Paul Kompfner
6a717fbbd1
Updating the README to reflect that:
...
- various dependencies that previously didn't work with Python 3.13 now seem to
- ultravox isn't fully supported on macOS
2025-09-11 12:27:43 -04:00
marcus-daily
66ce5fe6bd
Ruff fixes
2025-09-11 16:04:56 +01:00
marcus-daily
a9b53dc800
Update inference session options
2025-09-11 16:04:56 +01:00
marcus-daily
818352a300
Formatting
2025-09-11 16:04:56 +01:00
marcus-daily
3e9fc7be19
Update onnxruntime version
2025-09-11 16:04:56 +01:00
marcus-daily
a2e76bcad8
Smart Turn V3 support
2025-09-11 16:04:56 +01:00
kompfner
b31322e38e
Merge pull request #2619 from pipecat-ai/pk/aws-universal-context
...
Expand universal `LLMContext` support to AWS Bedrock
2025-09-11 09:33:08 -04:00
Aleix Conchillo Flaqué
908325484d
Merge pull request #2614 from pipecat-ai/aleix/readme-client-sdks-table
...
README: update clients' table
2025-09-10 10:21:18 -07:00
Mark Backman
dd6ff789c7
Merge pull request #2628 from pipecat-ai/mb/fix-13-push-frame
...
fix: 13 foundational examples now push frames from TranscriptionLogger
2025-09-10 09:13:04 -07:00
Mark Backman
f4938e0fad
fix: 13 foundational examples now push frames from TranscriptionLogger
2025-09-10 10:40:10 -04:00
James Hush
e8f60c7c6f
Handle missing rawResponse in transcription messages ( #2623 )
...
* Handle missing rawResponse in transcription messages
- Use message.get('rawResponse', {}) to safely access rawResponse field
- Default is_final to False when rawResponse is missing
- Add proper type annotations for better code clarity
- Minor import formatting cleanup
This prevents KeyError crashes when transcription messages from Daily's API
don't include the rawResponse field in edge cases.
* docs: add changelog line
2025-09-10 15:03:23 +08:00
Paul Kompfner
fedb8a201f
Update 12d example to use LLMContext, now that AWS Bedrock supports it
2025-09-09 16:24:13 -04:00
Paul Kompfner
8ccd220a60
Add universal LLMContext support to AWSBedrockLLMService.run_inference()
2025-09-09 16:00:32 -04:00
Paul Kompfner
fe79de8f27
When converting universal LLMContext messages to AWS Bedrock expected format, automatically update non-initial "system"-role messages to "user"-role messages, as we do in other non-OpenAI LLM services
2025-09-09 15:50:03 -04:00
Paul Kompfner
176573c342
Add to CHANGELOG AWS Bedrock's support for universal LLMContext
2025-09-09 15:31:56 -04:00
Paul Kompfner
75f9914f49
Add support for universal LLMContext to AWS Bedrock LLM service
2025-09-09 15:25:04 -04:00
Paul Kompfner
f4d6715e32
Add foundational example using AWS Bedrock with universal LLMContext
2025-09-09 10:49:51 -04:00
kompfner
38f6e33f97
Merge pull request #2598 from pipecat-ai/pk/deprecate-vision-image-raw-frame
...
Remove `VisionImageRawFrame`, which was previously being handled dire…
2025-09-08 17:13:28 -04:00
Paul Kompfner
1c3e4e34e5
Minor fix to AWS Bedrock console logging to handle image messages in the context
2025-09-08 17:10:11 -04:00
Paul Kompfner
623c660027
Remove debugging comment
2025-09-08 17:01:51 -04:00
Paul Kompfner
a3e65ab3b5
The VisionImageRawFrame removal and corresponding VisionImageFrameAggregator deprecation will now happen in version 0.0.85
2025-09-08 17:01:47 -04:00
Paul Kompfner
f3a4b416df
Remove VisionImageRawFrame, which was previously being handled directly by the LLM services, and deprecate the associated VisionImageFrameAggregator.
...
Removing `VisionImageRawFrame` lets us simplify LLM services' logic, getting us closer to the idealized architecture where all they care about is handling context frames.
This change is in service of getting us closer to ready to deprecate usage of `OpenAILLMContext` and subclasses in favor of the universal `LLMContext`, at least for the traditional text-to-text LLMs.
Why remove `VisionImageRawFrame` rather than deprecate? It's "internal"—only created by `VisionImageFrameAggregator`—and never intended to be used directly by users (it would be difficult to use directly anyway).
Move the logic that was once in `VisionImageFrameAggregator` directly into the examples. Reasoning:
- If `UserImageRequester` is defined in the examples, it makes sense for `UserImageProcessor` to be too, as it’s the flip side of the same coin, so to speak
- The logic is now pretty trivial
- This kind of one-shot, history-less image-describing pipeline shouldn't be common at all; it's ok for it to live in examples rather than as a dedicated class
- In the short term, this enables us to create `LLMContext`s for services that support it and `OpenAILLMContext`s for services that don't yet (AWS)
This commit also adds missing translation from OpenAI-format image context messages to AWS format. Note that this isn't a wasted effort in the face of the upcoming migration to universal `LLMContext`—this work will be reused as it has to be implemented there too.
