feat: add schema-linking awel example

[junewgl]

Description

feat: add schemalinking awel example：nl -> schema -> sql -> chart

How Has This Been Tested?

pre-requirements:
1. install openai python sdk
pip install -e ."[openai]"
2. set openai key and base
export OPENAI_API_KEY={your_openai_key} export OPENAI_API_BASE={your_openai_base}
or
import os os.environ["OPENAI_API_KEY"] = {your_openai_key} os.environ["OPENAI_API_BASE"] = {your_openai_base}
3. run
python examples/awel/simple_nl_schema_sql_chart_example.py
Examples:

curl --location 'http://127.0.0.1:5555/api/v1/awel/trigger/examples/rag/schema_linking' \
--header 'Content-Type: application/json' \
--data '{"query": "Statistics of user age in the user table are based on three categories: age is less than 10, age is greater than or equal to 10 and less than or equal to 20, and age is greater than 20. The first column of the statistical results is different ages, and the second column is count."}' 

Snapshots:

• data
  
• run
  
• sql
  
• chart
  

Checklist:

• My code follows the style guidelines of this project
• I have already rebased the commits and make the commit message conform to the project standard.
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• Any dependent changes have been merged and published in downstream modules

[Aries-ckt]

r+

[csunny]

Thanks for your PR at first, but i noticed that you created a new schemalinker package and put it in the rags directory. Why are the sql_exec.py and sql_gen.py files also put here?

Schemalinking will be a very critical capability in dbgpt and requires a detailed plan. The current implementation is more like an example, and the directory needs to be adjusted.

Don’t merge for now, please. @Aries-ckt

[junewgl]

Thanks for your PR at first, but i noticed that you created a new schemalinker package and put it in the rags directory. Why are the sql_exec.py and sql_gen.py files also put here?

Schemalinking will be a very critical capability in dbgpt and requires a detailed plan. The current implementation is more like an example, and the directory needs to be adjusted.

Don’t merge for now, please. @Aries-ckt

Thanks for your suggestion, I will revise it again @csunny

[csunny]

r+

[Aries-ckt]

r+