alihan/serge-chatgptui
1
0
Fork 0
mirror of https://github.com/serge-chat/serge.git synced 2024-01-15 09:32:12 +03:00
Code Issues Packages Projects Releases Wiki Activity
791 Commits 4 Branches 27 Tags
main
Commit Graph

39 Commits

Author SHA1 Message Date
Juan Calderon-Perez
78cff9c47f Updates to CI process for Python dependencies (#912) 2023-11-27 22:08:30 -05:00
Juan Calderon-Perez
5c724e6f1f Update README, remove CMAKE 2023-11-26 19:29:50 -05:00
Juan Calderon-Perez
80a23545a5 Add cmake 2023-11-26 19:07:08 -05:00
Juan Calderon-Perez
0f00099cd0 Remove build-deps 2023-11-26 18:51:40 -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
b4190e5616 Add support for latest debian release (#755) 2023-09-19 22:55:19 -04:00
Juan Calderon-Perez
0acf8e0911 Add /ping route to API (#685) 2023-09-04 00:59:26 -04:00
Juan Calderon-Perez
0500cb2266 Remove support for DragonflyDB (#684) 2023-09-03 23:37:23 -04:00
Juan Calderon-Perez
fbdcb64201 Split Docker build into separate CI job, Support for Node 20 (#683) 
* Split Docker build into separate CI job

* Update docker.yml

* Add build as part of CI process, bump Node to v20.x

* Add build as part of CI process, bump Node to v20.
 2023-09-02 22:38:59 -04:00
Juan Calderon-Perez
8844153111 Add support for gpu_layers, LLaMA2 parameters, and increase token and context window (#611) 2023-08-10 01:21:14 -04:00
dependabot[bot]
cb3c6c4395 Bump dragonflydb/dragonfly from v1.7.1 to v1.8.0 (#608) 
Bumps [dragonflydb/dragonfly](https://github.com/dragonflydb/dragonfly) from v1.7.1 to v1.8.0.
- [Release notes](https://github.com/dragonflydb/dragonfly/releases)
- [Commits](https://github.com/dragonflydb/dragonfly/compare/v1.7.1...v1.8.0)

---
updated-dependencies:
- dependency-name: dragonflydb/dragonfly
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2023-08-09 08:20:53 -04:00
Juan Calderon-Perez
86879884c6 Add missing dependency for Dragonfly 2023-08-06 23:23:46 -04:00
Juan Calderon-Perez
924831b069 Avoid installing recommended packages 2023-08-06 23:07:57 -04:00
Juan Calderon-Perez
12ec7b7f42 Support for DragonflyDB (#598) 2023-08-06 22:54:42 -04:00
Juan Calderon-Perez
696c2d288c Fixes to startup scripts and Dockerfiles (#517) 2023-07-09 18:28:33 -04:00
Juan Calderon-Perez
da8c3e27d3 Refactor production Dockerfile, Add development Dockerfile (#485) 
* Refactor Dockerfile, add Dockerfile.dev for development

* We need dev dependencies for running vite build
 2023-07-01 22:47:29 -04:00
Juan Calderon-Perez
a641860228 Update models.json and change Docker base images to Debian 11 (#484) 2023-07-01 19:49:27 -04:00
Juan Calderon-Perez
2d32686de8 Update Dockerfile (#261) 
Expose Serge port in Dockerfile
 2023-05-02 22:24:34 -04:00
Nathan Sarrazin
7a608bc6e6 Added build-essential and switched back to python 3.11 for match statements 2023-04-26 08:08:35 +02:00
Juan Calderon-Perez
330c5a8818 Use Debian Slim for base images, Fixes to CI actions (#221) 
* Use slim variant for Docker, CI fixes

* Config must be added after installation

* Use Python3.9, updates to CI

* Change min required version of Python
 2023-04-25 09:21:19 +02:00
Nathan Sarrazin
e512011470 Use python bindings, integrate with LangChain and get rid of MongoDB (#148) 
* integrate langchain
get rid of mongodb
use llama-cpp-python bindings

* fixed most chat endpoints except posting questions

* Working post endpoint !

