Merge pull request #51 from lighteternal/patch-1

Update semantic-caching.ipynb

labs/semantic-caching/semantic-caching.ipynb

@@ -9,7 +9,7 @@
     "## Semantic Caching lab\n",
     "![flow](../../images/semantic-caching.gif)\n",
     "\n",
-    "Playground to try the [sementic caching policy](https://learn.microsoft.com/en-us/azure/api-management/azure-openai-semantic-cache-lookup-policy). \n",
+    "Playground to try the [semantic caching policy](https://learn.microsoft.com/en-us/azure/api-management/azure-openai-semantic-cache-lookup-policy). \n",
     "\n",
     "The azure-openai-semantic-cache-lookup policy conducts a cache lookup of responses on Azure OpenAI Chat Completion API and Completion API requests from a pre-configured external cache. It operates by comparing the vector proximity of the prompt to prior requests and using a specific similarity score threshold. Caching responses helps reduce bandwidth and processing demands on the backend Azure OpenAI API, thus reducing latency perceived by API consumers.\n",
     "\n",