NamH
d2284070fc
fix: disable flash_attn if vulkan is enabled ( #3080 )
...
Signed-off-by: James <namnh0122@gmail.com>
2024-06-21 14:27:16 +07:00
NamH
6ee5d16e5c
fix: duplicate role inside messages cause some model to refuse to answer ( #3006 )
...
* fix: duplicate role inside messages cause some model to refuse to answer
Signed-off-by: James <namnh0122@gmail.com>
* update
* Bump cortex to 0.4.12
* some model require not empty message
update
---------
Signed-off-by: James <namnh0122@gmail.com>
Co-authored-by: Van Pham <64197333+Van-QA@users.noreply.github.com>
2024-06-10 16:19:31 +07:00
phoval
57177d4409
fix: undefined browser ( #3011 )
...
electron is not available
2024-06-10 10:13:27 +07:00
NamH
02478b3242
feat: add input actions for setting item ( #2978 )
...
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
2024-06-02 22:41:27 +07:00
Faisal Amir
faa09bd2bf
feat: Dekstop Revamp ( #2877 )
...
* feat: desktop revamp
* feat: refactor system monitor
* fix linter CI
* remove unused import component
* added responsive and resizeable component
* responsive and resizeable local server page
* finalize responsive and resizeable component
* fix scroll custom ui
* remove react scroll to bottom from modal troubleshoot
* fix modal troubleshoot ui
* fix setting gpu list
* text area custom scroll bar
* fix padding message input
* cleanup classname
* update inference engine model dropdown
* update loader style
* update quick ask ui
* prepare theme provider
* update dark theme
* remove update hotkey list model and navigation
* fix: cleanup hardcode classname
* fix: update feedback
* Set native theme electron
* update destop ui revamp from feedback
* update button icon component insider icon chat input message
* update model dropdown ui
* update tranaparent baclground
* update logo model provider
* fix: set background material acrylic support to blur background windows
* fix: update tranparent left and right panel
* fix: linter CI
* update app using frameless window
* styling custom style minimize, maximize and close app
* temporary hidden maximize window
* fix: responsive left and right panel
* fix: enable click outside when leftpanel responsive
* fix: remove unused import
* update transparent variable css windows
* fix: ui import model
* feat: Support Theme system (#2946 )
* feat: update support theme system
* update select component
* feat: add theme folder in root project
* fix: padding left and right center panel
* fix: update padding left and right
* chore: migrate themes
* fix: rmdirsync error
* chore: update gitignore
* fix: cp recursive
* fix: files electron package json
* fix: migration
* fix: update fgit ignore
---------
Co-authored-by: Louis <louis@jan.ai>
* fix: update feedback missing state when refrash app
* fix: error test CI
* chore: refactor useLoadThemes
* chore: cleanup unused vars
* fix: revert back menubar windows
* fix minor ui
* fix: minor ui
---------
Co-authored-by: Louis <louis@jan.ai>
2024-05-29 13:37:18 +07:00
Faisal Amir
b1856b689e
fix: unchange title and last message when clean or delete message ( #2937 )
2024-05-27 09:51:18 +07:00
Faisal Amir
a6ccd672c5
fix: validate max_token from context_length value ( #2870 )
2024-05-06 15:10:37 +07:00
NamH
7d4cc67aa1
fix: stop server if failed to load model ( #2807 )
...
fix: load model error start server state not update
Co-authored-by: James <james@jan.ai>
2024-04-24 20:20:15 +07:00
Louis
48f351aefd
fix: new thread with overridden settings ( #2798 )
2024-04-24 14:14:04 +07:00
Louis
54af9f9e43
fix: broken stop word input - support multiple stop words ( #2762 )
2024-04-21 17:54:41 +07:00
NamH
95632788e4
chore: default context length to 2048 ( #2746 )
2024-04-17 19:14:51 +07:00
NamH
31397de2d1
Refactor/deprecate hugging face ext ( #2620 )
...
