3252 Commits

Author SHA1 Message Date
Van Pham
aa1f01f4fa
Revert "chore: remove nutjs" and replace nutjs version (#2900)
* Revert "chore: remove nutjs (#2860)"

This reverts commit ce2d8e540582a73423efed02dbe484e213cdf0fe.

* feat: change nut-js to download from GitHub

* feat: change nut-js to use @nut-tree-fork/nut-js

* Revert "Chore: temporary disable cache for server migration (#2742)"

This reverts commit af9a35110ba2462279dfb988cc89748697a97899.

* feat: disable quickask settings on linux

* feat: enable quick ask linux again

* Change to @kirillvakalov/nut-tree__nut-js (#2906)

Co-authored-by: Hien To <tominhhien97@gmail.com>

---------

Co-authored-by: Van-QA <van@jan.ai>
Co-authored-by: hiento09 <136591877+hiento09@users.noreply.github.com>
Co-authored-by: Hien To <tominhhien97@gmail.com>
2024-05-15 15:03:29 +07:00
Hoang Ha
eb7e96393b
add: gpt4o (#2899) 2024-05-14 14:16:12 +07:00
NamH
08d15e5dc7
fix: deeplink when app not open on linux (#2893)
Co-authored-by: James <james@jan.ai>
2024-05-13 16:47:27 +07:00
Hoang Ha
1e0d4f3753
Feat: Adjust model hub v0.4.13 (#2879)
* fix: correct phi3

* redundant phi2 dolphin

* add: hermes llama3

* add: ngl settings

* correct ctx len

* correct ngl

* correct maxlen + ngl

* disable phi3

* add ngl

* add ngl

* add ngl

* add ngl

* add ngl

* add ngl

* add ngl

* remove redundant  hermes pro

* add ngl

* add ngl

* add ngl

* remove miqu

* add ngl

* add ngl

* add ngl

* add ngl

* remove redundant

* add ngl

* add ngl

* add ngl

* add ngl

* add ngl

* add ngl

* add ngl

* add ngl

* add ngl

* version package bump

* feat: resolve issue of cannot found model in the extensions due to the removal

* feat: completely remove hermes-pro-7b

* feat: completely remove openhermes-neural-7b and miqu-70b, and add llama3-hermes-8b via renaming from Rex

* fix: correct description

---------

Co-authored-by: Van-QA <van@jan.ai>
2024-05-13 11:48:03 +07:00
NamH
6af4a2d484
feat: add deeplink support (#2883)
* feat: add deeplink support

* fix windows not receive deeplink when not running

---------

Co-authored-by: James <james@jan.ai>
2024-05-13 09:37:05 +07:00
Henry
efbc96dad9
feat: inference anthropic extension (#2885)
* feat: implement inference anthropic extension

* chore: format style and correct typo of other extensions
2024-05-11 19:22:05 +07:00
NamH
0406b51615
fix: stop auto scroll if user manually scrolling up (#2874)
Co-authored-by: James <james@jan.ai>
2024-05-06 20:03:25 +07:00
Hoang Ha
2008aae100
Feat: Correct context length for models (#2867)
* fix: correct ctx

* version bump

* fix: correct ctxlen

* fix: correct ctxlen

* version bump

* fix: correct ctx + q4

* fix: correct ctxlen

* fix: correct ctx

* fix: correct ctx

* fix: correct ctx len

* fix: correct ctx

* fix: correct ctx

* fix: correct ctx

* fix: correct ctx

* fix: correct ctx

* fix: correct ctx

* fix: correct ctx

* fix: correct ctx

* version bump
2024-05-06 18:04:51 +07:00
Inchoker
d2266405cc
Add OpenRouter (#2826)
* Add OpenRouter

* fix cohere setting description

* fix: update to auto router

* fix: auto router

* add: config parameters

* fix: correct max tokens

---------

Co-authored-by: Jack Tri Le <Jack>
Co-authored-by: Hoang Ha <64120343+hahuyhoang411@users.noreply.github.com>
2024-05-06 17:36:52 +07:00
Faisal Amir
9effb6a3a6
fix: validate context length (#2871)
* fix: adjust context_length min and conditional for remote model

