InvalidRequestError: Must provide an 'engine' parameter while invoking openAI API for text generation

Question

I was trying this code given in OpenAI.

Code

import openai

prompt = """We’re releasing an API for accessing new AI models developed by OpenAI. Unlike most AI systems which are designed for one use-case, the API today provides a general-purpose “text in, text out” interface, allowing users to try it on virtually any English language task. You can now request access in order to integrate the API into your product, develop an entirely new application, or help us explore the strengths and limits of this technology."""

response = openai.Completion.create(model="davinci", prompt=prompt, stop="\n", temperature=0.9, max_tokens=100)

print(response)

I'm getting an error

Error

"Must provide an 'engine' parameter to create a %s" % cls, "engine". openai.error.InvalidRequestError: Must provide an 'engine' parameter to create a <class 'openai.api_resources.completion.Completion'>

I'm using python 3.7.6

Ujjawal Panchal · Accepted Answer · 2021-01-26 08:32:54Z

10

It seems you have confused the engine parameter with the model parameter. Please have a look at this documentation for the correct way to call: https://beta.openai.com/docs/developer-quickstart/python-bindings

Please change model = "davinci" to engine = "davinci" and you should be good to go.

edited Jan 26, 2021 at 8:32

answered Jan 25, 2021 at 6:44

Ujjawal Panchal

1161 silver badge4 bronze badges

Sign up to request clarification or add additional context in comments.

1 Comment

Alex Polymath Over a year ago

But if I have custom one?

Howie Yang · Accepted Answer · 2022-01-01 15:57:08Z

1

If you get the error code:

...
InvalidRequestError: Engine not found

One possible problem could be your account setting does not offer you access to the engine. For example, embedding engines are only available for "private beta." You may need to request access to it for your account. The following code may get you the available engines to your account:

import openai

openai.api_key = your_openai_api_key

data = openai.Engine.list() for eng in data['data']:
    print(eng['id'])

answered Jan 1, 2022 at 15:57

Howie Yang

112 bronze badges

Comments

zora · Accepted Answer · 2023-02-13 19:09:23Z

1

Here is complete prompt in a function, for a successful query:

import os
import openai

openai.api_key = os.environ["openai_key"]

start = "Your are a AI Search Engine, answer the following query with a witty answer and include validated facts only."

def generate(prompt):
    start_sequence = "{}.{}".format(start,prompt)
    completions = openai.Completion.create(
      model="text-davinci-003",
      prompt=start_sequence,
      temperature=0.1,
      max_tokens=256,
      top_p=1,
      frequency_penalty=0.51,
      presence_penalty=0.5,
      #stream = False,
      #echo = True
    )
          
    
    message = completions.choices[0].text
    print(message)
    return message

answered Feb 13, 2023 at 19:09

zora

516 bronze badges

Comments

Joey Baruch · Accepted Answer · 2023-06-13 14:52:07Z

1

I was using langchain's AzureOpenAI object and what worked for me was replacing:

from langchain.llms import AzureOpenAI

llm = AzureOpenAI(
    deployment_name="td2",
    model_name="text-davinci-002", 
)

For

llm = AzureOpenAI(
    engine="td2",
    model_name="text-davinci-002", 
)

answered Jun 13, 2023 at 14:52

Joey Baruch

5,4097 gold badges39 silver badges58 bronze badges

Collectives™ on Stack Overflow

InvalidRequestError: Must provide an 'engine' parameter while invoking openAI API for text generation

4 Answers 4

1 Comment

Comments

Comments

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

4 Answers 4

1 Comment

Comments

Comments

Comments

Your Answer

Sign up or log in

Post as a guest

Related