65 Commits

Author SHA1 Message Date
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
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
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
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
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
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
hiro
e6c10202e0
feat: Jan can see (#2069)
* feat: jan can see

feat: Add GPT-4 Vision model (Preview)

fix: Add visionModel as property in ModelInfo

fix: Fix condition to load local messages in useSetActiveThread hook

feat: Enable Image as input for chat

fix: Update model parameters in JSON files for remote GPT models

fix: Add thread as optional

fix: Add support for message as image

fix: Linter

fix: Update proxyModel to proxy_model and add textModel

chore: Change proxyModel to proxy_model

fix: Update settings with visionModel and textModel

fix: vision model passed through the retrieval tool

fix: linter

* fix: could not load image and request is not able to be sent

---------

Co-authored-by: Louis <louis@jan.ai>
2024-03-05 08:33:09 +07:00
Louis
09e210af6b
fix: failed to send message blocks thread creation (#2091) 2024-02-19 20:08:36 +07:00
Louis
9e69946b73
fix: app stuck generating assistant response (#2001) 2024-02-12 13:38:08 +07:00
Faisal Amir
7ae6e35746
feat: add edit messages users (#1974)
* feat: add edit message user

* fix: delete messages should delete the rest below

---------

Co-authored-by: Louis <louis@jan.ai>
2024-02-12 13:00:24 +07:00
0xgokuz
875c2bc3c9
feat: Thread titles should auto-summarize Topic (#1976) 2024-02-10 19:16:42 +07:00
Louis
9e4658f5b2
fix: show generate response on message send (#1895)
* fix: show generate response on message send

* chore: typo
2024-02-01 23:59:45 +07:00
Louis
5ce2e422f8
fix: display error message on model load fail (#1894) 2024-02-01 23:28:15 +07:00
Louis
5ddc6ea4c8
fix: the selected model auto revert back to previous used model with setting mismatch (#1883)
* fix: the selected model auto revert back to previous used model with setting mismatch

* fix: view in finder and view file action
2024-02-01 12:31:26 +07:00
Faisal Amir
50fb0bc907 feat: add snackbar component and update style side banner 2024-01-31 12:40:28 +07:00
Faisal Amir
f338968232
Merge pull request #1820 from janhq/feat/improve-thread-left-panel
feat: put timestamp under thread name in left panel
2024-01-29 14:33:00 +07:00
Faisal Amir
391f053266 fix: typo copy 2024-01-29 14:04:17 +07:00
NamH
bb47d6869d
perf: remove unnecessary rerender when user typing input (#1818)
Co-authored-by: Faisal Amir <urmauur@gmail.com>
2024-01-29 13:53:18 +07:00
Faisal Amir
5fe68c16fd feat: put timestamp under thread name in left panel 2024-01-28 12:55:44 +07:00
hiro
28e4405498
feat: support RAG
chore: Update new model.json with multiple binaries

feat: Add updates for handling multiple model binaries

chore: jan can see

Update Model.json (#1005)

* add(mixtral): add model.json for mixtral

* archived some models + update the model.json

* add(model): add pandora 10.7b

* fix(model): update description

* fix(model): pump vers and change the featured model to trinity

* fix(model): archive neuralchat

* fix(model): decapriated all old models

* fix(trinity): add cover image and change description

* fix(trinity): update cover png

* add(pandora): cover image

* fix(pandora): cover image

* add(mixtral): add model.json for mixtral

* archived some models + update the model.json

* add(model): add pandora 10.7b

* fix(model): update description

* fix(model): pump vers and change the featured model to trinity

* fix(model): archive neuralchat

* fix(model): decapriated all old models

* fix(trinity): add cover image and change description

* fix(trinity): update cover png

* add(pandora): cover image

* fix(pandora): cover image

* chore: model desc nits

* fix(models): adjust the size for solars and pandoras

* add(mixtral): description

---------

Co-authored-by: 0xSage <n@pragmatic.vc>

chore: reformat model.json and use new template

fix(Model): download/abort model (#1163)