2025-09-08 17:00:08 -04:00
Aleix Conchillo Flaqué
aa471a4ef5
update CHANGELOG with LiveKitTransport updates
2025-09-08 13:53:21 -07:00
Aleix Conchillo Flaqué
d55133a44f
Merge pull request #2604 from alexyzhou/feature/livekit_video_and_bug_fix
...
Feature: Add support for livekit video stream and minor bug fixes
2025-09-08 13:51:14 -07:00
Aleix Conchillo Flaqué
0f1cf81691
README: update clients' table
2025-09-08 12:08:32 -07:00
kompfner
ac4d335799
Merge pull request #2613 from pipecat-ai/pk/mistral-message-fixups
...
Apply additional fixups to context messages to meet Mistral-specific …
2025-09-08 13:59:54 -04:00
Paul Kompfner
e65385c151
Tweak the Mistral-specific context messages fixup logic to handle the (mostly academic) possibility of a "tool" message appearing at the end
2025-09-08 13:55:09 -04:00
Paul Kompfner
0bb7df7a6b
Remove stray debugging message
2025-09-08 13:38:26 -04:00
Paul Kompfner
daee1ddf3b
Apply additional fixups to context messages to meet Mistral-specific requirements
2025-09-08 11:26:58 -04:00
Aleix Conchillo Flaqué
1cccb97ccf
Merge pull request #2608 from pipecat-ai/aleix/deprecate-noisereducefilter
...
audio(filters): deprecate NoisereduceFilter
2025-09-07 20:54:09 -07:00
Aleix Conchillo Flaqué
d7794abf21
audio(filters): deprecate NoisereduceFilter
2025-09-07 20:52:17 -07:00
Aleix Conchillo Flaqué
6a6a63a532
Merge pull request #2607 from pipecat-ai/aleix/scripts-evals-improve-eval-prompt
...
scripts(evals): allow user to talk and only eval when needed
2025-09-07 20:49:43 -07:00
Mark Backman
6edb6fed41
Merge pull request #2606 from pipecat-ai/mb/quickstart-lockfile
...
Remove uv.lock from quickstart
2025-09-07 06:10:14 -07:00
Mark Backman
a537382816
Add OpenAIRealtimeLLMService, AzureRealtimeLLMService ( #2596 )
...
* Add OpenAI Realtime module
* Add foundational examples for OpenAI Realtime
* Add deprecation warning to OpenAIRealtimeBetaLLMService
* Add deprecation warning to AzureRealtimeBetaLLMService
* Update Changelog
2025-09-07 09:09:57 -04:00
Aleix Conchillo Flaqué
46deaada70
scripts(evals): allow user to talk and only eval when needed
2025-09-06 19:19:08 -07:00
Mark Backman
dbc52bc6b0
Remove uv.lock from quickstart
2025-09-06 11:13:50 -04:00
Alex Zhou
d6432589f6
fix: fix format and lint by ruff
2025-09-06 10:50:47 +08:00
Alex Zhou
13b73d4406
feat: Add support for pipecat video stream; fix the bug of duplicate participants when connecting; fix the bug of RTVI messages sent via livekit messages;
2025-09-06 10:41:33 +08:00
Aleix Conchillo Flaqué
85d8282f7e
Merge pull request #2602 from pipecat-ai/aleix/pipecat-0.0.84
...
update CHANGELOG for 0.0.84
2025-09-05 19:35:26 -07:00
Aleix Conchillo Flaqué
070690ec64
update CHANGELOG for 0.0.84
2025-09-05 18:22:50 -07:00
Aleix Conchillo Flaqué
b9c96fd623
Merge pull request #2601 from pipecat-ai/aleix/daily-python-0.19.9
...
pyproject: update daily-python to 0.19.9
2025-09-05 18:21:49 -07:00
Aleix Conchillo Flaqué
f8b2ab6331
pyproject: update daily-python to 0.19.9
2025-09-05 18:14:57 -07:00
Mark Backman
ea3f7e3c34
Merge pull request #2600 from pipecat-ai/mb/livekit-dtmf
...
LiveKitTransport: Add support to send DTMF
2025-09-05 15:25:32 -07:00
Mark Backman
2f44f88b08
LiveKitTransport: Add support to send DTMF
2025-09-05 18:23:04 -04:00
Mark Backman
25747a001b
Merge pull request #2599 from pipecat-ai/mb/fix-daily-dtmf
...
DTMF: Add support for native DTMF implementation where available
2025-09-05 15:20:05 -07:00
Mark Backman
fbe4338440
DTMF: Add support for native DTMF implementation where available
2025-09-05 18:16:56 -04:00
Filipi da Silva Fuchter
64b4c65728
Merge pull request #2595 from pipecat-ai/filipi/heygen_quality
...
Improving HeyGen example video quality.
2025-09-05 17:19:25 -03:00
kompfner
29442969a9
Merge pull request #2597 from pipecat-ai/pk/fix-anthropic-tool-less-usage
...
Fix Anthropic tool-less usage
2025-09-05 15:30:29 -04:00
Paul Kompfner
dc2e1d4ad3
Fix Anthropic tool-less usage
2025-09-05 11:47:31 -04:00
Filipi Fuchter
5477dfcbea
Improving HeyGen example video quality.
2025-09-05 11:30:01 -03:00