* refactor: deprecate huggingface extension
Signed-off-by: James <james@jan.ai>
2024-04-16 17:23:45 +07:00
Louis
9369ac3e8b
Merge branch 'dev' into main
2024-04-15 14:57:31 +07:00
Andreas Deininger
81e8889568
Fix typos ( #2714 )
2024-04-15 13:27:28 +07:00
Louis
02c49e796d
fix: race condition issue - reading settings.json file ( #2683 )
...
* fix: race condition issue - reading settings.json file
* fix: cannot reset data while starting model
* chore: remove extension suffix
2024-04-11 15:37:46 +07:00
Louis
d93d74c86b
feat: nitro additional dependencies ( #2674 )
2024-04-11 09:13:02 +07:00
Louis
3f23de6c28
feat: move log into monitoring extension ( #2662 )
2024-04-10 14:35:15 +07:00
Louis
9479beb7d1
fix: unload model while loading cause unknown error ( #2649 )
...
* fix: unload model while loading cause unknown error
* chore: mask placeholder
2024-04-09 11:31:42 +07:00
Louis
f8cf93a906
chore: add GPU driver and toolkit status ( #2628 )
2024-04-08 09:50:16 +07:00
Louis
9303e7aeb4
fix: object is destroyed block app exit ( #2623 )
2024-04-05 14:30:43 +07:00
Louis
1eaf13b13e
fix: cancel loading model with stop action ( #2607 )
2024-04-04 10:57:54 +07:00
Louis
52654b1055
chore: add open log dir to troubleshooting modal ( #2605 )
2024-04-04 08:55:00 +07:00
Louis
d579d8a45c
fix: app does not gracefully stop a model ( #2593 )
2024-04-03 22:22:43 +07:00
Louis
3fded8fd20
fix: regenerate message should not include the assistant's previous response ( #2583 )
2024-04-02 22:17:35 +07:00
Louis
6f0ee23776
fix: missing load model error message ( #2581 )
2024-04-02 22:16:43 +07:00
Louis
89653eda08
fix: disabling Vulkan causes users to be stuck in GPU-accelerated mode ( #2578 )
2024-04-02 17:35:15 +07:00
Louis
f6d3b53ab5
Merge branch 'main' into dev
...
# Conflicts:
# web/screens/Chat/ErrorMessage/index.tsx
2024-04-02 11:09:59 +07:00
Louis
1451f678db
fix: file input update delay ( #2540 )
2024-03-29 22:02:48 +07:00
NamH
fa35aa6e14
feat: dynamically register extension settings ( #2494 )
...
* feat: add extesion settings
Signed-off-by: James <james@jan.ai>
---------
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
Co-authored-by: Louis <louis@jan.ai>
2024-03-29 15:44:46 +07:00
NamH
3ecdb81881
fix: file explore on windows show empty when importing model ( #2484 )
...
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
2024-03-29 01:24:53 +07:00
NamH
1f8dc893ba
fix: remove files and memory when user clean thread ( #2524 )
...
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
2024-03-28 13:54:38 +07:00
Louis
784af8cf55
fix: model recommendation label is not based on VRAM ( #2517 )
2024-03-27 18:21:33 +07:00
Louis
fe730fbe42
fix: load model fails - generating button is not updated ( #2498 )
2024-03-27 15:52:06 +07:00
Louis
8e8dfd4b37
refactor: introduce inference tools ( #2493 )
2024-03-25 23:26:05 +07:00
Louis
14a67463dc
chore: refactor core folder structure - module based
2024-03-25 16:20:06 +07:00
Louis
77cbdc2dcf
refactor: introduce message request builder ( #2481 )
2024-03-25 12:50:29 +07:00
Louis
9551996e34
chore: load, unload model and inference synchronously
2024-03-25 12:25:30 +07:00
Louis
5edc24d8e0
fix: deleting threads manually breaks model settings and document upload ( #2456 )
...
