James Hush
|
c8a3d65aa4
|
Save progress
|
2025-09-17 11:39:21 +08:00 |
|
James Hush
|
50a2a0dc86
|
ok its kinda working
|
2025-09-17 11:29:11 +08:00 |
|
James Hush
|
0421d97954
|
Save changes
|
2025-09-17 11:09:03 +08:00 |
|
James Hush
|
54c8f336c3
|
Save progress
|
2025-09-16 16:43:38 +08:00 |
|
James Hush
|
b086fbafe6
|
feat: Add OpenAI Agents SDK integration service
- Create new OpenAIAgentService that integrates OpenAI Agents SDK with Pipecat
- Support for agent loops, handoffs, guardrails, and session management
- Add streaming and non-streaming response modes
- Include comprehensive tool integration and error handling
- Add optional dependency for openai-agents package
- Create foundational examples showing basic usage and agent handoffs
- Add comprehensive tests with mocked dependencies
- Include detailed documentation and README
Key features:
- Real-time streaming responses compatible with Pipecat pipelines
- Agent handoffs for specialized task delegation
- Tool calling with automatic schema generation
- Input/output guardrails for safety and validation
- Session context management for conversation continuity
- Built-in tracing and monitoring integration
Examples:
- 45-openai-agent-basic.py: Basic agent with weather and trivia tools
- 46-openai-agent-handoffs.py: Multi-agent system with specialist handoffs
|
2025-09-16 16:20:30 +08:00 |
|
Mark Backman
|
cca90791c4
|
Merge pull request #2652 from pipecat-ai/mb/fix-audio-buffer-processor-has-audio
fix: AudioBufferProcessor has_audio returns based on user or bot audi…
|
2025-09-15 18:43:59 -07:00 |
|
Mark Backman
|
f2a5d408de
|
fix: AudioBufferProcessor has_audio returns based on user or bot audio existing
|
2025-09-15 21:35:35 -04:00 |
|
Aleix Conchillo Flaqué
|
044c6eba46
|
Merge pull request #2655 from pipecat-ai/aleix/add-on-pipeline-finalized
PipelineTask: add on_pipeline_finished event
|
2025-09-15 15:32:04 -07:00 |
|
Aleix Conchillo Flaqué
|
db71089f5e
|
PipelineTask: add on_pipeline_finished event
This deprecates `on_pipeline_stopped`, `on_pipeline_ended` and
`on_pipeline_cancelled`.
|
2025-09-15 15:28:33 -07:00 |
|
Aleix Conchillo Flaqué
|
f861f5066f
|
Merge pull request #2654 from pipecat-ai/aleix/unify-on-client-disconnected
transports: on_client_disconnected only if remote client disconnects
|
2025-09-15 15:18:57 -07:00 |
|
kompfner
|
81cede2c60
|
Merge pull request #2653 from pipecat-ai/pk/llm-context-adapting-tests
`LLMContext`-adapting unit tests
|
2025-09-15 16:38:46 -04:00 |
|
kompfner
|
7603203230
|
Merge pull request #2644 from pipecat-ai/pk/run-inference-unit-tests
`run_inference` unit tests
|
2025-09-15 16:26:10 -04:00 |
|
Aleix Conchillo Flaqué
|
8569b61598
|
transports: on_client_disconnected only if remote client disconnects
|
2025-09-15 11:35:40 -07:00 |
|
Paul Kompfner
|
fe42187dc1
|
Implement LLMService.create_llm_specific_message() so that users don't need to just know what value of llm to provide to the LLMSpecificMessage constructor
|
2025-09-15 14:15:22 -04:00 |
|
Paul Kompfner
|
999e88c942
|
Add unit tests for AWSBedrockLLMAdapter.get_llm_invocation_params(), focusing on messages specifically
|
2025-09-15 12:08:21 -04:00 |
|
Paul Kompfner
|
c04df2f28b
|
Add unit tests for AnthropicLLMAdapter.get_llm_invocation_params(), focusing on messages specifically
|
2025-09-15 11:55:48 -04:00 |
|
Paul Kompfner
|
100ef0ab5c
|
Add unit tests for GeminiLLMAdapter.get_llm_invocation_params(), focusing on messages specifically
|
2025-09-15 11:38:23 -04:00 |
|
Paul Kompfner
|
42886d7105
|
Add unit tests for OpenAILLMAdapter.get_llm_invocation_params(), focusing on messages specifically. Also, fix a bug in OpenAILLMAdapter (found thanks to the unit tests) where it wasn't "unwrapping" LLMSpecificMessages.