* fix(Model): download/abort model
* fix: image preview

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>

add preview and reduce time re-render all chat screen

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

store files under thread_id/files

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

fix: Update llava 1.5 size

fix: Nitro extension path resolver

feat: Add upload preview clearance

chore: Update FileType to multiple targets

fix: delete file preview once new thread created

chore: Add langchain import

support storing pdf file

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

feat: add retrieval tool in node runtime

fix: import module done

Co-authored-by: Louis <louis-jan@users.noreply.github.com>

feat: Add type assistant tool

chore: Add tool_retrieval_enabled to InferenceEngine

chore: Add AssistantTool to thread entity

chore: refactor tool retrieval base class

feat: Add handler for assistant with rag enabled

chore: Update inferenceEngine type properly

chore: Update inferenceEngine type properly

fix: Update retrieval tool

chore: main entry correction

refactor: tsconfig files

chore: Update ModelRuntimeParams type

refactor: Remove unused files

fix: wip

chore: remove unused console.log for FileUploadPreview

fix: Update mapping correctly for engine and proxyEngine

feat: Add proxyEngine to type ModelInfo

fix: WIP with test route

fix: Add bundleDependencies to package.json

chore: remove conversational history memory

fix: refactor data passing

reafactor: remove unused code

fix: Update module

chore: export import correction

fix conflict

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

fix: resolve after rebased

fix: Update llava 1.5 model json

feat: Add bakllava 1 model json

refactor: node module export, ES syntax and langchain import

fix: WIP

fix: WIP

fix: WIP

fix: external module import

fix: WIP

Add UI attachment fot file upload

Prepare Thumbnail UI image

chore: rebase model folder to dev branch

chore: remove multiple binaries related commits

fix: remove multiple binaries related commits part 2

fix: Remove transformer.js related deps

Fix truncate file name attachment

remove unused code image preview attachment

fix: remove multi binaries error

chore: remove commented code for ModelArtifacts type

Dropzone for drag and drop attachment

Avoid conditional showing 0 using length

fix symbol windows

avoid undefined tools

fix: add tool retrieval to true by default and disable the change

chore: remove unused code

fix: Enable nitro embedding by default

fix: Update code WIP with nitro embedding

chore: remove unused running function

fix: assistant extension missing module

feat: Retrieval ingest, query and reforward

fix: Update hnswlib version conflict

fix: Add tool settings

fix: Update path to thread_id/memory

fix: Add support for nitro embedding usage

fix: RAG does not work with plain content message

fix(Model): #1662 imported model does not use gpu (#1723)

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

feat: allow users to update retrieval settings

chore: pass thread assistant settings to assistant extensions

chore: eslint fix

fix bug border right panel showing in thread while not have active thread

Update setting layout retrieval assistant

Renaming file settingcomponent

change default value in core extention

add fake loader generate response

fix conditional fake loader

remove unused import

Proper error message on file typr

fix: loading indicator

fix: chunk size and overlap constraint

conditional drag and drop when retrieval off

fix: enable retrieval middleware as soon as its tool is enabled

fix: configure embedding engine according to request

fix: Retrieval false by default

fix: engine json

chore: migrate assistant

disabled collapse panel when retrieval or children null

chore: remove unused log

chore: Bump nitro version to 0.2.14 for batch embedding

chore: remove unused console.log
2024-01-26 23:12:28 +07:00
Louis
a50ea4a634
refactor: deprecate extension type implementation (#1677)
* refactor: deprecate extension type implementation

* chore: update README.md

* refactor: EventName to use the events defined in /types
2024-01-22 10:26:49 +07:00
Louis
8b6f7e846e refactor: default max_tokens and ctx_len 2024-01-11 14:13:39 +07:00
Faisal Amir
214739e143 reloading model when engine params have new values 2024-01-04 14:39:33 +07:00
Faisal Amir
49d5703ac3 bring back tooltip each params setting 2024-01-04 14:39:33 +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
NamH
c580b4c848
feat: add engine settings (#1199)
* feat: add engine settings

