wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
6,789 Commits 276 Branches 111 Tags
604384b3ced6ef5b5c2d75f5ebcefc5d970b25a9
Commit Graph

214 Commits

Author SHA1 Message Date
Aleix Conchillo Flaqué
ffb5895404 tests: add initial tests for universal LLMUserAggregator 2025-12-23 15:51:06 -08:00
Aleix Conchillo Flaqué
a0d5ee3873 MinWordsUserTurnStartStrategy: single word interrupt if bot not speaking 2025-12-22 14:32:21 -08:00
Aleix Conchillo Flaqué
2cdf207227 turns: add TranscriptionUserTurnStartStrategy 2025-12-19 14:47:02 -08:00
Aleix Conchillo Flaqué
3d62b9c203 tests: added user turn start strategies unit tests 2025-12-19 14:47:01 -08:00
Aleix Conchillo Flaqué
7e69288898 tests: added bot turn start strategies unit tests 2025-12-19 14:47:01 -08:00
Aleix Conchillo Flaqué
6c0e4be4ac Merge pull request #3205 from gui217/feat/rnnoise 
Feat/rnnoise
 2025-12-17 18:22:22 -08:00
Mark Backman
21a55f6aae Update run_inference to use the provided LLM configuration params 2025-12-17 10:58:05 -05:00
Mark Backman
6cda357ce8 Remove timestamp check from TestThoughtTranscription 2025-12-12 14:28:39 -05:00
kompfner
1e98094394 Merge pull request #3175 from pipecat-ai/pk/thinking-exploration 
Additional functionality related to thinking, for Google and Anthropic LLMs.
 2025-12-11 17:15:37 -05:00
gui217
1c0e25a90d fix unit tests 2025-12-09 09:56:20 +02:00
Aleix Conchillo Flaqué
88289f578a Merge pull request #3208 from pipecat-ai/thor/add-client-identification 
add Gemini client identification
 2025-12-08 13:05:04 -08:00
Aleix Conchillo Flaqué
d289b38ba7 tests(google): mock the new pipecat.version() 2025-12-08 11:51:01 -08:00
Paul Kompfner
61674d7758 Add process_thought constructor argument to TranscriptProcessor to control whether to handle thoughts in addition to assistant utterances. Defaults to False. 2025-12-08 10:27:36 -05:00
Paul Kompfner
8ccc2cbf31 Add unit tests for ThoughtTranscriptProcessor 2025-12-08 10:14:31 -05:00
gui217
d3ae0b6a14 rebase 2025-12-08 11:36:44 +02:00
thorwebdev
15df3c06e8 chore: add test. 2025-12-06 22:36:04 -05:00
Aleix Conchillo Flaqué
7ad3969690 introduce UninterruptibleFrame frames 2025-12-05 09:21:36 -08:00
Mark Backman
d79dd94019 Make aggregate return an AsyncIterator, other clean up 2025-12-03 22:00:34 -05:00
Mark Backman
4d66191963 fix: PatternPairAggregator to process patterns only once 2025-12-03 22:00:04 -05:00
Mark Backman
7e9d67002e SkipTagsAggregator and PatternPairAggregator now subclass SimpleTextAggregator 2025-12-03 22:00:04 -05:00
Mark Backman
ffbb6e5937 Update SimpleTextAggregator to handle character by character input, use a buffer to handle ambiguous EOS scenarios, and add a flush method to all aggregators 2025-12-03 22:00:02 -05:00
Mark Backman
535b85cf90 Add split_text_by_spaces string util 2025-12-03 21:55:30 -05:00
mattie ruth backman
6b6d760cf1 Introduced LLMTextProcessor and deprecatd custom text_aggregators in TTS 
Introduced `LLMTextProcessor`: A new processor meant to allow customization for how
LLMTextFrames should be aggregated and considered. It's purpose is to turn
`LLMTextFrame`s into `AggregatedTextFrame`s. By default, a TTSService will still
aggregate `LLMTextFrame`s by sentence for the service to consume. However, if you
wish to override how the llm text is aggregated, you should no longer override the
TTS's internal text_aggregator, but instead, insert this processor between your LLM
and TTS in the pipeline.
 2025-11-21 17:16:10 -05:00
mattie ruth backman
7a4372a909 Introduced a new AggregatedTextFrame Frame type that TTSTextFrame inherits from 
This frame introduces an `aggregated_by` field to describe the type of text included
in the frame and allows unspoken groupings of text to be pushed through the pipeline
and treated similar to TTSTextFrames.
 2025-11-21 17:16:10 -05:00
mattie ruth backman
24266c238f Augmented PatternPairAggregator so that matched patterns can... 
be treated as their own aggregation, taking advantage of the new
ability to assign a type to an aggregation
 2025-11-21 17:16:10 -05:00
mattie ruth backman
dcc20f86e1 Updated the BaseTextAggregator to categorize aggregations 
Modified the BaseTextAggregator type so that when text gets aggregated, metadata can
be associated with it. Currently, that just means a `type`, so that the aggregation
can be classified or described. Changes made to support this:
  - **IMPORTANT**: Aggregators are now expected to strip leading/trailing white space
    characters before returning their aggregation from `aggregation()` or `.text`. This
    way all aggregators have a consistent contract allowing downstream use to know how
    to stitch aggregations back together
  - Introduced a new `Aggregation` dataclass to represent both the aggregated `text` and
    a string identifying the `type` of aggregation (ex. "sentence", "word", "my custom
    aggregation")
  - **BREAKING**: `BaseTextAggregator.text` now returns an `Aggregation` (instead of `str`).
    To update: `aggregated_text = myAggregator.text` -> `aggregated_text = myAggregator.text.text`
  - **BREAKING**: `BaseTextAggregator.aggregate()` now returns `Optional[Aggregation]`
    (instead of `Optional[str]`). To update:
      ```
      aggregation = myAggregator.aggregate(text)
      if (aggregation):
        print(f"successfully aggregated text: {aggregation.text}") // instead of {aggregation}
      ```
  - `SimpleTextAggregator`, `SkipTagsAggregator`, `PatternPairAggregator` updated to
     produce/consume `Aggregation` objects.
  - All uses of the above Aggregators have been updated accordingly.
 2025-11-21 17:16:10 -05:00
Paul Kompfner
3d21faaac2 LLMAssistantAggregator now properly aggregates text that might be a mix of includes_inter_frame_spaces=True and includes_inter_frame_spaces=False frames 2025-11-18 15:12:25 -05:00
Paul Kompfner
913194844e Make the mechanism of adding spaces when concatenating TTS (or speech-to-speech LLM) output text explicit and deterministic, rather than heuristic-based. 
This fixes a bug where spaces were sometimes missing from assistant messages in context.
 2025-11-10 14:22:32 -05:00
Mark Backman
2300941bb8 Revert "Merge pull request #3004 from pipecat-ai/mb/improve-concat-aggregated-text" 
This reverts commit 5e7f59a0b0, reversing
changes made to 2ad4122b77.
 2025-11-10 09:58:19 -05:00
Mark Backman
03001f8047 Update TranscriptProcessor unit tests 2025-11-07 11:44:04 -05:00
Mark Backman
f6b6aa8766 fix: STTMuteFilter no longer sends STTMuteFrame 2025-11-06 11:53:32 -05:00
Aleix Conchillo Flaqué
d844829538 Revert "fix interruption task frame context ordering" 2025-11-05 12:14:03 -08:00
Aleix Conchillo Flaqué
e4212fb3c0 tests: add interruption strategies context ordering tests 2025-11-05 09:38:18 -08:00
Aleix Conchillo Flaqué
0f5030bafa tests: add unit test to check for idle timeout on swallowed frames 2025-10-31 08:45:56 -07:00
Paul Kompfner
ac5734d0ed Deprecate expect_stripped_words option from LLMAssistantAggregatorParams, when used with the newer LLMAssistantAggregator, which now handles word spacing automatically. 
This commit does not change how it works in the older `LLMAssistantContextAggregator`.
 2025-10-30 17:22:47 -04:00
Paul Kompfner
ea6e146f2d Update TestServiceSwitcher to exercise targeting system frames only to the active service 2025-10-22 11:14:27 -04:00
Aleix Conchillo Flaqué
1b9e96c016 PipelineTask: fix task cancellation issues 2025-10-16 13:16:19 -07:00
Aleix Conchillo Flaqué
62b7c3d3b2 PipelineTask: add on_pipeline_error event 2025-10-07 18:36:38 -07:00
Aleix Conchillo Flaqué
7c15a8c800 Revert "fix context order when using interruption strategies" 
This reverts commit de8ee96927.
 2025-10-07 17:42:35 -07:00
Aleix Conchillo Flaqué
de8ee96927 fix context order when using interruption strategies 2025-10-06 22:43:01 -07:00
Aleix Conchillo Flaqué
4dc1e15a99 frames: use OutputTransportMessage(Urgent)Frame instead of TransportMessage(Urgent)Frame 2025-10-01 16:00:42 -07:00
Paul Kompfner
6faa50ae5b Remove remaining usage of OpenAILLMContext throughout the codebase in favor of LLMContext, except for: 
- Usage in classes that are already deprecated
- Usage related to realtime LLMs, which don't yet support `LLMContext`
- Usage in (soon-to-be-deprecated) code paths related to `OpenAILLMContext` itself and associated machinery
 2025-09-24 16:35:03 -04:00
Aleix Conchillo Flaqué
2571cb2e69 tests: fix formatting 2025-09-23 15:28:07 -07:00
Aleix Conchillo Flaqué
15782be27c Merge pull request #2676 from golbin/main 
Fix audio buffer flush and silence handling
 2025-09-23 15:27:31 -07:00
Aleix Conchillo Flaqué
3d88b42e0b FrameProcessor: add before/after events for processed/pushed frames 2025-09-19 20:47:21 -07:00
Jin Kim
58f70e7e0d Add tests for audio buffer processor flush alignment 2025-09-18 22:19:32 +09:00
Aleix Conchillo Flaqué
42344125b1 tests: add unit tests for push_interruption_task_frame_and_wait() 2025-09-17 13:38:22 -07:00
Paul Kompfner
8bc3c89140 Fix a bug preventing usage of multiple ServiceSwitchers in a pipeline 2025-09-17 16:09:18 -04:00
Paul Kompfner
2cd2567a37 Add a unit tests validating that multiple ServiceSwitchers can be used in the same pipeline (currently failing) 2025-09-17 16:04:30 -04:00
Paul Kompfner
a12392182c Simplify, undoing the change allowing controlling ServiceSwitcher with immediate frames (SystemFrames). Service switcher frames are ControlFrames, which are easier to reason about. We can always build the immediate option later if needed (i.e. if there's sufficient user pull for it) 2025-09-17 15:35:02 -04:00