NL2SQL进阶系列(1)：DB-GPT-Hub、SQLcoder、Text2SQL开源应用实践详解

#!pip install mindsql

from mindsql.core import MindSQLCore
from mindsql.databases import Sqlite
from mindsql.llms import GoogleGenAi
from mindsql.vectorstores import ChromaDB

#Add Your Configurations
config = {"api_key": "YOUR-API-KEY"}

#Choose the Vector Store. LLM and DB You Want to Work With And
#Create MindSQLCore Instance With Configured Llm, Vectorstore, And Database
minds = MindSQLCore(
    llm=GoogleGenAi(config=config),
    vectorstore=ChromaDB(),
    database=Sqlite()
)

#Create a Database Connection Using The Specified URL
connection = minds.database.create_connection(url="YOUR_DATABASE_CONNECTION_URL")

#Index All Data Definition Language (DDL) Statements in The Specified Database Into The Vectorstore
minds.index_all_ddls(connection=connection, db_name='NAME_OF_THE_DB')

#Index Question-Sql Pair in Bulk From the Specified Example Path
minds.index(bulk=True, path="your-qsn-sql-example.json")

#Ask a Question to The Database And Visualize The Result
response = minds.ask_db(
    question="YOUR_QUESTION",
    connection=connection,
    visualize=True
)

#Extract And Display The Chart From The Response
chart = response["chart"]
chart.show()

#Close The Connection to Your DB
connection.close()

git clone https://github.com/eosphoros-ai/DB-GPT-Hub.git
cd DB-GPT-Hub
conda create -n dbgpt_hub python=3.10 
conda activate dbgpt_hub
pip install poetry
poetry install

##生成train数据 和dev(eval)数据,
poetry run sh dbgpt_hub/scripts/gen_train_eval_data.sh

    {
        "db_id": "department_management",
        "instruction": "I want you to act as a SQL terminal in front of an example database, you need only to return the sql command to me.Below is an instruction that describes a task, Write a response that appropriately completes the request.\n\"\n##Instruction:\ndepartment_management contains tables such as department, head, management. Table department has columns such as Department_ID, Name, Creation, Ranking, Budget_in_Billions, Num_Employees. Department_ID is the primary key.\nTable head has columns such as head_ID, name, born_state, age. head_ID is the primary key.\nTable management has columns such as department_ID, head_ID, temporary_acting. department_ID is the primary key.\nThe head_ID of management is the foreign key of head_ID of head.\nThe department_ID of management is the foreign key of Department_ID of department.\n\n",
        "input": "###Input:\nHow many heads of the departments are older than 56 ?\n\n###Response:",
        "output": "SELECT count(*) FROM head WHERE age  >  56",
        "history": []
    }, 

from dbgpt_hub.data_process import preprocess_sft_data
from dbgpt_hub.train import start_sft
from dbgpt_hub.predict import start_predict
from dbgpt_hub.eval import start_evaluate

#配置训练和验证集路径和参数
data_folder = "dbgpt_hub/data"
data_info = [
        {
            "data_source": "spider",
            "train_file": ["train_spider.json", "train_others.json"],
            "dev_file": ["dev.json"],
            "tables_file": "tables.json",
            "db_id_name": "db_id",
            "is_multiple_turn": False,
            "train_output": "spider_train.json",
            "dev_output": "spider_dev.json",
        }
]

#配置fine-tune参数
train_args = {
            "model_name_or_path": "codellama/CodeLlama-13b-Instruct-hf",
            "do_train": True,
            "dataset": "example_text2sql_train",
            "max_source_length": 2048,
            "max_target_length": 512,
            "finetuning_type": "lora",
            "lora_target": "q_proj,v_proj",
            "template": "llama2",
            "lora_rank": 64,
            "lora_alpha": 32,
            "output_dir": "dbgpt_hub/output/adapter/CodeLlama-13b-sql-lora",
            "overwrite_cache": True,
            "overwrite_output_dir": True,
            "per_device_train_batch_size": 1,
            "gradient_accumulation_steps": 16,
            "lr_scheduler_type": "cosine_with_restarts",
            "logging_steps": 50,
            "save_steps": 2000,
            "learning_rate": 2e-4,
            "num_train_epochs": 8,
            "plot_loss": True,
            "bf16": True,
}

#配置预测参数
predict_args = {
            "model_name_or_path": "codellama/CodeLlama-13b-Instruct-hf",
            "template": "llama2",
            "finetuning_type": "lora",
            "checkpoint_dir": "dbgpt_hub/output/adapter/CodeLlama-13b-sql-lora",
            "predict_file_path": "dbgpt_hub/data/eval_data/dev_sql.json",
            "predict_out_dir": "dbgpt_hub/output/",
            "predicted_out_filename": "pred_sql.sql",
}

#配置评估参数
evaluate_args =  {
            "input": "./dbgpt_hub/output/pred/pred_sql_dev_skeleton.sql",
            "gold": "./dbgpt_hub/data/eval_data/gold.txt",
            "gold_natsql": "./dbgpt_hub/data/eval_data/gold_natsql2sql.txt",
            "db": "./dbgpt_hub/data/spider/database",
            "table": "./dbgpt_hub/data/eval_data/tables.json",
            "table_natsql": "./dbgpt_hub/data/eval_data/tables_for_natsql2sql.json",
            "etype": "exec",
            "plug_value": True,
            "keep_distict": False,
            "progress_bar_for_each_datapoint": False,
            "natsql": False,
}

#执行整个Fine-tune流程
preprocess_sft_data(
      data_folder = data_folder,
      data_info = data_info
)

start_sft(train_args)
start_predict(predict_args)
start_evaluate(evaluate_args)

poetry run sh dbgpt_hub/scripts/train_sft.sh

CUDA_VISIBLE_DEVICES=0 python dbgpt_hub/train/sft_train.py \
    --quantization_bit 4 \
    ...

deepspeed --num_gpus 2  dbgpt_hub/train/sft_train.py \
    --deepspeed dbgpt_hub/configs/ds_config.json \
    --quantization_bit 4 \
    ...

deepspeed --include localhost:3,4  dbgpt_hub/train/sft_train.py \
    --deepspeed dbgpt_hub/configs/ds_config.json \
    --quantization_bit 4 \
    ...

poetry run sh ./dbgpt_hub/scripts/predict_sft.sh

poetry run sh ./dbgpt_hub/scripts/export_merge.sh

poetry run python dbgpt_hub/eval/evaluation.py --plug_value --input  Your_model_pred_file

- 搭建基本框架，基于数个大模型打通从数据处理、模型SFT训练、预测输出和评估的整个流程 现在支持
    -  CodeLlama
    -  Baichuan2
    -  LLaMa/LLaMa2
    -  Falcon
    -  Qwen
    -  XVERSE
    -  ChatGLM2
    -  ChatGLM3
    -  internlm
    -  sqlcoder-7b(mistral)
    -  sqlcoder2-15b(starcoder)阶段二:

-  优化模型效果，支持更多不同模型进行不同方式的微调。
-  对`prompt`优化
-  放出评估效果，和优化后的还不错的模型，并且给出复现教程(见微信公众号EosphorosAI)阶段三：

-  推理速度优化提升
-  业务场景和中文效果针对性优化提升