filipi87
c542167065
Refactored on_function_calls_cancelled to use FunctionCallFromLLM.
2026-04-10 15:06:39 -03:00
filipi87
8cce25d2d2
Fixing openai examples.
2026-04-10 08:25:50 -03:00
filipi87
891f00cb5f
Using the on_function_calls_cancelled inside the examples.
2026-04-10 07:45:20 -03:00
filipi87
1ca094dad7
Not invoking on_function_calls_started for the cancel function, and creating on_function_calls_cancelled
2026-04-10 07:40:52 -03:00
filipi87
346c585290
Enabling the option to cancel the tools for all the async examples.
2026-04-10 07:31:51 -03:00
filipi87
2dd1170229
Updating the Anthropic stream example to allow cancel the location tracking.
2026-04-09 17:26:51 -03:00
filipi87
5cf90cba98
Addressing PR review comments.
2026-04-09 17:11:04 -03:00
filipi87
772fb57090
Enable async tool cancellation feature.
2026-04-09 10:29:23 -03:00
Filipi da Silva Fuchter
76601944c6
Merge pull request #4230 from pipecat-ai/filipi/async_tools_stream
...
Support for streaming multiple responses via function calls
2026-04-09 10:26:33 -03:00
filipi87
178985ec8a
Refactoring the frame queue to avoid overhead.
2026-04-09 10:24:22 -03:00
filipi87
edc197d050
Creating a new example for async stream using Google.
2026-04-09 09:50:00 -03:00
filipi87
7ece8e3c4a
Creating a new example for async stream using Anthropic.
2026-04-09 09:41:07 -03:00
filipi87
7b45a56119
Changelogs for the new feature and the fix.
2026-04-09 09:04:19 -03:00
filipi87
a544f885a3
Added new examples: function-calling-openai-async-stream.py and function-calling-openai-responses-async-stream.py
2026-04-09 09:04:06 -03:00
filipi87
375deac912
Support for streaming multiple responses via function calls.
2026-04-09 09:03:53 -03:00
filipi87
699ca38dc1
Allowing to check if a specific frame is in the queue.
2026-04-09 09:03:06 -03:00
filipi87
aeda60f761
Refactoring the FrameQueue to be able to track any Frame.
2026-04-09 09:02:47 -03:00
Mark Backman
0acfb4dd49
Merge pull request #4251 from pipecat-ai/mb/mistral-tts
...
Add Mistral Voxtral streaming TTS service
2026-04-07 12:50:48 -04:00
Mark Backman
8594401024
Add changelog for PR #4251
2026-04-07 12:32:06 -04:00
Mark Backman
aa7a014518
Add mistral voice example
2026-04-07 12:32:06 -04:00
Filipi da Silva Fuchter
27a8a973b1
Merge pull request #4201 from pipecat-ai/mb/handle-recurring-disconnects
...
Fix WebsocketService infinite reconnection loop
2026-04-07 11:02:24 -03:00
Mark Backman
7f3f23dcb9
Add Mistral Voxtral streaming TTS service
...
Integrate with Mistral's Voxtral TTS API (voxtral-mini-tts-2603) using
HTTP streaming with Server-Sent Events. Converts base64-encoded float32
PCM chunks from the API to int16 for the Pipecat pipeline.
2026-04-07 09:39:36 -04:00
Filipi da Silva Fuchter
be509e5647
Merge pull request #4245 from kollaikal-rupesh/fix/mixer-cancel-cleanup
...
Stop audio mixer on pipeline cancellation
2026-04-07 10:36:18 -03:00
Filipi da Silva Fuchter
6eccd16543
Merge pull request #4217 from pipecat-ai/filipi/async_tools
...
Supporting async function calls.
2026-04-07 09:35:03 -03:00
filipi87
d8dc6bc7d0
New example for async function calls using Google.
2026-04-07 09:31:22 -03:00
filipi87
d12a8529e2
New example for async function calls using OpenAI responses.
2026-04-07 09:28:01 -03:00
filipi87
aa061f7e2c
Renaming the openai and anthropic examples to async instead of delayed.
2026-04-07 09:23:45 -03:00
Filipi da Silva Fuchter
e863293198
Improving docstring description.
...
Co-authored-by: kompfner <paul@daily.co >
2026-04-07 08:14:39 -04:00
filipi87
9c7d5a9de2
Improving changelog description to mention group_parallel_tools.
2026-04-07 09:13:08 -03:00
Filipi da Silva Fuchter
a451c42dc7
Merge pull request #4247 from pipecat-ai/filipi/background_sound_example
...
Fixing the background sound example.
2026-04-07 09:06:14 -03:00
Rupesh
67ee802772
Remove changelog entry per review feedback
2026-04-06 21:36:53 -07:00
filipi87
ceaa27ee6e
Fixing the background sound example.
2026-04-06 18:25:30 -03:00
filipi87
42335e2ef0
Renaming to async_tool and providing description.
