fix inference demo_pipeline_standalone_kfp

OSS-MLOPS-PLATFORM · Apr 23, 2024 · 7b7e29d · 7b7e29d
1 parent 5392e47
commit 7b7e29d
Show file tree

Hide file tree

Showing 2 changed files with 17 additions and 10 deletions.
diff --git a/tutorials/demo_notebooks/demo_pipeline/demo-pipeline.ipynb b/tutorials/demo_notebooks/demo_pipeline/demo-pipeline.ipynb
@@ -751,8 +751,8 @@
     "    logger.info(f\"\\nInference service URL:\\n{is_url}\\n\")\n",
     "\n",
     "    inference_input = {\n",
-    "          'instances': input_sample.tolist()\n",
-    "        }\n",
+    "        'instances': input_sample.tolist()\n",
+    "    }\n",
     "    response = requests.post(\n",
     "        is_url,\n",
     "        json=inference_input,\n",

diff --git a/tutorials/demo_notebooks/demo_pipeline_standalone_kfp/demo-pipeline.ipynb b/tutorials/demo_notebooks/demo_pipeline_standalone_kfp/demo-pipeline.ipynb
@@ -493,7 +493,7 @@
     "    logger = logging.getLogger(__name__)\n",
     "\n",
     "    namespace = 'kserve-inference'\n",
-    "\n",
+    "    \n",
     "    input_sample = [[5.6, 0.54, 0.04, 1.7, 0.049, 5, 13, 0.9942, 3.72, 0.58, 11.4],\n",
     "                    [11.3, 0.34, 0.45, 2, 0.082, 6, 15, 0.9988, 2.94, 0.66, 9.2]]\n",
     "\n",
@@ -511,17 +511,24 @@
     "    KServe.get(model_name, namespace=namespace, watch=True, timeout_seconds=120)\n",
     "\n",
     "    inference_service = KServe.get(model_name, namespace=namespace)\n",
-    "    is_url = inference_service['status']['address']['url']\n",
-    "\n",
+    "    header = {\"Host\": f\"{model_name}.{namespace}.example.com\"}\n",
+    "    is_url = f\"http://istio-ingressgateway.istio-system.svc.cluster.local:80/v1/models/{model_name}:predict\"\n",
+    "    \n",
     "    logger.info(f\"\\nInference service status:\\n{inference_service['status']}\")\n",
     "    logger.info(f\"\\nInference service URL:\\n{is_url}\\n\")\n",
     "\n",
     "    inference_input = {\n",
-    "          'instances': input_sample.tolist()\n",
-    "        }\n",
-    "\n",
-    "    response = requests.post(is_url, json=inference_input)\n",
-    "    logger.info(f\"\\nPrediction response:\\n{response.text}\\n\")"
+    "        'instances': input_sample.tolist()\n",
+    "    }\n",
+    "    response = requests.post(\n",
+    "        is_url,\n",
+    "        json=inference_input,\n",
+    "        headers=header,\n",
+    "    )\n",
+    "    if response.status_code != 200:\n",
+    "        raise RuntimeError(f\"HTTP status code '{response.status_code}': {response.json()}\")\n",
+    "    \n",
+    "    logger.info(f\"\\nPrediction response:\\n{response.json()}\\n\")"
    ],
    "outputs": [],
    "execution_count": null