58 Commits

Author SHA1 Message Date
Juan Calderon-Perez
7b06ddfb9d
Bump llama-cpp-python to v0.2.83, Update ENV variables 2024-07-27 14:52:39 -04:00
Jon Pro
80833600eb
Add support for User Management (#1313)
* Add users - checkpoint

* Working

* Finish workflow

* switch to cookies instead of bearer token

* Fix settings not saved

* Add sqlite

* Cleanup

* Get db url from env var

* PR Prep

* Maybe later

* Code review

* Update poetry and readme

* Things for status checks

* Add chats table to DB

* Bad merge

* Personal code review

* Add default user called system

* Fix poetry

* fix status checks

* Formatting

* Fix deleting a chat

* Fix bug when auth times out but user isn't logged out

* Code review comments

* fix lockfile

---------

Co-authored-by: Juan Calderon-Perez <835733+gaby@users.noreply.github.com>
2024-07-27 14:48:53 -04:00
Juan Calderon-Perez
1c6f744c13
Bump llama-cpp-python to v0.2.82 2024-07-20 20:39:35 -04:00
Juan Calderon-Perez
b19ce0b83a
Bump llama-cpp-python to v0.2.79 (#1359) 2024-06-21 19:54:04 -04:00
Juan Calderon-Perez
0dc3097d59
Bump llama-cpp-python to v0.2.78 2024-06-13 08:47:53 -04:00
Olivier DEBAUCHE
1c6a0770c3
Bump Llama cpp pthon to 0.2.75 (#1289) 2024-05-19 14:55:11 -04:00
Juan Calderon-Perez
aaa1596703
Bump llama-cpp-python to v0.2.71 2024-05-09 09:13:46 -04:00
Olivier DEBAUCHE
1cc58cd4b1
Bump llama-cpp-python to v0.2.69 (#1266)
* Update serge.env

* Update dev.sh

* Update deploy.sh

* Update dev.sh

* Update dev.sh

* Update deploy.sh

* Bump LLaMA CPP Python to 0.2.68

* Update dev.sh

* Update deploy.sh

* Update deploy.sh

* Update dev.sh

* Update dev.sh

* Update deploy.sh

* Update deploy.sh

* Update dev.sh

* Update deploy.sh

* Update dev.sh

* Update serge.env

* Update serge.env

* Update scripts/deploy.sh

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>

* Update scripts/dev.sh

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>

* Update dev.sh

* Update deploy.sh

* Only use official wheels for now

* Fix lint issues

---------

Co-authored-by: Juan Calderon-Perez <835733+gaby@users.noreply.github.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
2024-05-06 09:37:25 -04:00
Olivier DEBAUCHE
4f063d2050
Add LLaMA 3 Compatibility (#1263)
* Bump LLaMA CPP  Python  from 0.2.50 to 0.2.63

* Update serge.env
2024-04-24 07:37:07 -04:00
Olivier DEBAUCHE
3fae443357
Bump LLaMA CPP Python from 0.2.50 to 0.2.63 (#1258) 2024-04-22 19:42:04 -04:00
Olivier DEBAUCHE
e1f966ace3
Fix ipv4/ipv6 modes (#1153)
* Update serge.env

Add ISERGE_ENABLE_IPV4

* Update deploy.sh

Now IPV4 is activate by deflault
We can activate IPV4+IPV6 or IPV6 only

* Update dev.sh

Now ipv4 is activated by default but we can also activate ipv4+ipv6 or ipv6 only

* Update dev.sh

fix port for ipv4

* Update serge.env

fix SERGE_ENABLE_IPV4 value

* Update deploy.sh

code formating

* Update dev.sh

code formating

* Update dev.sh

bugfix

* Update serge.env

---------

Co-authored-by: Juan Calderon-Perez <835733+gaby@users.noreply.github.com>
2024-02-24 11:41:51 -05:00
Olivier DEBAUCHE
b5b35fc11e
Models update (#1154)
* Update models.json

Add support for Gemma 2B and 7B

* Update models.json

Add support for LLama pro

* Update models.json

Add support for TinyLlama

* Update models.json

Update Medicine LLM

* Update README.md

* Update serge.env

Bump version of LLama cpp to support Gemma Model
2024-02-24 00:55:16 -05:00
Olivier DEBAUCHE
2b0cfb2050
Update llama-cpp-python (#1137)
* Update serge.env

Update Llama cpp python version

* Update deploy.sh

Update path

* Update dev.sh

Update  path

* Update serge.env

Bump version to v0.2.43

* Update serge.env

Bump version of Llama cpp python to v0.2.44
2024-02-18 10:00:04 -05:00
Juan Calderon-Perez
e24c8feb98
Updates to UI components, cleanup of unused dependencies (#1136)
Fixes to UI components, accessibility labels. Removal of unused python dependencies. Migrate from black to ruff for formatting.
---------