2026-04-06 09:56:48 -03:00
Rupesh
7585864113
Stop audio mixer on pipeline cancellation to prevent 100% CPU usage
2026-04-06 01:51:29 -07:00
kompfner
18852adc28
Merge pull request #4242 from pipecat-ai/pk/gemini-live-fix-session-resumption
...
Fix Gemini Live session resumption hanging after reconnect
2026-04-04 11:43:24 -04:00
Paul Kompfner
f11b6d7151
Fix Gemini Live session resumption hanging after reconnect
...
After a reconnect, _ready_for_realtime_input was never set back to True
because _create_initial_response (which sets the flag) is only called on
initial connection. This caused all audio/video/text to be silently
dropped after reconnecting, making the bot appear to hang.
Set the flag in _handle_session_ready when we detect a reconnect, either
via session_resumption_handle (server restores state) or via existing
context (rare case where connection drops before first resumption handle).
2026-04-03 18:27:10 -04:00
Paul Kompfner
9df1e18b43
Fix Gemini Live session resumption hanging after reconnect
...
After a reconnect, _ready_for_realtime_input was never set back to True
because _create_initial_response (which sets the flag) is only called on
initial connection. This caused all audio/video/text to be silently
dropped after reconnecting, making the bot appear to hang.
Set the flag in _handle_session_ready when context already exists
(i.e. reconnect case) since we don't need to go through
_create_initial_response again.
2026-04-03 16:32:03 -04:00
Mark Backman
b8f9a21e0c
Merge pull request #4240 from pipecat-ai/mb/remove-old-files
...
Remove orphaned .dockerignore and CHANGELOG.md.template
2026-04-03 15:40:57 -04:00
Mark Backman
c18d997ad8
Remove orphaned .dockerignore and CHANGELOG.md.template
2026-04-03 14:55:25 -04:00
Mark Backman
56aaebe1b0
Merge pull request #4239 from pipecat-ai/mb/remove-deprecation-module-proxy
...
Remove DeprecatedModuleProxy and service re-export shims
2026-04-03 14:03:17 -04:00
Mark Backman
916af84974
Remove DeprecatedModuleProxy and service re-export shims
...
Remove the deprecation proxy infrastructure that allowed old-style flat
imports (e.g. `from pipecat.services.openai import OpenAILLMService`).
Users must now import from specific submodules
(`from pipecat.services.openai.llm import OpenAILLMService`), which is
already the established pattern across all internal code and 179+ examples.
- Strip 32 proxy `__init__.py` files to empty
- Strip 3 non-proxy files with bare star imports (minimax, sambanova, sarvam)
- Strip google/gemini_live `__init__.py` re-exports
- Remove DeprecatedModuleProxy class and helpers from services/__init__.py
- Remove ruff per-file ignore for services/__init__.py
- Fix 2 examples using old-style imports
2026-04-03 13:43:02 -04:00
Mark Backman
3e911b5fa0
Merge pull request #4236 from pipecat-ai/mb/more-deprecation-removals-2026-04-03
...
Remove deprecated fields, shims, and backward-compatibility code
2026-04-03 13:28:03 -04:00
Aleix Conchillo Flaqué
7c08779a2f
Merge pull request #4234 from pipecat-ai/aleix/export-runner-app
...
Export FastAPI app from runner for custom routes
2026-04-03 09:45:39 -07:00
Mark Backman
988c08a5b6
Merge pull request #4238 from pipecat-ai/mb/fix-daily-utils-docs
...
Fix Pydantic v2 + Sphinx autodoc incompatibility for Daily utils
2026-04-03 12:39:09 -04:00
Mark Backman
7351298849
Fix Pydantic v2 + Sphinx autodoc incompatibility for Daily utils
...
Patch Pydantic's DICT_TYPES check in conf.py to accept Union-wrapped
dict types, fixing the autodoc import failure for models using
ConfigDict(extra="allow").
2026-04-03 12:00:11 -04:00
kompfner
392134be46
Merge pull request #4231 from pipecat-ai/pk/llm-messages-transform-frame
...
Add a `LLMMessagesTransformFrame` to facilitate programmatically edit…
2026-04-03 11:54:34 -04:00
Paul Kompfner
9266e1e7ad
Remove comment referencing removed OpenAILLMContext
2026-04-03 11:53:57 -04:00
Mark Backman
e9eff4626f
Merge pull request #4237 from pipecat-ai/mb/docstring-fixes-2026-04-03
...
Docstring fixes for docs auto-generation
2026-04-03 11:50:20 -04:00
Mark Backman
21aa50283e
Update docs build script and README for current workflow
...
Make -W (warnings as errors) opt-in via --strict flag instead of
default, and update README to reflect uv-based workflow and current
directory structure.
2026-04-03 11:43:44 -04:00
Paul Kompfner
70469e3c0c
Assert no LLMContextFrame when run_llm is not set in message frame tests
2026-04-03 11:34:58 -04:00