Format

doc/source/notebooks/embedding.ipynb

@@ -149,9 +149,9 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Generating without Indexing Embeddings\n",
+    "## Generating Embeddings without Indexing \n",
     "\n",
-    "Now, if we just want to generate the embeddings without creating a vector index, we can use the function `create_embedding` from the `embedding` module:"
+    "If we just want to generate the embeddings without creating a vector index, we can use the function `create_embedding()` from the `embedding` module:"
    ]
   },
   {
@@ -168,9 +168,9 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Since we're not indexing vectors, the dataframe doesn't need to be stored as a table in the database. And we do not need to check the unique index of our columns.\n",
+    "Since we're not indexing vectors, the dataframe doesn't need to be stored as a table in the database. And we do not need to specify the unique key if the embeddings are in the same dataframe.\n",
     "\n",
-    "Furthermore, if we want to save the embeddings as vector type with embedding dimension, so that we can index them later, we need to cast the result with `gp.type_(\"vector\", modifier=embedding_dimension)`."
+    "Furthermore, if we want to save the embeddings as vector type with embedding dimension, so that we can index them later, we need to cast the result to type `gp.type_(\"vector\", modifier=<embedding_dimension>)`."
    ]
   },
   {
@@ -217,8 +217,7 @@
    "source": [
     "db.create_dataframe(columns={\"id\": range(len(content)), \"content\": content}).assign(\n",
     "    embedding_col=lambda t: (\n",
-    "        gp.type_(\"vector\", modifier=384)\n",
-    "        (create_embedding(t[\"content\"], \"all-MiniLM-L6-v2\"))\n",
+    "        gp.type_(\"vector\", modifier=384)(create_embedding(t[\"content\"], \"all-MiniLM-L6-v2\"))\n",
     "    ),\n",
     ")"
    ]