Text To Sql With Table Schema

🚀 文本转SQL模型

本项目是一个文本转SQL的模型，能够根据自然语言问题和表格结构生成对应的SQL语句。它可以帮助用户更方便地从表格数据中获取所需信息。

🚀 快速开始

这里有一个基于Flan - T5模型的升级版，它支持多表查询并支持 “<” 符号，点击查看。

💻 使用示例

基础用法

from typing import List
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("juierror/text-to-sql-with-table-schema")
model = AutoModelForSeq2SeqLM.from_pretrained("juierror/text-to-sql-with-table-schema")

def prepare_input(question: str, table: List[str]):
    table_prefix = "table:"
    question_prefix = "question:"
    join_table = ",".join(table)
    inputs = f"{question_prefix} {question} {table_prefix} {join_table}"
    input_ids = tokenizer(inputs, max_length=700, return_tensors="pt").input_ids
    return input_ids

def inference(question: str, table: List[str]) -> str:
    input_data = prepare_input(question=question, table=table)
    input_data = input_data.to(model.device)
    outputs = model.generate(inputs=input_data, num_beams=10, top_k=10, max_length=700)
    result = tokenizer.decode(token_ids=outputs[0], skip_special_tokens=True)
    return result

print(inference(question="get people name with age equal 25", table=["id", "name", "age"]))

数据集

小工具示例

输入示例：

question: get people name with age equal 25 table: id, name, age