Add vision config files in enhancements and RAG notebook

Author: Zhi Zhou

Basic_Samples/GPT-4V/RAG_chatcompletions_example_restapi.ipynb

@@ -11,14 +11,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
     "import json\n",
     "import os\n",
     "import requests\n",
-    "import base64"
+    "import time"
    ]
   },
   {
@@ -33,7 +33,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -63,12 +63,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
     "# Define GPT-4V API call with image\n",
-    "def call_GPT4V_image(messages, ocr=False, grounding=False, in_context=None):\n",
+    "def call_GPT4V_image(messages, ocr=False, grounding=False, in_context=None, vision_api=None):\n",
     "    # Construct the API request URL\n",
     "    if ocr or grounding or in_context is not None:\n",
     "        api_url = f\"{openai_api_base}/openai/deployments/{deployment_name}/extensions/chat/completions?api-version={openai_api_version}\"\n",
@@ -92,23 +92,37 @@
     "\n",
     "    if ocr or grounding:\n",
     "        payload[\"enhancements\"]={\n",
-    "                            \"ocr\": {\n",
-    "                                \"enabled\": ocr # Enable OCR enhancement\n",
-    "                            },\n",
-    "                            \"grounding\": {\n",
-    "                                \"enabled\": grounding  # Enable grounding enhancement\n",
-    "                            }\n",
-    "                        }\n",
+    "              \"ocr\": {\n",
+    "                \"enabled\": ocr # Enable OCR enhancement\n",
+    "              },\n",
+    "              \"grounding\": {\n",
+    "                \"enabled\": grounding  # Enable grounding enhancement\n",
+    "              }\n",
+    "        }\n",
+    "\n",
+    "    data_sources = []\n",
+    "\n",
     "    if in_context is not None:\n",
-    "        data_source = {\n",
+    "        data_sources.append({\n",
     "            \"type\": \"AzureCognitiveSearch\",\n",
     "            \"parameters\": {\n",
     "                \"endpoint\": in_context.get(\"endpoint\"),\n",
     "                \"key\": in_context.get(\"key\"),\n",
     "                \"indexName\": in_context.get(\"indexName\"),\n",
     "            }\n",
-    "        }\n",
-    "        payload[\"dataSources\"] = [data_source]\n",
+    "        })\n",
+    "\n",
+    "    if vision_api is not None:\n",
+    "        data_sources.append({\n",
+    "            \"type\": \"AzureComputerVision\",\n",
+    "            \"parameters\": {\n",
+    "                \"endpoint\": vision_api.get(\"endpoint\"),\n",
+    "                \"key\": vision_api.get(\"key\"),\n",
+    "            }\n",
+    "        })\n",
+    "\n",
+    "    if data_sources:\n",
+    "        payload[\"dataSources\"] = data_sources\n",
     "\n",
     "    # Send the request and handle the response\n",
     "    try:\n",
@@ -128,7 +142,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 4,
    "id": "f4b3d21a",
    "metadata": {},
    "outputs": [],
@@ -187,7 +201,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [