diff --git a/examples/Question_answering_using_a_search_API.ipynb b/examples/Question_answering_using_a_search_API.ipynb
index ca333cb..dee3abe 100644
--- a/examples/Question_answering_using_a_search_API.ipynb
+++ b/examples/Question_answering_using_a_search_API.ipynb
@@ -292,7 +292,7 @@
    "source": [
     "As we can see, oftentimes, the search queries will return a large number of results, many of which are not relevant to the original question asked by the user. In order to improve the quality of the final answer, we use embeddings to re-rank and filter the results.\n",
     "\n",
-    "# 2. Re-rank\n",
+    "## 2. Re-rank\n",
     "\n",
     "Drawing inspiration from [HyDE (Gao et al.)](https://arxiv.org/abs/2212.10496), we first generate a hypothetical ideal answer to rerank our compare our results against. This helps prioritize results that look like good answers, rather than those similar to our question. Here’s the prompt we use to generate our hypothetical answer.\n"
    ]