wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
6,865 Commits 276 Branches 111 Tags
3e00a16f0f7a16263e796f41d6f3319ca6dee7aa
Commit Graph

227 Commits

Author SHA1 Message Date
Aleix Conchillo Flaqué
eb5a797b12 turns: rename bot turn start to user turn stop strategies 2025-12-30 14:33:58 -08:00
Mark Backman
9c6d0f1be1 Merge pull request #3322 from gui217/fix/rnnoise_filter_handle_empty_audio 
Fix/rnnoise filter handle empty audio
 2025-12-30 08:39:42 -05:00
gui217
32c3298eff Apply ruff formatting to test file 2025-12-30 13:39:36 +02:00
gui217
ec5fb392c4 Clean up test comments after rnnoise filter fix 2025-12-30 13:35:13 +02:00
gui217
bad8f8aa51 Fix rnnoise filter to handle empty audio 2025-12-30 13:32:36 +02:00
Aleix Conchillo Flaqué
ffbbb1b3f5 turns(user): add support for enabling/disabling interruptions 2025-12-29 17:00:03 -08:00
Aleix Conchillo Flaqué
e757b4bf6f tests: added external user and bot turn start strategies 2025-12-29 10:17:35 -08:00
Aleix Conchillo Flaqué
c821e9f8fd turns: add external user and bot turn start strategies 
External strategies are strategies where the logic for user turn start and turn
end come from a different processors (e.g. an STT).
 2025-12-29 10:17:35 -08:00
Aleix Conchillo Flaqué
5496aa722f turns: simplify imports and don't require full strategy module path 2025-12-28 16:20:15 -08:00
Aleix Conchillo Flaqué
8b861d9143 LLMUserAggregator: move turn_start_strategies from PipelineTask 2025-12-28 08:16:34 -08:00
Aleix Conchillo Flaqué
a962c4eeba STTMuteFilter: use FunctionCallsStartedFrame and support multiple function calls 2025-12-27 13:52:30 -08:00
Aleix Conchillo Flaqué
43fc26cf0e tests: add user mute strategies tests to user aggregator 2025-12-27 13:49:31 -08:00
Aleix Conchillo Flaqué
5a4236bc71 tests: add user mute strategy tests 2025-12-24 11:08:43 -08:00
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