Refactor Qdrant notebooks (#556)

* Upgrade Qdrant to 1.3.0

* Adapt the descriptions and run the missing cells

examples/vector_databases/qdrant/Using_Qdrant_for_embeddings_search.ipynb

@@ -42,10 +42,35 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "id": "8d8810f9",
-   "metadata": {},
+   "metadata": {
-   "outputs": [],
+    "ExecuteTime": {
+     "end_time": "2023-06-29T12:59:21.344233180Z",
+     "start_time": "2023-06-29T12:59:00.815088712Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Collecting qdrant-client\r\n",
+      "  ...\r\n",
+      "Successfully installed certifi-2023.5.7 grpcio-1.56.0 grpcio-tools-1.56.0 h11-0.14.0 h2-4.1.0 hpack-4.0.0 httpcore-0.17.2 httpx-0.24.1 hyperframe-6.0.1 numpy-1.25.0 portalocker-2.7.0 protobuf-4.23.3 pydantic-1.10.9 qdrant-client-1.3.1 typing-extensions-4.5.0 urllib3-1.26.16\r\n",
+      "Collecting wget\r\n",
+      "  Using cached wget-3.2.zip (10 kB)\r\n",
+      "  Preparing metadata (setup.py) ... \u001B[?25ldone\r\n",
+      "\u001B[?25hBuilding wheels for collected packages: wget\r\n",
+      "  Building wheel for wget (setup.py) ... \u001B[?25ldone\r\n",
+      "\u001B[?25h  Created wheel for wget: filename=wget-3.2-py3-none-any.whl size=9657 sha256=eb5f15f12150fc304e7b14973424f696fa8d95225772bc0cbc0b318bf92e04b9\r\n",
+      "  Stored in directory: /home/user/.cache/pip/wheels/04/5f/3e/46cc37c5d698415694d83f607f833f83f0149e49b3af9d0f38\r\n",
+      "Successfully built wget\r\n",
+      "Installing collected packages: wget\r\n",
+      "Successfully installed wget-3.2\r\n"
+     ]
+    }
+   ],
    "source": [
     "# We'll need to install Qdrant client\n",
     "!pip install qdrant-client\n",
@@ -58,7 +83,12 @@
    "cell_type": "code",
    "execution_count": 4,
    "id": "5be94df6",
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-06-29T13:00:32.715638041Z",
+     "start_time": "2023-06-29T13:00:31.654032435Z"
+    }
+   },
    "outputs": [],
    "source": [
     "import openai\n",
@@ -95,10 +125,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "id": "5dff8b55",
-   "metadata": {},
+   "metadata": {
-   "outputs": [],
+    "ExecuteTime": {
+     "end_time": "2023-06-29T13:02:47.656128622Z",
+     "start_time": "2023-06-29T13:00:39.079229873Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "'vector_database_wikipedia_articles_embedded.zip'"
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "embeddings_url = 'https://cdn.openai.com/API/examples/data/vector_database_wikipedia_articles_embedded.zip'\n",
     "\n",
@@ -108,9 +152,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "id": "21097972",
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-06-29T13:03:08.268413005Z",
+     "start_time": "2023-06-29T13:02:47.626254476Z"
+    }
+   },
    "outputs": [],
    "source": [
     "import zipfile\n",
@@ -120,9 +169,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 7,
    "id": "70bbd8ba",
-   "metadata": {},
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-06-29T13:03:28.291797292Z",
+     "start_time": "2023-06-29T13:03:08.269033964Z"
+    }
+   },
    "outputs": [],
    "source": [
     "article_df = pd.read_csv('../data/vector_database_wikipedia_articles_embedded.csv')"
@@ -311,7 +365,7 @@
    "source": [
     "## Qdrant\n",
     "\n",
-    "The last vector database we'll consider is **[Qdrant](https://qdrant.tech/)**. This is a high-performant vector search database written in Rust. It offers both on-premise and cloud version, but for the purposes of that example we're going to use the local deployment mode.\n",
+    "**[Qdrant](https://qdrant.tech/)**. is a high-performant vector search database written in Rust. It offers both on-premise and cloud version, but for the purposes of that example we're going to use the local deployment mode.\n",
     "\n",
     "Setting everything up will require:\n",
     "- Spinning up a local instance of Qdrant\n",
@@ -646,9 +700,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "vector_db_split",
+   "name": "python3",
    "language": "python",
-   "name": "vector_db_split"
+   "display_name": "Python 3 (ipykernel)"
   },
   "language_info": {
    "codemirror_mode": {

examples/vector_databases/qdrant/docker-compose.yaml

@@ -1,7 +1,7 @@
 version: '3.4'
 services:
   qdrant:
-    image: qdrant/qdrant:v1.0.1
+    image: qdrant/qdrant:v1.3.0
     restart: on-failure
     ports:
       - "6333:6333"