Co-authored-by: morpheus2448 <41052975+morpheus2448@users.noreply.github.com>
2024-02-13 23:51:54 -05:00
Juan Calderon-Perez
d91dd4f689 Fix duplicated ports 2024-02-13 22:31:05 -05:00
Juan Calderon-Perez
6ecf1797b8
Revert back to llama-cpp-python v0.2.39 2024-02-13 22:17:07 -05:00
Juan Calderon-Perez
61ae2eaf80
Update llama-cpp-python to v0.2.41 (#1133) 2024-02-13 22:02:01 -05:00
Olivier DEBAUCHE
86a2c7f18d
Update Llama cpp python from 0.2.38 to 0.2.39 (#1119)
* Update serge.env

Bump llama python in 0.2.28

* Update serge.env

* Update deploy.sh

change lama-cpp-python provider

* Update dev.sh

* Update serge.env

Bump version from 0.2.26 to 0.2.38

* Update dev.sh

* Update serge.env

Bump version from 0.2.38 to 0.2.39

---------

Co-authored-by: Juan Calderon-Perez <835733+gaby@users.noreply.github.com>
2024-02-07 09:01:46 -05:00
Olivier DEBAUCHE
583d344338
Update llama-cpp-python to v0.2.38 (#1062)
* Update serge.env

Bump llama python in 0.2.28

* Update serge.env

* Update deploy.sh

change lama-cpp-python provider

* Update dev.sh

* Update serge.env

Bump version from 0.2.26 to 0.2.38

* Update dev.sh

---------

Co-authored-by: Juan Calderon-Perez <835733+gaby@users.noreply.github.com>
2024-02-04 20:00:58 -05:00
Olivier DEBAUCHE
1424475db6
Fix ipv6 support conditional check (#1074)
must be true not false
2024-01-18 18:09:50 -05:00
Olivier DEBAUCHE
f9d8ed2ff1
Add support for IPv6 (#1055)
* Update deploy.sh

add support ipv6

* Update dev.sh

add support for ipv6

* Update deploy.sh

add support for ipv6

* Update deploy.sh

add support for ipv6

* Update dev.sh

support  for ipv6

* Update dev.sh

support for ipv6 reworked
Thanks Gaby :)

* Update serge.env

add support for ipv6

* Update deploy.sh

support for ipv6 reworked
Thanks Gaby :)

* Update deploy.sh

bugfix

* Update serge.env

* Update serge.env

rename variable in SERGE_ENABLE_IPV6

* Update deploy.sh

rename variable in SERGE_ENABLE_IPV6

* Update dev.sh

rename variable in SERGE_ENABLE_IPV6

* Update deploy.sh

remove redudant code

* Update dev.sh

add missing code

* Update deploy.sh

tiny change

* Update dev.sh

bugfix

* Update deploy.sh

bugfix

* Update dev.sh

bugfix

* Update deploy.sh

change unicorn by hypercorn

* Update serge.env

delete unecessary param

* Update dev.sh

replace unicorn by hypercorn

* Update pyproject.toml

replace unicorn by hypercorn

* Update poetry.lock

replace unicorn by hypercorn

* Update poetry.lock

poetry updated

* Update pyproject.toml

update

* Update poetry.lock

hypercorn update

* Update deploy.sh

shmft applied

* Update dev.sh

shmft applied

* Update deploy.sh

shmft applied

* Update dev.sh

shmft applied

* Update dev.sh

bugfix

* Update serge.env

missing value

* Update deploy.sh

code corrected

* Update dev.sh

code corrected

* Update serge.env

 code corrected

* Update deploy.sh

rollback

* Update dev.sh

rollback

* Update serge.env

* Update deploy.sh

add SERGE_IPV6_SUPPORT

* Update dev.sh

Add SERGE_IPV6_SUPPORT

* Update dev.sh

* Update deploy.sh

---------

Co-authored-by: Juan Calderon-Perez <835733+gaby@users.noreply.github.com>
2024-01-18 08:31:22 -05:00
Juan Calderon-Perez
b0f19fbc57
Update llama-cpp-python to v0.2.26 (#1020) 2023-12-30 19:58:14 -05:00
Juan Calderon-Perez
586f556577
Update llama-cpp-python to v0.2.25 (#1015) 2023-12-26 22:41:08 -05:00
Juan Calderon-Perez
82db8ac930
Bump llama-cpp-python to v0.2.23 (#982) 2023-12-15 07:56:56 -05:00
Juan Calderon-Perez
1684466304
Fix installation of aarch64 wheels (#938)
* Add support for installing aarch64 wheels

