[Docs] Have a try to improve frameworks/streamlit.md (vllm-project#24841)

Signed-off-by: windsonsea <haifeng.yao@daocloud.io>

Author: windsonsea

docs/deployment/frameworks/streamlit.md

@@ -6,35 +6,33 @@ It can be quickly integrated with vLLM as a backend API server, enabling powerfu
 
 ## Prerequisites
 
-- Setup vLLM environment
-
-## Deploy
-
-- Start the vLLM server with the supported chat completion model, e.g.
+Set up the vLLM environment by installing all required packages:
 
 ```bash
-vllm serve qwen/Qwen1.5-0.5B-Chat
+pip install vllm streamlit openai
 ```
 
-- Install streamlit and openai:
+## Deploy
 
-```bash
-pip install streamlit openai
-```
+1. Start the vLLM server with a supported chat completion model, e.g.
 
-- Use the script: <gh-file:examples/online_serving/streamlit_openai_chatbot_webserver.py>
+    ```bash
+    vllm serve Qwen/Qwen1.5-0.5B-Chat
+    ```
 
-- Start the streamlit web UI and start to chat:
+1. Use the script: <gh-file:examples/online_serving/streamlit_openai_chatbot_webserver.py>
 
-```bash
-streamlit run streamlit_openai_chatbot_webserver.py
+1. Start the streamlit web UI and start to chat:
 
-# or specify the VLLM_API_BASE or VLLM_API_KEY
-VLLM_API_BASE="http://vllm-server-host:vllm-server-port/v1" \
+    ```bash
     streamlit run streamlit_openai_chatbot_webserver.py
 
-# start with debug mode to view more details
-streamlit run streamlit_openai_chatbot_webserver.py --logger.level=debug
-```
+    # or specify the VLLM_API_BASE or VLLM_API_KEY
+    VLLM_API_BASE="http://vllm-server-host:vllm-server-port/v1" \
+        streamlit run streamlit_openai_chatbot_webserver.py
+
+    # start with debug mode to view more details
+    streamlit run streamlit_openai_chatbot_webserver.py --logger.level=debug
+    ```
 
-![](../../assets/deployment/streamlit-chat.png)
+    ![Chat with vLLM assistant in Streamlit](../../assets/deployment/streamlit-chat.png)