* fix: blank model settings and rag does not work
* fix: fallback support fro previous broken threads
2024-03-22 13:56:46 +07:00
Louis
c2f6330daf
chore: log system information for debugging ( #2453 )
2024-03-22 12:34:44 +07:00
Louis
ff7ec39915
fix: incompatible browser dependency ( #2439 )
...
* fix: incompatible browser dependency
* fix: update model extension to use rollup
* fix: test timeout
2024-03-21 16:54:42 +07:00
NamH
b8d86df688
Fix/unable factory reset windows nitro running ( #2422 )
...
* fix: unable to factory reset when nitro is running on windows
---------
Signed-off-by: James <james@jan.ai>
2024-03-19 18:05:03 +07:00
Louis
489e8aab24
Sync release 0.4.9 to dev ( #2407 )
...
* fix: move tensorrt executable to engine (#2400 )
* fix: move tensorrt executable to engine
Signed-off-by: James <james@jan.ai>
* some update
Signed-off-by: hiro <hiro@jan.ai>
* chore: bump tensorrt version
* fix: wrong destroy path
* fix: install extensions in parallel
* chore: update path for tensorrt engine (#2404 )
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
---------
Signed-off-by: James <james@jan.ai>
Signed-off-by: hiro <hiro@jan.ai>
Co-authored-by: James <james@jan.ai>
Co-authored-by: hiro <hiro@jan.ai>
Co-authored-by: Louis <louis@jan.ai>
* Release/v0.4.9 (#2421 )
* fix: turn off experimental settings should also turn off quick ask (#2411 )
* fix: app glitches 1s generating response before starting model (#2412 )
* fix: disable experimental feature should also disable vulkan (#2414 )
* fix: model load stuck on windows when can't get CPU core count (#2413 )
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
* feat: TensorRT-LLM engine update support (#2415 )
* fix: engine update
* chore: add remove prepopulated models
Signed-off-by: James <james@jan.ai>
* update tinyjensen url
Signed-off-by: James <james@jan.ai>
* update llamacorn
Signed-off-by: James <james@jan.ai>
* update Mistral 7B Instruct v0.1 int4
Signed-off-by: James <james@jan.ai>
* update tensorrt
Signed-off-by: James <james@jan.ai>
* update
Signed-off-by: hiro <hiro@jan.ai>
* update
Signed-off-by: James <james@jan.ai>
* prettier
Signed-off-by: James <james@jan.ai>
* update mistral config
Signed-off-by: James <james@jan.ai>
* fix some lint
Signed-off-by: James <james@jan.ai>
---------
Signed-off-by: James <james@jan.ai>
Signed-off-by: hiro <hiro@jan.ai>
Co-authored-by: James <james@jan.ai>
Co-authored-by: hiro <hiro@jan.ai>
* Tensorrt LLM disable turing support (#2418 )
Co-authored-by: Hien To <tominhhien97@gmail.com>
* chore: add prompt template tensorrtllm (#2375 )
* chore: add prompt template tensorrtllm
* Add Prompt template for mistral and correct model metadata
---------
Co-authored-by: Hien To <tominhhien97@gmail.com>
* fix: correct tensorrt mistral model.json (#2419 )
---------
Signed-off-by: James <james@jan.ai>
Signed-off-by: hiro <hiro@jan.ai>
Co-authored-by: Louis <louis@jan.ai>
Co-authored-by: James <james@jan.ai>
Co-authored-by: hiro <hiro@jan.ai>
Co-authored-by: hiento09 <136591877+hiento09@users.noreply.github.com>
Co-authored-by: Hien To <tominhhien97@gmail.com>
---------
Signed-off-by: James <james@jan.ai>
Signed-off-by: hiro <hiro@jan.ai>
Co-authored-by: NamH <NamNh0122@gmail.com>
Co-authored-by: James <james@jan.ai>
Co-authored-by: hiro <hiro@jan.ai>
Co-authored-by: hiento09 <136591877+hiento09@users.noreply.github.com>
Co-authored-by: Hien To <tominhhien97@gmail.com>
2024-03-19 12:20:09 +07:00
Meta Spartan
0348aa3321
feat: Groq Inference Extension ( #2263 )
...
