Update document (#3746)

### What problem does this PR solve?

Fix description on local LLM deployment case

### Type of change

- [x] Documentation Update

---------

Signed-off-by: jinhai <[email protected]>
Co-authored-by: writinwaters <[email protected]>

docs/guides/deploy_local_llm.mdx

@@ -74,9 +74,9 @@ In the popup window, complete basic settings for Ollama:
 4. OPTIONAL: Switch on the toggle under **Does it support Vision?** if your model includes an image-to-text model.
 
 :::caution NOTE
+- If RAGFlow is in Docker and Ollama runs on the same host machine, use `http://host.docker.internal:11434` as base URL.
 - If your Ollama and RAGFlow run on the same machine, use `http://localhost:11434` as base URL.
-- If your Ollama and RAGFlow run on the same machine and Ollama is in Docker, use `http://host.docker.internal:11434` as base URL. 
-- If your Ollama runs on a different machine from RAGFlow, use `http://<IP_OF_OLLAMA_MACHINE>:11434` as base URL. 
+- If your Ollama runs on a different machine from RAGFlow, use `http://<IP_OF_OLLAMA_MACHINE>:11434` as base URL.
 :::
 
 :::danger WARNING