TypeError: Missing required arguments; Expected either ('messages' and 'model') or ('messages', 'model' and 'stream') arguments to be given

Getting an error while creating a Natural language to SQL code converter

import openai

# Set your OpenAI GPT-3.5 Turbo API key
openai.api_key = 'your-api-key'


def convert_to_sql(natural_language_text):
    prompt = f"Convert the following natural language text to SQL: {natural_language_text}"
    
    response = openai.chat.completions.create(
        engine="text-davinci-003",  # You can also use "text-davinci-003" for the Davinci model
        prompt=prompt,
        max_tokens=100  # You can adjust the maximum number of tokens based on your requirements
    )

    return response.choices[0].text.strip()

# Example usage
natural_language_text = "Retrieve all employees who joined the company after 2020."
sql_query = convert_to_sql(natural_language_text)

print(f"Natural Language Text: {natural_language_text}")
print(f"SQL Query: {sql_query}")

Any input/suggestions will be really helpful.

2 Likes

text-davinci-003 used the legacy completions endpoint not chat/completions, but has been deprecated.

You can use gpt-3.5-turbo-instruct as a replacement on the completions endpoint,

https://platform.openai.com/docs/api-reference/completions

Or use one of the current models.

1 Like

Thanks but this is still not working -

import openai

# Set your OpenAI GPT-3.5 Turbo API key
openai.api_key = 'your-api-key'

def convert_to_sql(natural_language_text):
    prompt = f"Convert the following natural language text to SQL: {natural_language_text}"
    
    response = openai.chat.completions.create(
        engine="gpt-3.5-turbo-instruct",  # You can also use "text-davinci-003" for the Davinci model
        prompt=prompt,
        max_tokens=100  # You can adjust the maximum number of tokens based on your requirements
    )

    return response.choices[0].text.strip()

# Example usage
natural_language_text = "Retrieve all employees who joined the company after 2020."
sql_query = convert_to_sql(natural_language_text)

print(f"Natural Language Text: {natural_language_text}")
print(f"SQL Query: {sql_query}")

Error -

1 Like

API Reference - OpenAI API

You need to use the new Chat Completions Endpoint, as shown below.

from openai import OpenAI
client = OpenAI()

completion = client.chat.completions.create(
  model="gpt-3.5-turbo",
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello!"}
  ]
)

print(completion.choices[0].message)

You may also need to run pip install --upgrade openai

2 Likes