CODEWITHSUNDEEP
pythonazureopenai-apichatgpt-api
Rostislav
Rostislav

Reputation: 29

Problem with Azure Api and ChatGPT (python)

I was given the task to deal with the Azure OpenAI Service and ChatGPT. In the process, when they gave me the keys, endpoint, etc., I ran into this problem:

openai.error.AuthenticationError: No API key provided. You can set your API key in code using 'openai.api_key = <API-KEY>', or you can set the environment variable OPENAI_API_KEY=<API-KEY>). If your API key is stored in a file, you can point the openai module at it with 'openai.api_key_path = <PATH>'. You can generate API keys in the OpenAI web interface. See https://platform.openai.com/account/api-keys for details.

Here is code:

import os
import openai
openai.api_type = "azure"
openai.api_version = "2023-05-15" 
openai.api_base = os.getenv("EndPointHERE")
openai.api_key = os.getenv("KeyHere")

response = openai.ChatCompletion.create(
    engine="KSUAI", 
    messages=[
    {"role": "system", "content": "Assistant is a large language model trained by OpenAI."},
    {"role": "user", "content": "Who were the founders of Microsoft?"}
    ]
)

print(response)

print(response['choices'][0]['message']['content'])

Upvotes: 0

Views: 1327

Answers (2)

jayant k
jayant k

Reputation: 93

I was getting same issue so I removed 'dotenv' stuff and directly hardcoded the keys into the code but its not ideal method.

import openai

openai.api_key = '***********************'
openai.api_base = '******************' 
openai.api_type = 'azure'
openai.api_version = '2023-05-15' 
deployment_name = 'Engine or deployment name on which model is deployed'  

prompt_in = "give your prompt here + input "
response = openai.Completion.create(
    engine=deployment_name,
    prompt=prompt_in,
    temperature=0,
    max_tokens=200,
    top_p=0.5,
    frequency_penalty=0,
    presence_penalty=0,
    best_of=1,
    stop=None)

you can also use langchain for prompt and for running model. I hope it will help...!

Upvotes: 0

Rostislav
Rostislav

Reputation: 29

The problem was solved by removing os.getenv from the code, and writing the given keys and endpoint directly into a variable

Upvotes: 0

Related Questions