Aleix Conchillo Flaqué
32d2f0db66
update CHANGELOG.ms with filters updates
2024-05-22 15:46:13 -07:00
Aleix Conchillo Flaqué
e1169a4e82
processors(WakeCheckFilter): push error
2024-05-22 15:44:44 -07:00
Aleix Conchillo Flaqué
0e5711e62d
examples: update 10-wake-work.py to use WakeCheckFilter
2024-05-22 15:44:44 -07:00
Aleix Conchillo Flaqué
0ddfa3de5b
move WakeCheckFilter to processors/filters
2024-05-22 15:44:43 -07:00
Kwindla Hultman Kramer
661aa79b7c
fix user_id str field name in TranscriptionFrame
2024-05-22 15:44:43 -07:00
Kwindla Hultman Kramer
2c32cc2f27
improved wake word filter
2024-05-22 15:44:43 -07:00
Aleix Conchillo Flaqué
d7bb0bc5cb
Merge pull request #164 from pipecat-ai/readd-vad-exp-smoothing
...
vad: re-add volume exponential smoothing
2024-05-23 06:44:27 +08:00
Aleix Conchillo Flaqué
d5644c3ab9
vad: re-add volume exponential smoothing
2024-05-22 15:26:32 -07:00
Aleix Conchillo Flaqué
09ab8e3efd
Merge pull request #163 from pipecat-ai/update-0.0.20-deps
...
update requirements files
2024-05-23 05:40:12 +08:00
Aleix Conchillo Flaqué
2f683529ec
update requirements files
2024-05-22 14:39:26 -07:00
Aleix Conchillo Flaqué
6ac012a82b
Merge pull request #158 from pipecat-ai/use-pyloudnorm-loudness
...
interruptions: introduce pyloudnorm to compute loudness
2024-05-23 05:24:38 +08:00
Aleix Conchillo Flaqué
075194cb54
update CHANGELOG for 0.0.20
2024-05-22 14:21:13 -07:00
Aleix Conchillo Flaqué
269f070051
audio: no need for compute_rms
2024-05-22 14:09:24 -07:00
Aleix Conchillo Flaqué
3342c9d7c2
services(stt): use calculate_audio_volume
2024-05-22 13:05:20 -07:00
Aleix Conchillo Flaqué
b468b2f926
audio: clamp normalized volume
2024-05-22 13:04:09 -07:00
Aleix Conchillo Flaqué
af1c7d0023
interruptions: introduce pyloudnorm to compute loudness
...
https://github.com/csteinmetz1/pyloudnorm
2024-05-22 11:52:07 -07:00
Aleix Conchillo Flaqué
34670eef79
Merge pull request #162 from pipecat-ai/reset-before-pushing
...
processors: reset aggergator before pushing
2024-05-23 02:51:55 +08:00
Aleix Conchillo Flaqué
979739c1b7
processors: reset aggergator before pushing
2024-05-22 11:26:08 -07:00
Aleix Conchillo Flaqué
83ed6870b9
Merge pull request #161 from pipecat-ai/only-interrupt-assistant
...
processors: only interrupt asssisstant
2024-05-23 02:02:43 +08:00
Aleix Conchillo Flaqué
57a568986a
processors: only interrupt asssisstant
...
We were pushing interruption frames in the audio task. This was caussing the
LLMUserResponseAggregator to push the accumulated text and then casuing the LLM
to respond.
2024-05-22 10:15:35 -07:00
Aleix Conchillo Flaqué
e828e26b5b
Merge pull request #159 from pipecat-ai/create-pool-executor
...
transports: run threads in their own ThreadPoolExecutor
2024-05-22 15:49:03 +08:00
Aleix Conchillo Flaqué
825738440e
transports: run threads in their own ThreadPoolExecutor
2024-05-21 18:52:27 -07:00
Aleix Conchillo Flaqué
147bd1a075
Merge pull request #156 from pipecat-ai/pipecat-0.0.19
...
update CHANGELOG.md for 0.0.19
2024-05-21 12:36:48 +08:00
Aleix Conchillo Flaqué
209e97f372
update CHANGELOG.md for 0.0.19
2024-05-20 21:33:15 -07:00
Aleix Conchillo Flaqué
47f8627432
Merge pull request #155 from pipecat-ai/llm-accumlate-full-response
...
