kinda a lot

.env.local.template

@@ -40,7 +40,7 @@ MODELS=`[
     "endpoints": [
       {
         "type": "tgi",
-        "url": "http://127.0.0.1:8080"
+        "url": "${MODEL_URL}"
       }
     ],
     "parameters": ${MODEL_PARAMS}

entrypoint.sh.template

@@ -3,11 +3,11 @@
 # Start the local Mongo database
 mongod &
 
-# Start the text-generation-inference process
-text-generation-launcher --model-id ${MODEL_NAME} --num-shard 1 --port 8080 --trust-remote-code &
+# # Start the text-generation-inference process
+# text-generation-launcher --model-id ${MODEL_NAME} --num-shard 1 --port 8080 --trust-remote-code &
 
-# Wait for text-generation-inference to start
-curl --retry 60 --retry-delay 10 --retry-connrefused http://127.0.0.1:8080/health
+# # Wait for text-generation-inference to start
+# curl --retry 60 --retry-delay 10 --retry-connrefused http://127.0.0.1:8080/health
 
 # Start the chat-ui process
 pm2 start /app/build/index.js -i $CPU_CORES --no-daemon &