docs(project): update

README.md

@@ -98,7 +98,7 @@ The first run will automatically download the configuration of internlm2-7B.
     # config.ini
     [llm]
     ..
-    client_url = "http://10.140.24.142:39999/inference" # example
+    client_url = "http://10.140.24.142:8888/inference" # example
 
     python3 main.py workdir
     ```
@@ -124,7 +124,8 @@ python3 main.py workdir
 If you still need to read Feishu group messages, see [Feishu Developer Square - Add Application Capabilities - Robots](https://open.feishu.cn/app?lang=zh-CN).
 
 ## STEP4. Advanced Version [Optional]
-To further enhance the experience of the assistant's response, the more features you turn on, the better.
+
+The basic version may not perform well. You can enable these features to enhance performance. The more features you turn on, the better.
 
 1. Use higher accuracy local LLM
 
@@ -134,7 +135,7 @@ To further enhance the experience of the assistant's response, the more features
 2. Hybrid LLM Service
 
     For LLM services that support the openai interface, HuixiangDou can utilize its Long Context ability.
-    Using Kimi as an example, below is an example of `config.ini` configuration:
+    Using [kimi](https://platform.moonshot.cn/) as an example, below is an example of `config.ini` configuration:
 
     ```shell
     # config.ini
@@ -146,7 +147,7 @@ To further enhance the experience of the assistant's response, the more features
     remote_llm_max_text_length = 128000
     remote_llm_model = "moonshot-v1-128k"
     ```
-    We also support the gpt API. Note that this feature will increase response time and operating costs.
+    We also support chatgpt API. Note that this feature will increase response time and operating costs.
 
 3. Repo search enhancement
 

README_zh.md

@@ -18,7 +18,7 @@
 
 以下是运行茴香豆的硬件需求。建议遵循部署流程，从基础版开始，逐渐体验高级特性。
 
-| 版本 | 硬件需求 | 描述 | Linux 系统已验证设备 |
+| 版本 | GPU显存需求 | 描述 | Linux 系统已验证设备 |
 | :-: | :-: | :-: | :-: |
 | 基础版 | 20GB | 能回答领域知识的基础问题，零成本运行 | ![](https://img.shields.io/badge/3090%2024G-passed-blue?style=for-the-badge) |
 | 高级版 | 40GB | 能够回答源码级问题，零成本运行 | ![](https://img.shields.io/badge/A100%2080G-passed-blue?style=for-the-badge) |
@@ -139,7 +139,7 @@ python3 main.py workdir
 2. Hybrid LLM Service
 
     对于支持 openai 接口的 LLM 服务，茴香豆可以发挥它的 Long Context 能力。
-    以 kimi 为例，以下是 `config.ini` 配置示例：
+    以 [kimi](https://platform.moonshot.cn/) 为例，以下是 `config.ini` 配置示例：
 
     ```shell
     # config.ini
@@ -151,7 +151,7 @@ python3 main.py workdir
     remote_llm_max_text_length = 128000
     remote_llm_model = "moonshot-v1-128k"
     ```
-    我们同样支持 gpt API。注意此特性会增加响应耗时和运行成本。
+    我们同样支持 chatgpt API。注意此特性会增加响应耗时和运行成本。
 
 3. repo 搜索增强