aggregators: accumulate full responses and take interruptions into ac…
2024-05-21 11:34:39 +08:00
Aleix Conchillo Flaqué
cc6713837a
github: publish test to pypi again. simply always use PRs
2024-05-20 12:19:39 -07:00
Aleix Conchillo Flaqué
728fe0ad88
github: don't publish to test pypi twice
2024-05-20 12:15:54 -07:00
Aleix Conchillo Flaqué
dbba45349f
github: don't run publish_test on main branch
2024-05-20 12:14:00 -07:00
Aleix Conchillo Flaqué
40ccf46b4b
aggregators: accumulate full responses and take interruptions into account
2024-05-20 11:40:57 -07:00
Aleix Conchillo Flaqué
077bb9f20a
Merge pull request #153 from pipecat-ai/expose-llm-messages
...
aggregators: expose LLM messages
2024-05-21 02:40:26 +08:00
Aleix Conchillo Flaqué
e4c990c677
aggregators: expose LLM messages
2024-05-20 10:51:37 -07:00
Aleix Conchillo Flaqué
1c8b9d813a
examples: minot updates to storytelling-chatbot instructions
2024-05-20 10:31:33 -07:00
Aleix Conchillo Flaqué
83812f2671
transports(daily): implement DailyOutputTransport.send_message
2024-05-20 10:30:59 -07:00
Aleix Conchillo Flaqué
4053c33899
update CHANGELOG for 0.0.17
2024-05-19 19:27:20 -07:00
Aleix Conchillo Flaqué
03978b63bc
update linux-py3.10-requirements.txt
2024-05-19 19:27:04 -07:00
Aleix Conchillo Flaqué
bf036be6b8
Merge pull request #150 from pipecat-ai/khk-gemini
...
Initial commit of Google Gemini LLM service.
2024-05-20 10:24:31 +08:00
Kwindla Hultman Kramer
7ffb10d7f5
add to CHANGELOG.md
2024-05-19 12:44:45 -07:00
Kwindla Hultman Kramer
66377954cb
fix up openai vision and gemini implementation
2024-05-19 12:33:57 -07:00
Kwindla Hultman Kramer
e507686cef
oops, fix openai.py
2024-05-19 11:13:39 -07:00
Kwindla Hultman Kramer
e5ddaf14f4
add google and deepgram to README.md
2024-05-19 11:09:30 -07:00
Kwindla Hultman Kramer
cf597a2f6b
add back in debug log line in openai.py
2024-05-19 11:08:38 -07:00
Kwindla Hultman Kramer
d83f0aabca
generate macos-py3.10-requirements.txt with Python 3.10
2024-05-19 10:53:50 -07:00
Kwindla Hultman Kramer
b337e984b3
Initial commit of Google Gemini LLM service.
...
Gemini text input works. We translate from OpenAILLMContext format
on the fly in the GoogleLLMService implementation. This commit also
implements image input (vision) in both the GoogleLLMService and in
the OpenAILLMService. Image input is a hack and needs to be revisited.
OpenAI expects images to be uploaded as base64-encoded JPEGs. Google
does not require the base64 encoding. Other than for images, we use
the OpenAI format as our standard, but base64-encoding the images
and then unencoding them in the GoogleLLMService feels wasteful.
2024-05-19 10:35:20 -07:00
Aleix Conchillo Flaqué
6366ee072e
Merge pull request #144 from pipecat-ai/initial-interruptions
...
intial basic interruptions support
2024-05-20 01:33:15 +08:00
Aleix Conchillo Flaqué
c3bfcbd562
aggregators: clear accumulated responses if interruption happens
2024-05-19 10:21:45 -07:00
Aleix Conchillo Flaqué
c0d5054798
examples: some prompt tweaking
2024-05-19 09:41:36 -07:00
Aleix Conchillo Flaqué
810dc30d3d
examples: fix examples to use LLMFullResponseEndFrame
2024-05-19 09:39:34 -07:00
Aleix Conchillo Flaqué
36dd4933e9
example: add assistant responses to simple chatbot
2024-05-18 10:01:46 -07:00
Aleix Conchillo Flaqué
435fffe1b0
add LLMFullResponseStartFrame/LLMFullResponseEndFrame
2024-05-18 09:49:38 -07:00
Aleix Conchillo Flaqué
2b8f1c4cda
services(openai): send LLMResponseStartFrame for each completion
2024-05-17 17:47:33 -07:00
