XiYan

Table of Contents

• Features
• Preview
  • Architecture
  • Best Practice
  • Tools Preview
• Installation
  • Installing from pip
  • Installing from Smithery.ai
• Configuration
  • LLM Configuration
    • General LLMs
    • Text-to-SQL SOTA model
    • Local Model
  • Database Configuration
    • MySQL
    • PostgreSQL
• Launch
  • Claude Desktop
  • Cline
  • Goose
  • Cursor
• It Does Not Work
• Citation

Features

• 🌐 Fetch data by natural language through XiYanSQL
• 🤖 Support general LLMs (GPT,qwenmax), Text-to-SQL SOTA model
• 💻 Support pure local mode (high security!)
• 📝 Support MySQL and PostgreSQL.
• 🖱️ List available tables as resources
• 🔧 Read table contents

Preview

Architecture

Best practice and reports

Evaluation on MCPBench

Tools Preview

• The tool

  get_data

  provides a natural language interface for retrieving data from a database. This server will convert the input natural language into SQL using a built-in model and call the database to return the query results.
• The

  {dialect}://{table_name}

  resource allows obtaining a portion of sample data from the database for model reference when a specific table_name is specified.
• The

  {dialect}://

  resource will list the names of the current databases

Installation

Installing from pip

pip install xiyan-mcp-server

python -m xiyan_mcp_server

env YML=path/to/yml python -m xiyan_mcp_server

Installing from Smithery.ai

Configuration

model:
  name: "XGenerationLab/XiYanSQL-QwenCoder-32B-2412"
  key: ""
  url: "https://api-inference.modelscope.cn/v1/"

database:
  host: "localhost"
  port: 3306
  user: "root"
  password: ""
  database: ""

LLM Configuration

Name

key

url

General LLMs

model:
  name: "gpt-3.5-turbo"
  key: "YOUR KEY "
  url: "https://api.openai.com/v1"
database:

model:
  name: "qwen-max"
  key: "YOUR KEY "
  url: "https://dashscope.aliyuncs.com/compatible-mode/v1"
database:

Text-to-SQL SOTA model

(1) Modelscope version

key

model:
  name: "XGenerationLab/XiYanSQL-QwenCoder-32B-2412"
  key: ""
  url: "https://api-inference.modelscope.cn/v1/"

(2) Dashscope version

key

name: "YOUR NAME",
email: "YOUR EMAIL",
organization: "your college or Company or Organization"

key

key

key

model:
  name: "xiyansql-qwencoder-32b"
  key: "KEY"
  url: "https://xiyan-stream.biz.aliyun.com/service/api/xiyan-sql"
database:

Local Model

1. a PC/Mac with at least 16GB RAM
2. 6GB disk space

pip install flask modelscope torch==2.2.2 accelerate>=0.26.0 numpy=2.2.3

modelscope download --model XGenerationLab/XiYanSQL-QwenCoder-3B-2502

python local_xiyan_server.py

model:
  name: "xiyansql-qwencoder-3b"
  key: "KEY"
  url: "http://127.0.0.1:5090"

Database Configuration

host

port

user

password

database

MySQL

database:
  host: "localhost"
  port: 3306
  user: "root"
  password: ""
  database: ""

PostgreSQL

pip install psycopg2

database:
  dialect: "postgresql"
  host: "localhost"
  port: 5432
  user: ""
  password: ""
  database: ""

dialect

postgresql

Launch

Claude Desktop

{
    "mcpServers": {
        "xiyan-mcp-server": {
            "command": "/xxx/python",
            "args": [
                "-m",
                "xiyan_mcp_server"
            ],
            "env": {
                "YML": "PATH/TO/YML"
            }
        }
    }
}

/xxx/python

which python

Cline

Goose

env YML=path/to/yml /xxx/python -m xiyan_mcp_server

Cursor

Witsy

/xxx/python -m xiyan_mcp_server

It Does Not Work!

Citation

@article{xiyansql,
      title={A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL}, 
      author={Yingqi Gao and Yifu Liu and Xiaoxia Li and Xiaorong Shi and Yin Zhu and Yiming Wang and Shiqi Li and Wei Li and Yuntao Hong and Zhiling Luo and Jinyang Gao and Liyu Mou and Yu Li},
      year={2024},
      journal={arXiv preprint arXiv:2411.08599},
      url={https://arxiv.org/abs/2411.08599},
      primaryClass={cs.AI}
}