Initial support for Kubernetes (#71)

* Initial Kubernetes support

* Adding manifest.yaml

* removed custom config & added placeholder variables

* Adding K8S deployment steps on README.md

* adding --host parameter to uvicorn deploy.sh

* changed web/vite.config.ts placeholder variable to service name

* migrated manifest.yaml to the wiki and edited README.md

README.md

@@ -29,6 +29,10 @@ docker compose exec serge python3 /usr/src/app/api/utils/download.py tokenizer 7
 Make sure you have docker desktop installed, WSL2 configured and enough free RAM to run models. (see below)
 
 
+#### Kubernetes
+
+Setting up Serge on Kubernetes can be found in the wiki: https://github.com/nsarrazin/serge/wiki/Integrating-Serge-in-your-orchestration#kubernetes-example
+
 ### Using serge
 
 (You can pass `7B 13B 30B` as an argument to the `download.py` script to download multiple models.)

deploy.sh

@@ -6,7 +6,7 @@ mongod &
 cd web && npm run dev -- --host 0.0.0.0 --port 8008 &
   
 # Start the API
-cd api && uvicorn main:app --port 9124 --root-path /api/ &
+cd api && uvicorn main:app --host 0.0.0.0 --port 9124 --root-path /api/ &
 
 # Wait for any process to exit
 wait -n

web/vite.config.ts

@@ -6,7 +6,7 @@ export default defineConfig({
   server: {
     proxy: {
       "/api": {
-        target: "http://localhost:9124/",
+        target: "http://serge:9124/",
         changeOrigin: true,
         secure: false,
         rewrite: (path) => path.replace(/^\/api/u, ""),