# Get\_llm\_response( ) function **URL:** \ **Category:** AI Python for Beginners\ **Tags:** week-module-3\ **Created:** [January 7, 2025, 3:27pm UTC](https://community.deeplearning.ai/t/get-llm-response-function/747802 "2025-01-07T15:27:55Z")\ **Posts on this page:** 3\ **Page:** 1
**Author:** ![hayou](https://avatars.discourse-cdn.com/v4/letter/h/e0b2c6/32.png) [@hayou](https://community.deeplearning.ai/u/hayou)\ **Post date:** [January 7, 2025, 3:27pm UTC](https://community.deeplearning.ai/t/get-llm-response-function/747802/1 "2025-01-07T15:27:55Z")
Whenever I try to run the code get\_llm\_response( prompt), I start noticing this error at the end of module 2 and the debut of module 3: \*\*--------------------------------------------------------------------------- PermissionDeniedError Traceback (most recent call last) Cell In[2], line 11 5 prompt = f"“” 6 Create a short recipe that uses the following ingredients: 7 {ingredients} 8 “”" 10 # Get the response from the LLM —\> 11 response = get\_llm\_response(prompt) 13 # Print the LLM response 14 print(response) File ~/work/L1/helper\_functions.py:66, in get\_llm\_response(prompt) 61 def get\_llm\_response(prompt): 62 “”“This function takes as input a prompt, which must be a string enclosed in quotation marks, 63 and passes it to OpenAI’s GPT3.5 model. The function then saves the response of the model as 64 a string. 65 “”” —\> 66 completion = client.chat.completions.create( 67 model=“gpt-4o-mini”, 68 messages=[ 69 { 70 “role”: “system”, 71 “content”: “You are a helpful but terse AI assistant who gets straight to the point.”, 72 }, 73 {“role”: “user”, “content”: prompt}, 74 ], 75 temperature=0.0, 76 ) 77 response = completion.choices[0].message.content 78 return response File /usr/local/lib/python3.9/site-packages/openai/\_utils/\_utils.py:277, in required\_args..inner..wrapper(\*args, \*\*kwargs) 275 msg = f"Missing required argument: {quote(missing[0])}" 276 raise TypeError(msg) → 277 return func(\*args, \*\*kwargs) File /usr/local/lib/python3.9/site-packages/openai/resources/chat/completions.py:590, in Completions.create(self, messages, model, frequency\_penalty, function\_call, functions, logit\_bias, logprobs, max\_tokens, n, presence\_penalty, response\_format, seed, stop, stream, stream\_options, temperature, tool\_choice, tools, top\_logprobs, top\_p, user, extra\_headers, extra\_query, extra\_body, timeout) 558 @required\_args([“messages”, “model”], [“messages”, “model”, “stream”]) 559 def create( 560 self, (…) 588 timeout: float | httpx.Timeout | None | NotGiven = NOT\_GIVEN, 589 ) → ChatCompletion | Stream[ChatCompletionChunk]: → 590 return self.\_post( 591 “/chat/completions”, 592 body=maybe\_transform( 593 { 594 “messages”: messages, 595 “model”: model, 596 “frequency\_penalty”: frequency\_penalty, 597 “function\_call”: function\_call, 598 “functions”: functions, 599 “logit\_bias”: logit\_bias, 600 “logprobs”: logprobs, 601 “max\_tokens”: max\_tokens, 602 “n”: n, 603 “presence\_penalty”: presence\_penalty, 604 “response\_format”: response\_format, 605 “seed”: seed, 606 “stop”: stop, 607 “stream”: stream, 608 “stream\_options”: stream\_options, 609 “temperature”: temperature, 610 “tool\_choice”: tool\_choice, 611 “tools”: tools, 612 “top\_logprobs”: top\_logprobs, 613 “top\_p”: top\_p, 614 “user”: user, 615 }, 616 completion\_create\_params.CompletionCreateParams, 617 ), 618 options=make\_request\_options( 619 extra\_headers=extra\_headers, extra\_query=extra\_query, extra\_body=extra\_body, timeout=timeout 620 ), 621 cast\_to=ChatCompletion, 622 stream=stream or False, 623 stream\_cls=Stream[ChatCompletionChunk], 624 ) File /usr/local/lib/python3.9/site-packages/openai/\_base\_client.py:1240, in SyncAPIClient.post(self, path, cast\_to, body, options, files, stream, stream\_cls) 1226 def post( 1227 self, 1228 path: str, (…) 1235 stream\_cls: type[\_StreamT] | None = None, 1236 ) → ResponseT | \_StreamT: 1237 opts = FinalRequestOptions.construct( 1238 method=“post”, url=path, json\_data=body, files=to\_httpx\_files(files), \*\*options 1239 ) → 1240 return cast(ResponseT, self.request(cast\_to, opts, stream=stream, stream\_cls=stream\_cls)) File /usr/local/lib/python3.9/site-packages/openai/\_base\_client.py:921, in SyncAPIClient.request(self, cast\_to, options, remaining\_retries, stream, stream\_cls) 912 def request( 913 self, 914 cast\_to: Type[ResponseT], (…) 919 stream\_cls: type[\_StreamT] | None = None, 920 ) → ResponseT | \_StreamT: → 921 return self.\_request( 922 cast\_to=cast\_to, 923 options=options, 924 stream=stream, 925 stream\_cls=stream\_cls, 926 remaining\_retries=remaining\_retries, 927 ) File /usr/local/lib/python3.9/site-packages/openai/\_base\_client.py:1020, in SyncAPIClient.\_request(self, cast\_to, options, remaining\_retries, stream, stream\_cls) 1017 err.response.read() 1019 log.debug(“Re-raising status error”) → 1020 raise self.\_make\_status\_error\_from\_response(err.response) from None 1022 return self.\_process\_response( 1023 cast\_to=cast\_to, 1024 options=options, (…) 1027 stream\_cls=stream\_cls, 1028 ) PermissionDeniedError: Error code: 403 - {‘error’: {‘message’: ‘Project proj\_OXEC08aO6rKYJweAEj6Aae5D does not have access to model gpt-4o-mini’, ‘type’: ‘invalid\_request\_error’, ‘param’: None, ‘code’: ‘model\_not\_found’}}\*\* ---
**Author:** ![Mubsi](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/mubsi/32/94983_2.png) [@Mubsi](https://community.deeplearning.ai/u/Mubsi)\ **Post date:** [January 7, 2025, 4:00pm UTC](https://community.deeplearning.ai/t/get-llm-response-function/747802/2 "2025-01-07T16:00:26Z")
Hi @hayou, We have recently been aware of this issue. Please follow this [thread](https://community.deeplearning.ai/t/cannot-use-chat-or-run-any-exercise-that-involves-print-get-llm-response/747776/6) for an update on this. Thanks, Mubsi ---
**Author:** ![Mubsi](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/mubsi/32/94983_2.png) [@Mubsi](https://community.deeplearning.ai/u/Mubsi)\ **Post date:** [January 9, 2025, 4:28pm UTC](https://community.deeplearning.ai/t/get-llm-response-function/747802/3 "2025-01-09T16:28:19Z")