wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
5,754 Commits 276 Branches 111 Tags
c219f8d55d8d3cbcf5f5b4dc8a342adab3bdb0ac
Commit Graph

1317 Commits

Author SHA1 Message Date
James Hush
c219f8d55d Add WebSocket reconnection test example 
This example helps test and verify the fix for on_client_disconnected
not firing after the first disconnection in long-running containers.

The test bot stays alive and logs each connection/disconnection event,
making it easy to manually verify that the event handlers fire correctly
on multiple reconnect cycles.
 2025-10-02 14:24:09 +08:00
Filipi da Silva Fuchter
2ca1b2d6f8 Merge pull request #2612 from pipecat-ai/filipi/deepgram_flux 
Integrating the new Deepgram model (Flux) with Pipecat
 2025-10-01 21:20:47 -03:00
Aleix Conchillo Flaqué
be562cedfc DailyTransport: deprecate DailyTransportMessage(Urgent)Frame 2025-10-01 16:00:42 -07:00
Mark Backman
af1f51d49e Remove DailyLogLevel from 04a example 2025-10-01 17:06:35 -04:00
Filipi Fuchter
e6ee8f7a16 New example using DeepgramFluxSTTService. 2025-10-01 15:43:25 -03:00
Mark Backman
d0178edad0 Merge pull request #2753 from pipecat-ai/mb/quickstart-0.0.86 
Quickstart: Update to 0.0.86, removing pytorch requirements
 2025-09-29 09:43:33 -04:00
Mark Backman
795c5e55d9 Quickstart: Update to 0.0.86, removing pytorch requirements 2025-09-27 08:30:37 -04:00
Vanessa Pyne
741f192d04 Merge pull request #2096 from pipecat-ai/vp-mcp-ex-nit 
mcp examples: check for env vars needed for examples
 2025-09-26 10:21:22 -05:00
Aleix Conchillo Flaqué
6c2c43ade0 Merge pull request #2724 from pipecat-ai/pk/update-natural-conversation-examples-with-universal-context 
Update natural conversation examples with universal context
 2025-09-24 11:07:50 -07:00
Aleix Conchillo Flaqué
f899c15b03 Merge pull request #2731 from pipecat-ai/pk/update-example-25-to-use-universal-context 
Update example 25 to use universal `LLMContext`
 2025-09-24 11:05:36 -07:00
Aleix Conchillo Flaqué
4bff0a7c49 Merge pull request #2732 from pipecat-ai/pk/update-voicemail-detector-to-use-llm-context 
Update `VoicemailDetector` to use universal `LLMContext`
 2025-09-24 11:04:42 -07:00
Filipi Fuchter
f6164e3bde HeyGen implementation for Pipecat - HeyGenTransport. 2025-09-24 14:33:56 -03:00
Paul Kompfner
6d0beef944 Update VoicemailDetector to use universal LLMContext 2025-09-24 12:58:42 -04:00
Paul Kompfner
b9fd6b873b Update comment in example 07b to reference LLMContext rather than OpenAILLMContext 2025-09-24 12:49:34 -04:00
Paul Kompfner
da66c38795 Update example 25 to use universal LLMContext 2025-09-24 12:37:29 -04:00
Paul Kompfner
8896179b00 Update another "natural conversation" example to use universal LLMContext. Note that this one had to also be fixed in various ways, as it wasn't working. 2025-09-24 09:55:11 -04:00
Aleix Conchillo Flaqué
997e4b66c6 Merge pull request #2722 from pipecat-ai/aleix/strands-agents-update-and-evals 
examples: update Strands Agents with universal context and add evals
 2025-09-23 15:21:41 -07:00
Paul Kompfner
6ccbfd9b57 Update "natural conversation" examples to use universal LLMContext 2025-09-23 16:20:16 -04:00
Paul Kompfner
677f69971c Add filters in 22b and 22c examples to prevent function call results triggering the "statement judge" LLM from running unnecessarily, and with the wrong system prompt, which would result in garbled output statements comprised of both LLMs outputs combined 2025-09-23 16:14:58 -04:00
Paul Kompfner
678dd22b8e Add missing sender argument to a few "on_app_message" handlers in examples 2025-09-23 15:29:20 -04:00
Aleix Conchillo Flaqué
620b1f785c examples: update Strands Agents with universal context and add evals 2025-09-23 11:37:57 -07:00
Paul Kompfner
780e91eb91 Update persistent conversation storage examples to use universal LLMContext. 
Note that `LLMContext` doesn't have a `get_messages_for_persistent_storage()`; the messages are already in the "standard" format so they can be used directly for storage.
 2025-09-23 14:16:35 -04:00
Aleix Conchillo Flaqué
3fc5214c15 BaseOutputTransport: only push downstream if transport write successful 
Fixes #2589
 2025-09-23 11:04:37 -07:00
kompfner
8649368337 Merge pull request #2719 from pipecat-ai/pk/update-more-examples-to-use-universal-llmcontext 
Update more examples to use universal `LLMContext`. Specifically, upd…
 2025-09-23 13:44:20 -04:00
Aleix Conchillo Flaqué
5c22b2e1de Merge pull request #2610 from adithyaxx/add-strands-processor 
Add native Strands Agents support to Pipecat
 2025-09-23 10:33:22 -07:00
Paul Kompfner
d4b1e1ab41 Update more examples to use universal LLMContext. Specifically, update examples we didn't update before because they weren't using ToolsSchema for their tool definitions, which is a requirement for using LLMContext. 
NOTE: oops! Turns out some of these files had *already* been updated to use universal `LLMContext` even though they weren't yet using `ToolsSchema`. This commit should fix those examples.
 2025-09-23 12:41:35 -04:00
Mark Backman
fafe0cc4a3 Merge pull request #2718 from lshaun/fix-openai-deprecation-warning 
update imports to avoid deprecated module
 2025-09-23 12:29:16 -04:00
Mark Backman
40c82a8530 Merge pull request #2716 from pipecat-ai/mb/add-11labs-stt 
Add ElevenLabsSTTService
 2025-09-23 12:21:08 -04:00
lshaun
98d3686861 update imports to avoid deprecated module 2025-09-23 15:58:09 +00:00
kompfner
88337fc21f Merge pull request #2717 from pipecat-ai/pk/mem0-support-univeral-context 
Add support for universal `LLMContext` to `Mem0MemoryService`
 2025-09-23 11:54:55 -04:00
kompfner
928c0ef1b4 Merge pull request #2715 from pipecat-ai/pk/langchain-processor-support-univeral-context 
Add support for universal `LLMContext` to `LangchainProcessor`
 2025-09-23 11:54:44 -04:00
kompfner
1f005e7075 Merge pull request #2714 from pipecat-ai/pk/gated-openai-llm-context-aggregator-support-univeral-context 
Add support for universal `LLMContext` to `GatedOpenAILLMContextAggre…
 2025-09-23 11:54:26 -04:00
Paul Kompfner
e21ab89509 Add support for universal LLMContext to Mem0MemoryService 2025-09-23 10:35:54 -04:00
Mark Backman
cbce2075eb Add ElevenLabsSTTService 2025-09-23 10:27:31 -04:00
Paul Kompfner
97868175e6 Add support for universal LLMContext to LangchainProcessor 2025-09-23 10:00:48 -04:00
Paul Kompfner
99731ca40a Add support for universal LLMContext to GatedOpenAILLMContextAggregator, renaming it to GatedLLMContextAggregator in the process 2025-09-23 09:52:13 -04:00
Paul Kompfner
f96cbcce22 Add support for universal LLMContext to LLMLogObserver 2025-09-23 09:30:14 -04:00
kompfner
a19b9f70c0 Merge pull request #2706 from pipecat-ai/pk/update-examples-to-use-universal-llm-context 
Update examples, wherever possible, to use `LLMContext` and associate…
 2025-09-23 09:20:39 -04:00
Filipi Fuchter
1647b5b665 Created a new example using the video processor to make it easier to investigate memory leaks. 2025-09-23 08:05:28 -03:00
Paul Kompfner
272532a3ea Update examples, wherever possible, to use LLMContext and associated machinery instead of OpenAILLMContext and associated machinery. 
With all these examples updated, we no longer need dedicated examples illustrating `LLMContext`, so they're removed.

