How to prompt engineer/ context for llm (Code Generation)

Question

I am building a natural language to sql application and for that im using: https://teknium-replit-v2-codeinstruct-3b.hf.space/ using its api, im generating sql code but I dont know how to provide context or how to style the prompt template so that it return relevant prompt.

from gradio_client import Client

client = Client("https://teknium-replit-v2-codeinstruct-3b.hf.space/")
result = client.predict
(

    '''
        ### Instruction: give me sql query to get all data from table 
        ### Input: I have 2 relations: Orders(Customer id, name, product SKU, date, cost) and Product               (product SKU, product name, SKU cost)
        ''',

          8,    0.1,    api_name="/predict"
)

print(result)

context : I have 2 relations: Orders(Customer id, name, product SKU, date, cost) and Product (product SKU, product name, SKU cost).

I tried to pass the string in the format give in the documentation here: https://huggingface.co/teknium/Replit-v2-CodeInstruct-3B but im not getting relevant result.