Paul Kompfner
75245e1daa
Fix a bug in GeminiLiveLLMService where in some circumstances it wouldn't respond after a tool call
2025-11-05 15:29:04 -05:00
Paul Kompfner
29ef0f419f
Add typing formalizing MCPClient support for registering tools on an LLMSwitcher in addition to an LLMService.
2025-11-05 15:29:01 -05:00
Paul Kompfner
a9d78bd956
Make it possible to get a ToolsSchema out of an MCPClient without passing in an LLM service.
...
This allows folks to use `MCPClient` alongside the pattern of passing in tools at LLM init time, a pattern supported by speech-to-speech services such as `GeminiLiveLLMService`.
2025-11-05 15:28:23 -05:00
Paul Kompfner
e6f881bb08
Remove the "needs alternate schema" mechanism in MCPClient, moving the necessary schema massaging into GeminiLLMAdapter instead.
...
This does a couple of things:
- Makes the `MCPClient` LLM agnostic, setting us up for some upcoming improvements (like making it possible to use with `LLMSwitcher`)
- Makes `GeminiLLMAdapter` more robust, as the schema massaging that was previously only done in `MCPClient` is useful for all tools, not just for MCP-provided ones
2025-11-05 15:28:23 -05:00
Paul Kompfner
bee4165ba4
Add LLMSwitcher.register_direct_function()
2025-11-05 15:28:19 -05:00
Mark Backman
e2f6ce1078
Fix docstrings for 0.0.93 release, fix classmethod placement in RequestHandler
2025-11-05 15:27:16 -05:00
Aleix Conchillo Flaqué
d844829538
Revert "fix interruption task frame context ordering"
2025-11-05 12:14:03 -08:00
Mark Backman
11b101e8a6
Merge pull request #2974 from pipecat-ai/mb/language-mapping-improvements
...
Improve language checking in STT and TTS services
2025-11-05 14:59:41 -05:00
Aleix Conchillo Flaqué
234aae3091
FrameProcessor: use finished_event for push_interruption_task_frame_and_wait
2025-11-05 09:38:17 -08:00
Aleix Conchillo Flaqué
c33b81bb92
PipelineTask: set finished_event InterruptionFrame is received
2025-11-05 09:37:55 -08:00
Aleix Conchillo Flaqué
a1c07039ee
frames: added finished_event to InterruptionFrame/InterruptionTaskFrame
2025-11-05 09:37:55 -08:00
Mark Backman
f6d7b6ae5f
Fix SpeechmaticsSTTService: use language checking for language and output_locale
2025-11-05 12:26:52 -05:00
Mark Backman
2ee54c985f
Improve language checking in STT and TTS services
2025-11-05 12:26:52 -05:00
Thu Nguyen
76c336644a
Merge branch 'main' into feature/whisper-stt-probability-metrics
2025-11-06 00:24:34 +07:00
Thu Nguyen
c26c27fe21
Update util with new docs and extract_deepgram_probability
2025-11-06 00:23:20 +07:00
Mark Backman
c18ff999a5
Update GoogleVertexLLMService default model to gemini-2.5-flash
2025-11-05 11:28:41 -05:00
Mark Backman
80d127aaa4
Refactor GoogleVertexLLMService to use GoogleLLMService as a base class
2025-11-05 09:33:02 -05:00
Thu Nguyen
3486d63ef6
Add docs
2025-11-05 13:30:49 +07:00
Thu Nguyen
842c4a3485
Update base_stt
2025-11-05 13:26:59 +07:00
Thu Nguyen
0b779a880b
Feat: allow accessing prob metrics for Whisper STT services with include_prob_metrics param
2025-11-05 13:24:49 +07:00
Mark Backman
01f3421052
Fix: support request data in SmallWebRTC
2025-11-04 17:14:29 -05:00
Aleix Conchillo Flaqué
38f27ad991
PipelineTask: load observers from PIPECAT_OBSERVER_FILES
2025-11-04 12:10:53 -08:00
Mark Backman
0c38585034
Merge pull request #2973 from pipecat-ai/mb/cartesia-sonic-3-languages
...
Add sonic-3 languages to Cartesia TTS services
2025-11-04 14:43:06 -05:00
Mark Backman
8a09bbbf0e
Merge pull request #2972 from akash-dutta-dev/hotfix/addCustomParamForExotel
...
