Rename app.py to start.sh

app.py

@@ -1,23 +0,0 @@
-from flask import Flask, request, jsonify
-import subprocess
-
-app = Flask(__name__)
-MODEL_PATH = "/llama.cpp/models/llama3.gguf"
-
-@app.route("/generate", methods=["POST"])
-def generate():
-    prompt = request.json.get("prompt", "")
-
-    cmd = [
-        "/llama.cpp/main",
-        "-m", MODEL_PATH,
-        "-p", prompt,
-        "--n-predict", "128",
-        "--ctx-size", "2048",
-        "--temp", "0.7"
-    ]
-
-    result = subprocess.run(cmd, capture_output=True, text=True)
-    return jsonify({"response": result.stdout})
-
-app.run(host="0.0.0.0", port=7860)

start.sh

@@ -0,0 +1,13 @@
+#!/bin/bash
+
+# Start Ollama server
+ollama serve &
+
+# Give it time to boot
+sleep 15
+
+# Pull LLaMA 3 (8B)
+ollama pull llama3
+
+# Keep container alive
+tail -f /dev/null