* fix: remove console
2024-05-06 16:48:53 +07:00
Henry
1e3e5a83f4
feat/implement-inference-martian-extension (#2869) 2024-05-06 15:24:07 +07:00
Faisal Amir
a6ccd672c5
fix: validate max_token from context_length value (#2870) 2024-05-06 15:10:37 +07:00
Henry
86fda1cf6c
feat: add model gpt-4 turbo (#2836)
* feat: add model gpt-4 turbo

* fix: correct naming

---------

Co-authored-by: Hoang Ha <64120343+hahuyhoang411@users.noreply.github.com>
2024-05-06 10:43:15 +07:00
Henry
4c88d03aa5
feat: add remote model command-r (#2868) 2024-05-06 10:37:57 +07:00
Hoang Ha
092a572684
Feat: Remote API Parameters Correction (#2802)
* fix: change to gpt4 turbo

* add: params

* fix: change to gpt 3.5 turbo

* delete: redundant

* fix: correct description

* version bump

* add: params

* fix: version bump

* delete: deprecated

* add: params

* add: new model

* chore: version bump

* fix: version correct

* add: params

* fix: version bump

* fix: change to gpt4 turbo

* add: params

* fix: change to gpt 3.5 turbo

* delete: redundant

* fix: correct description

* version bump

* add: params

* fix: version bump

* delete: deprecated

* add: params

* add: new model

* chore: version bump

* fix: version correct

* add: params

* fix: version bump

* fix: llama2 no longer supported

* fix: reverse mistral api

* fix: add params

* fix: mistral api redundant params

* fix: typo

* fix: typo

* fix: correct context length

* fix: remove stop

---------

Co-authored-by: Van Pham <64197333+Van-QA@users.noreply.github.com>
2024-05-04 15:44:19 +07:00
Quentin Macheda
c21bc08793
Fix eslint issue in EditChatInput (#2864) 2024-05-03 19:16:06 +07:00
Quentin Macheda
2016eae0c9
Remove hidden overflow property of tailwind + Update buttons position (under textarea) (#2856)
Please be aware of the lint prettier failed
2024-05-03 15:11:29 +07:00
Quentin Macheda
c6182ab59c
Customize scroll-bar style (#2857) 2024-05-03 10:17:05 +07:00
NamH
ce2d8e5405
chore: remove nutjs (#2860)
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
2024-05-02 21:02:05 +07:00
NamH
0bad1a479f
fix: remove scroll animation chat screen (#2819)
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
2024-04-25 17:24:29 +07:00
Van Pham
012cc801e9
Merge pull request #2815 from janhq/main
Sync main to dev 0.4.12
2024-04-25 14:57:10 +07:00
Louis
63a2f22414
Merge branch 'dev' into main 2024-04-25 14:14:54 +07:00
hiento09
3936ce1baa
change agent run macintel (#2814)
Co-authored-by: Service Account <service@jan.ai>
v0.4.12
2024-04-25 10:58:07 +07:00
hiento09
957f4629e2
Add workflow test openai api (#2778)
* Add workflow test openai api

* chore: add filename as attribute to each test case

* chore: correct label

* feat: create pytest.ini

* chore: remote extra "

* chore: rename workflow to group similar type

* chore: remove auto build on push to main

* chore: rename job

---------

Co-authored-by: Hien To <tominhhien97@gmail.com>
Co-authored-by: Van-QA <van@jan.ai>
2024-04-25 10:55:11 +07:00
Van Pham
36c86f2afe
Merge pull request #2808 from janhq/release/0.4.12
Release/0.4.12 to main
2024-04-25 09:21:31 +07:00
Hoang Ha
355ed9ff4f
Merge pull request #2812 from janhq/fix/model-version
Feat: Bump version
2024-04-24 22:48:29 +07:00
Hoang Ha
f9a8e06a4f
fix: version bump 2024-04-24 22:46:56 +07:00
Hoang Ha
eb3593e96a
fix: bump version 2024-04-24 22:24:22 +07:00
Hoang Ha
785b84d9ec
fix: bump version 2024-04-24 22:24:00 +07:00
Hoang Ha
ec589b1f22
fix: bump version 2024-04-24 22:23:40 +07:00
Hoang Ha
4d80f5c3c1
fix: bump version 2024-04-24 22:22:14 +07:00
Hoang Ha
984838a7bc
fix: bump version 2024-04-24 22:19:11 +07:00
Louis
b4b8c862c0
fix: infinite talking in auto thread titles generators (#2810) 2024-04-24 21:17:19 +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
Inchoker
96abd533c4
feat: cohere remote API extension (#2785)
* fix core

