97 Commits

Author SHA1 Message Date
hiento09
f11a59bece
Add detect cuda version (#1351)
Co-authored-by: Hien To <tominhhien97@gmail.com>
2024-01-04 22:53:21 +07:00
Louis
c07b418ff2
fix: Error occurred: Unexpected token "d", "data: ..." is not a valid JSON (#1332) 2024-01-04 18:22:07 +07:00
NamH
26eb1d9a67
feat(Model): #1028 made model.json optional (#1314)
* feat(Model): #1028 made model.json optional

Signed-off-by: James <james@jan.ai>

---------

Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
2024-01-04 16:50:32 +07:00
hiento09
c16da28186
correct type utf-8 (#1311)
Co-authored-by: Hien To <tominhhien97@gmail.com>
2024-01-03 16:01:50 +07:00
hiento09
0a7e26d5fb
Fix memory on mac included cached and swap (#1298)
* Fix memory on mac included cached and swap

* set inteval monitor to 0.5s

---------

Co-authored-by: Hien To <hien@jan.ai>
2024-01-03 02:09:17 +07:00
hiento09
45fdadf1ea
Switch from systeminformation to os-utils to resolve bitdefender antivirus on windows, and reduce memory leak for monitor extension (#1282)
Co-authored-by: Hien To <tominhhien97@gmail.com>
2024-01-02 13:39:22 +07:00
hiento09
b5078599ec
fix ci test run failed (#1267)
Co-authored-by: Hien To <tominhhien97@gmail.com>
2023-12-31 12:10:10 +07:00
hiento09
5300172836
Fix wrong linux nitro path (#1266)
Co-authored-by: Hien To <tominhhien97@gmail.com>
2023-12-31 11:37:55 +07:00
Hoang Ha
f68909bb20
Merge branch 'main' into add/model-list 2023-12-29 18:34:24 +07:00
Louis
a9579a3cbd
fix: remove redundant gpu detection prompt event (#1254) 2023-12-29 16:37:34 +07:00
Hoang Ha
d99fc186b9
Merge branch 'main' into add/model-list 2023-12-29 16:23:48 +07:00
hiento09
1ec8174700
Feature GPU detection for Jan on Windows and Linux (#1242)
* Add js function to generate gpu and cuda detection

* inference nitro manage via json file instead of bash and bat script

* Add /usr/lib/x86_64-linux-gnu/ to linux check gpu

* chore: add CPU - GPU toggle

* correct file path

* fix: exist file sync check

* fix: get resources path

* Fix error jan/engines create existed error

* Seting sync to file

* Fix error show notification for GPU

* Set notify default to true

---------

Co-authored-by: Hien To <tominhhien97@gmail.com>
Co-authored-by: Louis <louis@jan.ai>
2023-12-29 15:56:36 +07:00
hahuyhoang411
7fb2a60bca fix(package.json): update version to 1.0.17 2023-12-28 18:35:34 +07:00
Louis
5250061c11
feat: Jan Server, API and decoupled clients (#948)
* chore: expose fs apis

* chore: correct electron import path

* update download api

Signed-off-by: James <james@jan.ai>

* update chat_completion

Signed-off-by: James <james@jan.ai>

* fix electron import

Signed-off-by: James <james@jan.ai>

* feat: adding API support at 1337 (#991)

Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>

* feat: Add /chat/completion api and handler

* chore: add todo for modelList

* chore: read engine.json for openai chat_completion (#1030)

Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>

* refactor: move routes to shared node module

* refactor: exported modules from core with types (#1172)

* refactor: exported modules from core with types

* fix: fix file reading args

* refactor: fileManager handles

* fix: app issues with server refactoring

* refactor: shared server module (#1210)

* chore: resolve main

* chore: update makefile

---------

Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
Co-authored-by: NamH <NamNh0122@gmail.com>
Co-authored-by: hiro <vuonghoainam.work@gmail.com>
2023-12-28 17:57:39 +07:00
hiento09
cfbc5674fe
Remove un-use resource checking to free ram on windows - monitor extension (#1241)
Co-authored-by: Hien To <tominhhien97@gmail.com>
2023-12-28 15:34:11 +07:00
Louis
7feaf9694d
feat: Deprecate model.json ready state in favor of .download ext (#1238)
* feat: Deprecate model.json ready state in favor of .download ext

* refactor: resolve ts ignore

* chore: fix warning

* fix: path polyfill on Windows
2023-12-28 14:06:13 +07:00
hiento09
d4b4540505
add sleep 500ms if platform is windows (#1215)
Co-authored-by: Hien To <tominhhien97@gmail.com>
2023-12-26 19:15:38 +07:00
hiento09
7c0b45f0c5
Fix switch thread crash nitro windows linux (#1214)
* Add fix bug #1204 on windows

* nitro gpu exit on kill

* correct bat script syntax

* Remove wait 5 second before start nitro

---------

Co-authored-by: Hien To <tominhhien97@gmail.com>
2023-12-26 17:33:20 +07:00
hahuyhoang411
2aab5ff355 fix(package.json): update version to 1.0.16 2023-12-21 20:55:26 +07:00
hiro
f0c889ce6b
Merge pull request #1128 from janhq/feat/gh_codeql
feat: Add codeQL analysis for push main and pr main
2023-12-21 15:43:27 +07:00
hiento09
4f93e14d16
Fix token speed slow in machine has multi gpus (#1157)
* Update bat script windows choose GPU has highest ram to start nitro

* Update bash script for linux to choose gpu has highest vram

---------

Co-authored-by: Hien To <tominhhien97@gmail.com>
2023-12-21 15:38:21 +07:00
Louis
8d5fce9165
fix: malicious redirections & security risk 2023-12-21 14:10:33 +07:00
Louis
4e044df044
chore: bump model-extension version 2023-12-21 13:46:29 +07:00
Louis
e0370210a7
fix: #1096 yield error message upon thread switching (#1109) 2023-12-20 14:58:47 +07:00
NamH
84fb5ef346
fix(Thread): #1042 allow create new thread by clicking Use in Jan Hub (#1103)
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
2023-12-19 17:06:57 +07:00
Louis
4653030bc1
fix: #1097 streaming response is replaced by error message (#1099) 2023-12-19 16:42:13 +07:00
Louis
e3c1787d57
fix: app failed to load model sometime due to race condition (#1071) 2023-12-19 11:10:07 +07:00
hiento09
9398b734a1
Posthog disable click event and increase timeout for nitro load model request (#1060)
Co-authored-by: Service Account <service@jan.ai>
2023-12-18 21:10:36 +07:00
Louis
80f953ba1b
fix: thread is broken after deleted first generated message (#1061) 2023-12-18 15:39:29 +07:00
Louis
f62b0ca4ef
chore: remigrate if there is no models dir (#1038) 2023-12-15 21:09:35 +07:00
hiento09
fde176955a
bump nitro version to 0.1.30 (#1036) 2023-12-15 17:39:49 +07:00
Louis
92442ba093
fix: migrate new models (#1034)
* fix: migrate new models

* fix: filter out invalid model files

* chore: migrate models
2023-12-15 16:14:52 +07:00
0xSage
c556427905 more copy nits 2023-12-15 16:33:49 +08:00
Louis
cf7e9350b7 fix: show proper error message 2023-12-15 14:14:59 +07:00
Louis
bcc9bd6997
fix: delete first message then regenerate again will break the thread (#1015) 2023-12-15 09:57:06 +07:00
Faisal Amir
4f41dab9b5 feat: move stop inference button into the send button 2023-12-14 16:40:51 +07:00
hiro
b3405a6fdc
Merge pull request #975 from janhq/fix/kill_nitro
feat: Kill nitro process with API - nitro 0.1.27
2023-12-13 17:17:52 +07:00
hiro
257011309f fix: Kill nitro many times app onDispose 2023-12-13 16:47:34 +07:00
hiro
96fa392fba
Update extensions/inference-nitro-extension/src/module.ts
Co-authored-by: Louis <louis@jan.ai>
2023-12-13 16:40:56 +07:00
hiro
539f11e583 feat: Add api to kill nitro 2023-12-13 16:35:59 +07:00
hiro
7f60265b3e chore: Bump nitro to 0.1.27 to support api to kill process 2023-12-13 16:35:37 +07:00
Louis
3266014b29
fix: 963 can not run openai models on windows (#974) 2023-12-13 16:26:26 +07:00
hiro
5f404e2c3f
feat: Add prompt template resolver feature to system_prompt, ai_prompt, user_prompt 2023-12-13 14:29:34 +07:00
hiro
587f5addfa fix: Fix issues based on Louis comments 2023-12-13 01:27:18 +07:00
hiro
f2688771ff feat: Add triton trtllm for engine for remote models 2023-12-13 01:24:36 +07:00
hiro
8f5c5e1e42 chore: Bump nitro to 0.1.26 2023-12-12 19:41:48 +07:00
hiro
14f83ddb70 fix: Revert drogon thread to 1 instead of CPU num 2023-12-12 07:27:25 +07:00
hiro
16c66e968c chore: Update n_threads to cpu_threads 2023-12-12 06:15:22 +07:00
hiro
0e63689eae fix: inference engine nitro stopModel undefined in module.ts 2023-12-12 06:15:22 +07:00
hiro
f528e9ea77 fix: Update inference nitro with n_threads equals to physcial core num 2023-12-12 06:15:22 +07:00