Aleix Conchillo Flaqué
7eb9dfde38
pyproject: include langchain-community and langchain-openai
2024-06-04 15:43:54 -07:00
Aleix Conchillo Flaqué
0b691ff597
Merge pull request #198 from pipecat-ai/aleix/websocket-transport
...
websocket transport support
2024-06-01 04:40:39 +08:00
Aleix Conchillo Flaqué
0d6eee705f
Merge pull request #190 from TomTom101/TomTom101/langchain
...
Langchain service
2024-06-01 04:21:12 +08:00
Aleix Conchillo Flaqué
3e289a7bef
pyproject: add protobuf dependency
2024-05-31 11:36:52 -07:00
TomTom101
4b39efeee3
fix(langchain): try/catch langchain import in service; Only langchain is installed with the [langchain] extra ( #190 )
2024-05-31 10:19:27 +02:00
Kwindla Hultman Kramer
d5f106ae19
pr fixes
2024-05-29 23:41:35 -07:00
Kwindla Hultman Kramer
920745345a
cartesia tts support
2024-05-29 23:35:35 -07:00
TomTom101
143033d7db
fix: install langchain-community with the langchain extra
2024-05-30 03:15:14 +02:00
TomTom101
278a2fed56
wip: First stab at langchain support
...
Is this a service or processor?
How to deal with conversation history? LC has sophisticated means of this, but might get in the way of `LLMResponseAggregator`
2024-05-30 03:15:14 +02:00
Aleix Conchillo Flaqué
6a68d9a57e
pyproject: update daily-python to 0.9.0
2024-05-28 18:30:43 -07:00
Aleix Conchillo Flaqué
95bd58cced
pyproject: depend on daily-python 0.8.0
2024-05-23 13:10:48 -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
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
Jon Taylor
8fa9fdcd5a
Reworked readme to have more pipes and cats
2024-05-12 17:41:30 -07:00
Aleix Conchillo Flaqué
6d10027f2d
change pypi repo to pipecat-ai
2024-05-12 12:08:43 -07:00
Aleix Conchillo Flaqué
b026915d19
initial commit for new pipecat architecture
2024-05-12 10:07:25 -07:00
Aleix Conchillo Flaqué
2729c6bf5b
dependabot: update packages 05-06-24
2024-05-06 15:33:33 -07:00
Aleix Conchillo Flaqué
2f341e4fb0
pyproject: pillow security fixes
2024-04-22 10:28:42 -07:00
Aleix Conchillo Flaqué
0c2b3f8b65
minor fireworks updates
2024-04-11 15:34:23 -07:00
chadbailey59
0b7578056d
added fireworks adapter ( #118 )
2024-04-11 17:15:02 -05:00
Aleix Conchillo Flaqué
7b49c9ade3
services: FalImageGenService now uses fal-client library
2024-04-11 14:09:01 -07:00
Aleix Conchillo Flaqué
18bf09c704
services: added MoondreamService
2024-04-09 22:36:35 -07:00
Aleix Conchillo Flaqué
9ada56d0b0
pyproject: use compatible version
2024-04-09 08:41:54 -07:00
Aleix Conchillo Flaqué
2654ca1f62
pyproject: don't use local version for test pypi
2024-04-05 07:51:52 -07:00
Aleix Conchillo Flaqué
46d265514e
pyproject: update github url
2024-04-04 15:52:28 -07:00
Aleix Conchillo Flaqué
d57d473c13
pyproject.toml: use setuptools_scm to auto manage versions
2024-04-03 16:13:07 -07:00
Aleix Conchillo Flaqué
128d350abc
pyproject.toml: use project optional dependencies and pin them
2024-04-03 15:27:31 -07:00
chadbailey59
2f59e38a7a
Modularize tricky dependencies ( #95 )
...
* removed pyaudio from threaded transport
* modularized torch and torchaudio
* modularized local transport
* Working Dockerfile as well
* docker updates for fly.io
2024-04-03 10:48:11 -05:00
Moishe Lettvin
2bda4c3307
Websocket transport
2024-03-25 13:54:34 -04:00
Aleix Conchillo Flaqué
16257f8ec0
move src/dailyai/tests to tests
2024-03-19 14:59:48 -07:00
Moishe Lettvin
eacaea7db4
Anthropic LLM service
2024-03-15 19:40:37 -04:00
Moishe Lettvin
b8b35db89c
Remove run_to_queue and run from AIService class
2024-03-15 11:04:22 -04:00
Moishe Lettvin
33793ca9f8
update description
2024-03-11 07:31:39 -04:00
Moishe Lettvin
d26aede667
updates to pyproject.toml
2024-03-11 07:25:20 -04:00
Moishe Lettvin
ad993056d8
rename to dailyai
2024-03-11 07:16:20 -04:00
Moishe Lettvin
643be238f9
getting started
2024-03-03 16:31:31 -05:00
chadbailey59
d90fdb1cae
Isolated changes to add VAD ( #32 )
...
* added VAD
* added separate 'vad enabled' property
2024-02-28 15:16:44 -06:00
Moishe Lettvin
ee1ce8f288
Abstract base transport class & local transport class
2024-02-08 08:15:28 -05:00
chadbailey59
70d07b6ea2
WIP: environment cleanup ( #19 )
...
* removed env var usage from SDK services
* started consolidating configure.py
* 1–3 work
* cleaned up the rest
* more cleanup
* cleanup and 05 tinkering
* made fal keys optional
2024-02-06 15:07:16 -06:00
Moishe Lettvin
f0d9b0613e
Add faster_whisper to module dependencies; remove unneeded import
2024-01-25 11:27:00 -05:00
chadbailey59
6e8ebbd34c
fal.ai integration ( #3 )
...
* fal.ai image gen
* some sample and readme updates
* holy cow this is fast
* basic image-gen working
* starting audio prompt and reset
* short confirmation words
* moved fal module to pyproject.toml
---------
Co-authored-by: Moishe Lettvin <moishel@gmail.com >
2024-01-17 12:08:00 -06:00
Moishe Lettvin
b48a377b17
a little cleanup, uglier-than-I'd-like 01-say-one-thing sample added
2024-01-05 14:19:18 -05:00
Moishe Lettvin
ed192053e7
remove dist files, some updates to toml
2023-12-27 12:28:15 -05:00
Moishe Lettvin
9f92ddd331
builds properly
2023-12-27 08:27:09 -05:00
Moishe Lettvin
65ae8b0464
setting up for dist
2023-12-27 08:00:01 -05:00
