahil suman <sahilsuman933@gmail.com>
 2025-01-15 01:00:33 +05:30
Mark Backman
bc839492b6 Add support for DeepSeek LLM 2025-01-14 09:34:33 -05:00
Filipi da Silva Fuchter
4854645637 Merge pull request #960 from pipecat-ai/example_gemini_with_goolge_search 
Example with Gemini using google search to retrieve news.
 2025-01-14 10:07:15 -03:00
Mark Backman
da1878537b Merge pull request #974 from pipecat-ai/mb/26d-example 
Align 26d example with foundation norms
 2025-01-12 19:44:31 -05:00
Mark Backman
f406d93b0f Align 26d example with foundation norms 2025-01-12 19:19:16 -05:00
Aleix Conchillo Flaqué
95e69597f3 update copyright keeping original year (2024) 2025-01-12 11:34:00 -08:00
sahil suman
e04da334d7 add support for openrouter. 
Signed-off-by: sahil suman <sahilsuman933@gmail.com>
 2025-01-11 17:50:58 +05:30
Mark Backman
4d0c11fcab Update examples to align with latest best practices 2025-01-10 15:07:06 -05:00
Mark Backman
86516d2415 PlayHTHttpTTSService fixes 2025-01-10 13:21:27 -05:00
Vanessa Pyne
5cd9dab14b Merge pull request #949 from imsakg/main 
fix(examples): correct TTS service import and setup
 2025-01-10 10:58:50 -06:00
Filipi Fuchter
aa1b8879ee Fixing ruff format 2025-01-10 13:21:51 -03:00
Filipi Fuchter
6719d1fddc Example with Gemini using google search to retrieve news. 2025-01-10 13:13:59 -03:00
Mark Backman
cb22de0d13 Update the Tavus example and comment about using the PERSONA_ID 2025-01-10 08:01:00 -05:00
Mert Sefa AKGUN
67af4e619b style(examples): fix ruff formatting in Gemini text example 
Refactor `CartesiaTTSService` instantiation to comply with line
length requirements from the ruff linter.
 2025-01-10 12:32:53 +03:00
Mert Sefa AKGUN
21c274944e Update examples/foundational/26d-gemini-multimodal-live-text.py 
Co-authored-by: Vanessa Pyne <vipyne@gmail.com>
 2025-01-10 12:28:13 +03:00
Mert Sefa AKGUN
6664c492ac feat(gemini): enable audio transcription in live text example 
Add options to transcribe both user and model audio during the GeminiMultimodalLiveLLMService setup in the 26d-gemini-multimodal-live-text.py example.
 2025-01-09 15:38:33 +03:00
Mert Sefa AKGUN
7634058f97 fix(examples): correct TTS service import and setup 
- Update import to use CartesiaTTSService instead of CartesiaMultiLingualTTSService.
- Adjust GeminiMultimodalLiveLLMService setup to use set_model_modalities with TEXT modality.
 2025-01-09 02:19:08 +03:00
Mert Sefa AKGUN
40e9ee6d63 fix(examples): correct import order in Gemini example 
- Move `CartesiaMultiLingualTTSService` import to maintain proper order.
- Reorganize `enum` import to adhere to styling standards.
 2025-01-08 21:14:29 +03:00
Mert Sefa AKGUN
cdb909958c feat(examples): add Gemini multimodal live text example 
Introduce a new example `26d-gemini-multimodal-live-text.py` to
demonstrate the use of GeminiMultimodalLiveLLMService with text-only
responses. This example sets up a pipeline for audio input via DailyTransport,
processing with Gemini, and output via Cartesia TTS.
 2025-01-08 19:29:35 +03:00
Mark Backman
3e1ec4a8ee Added support for Google Journey TTS voices 2025-01-06 14:54:34 -05:00
Vaibhav159
b3b7a5f023 adding 2025 license 2025-01-06 22:10:46 +05:30
Vaibhav159
5138017b57 ruff changes 2025-01-06 22:07:59 +05:30
Vaibhav159
87670067d7 adding changelog 2025-01-06 22:03:11 +05:30