As I watch the tutorials the code is being typed in what I think is the Jupyter notebook. Is Jupyter, something I should use or load on my PC or is it just for this course tutorial? If I should use it. How/where to I get it?
Hi welcome to the forum! The Jupyter notebooks are built into the course environment, so no need to install Jupyter separately, as you can run all the code you need in the browser. That said, if you wanted to use Jupyter Notebooks locally, here is the official website where you can find the download/install instructions:
Hope that helps!
Thank you for your response. If I understand correctly, then I should be able to run the snippets of code shown using the Jupyter notebook inside the course, “ChatGPT - Prompt Engineering for Developers”, However, ,when I select RUN in the Jupyter notebook for the code the instructor uses in " Tactic 1: Use delimiters to clearly indicate distinct parts of the input" , I get the following response:
“NameError Traceback (most recent call last)
Cell In[3], line 18
1 text = f”“”
2 You should express what you want a model to do by \
3 providing instructions that are as clear and \
(…)
11 more detailed and relevant outputs.
12 “”"
13 prompt = f"“”
14 Summarize the text delimited by triple backticks \
15 into a single sentence.
16 {text}
17 “”"
—> 18 response = get_completion(prompt)
19 print(response)
Cell In[1], line 3, 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,
6 temperature=0, # this is the degree of randomness of the model’s output
7 )
8 return response.choices[0].message[“content”]
NameError: name ‘openai’ is not defined
Hi canclinijg,
Thanks for the question. If you’re running the notebooks online, check to see if you’re first running the first cell which has this line:
import openai
Hope that helps, but let me know if you’re still having issues.
Thank you for your patient assistant. I am a a neophyte to this field. I am using a local instance of Notebooks. I do start with import openai. I also am using the version 1.0.0 get_completion code annotated in the course shown below:
client = openai.OpenAI()
def get_completion(prompt, model="gpt-3.5-turbo"):
messages = [{"role": "user", "content": prompt}]
response = client.chat.completions.create(
model=model,
messages=messages,
temperature=0
)
return response.choices[0].message.content
I run the get_completion code above first with no errors... But then if I try to run the Tactic 1 code from courses Guidelines lesson (shown below), I get long list of errors shown below... It appears it doesn't like the backslash '\' syntax and its not liking one of the files for multiple reasons, and ends by telling me I "have exceeded my quota" Thanks in advance
I Run this
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)
Get these errors
<>:12: SyntaxWarning: invalid escape sequence '\ '
<>:17: SyntaxWarning: invalid escape sequence '\ '
<>:12: SyntaxWarning: invalid escape sequence '\ '
<>:17: SyntaxWarning: invalid escape sequence '\ '
C:\Users\jeffc\AppData\Local\Temp\ipykernel_14476\2496532566.py:12: SyntaxWarning: invalid escape sequence '\ '
"""
C:\Users\jeffc\AppData\Local\Temp\ipykernel_14476\2496532566.py:17: SyntaxWarning: invalid escape sequence '\ '
"""
---------------------------------------------------------------------------
RateLimitError Traceback (most recent call last)
Cell In[9], line 18
1 text = f"""
2 You should express what you want a model to do by \
3 providing instructions that are as clear and \
(...)
11 more detailed and relevant outputs.
12 """
13 prompt = f"""
14 Summarize the text delimited by triple backticks \
15 into a single sentence.
16 ```{text}```
17 """
---> 18 response = get_completion(prompt)
19 print(response)
Cell In[5], line 5, in get_completion(prompt, model)
3 def get_completion(prompt, model="gpt-3.5-turbo"):
4 messages = [{"role": "user", "content": prompt}]
----> 5 response = client.chat.completions.create(
6 model=model,
7 messages=messages,
8 temperature=0
9 )
10 return response.choices[0].message.content
File ~\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\openai\_utils\_utils.py:271, in required_args.<locals>.inner.<locals>.wrapper(*args, **kwargs)
269 msg = f"Missing required argument: {quote(missing[0])}"
270 raise TypeError(msg)
--> 271 return func(*args, **kwargs)
File ~\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\openai\resources\chat\completions.py:648, in Completions.create(self, messages, model, frequency_penalty, function_call, functions, logit_bias, logprobs, max_tokens, n, presence_penalty, response_format, seed, stop, stream, temperature, tool_choice, tools, top_logprobs, top_p, user, extra_headers, extra_query, extra_body, timeout)
599 @required_args(["messages", "model"], ["messages", "model", "stream"])
600 def create(
601 self,
(...)
