kompfner
351ef617ae
Merge pull request #2932 from pipecat-ai/pk/gemini-live-universal-llmcontext
...
Update `GeminiLLMService` to work with `LLMContext` and `LLMContextAg…
2025-10-29 15:35:13 -04:00
Paul Kompfner
9dafb715c4
Update some deprecation versions
2025-10-29 15:30:43 -04:00
Paul Kompfner
82d494d3d4
Fix a bug in GeminiLiveLLMService related to ending gracefully—i.e. waiting for the bot to stop responding before ending the pipeline—when the service is configured with the TEXT modality
2025-10-29 14:34:02 -04:00
Paul Kompfner
65c17a698e
Whoops - fix a bug in GeminiLiveLLMService where we weren't checking if a tool call result was already handled before reporting it to the LLM
2025-10-29 12:44:00 -04:00
Paul Kompfner
615aae5b95
Fix GeminiLiveLLMService's sending of LLMFullResponseStartFrame and LLMFullResponseEndFrame so that they properly bookend responses.
...
Properly bookended responses now work with:
- AUDIO modality (validated with 26b example)
- TEXT modality (validated with 26d example)
- AUDIO modality with Vertex AI (validated with 26h example)
It doesn't seem that TEXT modality is supported with Vertex AI, hence the missing "quadrant" of validation.
2025-10-29 12:33:37 -04:00
Ivan A
2f1061f300
Merge branch 'main' into hume-bugfix
2025-10-29 17:06:50 +01:00
Mark Backman
ede6c32149
Update Simli to align with Pipecat constructor norms
2025-10-29 11:47:23 -04:00
Paul Kompfner
f974c66e12
Update GeminiLLMService to work with LLMContext and LLMContextAggregatorPair
2025-10-28 15:46:28 -04:00
Mark Backman
533372ed37
Remove aiohttp_session arg from SarvamTTSService
2025-10-28 15:39:14 -04:00
ivaaan
a9118eb2cd
use Octave 1 if description provided
2025-10-28 20:36:34 +01:00
Aleix Conchillo Flaqué
84ed2468e5
Merge pull request #2924 from pipecat-ai/aleix/daily-transport-remove-join-timeout
...
DailyTransport: don't timeout prematurely on join
2025-10-28 10:43:28 -07:00
Aleix Conchillo Flaqué
d82d855c20
DailyTransport: don't timeout prematurely on leave
2025-10-28 10:41:19 -07:00
Mark Backman
412ff2a4a1
Merge pull request #2929 from pipecat-ai/mb/cartesia-sonic-3
...
Update Cartesia's default model to sonic-3
2025-10-28 13:07:28 -04:00
Mark Backman
9ef60bd468
Update Cartesia's default model to sonic-3
2025-10-28 11:49:54 -04:00
Aleix Conchillo Flaqué
f3c4bf08dd
DailyTransport: don't timeout prematurely on join
2025-10-27 17:52:19 -07:00
Mark Backman
f2cfbee3c3
Remove development runner requirement for proxy
2025-10-27 16:18:31 -04:00
vipyne
8096e62b34
cleanup logger message
2025-10-27 11:27:30 -05:00
kompfner
20f4b0e8ff
Merge pull request #2914 from pipecat-ai/pk/gemini-function-calling-fixes
...
Gemini function calling fixes
2025-10-27 09:45:29 -04:00
Paul Kompfner
6feaf91789
Fix a bug in GeminiLLMAdapter's handling of Gemini-specific context messages
2025-10-27 09:42:24 -04:00
Pyae Sone Myo
71841f71ef
fix: use correct property names
2025-10-25 00:47:46 +06:30
Paul Kompfner
949b807023
Close genai client more gracefully to avoid printed warnings. We're now following the genai library guidance: https://github.com/googleapis/python-genai?tab=readme-ov-file#close-a-client
2025-10-24 11:36:25 -04:00
Paul Kompfner
4ad15f9a01
Update Gemini service to include function name when sending function responses in context
2025-10-24 11:04:52 -04:00
Paul Kompfner
99d94fc625
Update Gemini service to use "user" role for function responses, as shown in the Gemini docs
2025-10-24 10:05:14 -04:00
Mark Backman
04b482c445
Merge branch 'main' into mb/runner-daily-start-route
2025-10-23 14:11:38 -04:00
Mark Backman
60e9817f16
fix: add support for DAILY_SAMPLE_ROOM_URL when calling /start for DailyTransport
2025-10-22 16:48:30 -04:00
Mark Backman
ec890a834f
Rename to filter_system_frames
2025-10-22 11:01:33 -04:00
Mark Backman
5b921fc054
fix: FunctionFilter adds block_system_frame arg
2025-10-22 10:53:01 -04:00
Mark Backman
f1040100f4
Update ServiceSwitcher and LLMSwitcher docstrings
2025-10-22 10:51:03 -04:00
Aleix Conchillo Flaqué
788465cb04
Merge pull request #2901 from pipecat-ai/pk/llmcontext-messages
...
