language: zh
datasets:

• wikisql
  widget:
• text: "问题: 获取年龄等于25岁的人员姓名 表: id, 姓名, 年龄"

此处提供基于Flan-T5模型的升级版本，支持多表查询及"<"运算符，详情请访问此链接。

使用方法

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 = "表:"  
    question_prefix = "问题:"  
    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="获取年龄等于25岁的人员姓名", table=["id", "姓名", "年龄"]))