Update index.mdx

Author: fpagny

tutorials/how-to-implement-rag-generativeapis/index.mdx

@@ -253,10 +253,14 @@ You can now execute your RAG pipeline with the following command:
    If you used the Scaleway cheatsheet provided as examples and asked for a CLI command to power of instance, you should see the following answer:
    ```sh
    scw instance server stop example-28f3-4e91-b2af-4c3502562d72 
-
-   This will shut down the Instance with the specified instance-uuid. Note that this command stops the Instance but does not shut it down completely.
+   ```
 
    This command is correct and can be used with the Scaleway CLI.
+
+   <Message type="tip">
+   You may also see a warning from Langchain: `LangSmithMissingAPIKeyWarning: API key must be provided when using hosted LangSmith API`. You can ignore this for the scope of this tutorial. This is due to Langchain requiring an API Key to activate the observability LangSmith module to store queries performed and optimize them afterwards. 
+   </Message>
+   
    Note that vector embedding enabled the system to retrieve proper document chunks even if the Scaleway cheatsheet never mentions `shut down` but only `power off`.
    You can compare this result without RAG (for instance, by using the same prompt in [Generative APIs Playground](https://console.scaleway.com/generative-api/models/fr-par/playground?modelName=llama-3.1-8b-instruct)):