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

Signed-off-by: James <james@jan.ai>
Co-authored-by: Louis <louis@jan.ai>
2023-12-28 09:11:37 +07:00
Louis
a7f186cc5e
feat: users should be able to switch models mid-thread (#1226)
## Problem
Right now users have to start a new thread to use another model which causes a lot of confusion to our users.

fixes #1201
2023-12-27 15:35:27 +07:00
NamH
121dc119f1
feat: adding model params (#886)
* feat: adding model params

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

* chore: inference request parameter

* Improve ui right panel model params

* Remove unused import

* Update slider track for darkmode

---------

Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
Co-authored-by: Louis <louis@jan.ai>
Co-authored-by: Faisal Amir <urmauur@gmail.com>
2023-12-11 23:58:24 +07:00
hiro
1177007ad6 fix: Update code based on comments from @james 2023-12-08 23:07:30 +07:00
hiro
9daee14167 fix: Add hack waiting for model loading 2023-12-08 23:06:49 +07:00
hiro
975e9718bf chore: remove unused console.log 2023-12-08 23:06:49 +07:00
hiro
bb4b4c5c20 fix: Fix resend button with model object 2023-12-08 23:06:49 +07:00
hiro
6add24c643 fix: debugging 2023-12-08 23:06:49 +07:00
hiro
6f55cffb20 fix: Add model object to MessageRequest 2023-12-08 23:06:49 +07:00
Louis
f3fbade975
fix: delete message break the entire thread (#869) 2023-12-06 11:41:16 +07:00
Louis
7656048e64
fix: can not download multiple models at once (#867) 2023-12-06 11:18:05 +07:00
Louis
07fc1a91f3
fix: empty assistant instruction by default (#855)
* fix: empty assistant instruction by default

* chore: there should be no error dialog for in-app update
2023-12-05 15:46:18 +07:00
NamH
dacb00ed37
fix: not update active model when using resend button (#834)
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
2023-12-04 17:40:47 +07:00
Faisal Amir
424b00338e
feat: revamp thread screen (#802)
* Make thread screen as default screen

* Blank state when user have not any model

* Cleanup topbar thread screen

* Improve style right panel

* Add instructions right panel

* Styling thread list history

* Resolve conflict

* Default title new thread

* Fix trigger panel sidebar

* Make default right panel false when no activethread

* Fix CI test

* chore: assistant instruction with system prompt

* Fix title and blank state explore the hub

* Claenup style thread screen and add buble message for assitant

* Remove unused import

* Styling more menus on thread list and right panel, and make max height textarea 400 pixel

* Finished revamp ui thread

* Finished system monitor UI

* Style box running models

* Make animate right panel more smooth

* Add status arround textarea for starting model info

* Temporary disable hide left panel

* chore: system resource monitoring update

* copy nits

* chore: typo

* Reverse icon chevron accordion

* Move my models into setting page

---------

Co-authored-by: Louis <louis@jan.ai>
Co-authored-by: 0xSage <n@pragmatic.vc>
2023-12-04 10:55:47 +07:00
NamH
1bf4c1b621
feat: pre-populate Jan's /models folder (#796)
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
2023-12-01 18:03:51 +07:00
Louis
1143bd3846
refactor: jan extensions (#799)
* refactor: rename plugin to extension
2023-12-01 11:30:29 +07:00
NamH
86e693b250
refactor: model plugin to follow new specs (#682)
* refactor: model plugin to follow new specs

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

* chore: rebase main

chore: rebase main

---------

Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
Co-authored-by: Louis <louis@jan.ai>
2023-11-29 11:36:59 +07:00
0xSage
1f59d7b167 chore: updated copy grammar 2023-11-28 18:15:36 +08:00
Louis
d74698a448
fix: error when switching between threads (#736)
* fix: error when switching between threads

* chore: fix model loading state
2023-11-27 16:02:41 +07:00
Louis
23c7586f15 chore: fix conversation summary threshold 2023-11-27 11:30:06 +07:00