646 timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
647 ) -> ChatCompletion | Stream[ChatCompletionChunk]:
--> 648 return self._post(
649 "/chat/completions",
650 body=maybe_transform(
651 {
652 "messages": messages,
653 "model": model,
654 "frequency_penalty": frequency_penalty,
655 "function_call": function_call,
656 "functions": functions,
657 "logit_bias": logit_bias,
658 "logprobs": logprobs,
659 "max_tokens": max_tokens,
660 "n": n,
661 "presence_penalty": presence_penalty,
662 "response_format": response_format,
663 "seed": seed,
664 "stop": stop,
665 "stream": stream,
666 "temperature": temperature,
667 "tool_choice": tool_choice,
668 "tools": tools,
669 "top_logprobs": top_logprobs,
670 "top_p": top_p,
671 "user": user,
672 },
673 completion_create_params.CompletionCreateParams,
674 ),
675 options=make_request_options(
676 extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
677 ),
678 cast_to=ChatCompletion,
679 stream=stream or False,
680 stream_cls=Stream[ChatCompletionChunk],
681 )
File ~\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\openai\_base_client.py:1167, in SyncAPIClient.post(self, path, cast_to, body, options, files, stream, stream_cls)
1153 def post(
1154 self,
1155 path: str,
(...)
1162 stream_cls: type[_StreamT] | None = None,
1163 ) -> ResponseT | _StreamT:
1164 opts = FinalRequestOptions.construct(
1165 method="post", url=path, json_data=body, files=to_httpx_files(files), **options
1166 )
-> 1167 return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
File ~\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\openai\_base_client.py:856, in SyncAPIClient.request(self, cast_to, options, remaining_retries, stream, stream_cls)
847 def request(
848 self,
849 cast_to: Type[ResponseT],
(...)
854 stream_cls: type[_StreamT] | None = None,
855 ) -> ResponseT | _StreamT:
--> 856 return self._request(
857 cast_to=cast_to,
858 options=options,
859 stream=stream,
860 stream_cls=stream_cls,
861 remaining_retries=remaining_retries,
862 )
File ~\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\openai\_base_client.py:932, in SyncAPIClient._request(self, cast_to, options, remaining_retries, stream, stream_cls)
930 if retries > 0 and self._should_retry(err.response):
931 err.response.close()
--> 932 return self._retry_request(
933 options,
934 cast_to,
935 retries,
936 err.response.headers,
937 stream=stream,
938 stream_cls=stream_cls,
939 )
941 # If the response is streamed then we need to explicitly read the response
942 # to completion before attempting to access the response text.
943 if not err.response.is_closed:
File ~\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\openai\_base_client.py:980, in SyncAPIClient._retry_request(self, options, cast_to, remaining_retries, response_headers, stream, stream_cls)
976 # In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a
977 # different thread if necessary.
978 time.sleep(timeout)
--> 980 return self._request(
981 options=options,
982 cast_to=cast_to,
983 remaining_retries=remaining,
984 stream=stream,
985 stream_cls=stream_cls,
986 )
File ~\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\openai\_base_client.py:932, in SyncAPIClient._request(self, cast_to, options, remaining_retries, stream, stream_cls)
930 if retries > 0 and self._should_retry(err.response):
931 err.response.close()
--> 932 return self._retry_request(
933 options,
934 cast_to,
935 retries,
936 err.response.headers,
937 stream=stream,
938 stream_cls=stream_cls,
939 )
941 # If the response is streamed then we need to explicitly read the response
942 # to completion before attempting to access the response text.
943 if not err.response.is_closed:
File ~\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\openai\_base_client.py:980, in SyncAPIClient._retry_request(self, options, cast_to, remaining_retries, response_headers, stream, stream_cls)
976 # In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a
977 # different thread if necessary.
