add fastembed

book/llm/Chapter.ipynb

@@ -438,6 +438,57 @@
     "\n",
     "results = ranker.rank(query=\"I love you\", docs=[\"I hate you\", \"I really like you\"], doc_ids=[0,1])"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create Embeddings on your CPU with `fastembed`"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "My favourite library for creating embeddings:\n",
+    "\n",
+    "`fastembed`, developed by Qdrant.\n",
+    "\n",
+    "`fastembed` is a lightweight and fast library for using popular embedding models.\n",
+    "\n",
+    "Without using your GPU.\n",
+    "\n",
+    "It also integrates seamlessly with Qdrant's vector database.\n",
+    "\n",
+    "I would like to see more supported models though, as `fastembed` has so much potential."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install fastembed"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from fastembed import TextEmbedding\n",
+    "\n",
+    "documents = [\n",
+    "    \"This is some\",\n",
+    "    \"example document\",\n",
+    "]\n",
+    "\n",
+    "embedding_model = TextEmbedding(model_name=\"jinaai/jina-embeddings-v2-small-en\")\n",
+    "\n",
+    "embeddings = list(embedding_model.embed(documents))"
+   ]
   }
  ],
  "metadata": {