Add Flask app for managing AI stacks

ai-portal/app.py

@@ -0,0 +1,117 @@
+import os
+import subprocess
+import threading
+from flask import Flask, render_template, redirect, jsonify
+
+app = Flask(__name__)
+
+IMAGE_STACK = os.environ.get("IMAGE_STACK", "/docker/ai-image-gen")
+LLM_STACK   = os.environ.get("LLM_STACK",   "/docker/ai-llm")
+
+# Track current active stack and swap status
+state = {
+    "active": None,       # "images" | "chat" | None
+    "swapping": False,
+    "message": "No stack active"
+}
+
+def run_compose(stack_dir, command):
+    """Run a docker compose command in a stack directory."""
+    subprocess.run(
+        ["docker", "compose", "-f", f"{stack_dir}/docker-compose.yml"] + command,
+        capture_output=True
+    )
+
+def is_stack_running(stack_dir):
+    """Check if the GPU container for this stack is running."""
+    container = "ai-image-gen-invokeai-1" if "image" in stack_dir else "ai-llm-ollama-1"
+    result = subprocess.run(
+        ["docker", "inspect", "--format", "{{.State.Running}}", container],
+        capture_output=True,
+        text=True
+    )
+    return result.stdout.strip() == "true"
+
+def do_swap(target):
+    """Stop the GPU-heavy container of inactive stack, start target."""
+    state["swapping"] = True
+
+    if target == "images":
+        state["message"] = "Stopping Ollama to free VRAM..."
+        subprocess.run(["docker", "stop", "ai-llm-ollama-1"], capture_output=True)
+        state["message"] = "Starting InvokeAI..."
+        subprocess.run(
+            ["docker", "compose", "-f", f"{IMAGE_STACK}/docker-compose.yml", "up", "-d"],
+            capture_output=True
+        )
+    else:
+        state["message"] = "Stopping InvokeAI to free VRAM..."
+        subprocess.run(["docker", "stop", "ai-image-gen-invokeai-1"], capture_output=True)
+        state["message"] = "Starting Ollama..."
+        subprocess.run(["docker", "start", "ai-llm-ollama-1"], capture_output=True)
+
+    state["active"] = target
+    state["swapping"] = False
+    state["message"] = f"{target.capitalize()} is ready."
+
+@app.route("/")
+@app.route("/portal")
+def portal():
+    image_running = is_stack_running(IMAGE_STACK)
+    llm_running   = is_stack_running(LLM_STACK)
+    return render_template(
+        "portal.html",
+        active=state["active"],
+        swapping=state["swapping"],
+        message=state["message"],
+        image_running=image_running,
+        llm_running=llm_running
+    )
+
+@app.route("/switch/<target>")
+def switch(target):
+    if target not in ("images", "chat"):
+        return "Invalid target", 400
+
+    if state["swapping"]:
+        return redirect("/portal")
+
+    # Warn if same stack requested
+    if state["active"] == target:
+        urls = {"chat": "https://chat.mydomain.com", "images": "https://images.mydomain.com"}
+        return redirect(urls[target])
+
+    # Run swap in background so browser gets immediate response
+    thread = threading.Thread(target=do_swap, args=(target,))
+    thread.daemon = True
+    thread.start()
+
+    return render_template(
+        "switching.html",
+        target=target,
+        message=f"Switching to {target}... this takes about 10 seconds."
+    )
+
+@app.route("/chat")
+def chat():
+    return redirect(URLS["chat"])
+
+@app.route("/images")
+def images():
+    return redirect(URLS["images"])
+
+@app.route("/status")
+def status():
+    """Polled by the switching page to know when swap is done."""
+    return jsonify(state)
+
+if __name__ == "__main__":
+    # Detect what's already running on startup
+    if is_stack_running(IMAGE_STACK):
+        state["active"] = "images"
+        state["message"] = "Images stack is active."
+    elif is_stack_running(LLM_STACK):
+        state["active"] = "chat"
+        state["message"] = "Chat stack is active."
+
+    app.run(host="0.0.0.0", port=8080)