978 time.sleep(timeout)
--> 980 return self._request(
981 options=options,
982 cast_to=cast_to,
983 remaining_retries=remaining,
984 stream=stream,
985 stream_cls=stream_cls,
986 )
File ~\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\openai\_base_client.py:947, in SyncAPIClient._request(self, cast_to, options, remaining_retries, stream, stream_cls)
944 err.response.read()
946 log.debug("Re-raising status error")
--> 947 raise self._make_status_error_from_response(err.response) from None
949 return self._process_response(
950 cast_to=cast_to,
951 options=options,
(...)
954 stream_cls=stream_cls,
955 )
RateLimitError: Error code: 429 - {'error': {'message': 'You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.', 'type': 'insufficient_quota', 'param': None, 'code': 'insufficient_quota'}}
Hello @canclinijg , assuming that you have your own OpenAI account so that you can run the notebooks locally, it appears that you’re hitting your limit of calls to OpenAI.
I went back to my local setup for this course and realized that I’m getting the same error about ‘quota,’ so I’m researching on the OpenAI site (API section), specifically these two pages:
If I figure out my issue and think that it can shed light for you and others, I’ll post back here. Good luck to you.
Update: My problem did indeed turn out to be $. I’ve evidently been using up all the ‘free’ allotments over the past few months. Adding $10 today cleared up the issue.
Thanks for running that down. I’ll add some $ and hopefully it will work
I added $ and tried again and it code ran! But only after deleting 2 lines of the code copied from the course (see below). And I still received a syntax warning.
For a full understanding would appreciate your help understanding why to these 2 questions. Thanks again.
Question 1 Why did I need to delete the 2 lines for dotenv module to get code snippet below to run? (otherwise I received a ModuleNotFoundError )
import openai
import os
from dotenv import load_dotenv, find_dotenv
_ = load_dotenv(find_dotenv())
openai.api_key = os.getenv(‘OPENAI_API_KEY’)
Error below
ModuleNotFoundError Traceback (most recent call last)
Cell In[6], line 4
1 import openai
2 import os
----> 4 from dotenv import load_dotenv, find_dotenv
5 _ = load_dotenv(find_dotenv())
7 openai.api_key = os.getenv(‘OPENAI_API_KEY’)
ModuleNotFoundError: No module named ‘dotenv’
Question 2 - I successfully ran the prompt below from the course, but it gave me a syntax warning below
Course prompt
prompt = f"“”
Generate a list of three made-up book titles along \
with their authors and genres.
Provide them in JSON format with the following keys:
book_id, title, author, genre.
“”"
response = get_completion(prompt)
print(response)
GPT response
{
“book_id”: 1,
“title”: “The Midnight Garden”,
“author”: “Elena Rivers”,
“genre”: “Fantasy”
},
{
“book_id”: 2,
“title”: “Echoes of the Past”,
“author”: “Nathan Black”,
“genre”: “Mystery”
},
{
“book_id”: 3,
“title”: “Whispers in the Wind”,
“author”: “Samantha Reed”,
“genre”: “Romance”
}
]
<>:6: SyntaxWarning: invalid escape sequence '\ ’
<>:6: SyntaxWarning: invalid escape sequence '\ ’
C:\Users\jeffc\AppData\Local\Temp\ipykernel_12380\1713482535.py:6: SyntaxWarning: invalid escape sequence '\ ’
“”"
Sorry, but your questions are beyond my knowledge. I don’t see that particular prompt in this course’s [“ChatGPT Prompt Engineering”] notebooks. Which lesson in the series is this notebook based on?
The syntax warning message might be easily gotten rid of by simply deleting the backslash () from the end of this line:
Generate a list of three made-up book titles along \
But that’s only a guess.
1 Like
Yes all the code I showed above was copied from the “Iterative” lesson examples. Yes this issue is trying to run the code locally outside the course. It runs fine inside the courses jupyter notebook.
Getting rid of the \ eliminated the syntax error! Thanks. The module must be something specific to the course structure
I learned, “Python-dotenv reads key-value pairs from a .env file and can set them as environment variables. It helps in the development of applications following the 12-factor principles.” Guess I didn’t need to do that since I added my API key to my environmental variables per the courses into instructions.
1 Like
Oh, yes, of course… adding API keys to environment is best. Glad you got it sorted. 
How do you call you api key if it is locally stored on your text file from the same directory with the .ipynb file?