Skip to content

Commit 0596776

Browse files
update readme
1 parent c7f7d77 commit 0596776

File tree

3 files changed

+16
-9
lines changed

3 files changed

+16
-9
lines changed

README.md

Lines changed: 7 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -12,7 +12,7 @@
1212
# XiYan MCP Server
1313

1414

15-
A Model Context Protocol (MCP) server that enables natural language queries to databases, power by [XiYanSQL](https://github.com/XGenerationLab/XiYan-SQL) as text-to-sql technique.
15+
A Model Context Protocol (MCP) server that enables natural language queries to databases, powered by [XiYanSQL](https://github.com/XGenerationLab/XiYan-SQL) as text-to-sql technique.
1616

1717
We support MySQL database now and more dialects are coming soon.
1818

@@ -39,12 +39,12 @@ pip install xiyan-mcp-server
3939

4040
After that you can directly run the server by:
4141
```bash
42-
python -m xiyan-mcp-server
42+
python -m xiyan_mcp_server
4343
```
4444
But it does not provide any functions until you complete following config.
4545
You will get a yml file. After that you can run the server by:
4646
```yaml
47-
env YML=path/to/yml python -m xiyan-mcp-server
47+
env YML=path/to/yml python -m xiyan_mcp_server
4848
```
4949

5050

@@ -94,8 +94,8 @@ database:
9494
```
9595
#### Using Text-to-SQL SOTA model
9696
Last, we recommend the XiYanSQL-qwencoder-32B (https://github.com/XGenerationLab/XiYanSQL-QwenCoder), which is the SOTA model in text-to-sql.
97-
We deployed the model on DashScope, so you need to set the following environment variables:
98-
Contact us to get the ``key``.
97+
We deployed the model on Alibaba Cloud DashScope, so you need to set the following environment variables:
98+
Contact us to get the ``key``. ( godot.lzl@alibaba-inc.com )
9999
```yaml
100100
model:
101101
name: "pre-xiyan_multi_dialect_v3"
@@ -104,6 +104,8 @@ model:
104104
database:
105105
```
106106
107+
Alternatively, you can also deploy the model (XiYanSQL-qwencoder-32B) on your own server.
108+
107109
#### Local LLMs
108110
To support in the future.
109111

README_zh.md

Lines changed: 6 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -92,9 +92,11 @@ model:
9292
database:
9393
```
9494
#### 使用文本到 SQL 的 SOTA 模型
95-
最后,我们推荐使用 XiYanSQL-qwencoder-32B (https://github.com/XGenerationLab/XiYanSQL-QwenCoder),这是文本到 SQL 的 SOTA 模型。
95+
最后,我们推荐使用 XiYanSQL-qwencoder-32B (https://github.com/XGenerationLab/XiYanSQL-QwenCoder),这是文本到 SQL 的 SOTA 模型,而且我们将其开源了
9696
我们将模型部署在 DashScope 上,因此您需要设置以下环境变量:
97-
请联系我们以获取 ``key``
97+
请联系我们以获取 ``key``。( godot.lzl@alibaba-inc.com )
98+
99+
98100
```yaml
99101
model:
100102
name: "pre-xiyan_multi_dialect_v3"
@@ -103,6 +105,8 @@ model:
103105
database:
104106
```
105107
108+
当然你也可以自己部署XiYanSQL-qwencoder-32B在任何有足够GPU配置的机器上,并以openai sdk的方式对外提供服务,就可以接入本MCP server
109+
106110
#### 本地 LLM
107111
未来将支持。
108112

setup.py

Lines changed: 3 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,7 @@
22

33
setup(
44
name='xiyan_mcp_server', # 包的名字
5-
version='0.1.0', # 版本号
5+
version='0.1.1', # 版本号
66
packages=find_packages(), # 自动找到项目中的包
77
install_requires=[ # 必要的包依赖
88
# 'numpy', # 示例:若有依赖包,将其列在此
@@ -11,7 +11,8 @@
1111
'sqlalchemy',
1212
'llama_index',
1313
'yaml',
14-
'pandas'
14+
'pandas',
15+
'pymysql'
1516
],
1617
author='Bruce Luo', # 作者
1718
author_email='godot.lzl@alibaba-inc.com', # 作者邮箱

0 commit comments

Comments
 (0)