Here’s where we *don’t* yet use `LLMContext` and associated machinery:
- Realtime services: OpenAI Realtime, Gemini Live, and AWS Nova Sonic (support coming soon)
- `GoogleLLMOpenAIBetaService` (it’s deprecated, so we didn’t bother adding support)
- `LLMLogObserver` (support coming soon)
- `GatedOpenAILLMContextAggregator` (support coming soon)
- `LangchainProcessor` (support coming soon)
- `Mem0MemoryService` (support coming soon)
- Examples that use LLM-specific tools definitions as opposed to `ToolsSchema` (these will be updated soon)
- Examples that rely `GoogleLLMContext.upgrade_to_google` (TBD what to do with these)

Examples that use `LLMLogObserver`:
- 30-

Examples that use `GatedOpenAILLMContextAggregator`:
- 22-

Examples that use `LangchainProcessor`:
- 07b-

Examples that use `Mem0MemoryService`:
- 37-

Examples that need updating to use `ToolsSchema`:
- 15-
- 15a-
- 20a-
- 20c-
- 20d-
- 22b-
- 22c-
- 33-
- 36-

Examples that use `GoogleLLMContext.upgrade_to_google`:
- 22d-
- 25-
 2025-09-22 16:21:35 -04:00
Filipi da Silva Fuchter
d0477edb6a Merge pull request #2696 from pipecat-ai/filipi/inworld_default_temperature 
Changing InworldTTSService default temperature to 1.1
 2025-09-22 09:33:52 -03:00
Filipi Fuchter
326bfe4239 Removing the temperature from InworldTTSService example. 2025-09-22 09:30:53 -03:00
Aleix Conchillo Flaqué
3cb78d839d examples(foundational): update comment in 45-before-and-afet-events.py 2025-09-20 10:33:52 -07:00
Aleix Conchillo Flaqué
ec664e2d33 examples(foundational): added 45-before-and-afet-events.py 2025-09-20 10:23:49 -07:00
Filipi Fuchter
9e098b5f79 Changing InworldTTSService default temperature to 1.1 2025-09-19 17:03:53 -03:00
vipyne
889dc19a27 mcp examples: check for env vars needed for examples 2025-09-19 12:09:50 -05:00
Mark Backman
4bc41466b7 Bump quickstart pipecat-ai version to require smart-turn v3, add local smart-turn dep, update quickstart 2025-09-19 08:03:06 -04:00
Mark Backman
9ab8ddee79 Update quickstart and foundational examples to use smart-turn v3 2025-09-18 23:54:18 -04:00
Aleix Conchillo Flaqué
2cf71239b0 examples(01b): use TTSSpeakFrame instead of TextFrame 2025-09-16 17:18:45 -04:00
Mark Backman
8ead309f8d 38b: Update bundled ONNX smart-turn model 2025-09-16 13:17:14 -04:00