482 Commits

Author SHA1 Message Date
hiento09
bd0e525d66
chore: upgrade to turbo v2 and reduce ci quality gate runtime (#4324)
* chore: upgrade to turbo v2 and reduce ci quality gate runtime

* chore: upgrade to yarn v4 and deprecate turborepo

* chore: reconfigure modules and fix tests

* chore: switch to github-hosted runner

* fix: dependency resolving

* chore: clean redundant step

* chore: headless test

* chore: remove headed param

* fix: resolve dependency version

* fix: ubuntu no-sandbox test

---------

Co-authored-by: Hien To <tominhhien97@gmail.com>
Co-authored-by: Louis <louis@jan.ai>
2024-12-29 17:46:15 +07:00
Louis
3cd4db0a92
chore: bump latest cortex stable release version (#4336) 2024-12-26 10:52:16 +07:00
Louis
dccd9dd77c
chore: bump cortex 1.0.6-rc (#4330) 2024-12-24 09:56:02 +07:00
Louis
24222679fb
fix: cleaning a thread should just clear out messages (#4316)
* fix: cleaning a thread should just clear out messages

* chore: clean up
2024-12-23 12:35:30 +07:00
Louis
5163e124d8
chore: add OpenAI gpt-4o-mini and o1 models (#4311) 2024-12-21 20:01:04 +07:00
Louis
4e43f9798d
fix: fetch threads and messages without limiting (#4304)
* fix: threads and messages are cutoff

* fix: threads sorting

* chore: bump cortex latest release and app version
2024-12-20 17:55:23 +07:00
Louis
4489af6ad9
chore: deprecate Jan core's REST module - all API requests go to cortex.cpp (#4297) 2024-12-19 21:37:37 +07:00
Louis
b81b008a93
chore: use seconds timestamp system 2024-12-19 11:38:10 +07:00
Louis
6e786170e8
chore: bump cortex 1.0.5 rc2 2024-12-18 16:56:07 +07:00
Louis
ef4dcb7d9e
chore: bump cortex and engine 2024-12-16 22:10:58 +07:00
Louis
bb106eba01
fix: image and attachments 2024-12-16 17:27:06 +07:00
Louis
5a4c5eee83
Merge branch 'dev' into feat/threads-messages-requests-to-backend 2024-12-13 13:12:57 +07:00
Louis
707c23fa83
Merge pull request #4266 from janhq/fix/4238-wrong-max-tokens-remote-models
fix: 4238 - fix default max_tokens set on remote models
2024-12-13 12:41:15 +07:00
Louis
174f1c7dcb
feat: reroute threads and messages requests to the backend 2024-12-12 16:38:55 +07:00
Louis
aac2216aef
fix: 4238 - fix default max_tokens set on remote models 2024-12-12 13:20:39 +07:00
Louis
977ac3ae98
chore: 4244 - deprecate groq llama 3.1 70B Versatile 2024-12-12 10:05:35 +07:00
Louis
20a652e0eb
chore: fix openai vision models 2024-12-07 14:35:03 +07:00
hiento09
1778620fe2
feat: macos universal (#4197)
* feat: macos universal

* chore: build universal for hnswlib-node on macos

---------

Co-authored-by: Service Account <service@jan.ai>
2024-12-04 16:00:44 +07:00
Louis
68a8293179
chore: add NGL settings for vision models 2024-12-04 13:40:39 +07:00
Louis
fb0a916c50
fix: 4155 - Queue up health check on server restarting 2024-12-03 16:17:46 +07:00
Louis
a4467cf5bf
chore: bump version 0.5.10 2024-12-02 17:33:01 +07:00
Louis
541a37b8f1
fix: 4171 - Model loading gets stuck on stop 2024-12-02 14:04:13 +07:00
Louis
351236b16a
Merge pull request #3888 from px100/patch-1
Anthropic Model Updates
2024-11-30 14:29:54 +07:00
Louis
ecb39e41c5
Merge pull request #3843 from sharunkumar/more-groq-models
feat: add more Groq models
2024-11-30 13:48:17 +07:00
Louis
0f403ffd34
Merge branch 'dev' into patch-1 2024-11-30 13:43:27 +07:00
Louis
b95fa0664c
chore: bump cortex cpp 1.0.4-rc4 2024-11-29 16:19:20 +07:00
Louis
e8558d8f77
chore: bump cortex 1.0.4-rc3 2024-11-29 13:45:21 +07:00
Louis
ed01db408a
chore: bump cortex.cpp and llama.cpp 2024-11-29 10:15:39 +07:00
Louis
ad8484533d
Merge pull request #4132 from janhq/fix/4094-gpu-mode-not-working-after-first-factory-reset
fix: 4094 - gpu mode toggle on by default but not affect for the first time launch
2024-11-26 23:46:06 +07:00
Louis
3854d43e8a fix: should queue engine set on changes 2024-11-26 22:58:30 +07:00
Louis
2478cf7bc3
Merge pull request #4130 from janhq/chore/4123-update-default-engine-request-body
feat: update Jan’s client request to adapt API changes from Cortex
2024-11-26 21:38:14 +07:00
Louis
d55b1dd2f8
fix: 4094 - gpu mode toggle on by default but not affect for the first time launch 2024-11-26 19:50:23 +07:00
Louis
638dbf178e
fix: 4012 - active model should be gone as soon as cortex.cpp server is killed 2024-11-26 19:03:26 +07:00
Louis
1108e6c221
test: correct test cases 2024-11-26 15:25:26 +07:00
Faisal Amir
4f45bd8136 chore: update version extension anthropic 2024-11-26 09:58:21 +07:00
Faisal Amir
8f54ab3e3a enhancement: increased max-token limit claude-3.5 2024-11-25 09:42:54 +07:00
Louis
f709c7723f
fix: factory reset hang on wiping data 2024-11-21 23:10:48 +07:00
Louis
ef3c090360
fix: Phi 3 Mini Instruct model download url replacement 2024-11-21 16:17:27 +07:00
Louis
b733a8738d
fix: incorrect gpu selection that cause performance degrade on CPU only mode 2024-11-21 14:15:28 +07:00
Louis
fe6412e1d4
feat: configure HuggingfaceToken via cortex.cpp 2024-11-21 13:13:29 +07:00
Louis
daefa99a9d chore: keep the deps folder with gitkeep placeholder file 2024-11-21 11:26:21 +07:00
Louis
8590709480 fix: correct download script to relocate dll files properly 2024-11-21 10:54:44 +07:00
Louis
06df084342
fix: temporary create a deps folder to have cortex.cpp work 2024-11-21 09:16:15 +07:00
Louis
43c5feb3cc
chore: disable stream: false on o1 models 2024-11-20 21:45:08 +07:00
Louis
df0801d6d9
chore: add back stream parameter to o1 models 2024-11-20 21:40:46 +07:00
Louis
4820218a11
fix: broken cohere API response transform 2024-11-20 21:36:08 +07:00
Louis
33bfd0eed8
fix: disable timeout on model load 2024-11-20 20:39:43 +07:00
Louis
239e5f52e8
fix: force vision models to run with legacy settings 2024-11-20 12:43:10 +07:00
Louis
3ea2d9c0ae
fix: bump cortex.cpp to latest version - recursively scanning models folder should also include remote models 2024-11-20 12:33:42 +07:00
Louis
10e1201083
Merge pull request #4049 from janhq/fix/openai-o1-model-parameters
fix: correct OpenAI o1 model parameters
2024-11-20 01:09:58 +07:00