* Fix syntax
2023-12-03 22:13:44 -05:00
Juan Calderon-Perez
52f3a82c52
Update deploy.sh 2023-11-28 09:47:29 -05:00
Juan Calderon-Perez
5298d130b1
Enable debug during pip failure 2023-11-28 09:41:04 -05:00
Juan Calderon-Perez
f787358121
Enable verbose when using pip 2023-11-28 09:21:43 -05:00
Juan Calderon-Perez
b49e7ceb57
Bump llama-cpp-python to v0.2.20 2023-11-28 08:16:35 -05:00
Juan Calderon-Perez
78cff9c47f
Updates to CI process for Python dependencies (#912) 2023-11-27 22:08:30 -05:00
Juan Calderon-Perez
9e9bc528d9
Fix for Apple Metal installation (#905)
* Update deploy.sh

* Update dev.sh
2023-11-26 22:03:50 -05:00
Juan Calderon-Perez
2dfcde881a
Add support for using wheels when installing llama-cpp-python (#904)
* Initial changes to support wheels

* Format shell files

* Remove curl, move location of .ENV file

* Fix path to shfmt

* Add OPT for ShellCheck

* Fix for SC1091

* Disable SC1091

* Fix delete prompt call when prompt in progress

* Add null check

* Revert changes to Dockerfile

* Fix syntax issue

* Remove duplicated command
2023-11-26 18:34:28 -05:00
Juan Calderon-Perez
947efe5d4b
Bump llama-cpp-python to v0.2.19 (#894) 2023-11-21 19:25:46 -05:00
Juan Calderon-Perez
c7f0b487aa
Add support for GGUF models (#866) 2023-11-17 09:07:02 -05:00
Mariusz Kogen
7f6321ae82
Fix llama-cpp-python build for Apple Silicon (#763)
* Fix llama-cpp-python build for Apple Silicon

* Make ShellCheck happy

* Make gaby happy

---------

Co-authored-by: Juan Calderon-Perez <835733+gaby@users.noreply.github.com>
2023-09-20 08:35:50 -04:00
Mariusz Kogen
e87d0209c8
Enhance Signal Handling for Graceful Termination (#727)
* Enhance Signal Handling for Graceful Termination

* Fixed formatting

---------

Co-authored-by: Juan Calderon-Perez <835733+gaby@users.noreply.github.com>
2023-09-13 20:29:34 -04:00
Juan Calderon-Perez
0500cb2266
Remove support for DragonflyDB (#684) 2023-09-03 23:37:23 -04:00
Juan Calderon-Perez
53793ca580
Update llama-cpp-python to v0.1.78 (#653)
* Update dev.sh

* Update deploy.sh
2023-08-24 23:31:01 -04:00
Gianni C
5aca2b27d6
Add Kubernetes helm charts for Serge (#500)
Co-authored-by: Juan Calderon-Perez <835733+gaby@users.noreply.github.com>
2023-08-10 23:02:14 -04:00
Juan Calderon-Perez
12ec7b7f42
Support for DragonflyDB (#598) 2023-08-06 22:54:42 -04:00
Juan Calderon-Perez
20c3dac583
Update llama-cpp-python to v0.1.77 2023-07-29 23:56:49 -04:00
Juan Calderon-Perez
6445c21af0
Update llama-cpp-python to v0.1.70 (#518) 2023-07-09 18:57:34 -04:00
Juan Calderon-Perez
696c2d288c
Fixes to startup scripts and Dockerfiles (#517) 2023-07-09 18:28:33 -04:00
Juan Calderon-Perez
65cfcfbfc3
Support for llama-cpp-python v0.1.69 (#516) 2023-07-09 15:51:07 -04:00
Juan Calderon-Perez
83819b2eba
Update llama-cpp-python to v0.1.66 (#469) 2023-06-26 23:51:33 -04:00
Juan Calderon-Perez
c31c464aec
Update llama-cpp-python to v0.1.65 (#454) 2023-06-20 20:07:16 -04:00
Juan Calderon-Perez
ee27eedeb3
Update llama-cpp-python to v0.1.64 (#441) 2023-06-18 13:15:45 -04:00
Juan Calderon-Perez
75dd5580d9
Update llama-cpp-python to v0.1.63 (#433) 2023-06-16 00:28:24 -04:00
Juan Calderon-Perez
4970865a49
Add support for validating shell scripts (#416) 2023-06-11 20:39:11 -04:00
PΔBLØ ᄃΞ
634fdacc08
Feature: add new k-quants q6_K models (#412)
* Feature: add new k-quants q6_K models

* Feature: update llama-cpp-python==0.1.62

* Fix: labels and 7b not use k-quants

* Fix: labels and 7b not use k-quants

* Fix: labels and 7b old one and q6_K

* Fix: labels and 7b old sizes

* Fix: labels and 7b Koala names

---------

Co-authored-by: pabl-o-ce <cye@poscye.com>
2023-06-10 23:28:05 -04:00