Update entrypoint.sh

entrypoint.sh

@@ -1,14 +1,14 @@
 #!/bin/bash
 set -e
 
-echo "==> Starting Ollama (internal on 11434)..."
 export OLLAMA_HOST=127.0.0.1:11434
 export OLLAMA_MODELS=/home/user/.ollama/models
 
+echo "==> Starting Ollama..."
 ollama serve &
 
 # Wait for ollama ready
-echo "==> Waiting for Ollama..."
+echo "==> Waiting for Ollama to be ready..."
 MAX_RETRIES=30
 COUNT=0
 until curl -s http://127.0.0.1:11434/api/version > /dev/null 2>&1; do
@@ -20,22 +20,17 @@ until curl -s http://127.0.0.1:11434/api/version > /dev/null 2>&1; do
     echo "  ... attempt $COUNT/$MAX_RETRIES"
     sleep 2
 done
-
 echo "==> Ollama ready!"
 
-# Pull models if not cached (fallback)
-if ! ollama list | grep -q "deepseek-r1"; then
-    echo "==> Pulling deepseek-r1:latest..."
-    ollama pull deepseek-r1:latest
-fi
+# Pull models
+echo "==> Pulling deepseek-r1:latest..."
+ollama pull deepseek-r1:latest
 
-if ! ollama list | grep -q "qwen3-vl"; then
-    echo "==> Pulling qwen3-vl:latest..."
-    ollama pull qwen3-vl:latest
-fi
+echo "==> Pulling qwen3-vl:latest..."
+ollama pull qwen3-vl:latest
 
-echo "==> Models available:"
+echo "==> Models loaded:"
 ollama list
 
-echo "==> Starting FastAPI proxy on 0.0.0.0:7860 (API key: connectkey)..."
-exec uvicorn proxy:app --host 0.0.0.0 --port 7860
+echo "==> Starting proxy on :7860..."
+exec uvicorn proxy:app --host 0.0.0.0 --port 7860