Add customer parameter in Call Data for Exotel
2025-11-04 14:29:58 -05:00
Paul Kompfner
a82158045a
Fix Gemini Live session resumption. The problem was that we weren't properly ignoring send errors during reconnection.
2025-11-04 09:18:40 -05:00
Mark Backman
b1533ddfc4
Add sonic-3 languages to Cartesia TTS services
2025-11-04 07:57:04 -05:00
Akash Dutta
09018071e8
Add customer parameter in Call Data for Exotel
2025-11-04 16:57:28 +05:30
Paul Kompfner
87131850bc
GeminiLiveLLMService supports context-provided system instruction and tools
2025-11-03 10:30:46 -05:00
Aleix Conchillo Flaqué
62e45f466a
EndFrame: add reason field to indicate why pipeline is being ended
2025-11-02 00:45:27 -07:00
Aleix Conchillo Flaqué
e85e93b9b1
CancelFrame: add reason field to indicate why pipeline is being cancelled
2025-11-02 00:44:47 -07:00
shreyas-sarvam
d680ec2e69
Merge branch 'main' into sarvam/stt
2025-10-31 23:09:47 +05:30
shreyas-sarvam
d905b21f72
fix: Pass input_audio_codec as an __init__ parameter
2025-10-31 23:07:48 +05:30
shreyas-sarvam
6c5d84ca4c
fix: Fixes for sample_rate being passed by PipelineParams
2025-10-31 23:03:25 +05:30
Mark Backman
653e84321b
Add support for token properties in Daily util and development runner
2025-10-31 12:08:53 -04:00
Mark Backman
3585f724c4
Merge pull request #2952 from pipecat-ai/mb/add-daily-room-properties-to-runner
...
Add support for dailyRoomProperties when calling /start using the dev…
2025-10-31 12:04:42 -04:00
Mark Backman
5fe597d355
Add support for dailyRoomProperties when calling /start using the development runner
2025-10-31 12:01:03 -04:00
Aleix Conchillo Flaqué
67ab3773f6
Merge pull request #2949 from pipecat-ai/aleix/idle-timeout-observer
...
PipelineTask: add IdleFrameObserver to detect idle pipelines
2025-10-31 08:51:09 -07:00
Aleix Conchillo Flaqué
ed93e29850
PipelineTask: add IdleFrameObserver to detect idle pipelines
2025-10-31 08:45:56 -07:00
Mark Backman
7eb880c5e8
Add DeepgramHttpTTSService
2025-10-31 11:39:32 -04:00
Aleix Conchillo Flaqué
4fa0de6660
Merge pull request #2947 from pipecat-ai/aleix/rename-add-to-context
...
UserImageRawFrame: rename add_to_context to append_to_context
2025-10-31 08:29:49 -07:00
kompfner
396c1bcc13
Merge pull request #2946 from pipecat-ai/pk/deprecate-expect-stripped-words
...
Deprecate `expect_stripped_words` option from `LLMAssistantAggregatorParams`…
2025-10-31 09:57:20 -04:00
shreyas-sarvam
57f6ae9e50
Merge branch 'main' into sarvam/stt
2025-10-31 17:36:52 +05:30
shreyas-sarvam
2d03e51109
fix: Remove unused imports, use sample_rate from base class
2025-10-31 17:31:59 +05:30
Mark Backman
83f395ff8f
Merge pull request #2940 from thsunkid/feature/google-tts-chirp-speaking-rate
...
Add dynamic speaking_rate control for Google TTS Chirp voices
2025-10-31 07:39:05 -04:00
shreyas-sarvam
09a7e08cbf
Merge branch 'main' into sarvam/stt
2025-10-31 15:21:09 +05:30
shreyas-sarvam
6f172bba8f
feat: Make input parameters accessible to users
2025-10-31 15:17:06 +05:30
shreyas-sarvam
1433df4de2
fix: Fix language param and include suggested way of handling STT response
2025-10-31 13:23:08 +05:30
Thu Nguyen
6ade5617fb
addressed comments
2025-10-31 09:53:47 +07:00
Aleix Conchillo Flaqué
685d440206
UserImageRawFrame: rename add_to_context to append_to_context
2025-10-30 15:18:27 -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
