diff --git a/docs/docs/integrations/vectorstores/oceanbase.ipynb b/docs/docs/integrations/vectorstores/oceanbase.ipynb
index a5ccb896d0797..ca12d2d81a4f4 100644
--- a/docs/docs/integrations/vectorstores/oceanbase.ipynb
+++ b/docs/docs/integrations/vectorstores/oceanbase.ipynb
@@ -15,7 +15,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Initialization\n",
+    "## Setup\n",
     "\n",
     "First donwload the partner package:"
    ]
@@ -68,7 +68,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Instantiation\n",
+    "## Initialization\n",
     "\n",
     "Configure the API key of the embedded model. Here we use `DashScopeEmbeddings` as an example. When deploying `Oceanbase` with a Docker image as described above, simply follow the script below to set the `host`, `port`, `user`, `password`, and `database name`. For other deployment methods, set these parameters according to the actual situation."
    ]
@@ -207,7 +207,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Query from OceanBase\n",
+    "## Query vector store\n",
     "\n",
     "Note that `OceanBase` currently only supports two vector distance functions: Euclidean distance (`l2`) and inner product distance (`ip`), and uses Euclidean distance by default."
    ]
@@ -356,7 +356,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Using as a Retriever\n",
+    "### Query by turning into retriever\n",
     "\n",
     "You can transform `OceanBase` vector store into a retriever for broader functionality in LangChain."
    ]
@@ -392,6 +392,28 @@
     "    print(\"-\" * 80)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Usage for retrieval-augmented generation\n",
+    "\n",
+    "For guides on how to use this vector store for retrieval-augmented generation (RAG), see the following sections:\n",
+    "\n",
+    "- [Tutorials: working with external knowledge](https://python.langchain.com/docs/tutorials/#working-with-external-knowledge)\n",
+    "- [How-to: Question and answer with RAG](https://python.langchain.com/docs/how_to/#qa-with-rag)\n",
+    "- [Retrieval conceptual docs](https://python.langchain.com/docs/concepts/retrieval)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "TODO"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},