* add cohere extension

* add cohere response customizable

* nitpicking

* use transformResponse

* Update extensions/inference-cohere-extension/src/index.ts

Co-authored-by: Louis <louis@jan.ai>

* use prettier

* Update extensions/inference-cohere-extension/src/index.ts

Co-authored-by: Louis <louis@jan.ai>

* pass requestBody as object

* transformPayload as a property

* This is not correct. CHATBOT is an equivalent role to assistant.
system message should be used with the preamble parameter and should not be included in the chat_history

---------

Co-authored-by: Jack Tri Le <Jack>
Co-authored-by: Louis <louis@jan.ai>
2024-04-24 18:16:57 +07:00
Hoang Ha
a1fd987567
Merge pull request #2805 from janhq/chore/update-featured-model
Feat: Change featured models
2024-04-24 17:37:52 +07:00
Hoang Ha
68b0018d55
fix: version bump 2024-04-24 16:40:27 +07:00
Hoang Ha
e076c5ba4e
fix: remove featured 2024-04-24 16:38:47 +07:00
Hoang Ha
f5c4324f79
fix: remove featured 2024-04-24 16:38:30 +07:00
Hoang Ha
6bf12e42a8
fix: remove featured 2024-04-24 16:38:09 +07:00
Hoang Ha
3810b1a009
fix: remove featured 2024-04-24 16:37:48 +07:00
Hoang Ha
d14c3af99b
add: featured 2024-04-24 16:35:05 +07:00
Hoang Ha
3c294d6a48
Chore: Add phi-3 (#2794)
* add: phi-3

* chore: bump version

* fix: correct model id
2024-04-24 14:17:42 +07:00
Louis
48f351aefd
fix: new thread with overridden settings (#2798) 2024-04-24 14:14:04 +07:00
Louis
da161cd159
fix: override cpu_threads setting from model.json (#2789) 2024-04-23 15:09:48 +07:00
Van Pham
e54e7c04b3
Merge pull request #2787 from janhq/dev
Release cut 0.4.12
2024-04-23 09:48:24 +07:00
Carsen Klock
f288a86647
Add new Llama 3 and models to Groq Extension (#2786) 2024-04-23 09:15:19 +07:00
NamH
97c15e6983
chore: detailed message when fetch invalid url (#2780)
Co-authored-by: James <james@jan.ai>
2024-04-22 21:42:31 +07:00
Van Pham
67db45ff3c
chore: add model.json for Llama3 and other outdated model version (#2773)
* chore: add model.json for Llama3 and other outdated model version

* fix: consistency format

* fix: correct folder id

* update: bump version

* add: stop words

* fix: model.json

* Update extensions/inference-nitro-extension/resources/models/llama3-8b-instruct/model.json

* Update extensions/inference-nitro-extension/resources/models/llama3-8b-instruct/model.json

Based on suggested change

Co-authored-by: Nikolaus Kühn <nikolaus.kuehn@commercetools.com>

---------

Co-authored-by: Van-QA <van@jan.ai>
Co-authored-by: Hoang Ha <64120343+hahuyhoang411@users.noreply.github.com>
Co-authored-by: Louis <louis@jan.ai>
Co-authored-by: Nikolaus Kühn <nikolaus.kuehn@commercetools.com>
2024-04-22 21:40:22 +07:00
NamH
83e9e2b80a
chore: set default context length to 2048 (#2776)
Co-authored-by: James <james@jan.ai>
2024-04-22 19:57:00 +07:00