wip

data-pipeline/utils/check-llm-server.ts

@@ -0,0 +1,43 @@
+/**
+ * Pings the local llama.cpp server to ensure it's up, running, and has a model loaded.
+ * If the server is offline or still loading, it terminates the pipeline gracefully.
+ */
+export async function checkLlmServer(
+  url = "http://127.0.0.1:8080/health",
+): Promise<void> {
+  try {
+    const response = await fetch(url);
+
+    // llama.cpp returns a 503 status if the server is up but the model weights are still loading
+    if (response.status === 503) {
+      console.error(
+        "\n ⏳ Local AI engine is starting up, but the model is still loading into memory.",
+      );
+      console.error(
+        "👉 Please wait a minute for the weights to load, then run the pipeline again.\n",
+      );
+      process.exit(1);
+    }
+
+    // Parse the JSON health response (expected: { status: "ok" })
+    const data = (await response.json()) as { status?: string };
+
+    if (response.ok && data.status === "ok") {
+      console.log("🟢 Local AI engine is connected and ready for inference!");
+      return;
+    }
+
+    // Catch-all for unexpected active server responses
+    console.error(
+      `\n ❌ Unknown response from local AI engine health check (Status: ${response.status}).`,
+    );
+    process.exit(1);
+  } catch (_error: unknown) {
+    console.error("\n ❌ Could not connect to the local AI engine.");
+    console.error(`🔗 Attempted endpoint: ${url}`);
+    console.error(
+      "👉 Make sure your './llama-server' command is actively running in another terminal tab!\n",
+    );
+    process.exit(1);
+  }
+}