Add `messages` property to `LLMContext` for usage parity with `OpenAI…
2025-10-21 18:00:33 -07:00
Aleix Conchillo Flaqué
db934eade0
Merge pull request #2891 from pipecat-ai/aleix/daily-pipecat-runner-args
...
runner: allow starting a bot from Daily's /start endpoint
2025-10-21 17:59:13 -07:00
Mark Backman
5849485bc6
fix: AWSBedrockLLMService compatibility for newer Claude models
2025-10-21 19:47:27 -04:00
Aleix Conchillo Flaqué
459af58540
runner: allow starting a bot from Daily's /start endpoint
2025-10-21 16:28:11 -07:00
Aleix Conchillo Flaqué
576bd67e85
runner: add body field to RunnerArguments
2025-10-21 16:27:48 -07:00
Aleix Conchillo Flaqué
1e8629bf96
runner: allow passing an api_key to configure
2025-10-21 16:27:48 -07:00
Paul Kompfner
776a3526f9
Add messages property to LLMContext for usage parity with OpenAILLMContext.
...
This wasn't really an issue before, when folks were *knowingly* migrating from `OpenAILLMContext` to `LLMContext`. But in the latest AWS Nova Sonic change, we're swapping it out from under folks, so this kind of compatibility is more important.
For context, the reason we *didn't* offer the `messages` property earlier was to aid in the development of `LLMContext`—we wanted to draw attention to all the places where messages were being read from context, so we could find the places where we might need to pass an argument to the read.
2025-10-21 17:38:39 -04:00
kompfner
2ced044418
Merge pull request #2896 from pipecat-ai/pk/add-back-types-that-were-meant-to-be-deprecated-not-removed
...
Add back types that were removed, when they should only have been dep…
2025-10-21 17:33:17 -04:00
Mark Backman
81645910e0
Merge pull request #2877 from nimobeeren/patch-1
...
Add ellipsis character to sentence ending punctuation list
2025-10-21 11:53:17 -04:00
Filipi Fuchter
2f92cb8781
Fixed an issue in the runner's proxy_request where a session that exists but has empty data was being treated as invalid.
2025-10-21 11:41:52 -03:00
Paul Kompfner
fbf274374c
Add back types that were removed, when they should only have been deprecated
2025-10-21 09:56:31 -04:00
Filipi Fuchter
de46631bac
Fixed an issue where the RTVIProcessor was sending duplicate UserStartedSpeakingFrame and UserStoppedSpeakingFrame messages.
2025-10-20 18:39:00 -03:00
Paul Kompfner
3b40079120
Add a detailed warning when trying to import things from pipecat.services.aws_nova_sonic.context or pipecat.services.aws.nova_sonic.context
2025-10-20 09:49:05 -04:00
Paul Kompfner
ff0b38859b
Remove AWS Nova Sonic's context.py, which was always concerned with types for internal use only. Now those types are either gone or moved elsewhere.
2025-10-20 09:49:05 -04:00
Paul Kompfner
4d499324d1
Re-apply a change to AWSNovaSonicLLMService that was lost in a rebase
2025-10-20 09:49:05 -04:00
Paul Kompfner
f13e006db2
Bump version in deprecation message in docstring
2025-10-20 09:49:05 -04:00
Paul Kompfner
87d9e8c9cd
Re-apply a couple of recent changes to AWSNovaSonicLLMService that were lost in a rebase
2025-10-20 09:49:05 -04:00
Paul Kompfner
4820f1c059
Address some AWSNovaSonicLLMService context-recording edge cases
2025-10-20 09:49:05 -04:00
Paul Kompfner
860c39d1b1
Get rid of LLMContext.get_messages_for_persistent_storage().
...
The reason for its `system_instruction` argument was to support usage with LLMs where you might pass the system instruction as a parameter to the `LLMService` rather than specifying it in the context.
But as I thought about it more I became unconvinced that the `system_instruction` argument was really beneficial:
- If you specified your system instruction in your context in the first place, it'll still be there when you read messages for persistent storage
- If you didn't specify your system instruction in the context and instead passed it in as an `LLMService` parameter, you most likely *don't* want it to be in the context when you read messages for persistent storage
- ...and if you really really do need to inject it at the start of the context, it's quite easy to do anyway
And if we remove the `system_instruction` argument from `get_messages_for_persistent_storage()`, then it's essentially just `get_messages()`.
2025-10-20 09:49:05 -04:00
Paul Kompfner
ae5c5ed7f6
Update AWSNovaSonicLLMService to work with LLMContext and LLMContextAggregatorPair
2025-10-20 09:49:00 -04:00
Aleix Conchillo Flaqué
7aa01c1ca8
Merge pull request #2882 from pipecat-ai/aleix/base-transport-output-cleanup
...
base output transport cleanup
2025-10-18 07:38:13 -07:00
Mark Backman
5b1a182421
Merge branch 'main' into sarvam/tts-v3
2025-10-18 09:34:10 -04:00