|
2025-09-15 11:17:11 -04:00 |
|
Mark Backman
|
22cbba002a
|
Merge pull request #2651 from pipecat-ai/mb/heygen-bot-speaking-frame
fix: push BotStartedSpeakingFrame in HeyGenVideoService
|
2025-09-15 08:02:25 -07:00 |
|
Mark Backman
|
c873798ce5
|
fix: push BotStartedSpeakingFrame in HeyGenVideoService
|
2025-09-14 08:12:44 -04:00 |
|
Aleix Conchillo Flaqué
|
d8cd28bb8b
|
Merge pull request #2640 from pipecat-ai/aleix/pipecat-0.0.85
update CHANGELOG for 0.0.85
v0.0.85
|
2025-09-12 11:06:41 -07:00 |
|
Aleix Conchillo Flaqué
|
c2df6c8aee
|
update CHANGELOG for 0.0.85
|
2025-09-12 11:03:32 -07:00 |
|
Aleix Conchillo Flaqué
|
82478be861
|
scripts(evals): add 19b-openai-realtime-text
|
2025-09-12 11:03:32 -07:00 |
|
Aleix Conchillo Flaqué
|
0f2b7bc01b
|
examples(foundational): fix 19b-openai-realtime-beta-text
|
2025-09-12 11:03:32 -07:00 |
|
Aleix Conchillo Flaqué
|
1b2a5df017
|
Merge pull request #2622 from pipecat-ai/mb/call-data-runner
Add to, from phone info and custom data to the development runner
|
2025-09-12 10:28:17 -07:00 |
|
Mark Backman
|
2f496ac74f
|
Add optional body parameter to WebsocketRunnerArguments
|
2025-09-12 11:28:12 -04:00 |
|
Mark Backman
|
22633a63b0
|
Update changelog
|
2025-09-12 11:15:03 -04:00 |
|
Mark Backman
|
e5ed0424e4
|
Remove to/from data from Plivo, as it will rely on body information
|
2025-09-12 11:10:03 -04:00 |
|
Paul Kompfner
|
786387722a
|
Fix an issue in AWSBedrockLLMService.run_inference—exceptions should propagate, just like with other LLM services
|
2025-09-12 11:09:32 -04:00 |
|
Paul Kompfner
|
9f82c6b4a4
|
Add unit tests for run_inference
|
2025-09-12 11:07:11 -04:00 |
|
Mark Backman
|
99cfcb1d4e
|
Parsed custom data from Plivo extraHeaders
|
2025-09-12 08:11:30 -04:00 |
|
Mark Backman
|
d595676436
|
Add custom data handling for Twilio
|
2025-09-12 08:11:30 -04:00 |
|
Aleix Conchillo Flaqué
|
0190812ee8
|
Merge pull request #2639 from pipecat-ai/aleix/min-words-interruption-unit-test
MinWordsInterruptionStrategy unit test
|
2025-09-11 18:52:39 -07:00 |
|
Aleix Conchillo Flaqué
|
2a24061bbb
|
examples(07ad): remove deprecated user_continuous_stream
|
2025-09-11 18:50:00 -07:00 |
|
Aleix Conchillo Flaqué
|
89f7e7d199
|
update CHANGELOG with BaseOutputTransport fix
|
2025-09-11 16:58:44 -07:00 |
|
Aleix Conchillo Flaqué
|
384814e640
|
Merge pull request #2456 from a6kme/patch-1
Only set last_frame_time when handling OutputAudioRawFrame
|
2025-09-11 16:56:25 -07:00 |
|
Aleix Conchillo Flaqué
|
ab4364b833
|
update CHANGELOG and fix formatting
|
2025-09-11 15:34:47 -07:00 |
|
Aleix Conchillo Flaqué
|
fafdadad3c
|
Merge pull request #2473 from TheNotary/adds-interim-transcription-frame-support
adds support to Azure STT for creating InterimTranscriptFrames
|
2025-09-11 15:33:38 -07:00 |
|
Aleix Conchillo Flaqué
|
05dc2fa916
|
updated CHANGELOG.md with GoogleTTSService updates
|
2025-09-11 14:36:21 -07:00 |
|
Aleix Conchillo Flaqué
|
0c30cc6ea6
|
Merge pull request #2547 from manishkjs/feat/google-tts-voice-cloning
feat: add voice cloning and speaking rate to GoogleTTSService
|
2025-09-11 14:32:21 -07:00 |
|
Aleix Conchillo Flaqué
|
c26d336e34
|
Merge pull request #2545 from pipecat-ai/aleix/aws-nova-sonic-pre-load-cue
AWSNovaSonicLLMService: pre-load audio cue in the constructor
|
2025-09-11 14:31:26 -07:00 |
|
Mark Backman
|
37b6198787
|
Merge pull request #2635 from pipecat-ai/mb/openai-tts-speed
|
2025-09-11 14:22:51 -07:00 |
|
kompfner
|
3c271da94c
|
Merge pull request #2633 from pipecat-ai/pk/uv-readme-updates
Updating the README to reflect that:
|
2025-09-11 17:07:41 -04:00 |
|
kompfner
|
be28d3f93b
|
Merge pull request #2637 from pipecat-ai/pk/llm-context-evals-and-bug-fix
`LLMContext` evals and bug fix
|
2025-09-11 17:00:07 -04:00 |
|
marcus-daily
|
d2f210e960
|
Bundle Smart Turn v3 with Pipecat
|
2025-09-11 21:37:16 +01:00 |
|
Aleix Conchillo Flaqué
|
57add41971
|
tests: add unit test for MinWordsInterruptionStrategy
|
2025-09-11 13:07:30 -07:00 |
|
Aleix Conchillo Flaqué
|
74b38b59d6
|
tests(utils): allow passing PipelineParams to run_test()
|
2025-09-11 13:02:21 -07:00 |
|
kompfner
|
dac58deffc
|
Merge pull request #2636 from pipecat-ai/pk/uv-lock-update-for-smart-turn-v3
uv.lock update for Smart Turn v3
|
2025-09-11 14:35:36 -04:00 |
|
Paul Kompfner
|
aff11f5121
|
Fix missing import in llm_response_universal.py
|
2025-09-11 14:33:17 -04:00 |
|
Paul Kompfner
|
a4023d3915
|
Update evals to include examples that exercise the universal LLMContext
|
2025-09-11 14:32:56 -04:00 |
|