diff --git a/mistral-embed-getting-started/mistral_qdrant_getting_started.ipynb b/mistral-embed-getting-started/mistral_qdrant_getting_started.ipynb
new file mode 100644
index 0000000..5d0ef2a
--- /dev/null
+++ b/mistral-embed-getting-started/mistral_qdrant_getting_started.ipynb
@@ -0,0 +1,169 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install qdrant-client mistralai -qq"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from mistralai.client import MistralClient\n",
+    "from qdrant_client import QdrantClient\n",
+    "from qdrant_client.http.models import PointStruct, VectorParams, Distance\n",
+    "collection_name = \"example_collection\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "MISTRAL_API_KEY = \"your_mistral_api_key\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "search_client = QdrantClient(\":memory:\")\n",
+    "mistral_client = MistralClient(api_key=MISTRAL_API_KEY)\n",
+    "texts = [\n",
+    "    \"Qdrant is the best vector search engine!\",\n",
+    "    \"Loved by Enterprises and everyone building for low latency, high performance, and scale.\",\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "result = mistral_client.embeddings(\n",
+    "    model=\"mistral-embed\",\n",
+    "    input=texts,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "1024"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(result.data[0].embedding)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "points = [\n",
+    "    PointStruct(\n",
+    "        id=idx,\n",
+    "        vector=response.embedding,\n",
+    "        payload={\"text\": text},\n",
+    "    )\n",
+    "    for idx, (response, text) in enumerate(zip(result.data, texts))\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "UpdateResult(operation_id=0, status=<UpdateStatus.COMPLETED: 'completed'>)"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "search_client.create_collection(collection_name, vectors_config=\n",
+    "    VectorParams(\n",
+    "        size=1024,\n",
+    "        distance=Distance.COSINE,\n",
+    "    )\n",
+    ")\n",
+    "search_client.upsert(collection_name, points)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[ScoredPoint(id=0, version=0, score=0.7706972129206147, payload={'text': 'Qdrant is the best vector search engine!'}, vector=None, shard_key=None),\n",
+       " ScoredPoint(id=1, version=0, score=0.6887654944454833, payload={'text': 'Loved by Enterprises and everyone building for low latency, high performance, and scale.'}, vector=None, shard_key=None)]"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "search_client.search(\n",
+    "    collection_name=collection_name,\n",
+    "    query_vector=mistral_client.embeddings(\n",
+    "        model=\"mistral-embed\", input=[\"What is the best to use for vector search scaling?\"]\n",
+    "    ).data[0].embedding,\n",
+    ")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "examples",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}