* feat: Groq Inference Extension
* Add Groq supported models
* Fix folder typo
* Add Groq options to interface and new API Key saving, tested working
* Fix linting
2024-03-18 06:40:20 +07:00
NamH
3e27e97110
fix: use model from model hub not load correct model in thread screen ( #2368 )
...
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
2024-03-15 10:33:59 +07:00
Louis
d85d02693b
feat: Nitro-Tensorrt-LLM Extension ( #2280 )
...
* feat: tensorrt-llm-extension
* fix: loading
* feat: add download tensorrt llm runner
Signed-off-by: James <james@jan.ai>
* feat: update to rollupjs instead of webpack for monitoring extension
Signed-off-by: James <james@jan.ai>
* feat: move update nvidia info to monitor extension
Signed-off-by: James <james@jan.ai>
* allow download tensorrt
Signed-off-by: James <james@jan.ai>
* update
Signed-off-by: James <james@jan.ai>
* allow download tensor rt based on gpu setting
Signed-off-by: James <james@jan.ai>
* update downloaded models
Signed-off-by: James <james@jan.ai>
* feat: add extension compatibility
* dynamic tensor rt engines
Signed-off-by: James <james@jan.ai>
* update models
Signed-off-by: James <james@jan.ai>
* chore: remove ts-ignore
* feat: getting installation state from extension
Signed-off-by: James <james@jan.ai>
* chore: adding type for decompress
Signed-off-by: James <james@jan.ai>
* feat: update according Louis's comment
Signed-off-by: James <james@jan.ai>
* feat: add progress for installing extension
Signed-off-by: James <james@jan.ai>
* chore: remove args from extension installation
* fix: model download does not work properly
* fix: do not allow user to stop tensorrtllm inference
* fix: extension installed style
* fix: download tensorrt does not update state
Signed-off-by: James <james@jan.ai>
* chore: replace int4 by fl16
* feat: modal for installing extension
Signed-off-by: James <james@jan.ai>
* fix: start download immediately after press install
Signed-off-by: James <james@jan.ai>
* fix: error switching between engines
* feat: rename inference provider to ai engine and refactor to core
* fix: missing ulid
* fix: core bundler
* feat: add cancel extension installing
Signed-off-by: James <james@jan.ai>
* remove mocking for mac
Signed-off-by: James <james@jan.ai>
* fix: show models only when extension is ready
* add tensorrt badge for model
Signed-off-by: James <james@jan.ai>
* fix: copy
* fix: add compatible check (#2342 )
* fix: add compatible check
Signed-off-by: James <james@jan.ai>
* fix: copy
* fix: font
* fix: copy
* fix: broken monitoring extension
* chore: bump engine
* fix: copy
* fix: model copy
* fix: copy
* fix: model json
---------
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
Co-authored-by: Louis <louis@jan.ai>
* fix: vulkan support
* fix: installation button padding
* fix: empty script
* fix: remove hard code string
---------
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
Co-authored-by: NamH <NamNh0122@gmail.com>
2024-03-14 14:07:22 +07:00
Louis
af5bcea773
fix: gate quick ask with feature toggle ( #2331 )
2024-03-12 20:10:59 +07:00
NamH
86af902d19
fix: message from quick ask not get the selected model ( #2307 )
...
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
2024-03-11 21:24:31 +07:00
NamH
f36d740b1e
feat: add quick ask ( #2197 )
...
* feat: add quick ask
Signed-off-by: James <james@jan.ai>
---------
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
Co-authored-by: Louis <louis@jan.ai>
2024-03-08 10:01:37 +07:00
Louis
7556430693
fix: should not attach error messages to the completion request ( #2258 )
2024-03-06 16:15:46 +07:00
Louis
5ca3069fa1
fix: image upload button and drag event are not enabled ( #2248 )
...
* fix: image upload button and drag event are not enabled
* fix: add tooltips for unsupported model
2024-03-06 09:09:38 +07:00
