From c623be1fe61631499c12257ba7f1304e3980abaf Mon Sep 17 00:00:00 2001
From: Bojun-Feng <davidfeng@uchicago.edu>
Date: Fri, 11 Aug 2023 17:04:05 +0800
Subject: [PATCH] update README files

---
 README.md       | 7 ++-----
 README_zh_CN.md | 5 +----
 2 files changed, 3 insertions(+), 9 deletions(-)

diff --git a/README.md b/README.md
index 2c861a8345..f44fe11b0c 100644
--- a/README.md
+++ b/README.md
@@ -112,11 +112,8 @@ Xinference  client.
 - For cluster deployment, the endpoint will be `http://${supervisor_host}:9997`, where
 `${supervisor_host}` is the hostname or IP address of the server where the supervisor is running.
 
-You can also view a web UI using the Xinference endpoint to chat with all the 
-builtin models. You can even **chat with two cutting-edge AI models side-by-side to compare
-their performance**!
-
-![web UI](assets/demo.gif)
+You can also view a web UI dashboard using the Xinference endpoint, where you can keep track of all 
+running models, delete them at will, and launch Gradio chatbots with any chat models.
 
 ### Xinference CLI
 Xinference provides a command line interface (CLI) for model management. Here are some useful 
diff --git a/README_zh_CN.md b/README_zh_CN.md
index 72ab4d931e..6a2b2d71d9 100644
--- a/README_zh_CN.md
+++ b/README_zh_CN.md
@@ -105,10 +105,7 @@ Xinference 启动后，将会打印服务的 endpoint。这个 endpoint 用于
 - 集群部署下, endpoint 默认为 `http://${supervisor_host}:9997`。其中 `${supervisor_host}` 为
 supervisor 所在服务器的主机名或 IP 地址。
 
-你还可以通过 web UI 与任意内置模型聊天。Xinference 甚至**支持同时与两个最前沿的 AI 模型聊天并比较它们的回复质
-量**！
-
-![web UI](assets/demo.gif)
+您还可以使用 Xinference 端点查看模型仪表板，在这里您可以监视所有运行的模型，随意删除它们，并使用任何聊天模型启动 Gradio 聊天机器人。
 
 ### Xinference 命令行
 Xinference 提供了命令行工具用于模型管理。支持的命令包括：