# I am getting this error in jupyter even though i copied as it is in the guidlines **URL:** \ **Category:** ChatGPT Prompt Engineering for Developers\ **Created:** [August 4, 2023, 3:57pm UTC](https://community.deeplearning.ai/t/i-am-getting-this-error-in-jupyter-even-though-i-copied-as-it-is-in-the-guidlines/408032 "2023-08-04T15:57:09Z")\ **Posts on this page:** 3\ **Page:** 1
**Author:** ![Manikanta\_Maduri](https://avatars.discourse-cdn.com/v4/letter/m/85f322/32.png) [@Manikanta\_Maduri](https://community.deeplearning.ai/u/Manikanta_Maduri)\ **Post date:** [August 4, 2023, 3:57pm UTC](https://community.deeplearning.ai/t/i-am-getting-this-error-in-jupyter-even-though-i-copied-as-it-is-in-the-guidlines/408032/1 "2023-08-04T15:57:09Z")
* * * AuthenticationError Traceback (most recent call last) in 16 `{text}` 17 “”" —\> 18 response = get\_completion(prompt) 19 print(response) in get\_completion(prompt, model) 1 def get\_completion(prompt, model=“gpt-3.5-turbo”): 2 messages = [{“role”: “user”, “content”: prompt}] ----\> 3 response = openai.ChatCompletion.create( 4 model=model, 5 messages=messages, ~\anaconda3\lib\site-packages\openai\api\_resources\chat\_completion.py in create(cls, \*args, \*\*kwargs) 23 while True: 24 try: —\> 25 return super().create(\*args, \*\*kwargs) 26 except TryAgain as e: 27 if timeout is not None and time.time() \> start + timeout: ~\anaconda3\lib\site-packages\openai\api\_resources\abstract\engine\_api\_resource.py in create(cls, api\_key, api\_base, api\_type, request\_id, api\_version, organization, \*\*params) 147 url, 148 params, → 149 ) = cls.\_\_prepare\_create\_request( 150 api\_key, api\_base, api\_type, api\_version, organization, \*\*params 151 ) ~\anaconda3\lib\site-packages\openai\api\_resources\abstract\engine\_api\_resource.py in \_\_prepare\_create\_request(cls, api\_key, api\_base, api\_type, api\_version, organization, \*\*params) 104 params[“timeout”] = MAX\_TIMEOUT 105 → 106 requestor = api\_requestor.APIRequestor( 107 api\_key, 108 api\_base=api\_base, ~\anaconda3\lib\site-packages\openai\api\_requestor.py in **init** (self, key, api\_base, api\_type, api\_version, organization) 136 ): 137 self.api\_base = api\_base or openai.api\_base → 138 self.api\_key = key or util.default\_api\_key() 139 self.api\_type = ( 140 ApiType.from\_str(api\_type) ~\anaconda3\lib\site-packages\openai\util.py in default\_api\_key() 184 return openai.api\_key 185 else: → 186 raise openai.error.AuthenticationError( 187 “No API key provided. You can set your API key in code using ‘openai.api\_key = ’, or you can set the environment variable OPENAI\_API\_KEY=). If your API key is stored in a file, you can point the openai module at it with ‘openai.api\_key\_path = ’. You can generate API keys in the OpenAI web interface. See [https://platform.openai.com/account/api-keys](https://platform.openai.com/account/api-keys) for details.” 188 ) AuthenticationError: No API key provided. You can set your API key in code using ‘openai.api\_key = ’, or you can set the environment variable OPENAI\_API\_KEY=). If your API key is stored in a file, you can point the openai module at it with ‘openai.api\_key\_path = ’. You can generate API keys in the OpenAI web interface. See [https://platform.openai.com/account/api-keys](https://platform.openai.com/account/api-keys) for details. ---
**Author:** ![Manikanta\_Maduri](https://avatars.discourse-cdn.com/v4/letter/m/85f322/32.png) [@Manikanta\_Maduri](https://community.deeplearning.ai/u/Manikanta_Maduri)\ **Post date:** [August 4, 2023, 3:58pm UTC](https://community.deeplearning.ai/t/i-am-getting-this-error-in-jupyter-even-though-i-copied-as-it-is-in-the-guidlines/408032/2 "2023-08-04T15:58:54Z")
This is my code: import openai import os from dotenv import load\_dotenv, find\_dotenv \_ = load\_dotenv(find\_dotenv()) openai.api\_key = os.getenv(‘OPENAI\_API\_KEY’) def get\_completion(prompt, model=“gpt-3.5-turbo”): messages = [{“role”: “user”, “content”: prompt}] response = openai.ChatCompletion.create( model=model, messages=messages, temperature=0, # this is the degree of randomness of the model’s output ) return response.choices[0].message[“content”] text = f"“” You should express what you want a model to do by \ providing instructions that are as clear and \ specific as you can possibly make them. \ This will guide the model towards the desired output, \ and reduce the chances of receiving irrelevant \ or incorrect responses. Don’t confuse writing a \ clear prompt with writing a short prompt. \ In many cases, longer prompts provide more clarity \ and context for the model, which can lead to \ more detailed and relevant outputs. “”" prompt = f"“” Summarize the text delimited by triple backticks \ into a single sentence. `{text}` “”" response = get\_completion(prompt) print(response) ---
**Author:** ![klchang](https://avatars.discourse-cdn.com/v4/letter/k/9f8e36/32.png) [@klchang](https://community.deeplearning.ai/u/klchang)\ **Post date:** [August 4, 2023, 11:28pm UTC](https://community.deeplearning.ai/t/i-am-getting-this-error-in-jupyter-even-though-i-copied-as-it-is-in-the-guidlines/408032/3 "2023-08-04T23:28:54Z")
The reason is as follows in your error info: > [@Manikanta\_Maduri](#): > > AuthenticationError: No API key provided. You need set your API key in code.