docs: update nb w/evaluate endpoint example and point to deployed endpoint

inference-api-dev-template.ipynb

@@ -45,9 +45,25 @@
     "!pip install gradio_client"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "549b9b2c-3074-446b-962e-90c8efd2bd59",
+   "metadata": {},
+   "source": [
+    "# PINDER inference and evaluation template API examples"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b979671e-97d6-4c52-bc6e-279a09d722c8",
+   "metadata": {},
+   "source": [
+    "## Run inference via predict endpoint"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 10,
    "id": "2c0171fa-ee2a-40b7-8578-aa8516b4ece9",
    "metadata": {},
    "outputs": [
@@ -55,8 +71,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Loaded as API: http://localhost:7860/ ✔\n",
-      "/private/var/folders/tt/x223wxwj6dzg3vjjgc_6y5bm0000gn/T/gradio/71ffa01e98046880d05412a8224722e201d6655a60acdf24242cffb67c4495ac/8i5w_R--8i5w_L.pdb 1.9153118133544922\n"
+      "Loaded as API: https://danielkovtun-pinder-inference-template.hf.space/ ✔\n",
+      "/private/var/folders/tt/x223wxwj6dzg3vjjgc_6y5bm0000gn/T/gradio/0cda59c2805986a9e5956ed00cb552b3c86f05915da91e6e14a0a31b962e664b/3g9w_R--3g9w_L.pdb 1.2273471355438232\n"
      ]
     }
    ],
@@ -64,13 +80,16 @@
     "from gradio_client import Client, handle_file\n",
     "from pathlib import Path\n",
     "\n",
-    "client = Client(\"http://localhost:7860/\")\n",
+    "uri = \"https://danielkovtun-pinder-inference-template.hf.space/\"\n",
+    "# If running docker container locally\n",
+    "dev_uri = \"http://localhost:7860/\"\n",
+    "client = Client(uri)\n",
     "result = client.predict(\n",
-    "\t\treceptor_pdb=handle_file('./8i5w_R.pdb'),\n",
-    "\t\tligand_pdb=handle_file('./8i5w_L.pdb'),\n",
-    "\t\treceptor_fasta=None,\n",
-    "\t\tligand_fasta=None,\n",
-    "\t\tapi_name=\"/predict\"\n",
+    "    receptor_pdb=handle_file(\"./3g9w_R.pdb\"),\n",
+    "    ligand_pdb=handle_file(\"./3g9w_L.pdb\"),\n",
+    "    receptor_fasta=None, # optional in this implementation\n",
+    "    ligand_fasta=None,\n",
+    "    api_name=\"/predict\"\n",
     ")\n",
     "output_pdb, runtime = Path(result[0]), result[1]\n",
     "print(output_pdb, runtime)\n"
@@ -78,17 +97,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 11,
    "id": "c530fde1-7f57-4991-a53e-b3855657f9fc",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "(PosixPath('pinder-inference-outputs/8i5w_R--8i5w_L.pdb'), True)"
+       "(PosixPath('pinder-inference-outputs/3g9w_R--3g9w_L.pdb'), True)"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -103,6 +122,125 @@
     "output_pdb, output_pdb.is_file() \n",
     "\n"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b3c1c03e-74c1-4010-b385-e4366d43cd6f",
+   "metadata": {},
+   "source": [
+    "## Fetch evaluation metrics via evaluate endpoint"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "e5e26250-f20d-484d-84e2-320cdfef830a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Loaded as API: http://localhost:7860/ ✔\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'headers': ['system', 'L_rms', 'I_rms', 'F_nat', 'DOCKQ', 'CAPRI_class'],\n",
+       " 'data': [['3g9w__A1_Q71LX4--3g9w__D1_P05556',\n",
+       "   34.781349182128906,\n",
+       "   15.405366897583008,\n",
+       "   0.0,\n",
+       "   0.021916405918697517,\n",
+       "   'Incorrect']],\n",
+       " 'metadata': None}"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "client = Client(uri)\n",
+    "result = client.predict(\n",
+    "    system_id=\"3g9w__A1_Q71LX4--3g9w__D1_P05556\",\n",
+    "    prediction_pdb=handle_file(\"3g9w_R--3g9w_L.pdb\"),\n",
+    "    api_name=\"/evaluate\"\n",
+    ")\n",
+    "metrics, pred_native, runtime = result\n",
+    "metrics"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "eef0d108-5d76-4bef-bd0c-4952d433ccaf",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>system</th>\n",
+       "      <th>L_rms</th>\n",
+       "      <th>I_rms</th>\n",
+       "      <th>F_nat</th>\n",
+       "      <th>DOCKQ</th>\n",
+       "      <th>CAPRI_class</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>3g9w__A1_Q71LX4--3g9w__D1_P05556</td>\n",
+       "      <td>34.781349</td>\n",
+       "      <td>15.405367</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.021916</td>\n",
+       "      <td>Incorrect</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                             system      L_rms      I_rms  F_nat     DOCKQ  \\\n",
+       "0  3g9w__A1_Q71LX4--3g9w__D1_P05556  34.781349  15.405367    0.0  0.021916   \n",
+       "\n",
+       "  CAPRI_class  \n",
+       "0   Incorrect  "
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "metric_df = pd.DataFrame(metrics[\"data\"], columns=metrics[\"headers\"])\n",
+    "metric_df"
+   ]
   }
  ],
  "metadata": {