Commit Graph

169 Commits

Author SHA1 Message Date
Ben Xu c2de04ab63 update profiles to be compatible with new interpreter 2024-12-09 13:37:50 -08:00
Ben Xu 178ffc83bd update logging with debug env variable 2024-12-09 13:37:36 -08:00
Ben Xu 07672f498b add voice assistant state communication and clear chat context 2024-12-09 13:37:19 -08:00
Ben Xu f6c13a13bd send multimodal message on startup of multimodal agent 2024-12-09 13:35:55 -08:00
ben 1720b783ce
LiveKit Pipeline Agent (#4)
* init processors

* fix image append for chat messages

* add pre tts cb

* stash non-functional worker changes

* add complete flag parsing worker

* stash worker changes

* update worker.py to handle message context correctly

* draft worker -- currently mismanages chat ctx

* stash draft delta changes

* working worker on push to talk happy path

* final working worker on push to talk

* refactor append image

* updated video frame processing

* rm text processor

* working draft main

* draft working poetry
2024-11-25 20:10:16 -08:00
killian befddaf205 Cartesia 2024-11-01 16:48:12 -07:00
killian a5b6948c9c Multimodal code execution 2024-10-23 19:32:19 -07:00
killian 207ec088b4
Merge pull request #309 from benxu3/livekit-realtime
add realtime livekit multimodal worker
2024-10-02 15:53:22 -07:00
Ben Xu 21e04c18fe isolate instruction update 2024-10-02 17:52:31 -04:00
Ben Xu 35b1c5caa2 Revert "update instructions"
This reverts commit 9c145d0209.
2024-10-02 17:51:32 -04:00
Ben Xu 9c145d0209 update instructions 2024-10-02 17:42:19 -04:00
Ben Xu 121e67e896 Revert "process custom flags on worker"
This reverts commit 12efc95688.
2024-10-02 17:34:53 -04:00
Ben Xu 5810db4692 init livekit quickstart multimodal worker 2024-10-02 17:32:33 -04:00
Ben Xu 551e28a9d6 update 01-app submodule 2024-09-23 14:30:50 -04:00
Ben Xu 15ab78a3aa replace old rn app with 01-app 2024-09-23 14:12:24 -04:00
Ben Xu 12efc95688 process custom flags on worker 2024-09-23 14:08:35 -04:00
killian 197417a65b Default tts to elevenlabs 2024-09-18 13:51:28 -07:00
killian 393d127540 Turn off debugging 2024-09-18 13:47:55 -07:00
killian b3ebbabcf1 Change tts and stt from profiles for app, set context mode to be True at the start 2024-09-18 13:46:47 -07:00
killian 81242d8568 Change tts and stt from profiles for app, set context mode to be True at the start 2024-09-18 13:15:00 -07:00
killian a0d1e7038b `01.1` 2024-09-09 12:02:03 -07:00
killian 4aec113c41 `01.1` (Later Tonight) 2024-09-05 12:57:06 -07:00
killian 1839cc6e74 Better default profile, better QR 2024-09-05 00:00:25 -07:00
killian f4d9cd39e7 OpenAI TTS and worker retry logic 2024-09-04 23:52:11 -07:00
killian 927fba85a6 OpenAI TTS 2024-09-04 15:02:32 -07:00
killian bb53f9f81f Change worker to be a python file 2024-09-01 21:21:29 -07:00
killian 6fb71dde41 Docs changes, minor fixes 2024-08-31 15:04:42 -07:00
killian 51c8206c57 Fixing auth 2024-08-28 10:45:43 -07:00
killian 36f765c4d1 Bumped OI and fixed auth 2024-08-28 08:55:39 -07:00
killian c1c3c377e2 01.1 2024-08-25 17:51:43 -07:00
killian a7f381cb36 01.1 2024-08-25 17:51:22 -07:00
human-bee f1ee068c0c Hardcode WiFi and server credentials moved to top of file for testing 2024-08-23 18:50:53 -07:00
human-bee 5f2ddc8ce3 Hardcode WiFi and server credentials moved to top of file for testing 2024-08-23 18:46:33 -07:00
killian 52d88fd72c Cleaned up starting logic 2024-08-22 18:56:30 -07:00
Ben Xu a595bdf570 consolidate tunneling to ngrok service 2024-08-15 15:18:56 -07:00
killian d4259759d1
Docs overhaul
[WIP] Improve docs
2024-08-01 10:59:37 -07:00
Mike Bird d1989027ef update default profile 2024-07-30 15:10:34 -04:00
killian 93f635b915 Changed tests, remove acknowledge requirement 2024-07-29 19:45:33 -07:00
Mike Bird 5fabfb06f0 Expand the configuration guide with examples and instructions on using custom profiles, including TTS provider setup 2024-07-22 16:24:05 -04:00
killian fc97ef6a24 Added tests 2024-07-22 12:12:50 -07:00
killian d2496fa8a2 Removed print statements, better audio playback 2024-07-16 08:28:29 -07:00
killian 4640b4f1a0 Use official OI server. 3 second latency. 2024-07-15 21:58:33 -07:00
killian fef311e5b3 Updated realtimestt, removed print statements 2024-07-15 14:22:37 -07:00
killian 6ee37e7f66 Updated packages, only run `mpv` if needed 2024-07-15 14:18:03 -07:00
killian 296d84ebd2 Global interpreter 2024-07-15 13:51:44 -07:00
killian d8d7658f8a Restored sending TTS service to client 2024-07-10 11:14:27 -07:00
killian d13c0cf3a4 Open Interpreter compatible `--profiles` 2024-07-10 11:08:37 -07:00
killian fda23e95b2 Implemented `profiles` 2024-07-10 10:56:54 -07:00
Ben Xu 632af7f7ba Merge branch 'main' of https://github.com/benxu3/01 into async-interpreter 2024-06-24 13:00:39 -04:00
Ben Xu 0e68bb7125 add docs fixes for esp32 and async interpreter 2024-06-24 13:00:27 -04:00