* everything works except streaming

* current state

* streaming as is

* got rid of langchain wrapper for calling llm, went back to using bindings directly

* working streaming

* sort chats by time

* cleaned up styling and added back loading indicator

* Add persistence support to redis

* fixed tooltips

* fixed default prompts

* added link to api docs (closes How to use the api #155 )
 2023-04-23 23:42:20 +02:00
Juan Calderon-Perez
6801ef86d2 Bug fixes and improvements (#202) 
* Bug fixes and improvements

* Simplify Dockerfile

* Update docker-compose.yml

* Update llama.cpp tag
 2023-04-21 18:30:31 -04:00
Juan Calderon-Perez
12e2d63319 Update llama.cpp tag to master-f7d0509 (#201) 2023-04-19 21:00:07 -04:00
Juan Calderon-Perez
c2e3d65746 Update Dockerfile to fix CI/CD (#194) 2023-04-18 21:59:10 -04:00
Juan Calderon-Perez
e1dbd3115c Update Dockerfile (#193) 2023-04-18 21:09:40 -04:00
Juan Calderon-Perez
46e8f4daf3 Update llama.cpp tag (#172) 2023-04-16 21:00:24 -04:00
Juan Calderon-Perez
944100a717 Update llama.cpp to master-be87b6e (#153) 
* Update llama.cpp to master-8b67998

* Update Dockerfile

* Update Dockerfile

* Update Dockerfile

---------

Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>
 2023-04-14 19:39:56 +02:00
Juan Calderon-Perez
f836578861 Update llama.cpp to master-180b693 (#147) 
* Update llama.cpp to master-aaf3b23

* Update Dockerfile
 2023-04-10 09:44:57 +02:00
Juan Calderon-Perez
af60cedf36 Update llama.cpp (#144) 2023-04-06 23:01:41 +02:00
Juan Calderon-Perez
cf84d0c7f5 Performance improvements for AVX2 via llama.cpp (#129) 2023-04-03 22:34:14 +02:00
Juan Calderon-Perez
424f670e0f Update llama.cpp to master-e986f94 (#124) 
* Update Dockerfile

* Add support for GPT4All

* Skip running Github Actions on .md changed

---------

Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>
 2023-04-02 20:38:28 +02:00
Juan Calderon-Perez
2c1146969e Update llama.cpp to master-3525899 (#122) 2023-04-01 09:44:19 +02:00
Nathan Sarrazin
b806c5a065 Update to latest llama.cpp (#118) 
* add script to migrate weights and update dockerfile to use the latest version

* bump version of llama.cpp to latest

* fixed conversion bug when downloading models
 2023-03-31 20:42:46 +02:00
Juan Calderon-Perez
323801ff0e Update llama.cpp to master-5a5f8b1 (#103) 2023-03-29 06:34:07 +02:00
Nathan Sarrazin
b5c423fe59 API Refactor & Model Manager (#101) 
* API refactoring

* delete partially downloaded files on startup

* remove unused deps
 2023-03-28 23:56:41 +02:00
Nathan Sarrazin
bd0c2c8650 Move the llama.cpp compilation step to after the image is built (#87) 
* Move the compilation step to after the image is built

* got rid of chmod steps, clone in dockerfile, delete folder after make
 2023-03-28 08:33:11 +02:00
Nathan Sarrazin
293a23e487 Proper dev & deployment images. Converts front-end to SPA. (#84) 
* begin work on dev environment

* more work on dev image

* working dev + prod images with SPA front-end

* reworked dockerfile

* make CI point to the right action

* Improvements to github actions (#79)

* Improvements to github actions

* Change username to repo owner username

* Add fix for login into ghcr (#81)

* Update bug_report.yml

* added dev instructions to readme

* reduced number of steps in dockerfile

---------

Co-authored-by: Juan Calderon-Perez <835733+gaby@users.noreply.github.com>
 2023-03-27 16:44:20 +02:00
Jason
19517024df Update Dockerfile to enable llama build on M1 mac (#62) 
gcc12 doesn't work when running make on M1 mac
 2023-03-25 14:33:18 +01:00
Nathan Sarrazin
d697059122 Move everything into a single dockerfile (#57) 
* initial work on linting & templates

* moved everyone into a nice dockerfile

* move everyone into a single dockerfile

* update sample .env file

* got rid of .env file

* rename db volume to avoid confusion and conflicts with previous version

* added bug report template
 2023-03-25 11:55:01 +01:00