Nicholai/jan
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #50 from janhq/docs1

Browse Source 
docs: small fixes
This commit is contained in:
0xSage 2023-09-05 16:18:58 +08:00 committed by GitHub
commit 223b987661
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 13 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
README.md
View File

@ -14,20 +14,19 @@ Jan is free, source-available, and fair-code licensed.
- GPU support with Nvidia hardware acceleration - GPU support with Nvidia hardware acceleration
- CPU support with optimizations via llama.cpp - CPU support with optimizations via llama.cpp
## Features ## Current Features
- [x] Web, Mobile and APIs (OpenAI compatible REST & GRPC) - [x] Llama 7Bn
- [x] LLMs and Generative Art models - [x] Web app and APIs (OpenAI compatible REST & GRPC)
- [x] Support for Apple Silicon, CPU architectures - [x] Supports Apple Silicon/CPU & GPU architectures
- [x] C++ inference backend with CUDA/TensorRT/Triton, dynamic batching
- [x] Load balancing via Traefik - [x] Load balancing via Traefik
- [x] Login and authz via Keycloak - [x] Login and authz via Keycloak
- [x] Data persistence via Postgres and/or MinIO - [x] Data storage via Postgres, MinIO
## Planned ## Planned Features
- [ ] Support opting out of optional, 3rd party integrations - [ ] Support more models, with acceleration ([WIP](https://github.com/janhq/accelerated_ai))
- [ ] C++ inference backend w/ CUDA & dynamic batching ([WIP](https://github.com/janhq/inference_backend))
- [ ] Universal model installer & compiler, targeting Nvidia GPU acceleration - [ ] Universal model installer & compiler, targeting Nvidia GPU acceleration
- [ ] Mobile UI with a swappable backend URL - [ ] Mobile UI with a swappable backend URL
- [ ] Support for controlnet, upscaler, and code llama
- [ ] Admin dashboards for user management and audit - [ ] Admin dashboards for user management and audit
## Quickstart ## Quickstart
@ -105,11 +104,11 @@ docker compose up -d
| Service | URL | Credentials | | Service | URL | Credentials |
| -------------------- | --------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | -------------------- | --------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Keycloak | http://localhost:8088 | Admin credentials are set via the environment variables `KEYCLOAK_ADMIN` and `KEYCLOAK_ADMIN_PASSWORD` | | Web App | http://localhost:3000 | Users are signed up to keycloak, default created user is set via `conf/keycloak_conf/example-realm.json` on keycloak with username: `username`, password: `password` |
| app-backend (hasura) | http://localhost:8080 | Admin credentials are set via the environment variables `HASURA_GRAPHQL_ADMIN_SECRET` in file `conf/sample.env_app-backend` | | Keycloak Admin | http://localhost:8088 | Admin credentials are set via the environment variables `KEYCLOAK_ADMIN` and `KEYCLOAK_ADMIN_PASSWORD` |
| web-client | http://localhost:3000 | Users are signed up to keycloak, default created user is set via `conf/keycloak_conf/example-realm.json` on keycloak with username: `username`, password: `password` | | Hasura App Backend | http://localhost:8080 | Admin credentials are set via the environment variables `HASURA_GRAPHQL_ADMIN_SECRET` in file `conf/sample.env_app-backend` |
| llm service | http://localhost:8000 | | | LLM Service | http://localhost:8000 | |
| sd service | http://localhost:8001 | | | Stable Diffusion Service | http://localhost:8001 | |
## Usage ## Usage