Type Object Error in Tutorial Example

[CoreyRN]

Hello,

I've been following the example provided at: https://github.com/openai/openai-cookbook/blob/main/examples/Question_answering_using_embeddings.ipynb

Unfortunately when I get to In [6] I continually obtain the following error in the code:

TypeError Traceback (most recent call last)
in
----> 1 def get_embedding(text: str, model: str=EMBEDDING_MODEL) -> list[float]:
2 result = openai.Embedding.create(
3 model=model,
4 input=text
5 )

TypeError: 'type' object is not subscriptable

Any recommendations on how to fix this would be much appreciated, as I can't seem to find an answer on Stack Overflow.

Thanks so much for your help!

[ted-at-openai]

I'll take a look to see if I can reproduce. I just pushed an update, so it could be something I just introduced.

[ted-at-openai]

Verified that the code works for me. Which version of Python are you using?

[ted-at-openai]

Might be that list[float] is not understood by a version of Python that's 3.7 or below.

One option is to delete the type hints.

Another option, depending on your version of Python, is to import the types. E.g., from typing import Float, List and then use those.

[CoreyRN]

Thank you so much for your responses! It's so strange that it is working for you and not me as I tried following the tutorial line by line. I am using python version 3.8.16. I tried both your recommendations but still no luck as I receive the same error.

When I tried importing the types as you recommended I received the Import Error: cannot import name 'Float' from 'typing' (/usr/lib/python3.8/typing.py).

I have attached an image of my google colab screen demonstrating the error. Any further help would be of much assistance!

Thank you!

[ted-at-openai]

Thanks for the screenshot and apologies for my insufficient advice. Two amendments:

• Turns out my memory was a bit off - built-in types were introduced in Python 3.9, not Python 3.8. So makes sense that Python 3.8 would throw this error.
• List can be imported from typing, but not Float

So in Python 3.8, I think the following should work:

from typing import List

def get_embedding(text: str, model: str=EMBEDDING_MODEL) -> List[float]:

And if it doesn't, try removing the type hints altogether, like:

def get_embedding(text: str, model: str=EMBEDDING_MODEL):

[mac4281]

@ted-at-openai Thanks for your input here. I'm having the exact same issues with the same example. I just attempted your fix to no avail. Still getting:

TypeError: 'type' object is not subscriptable

Any more thoughts?

[CoreyRN]

Thanks so much Ted! With a little ChatGPT assistance I was able to incorporate your responses. So I changed it to:

from typing import List, Tuple, Set, Dict
def get_embedding(text: str, model: str=EMBEDDING_MODEL) -> List[float]:

I also had to change all the other sections such as:

def compute_doc_embeddings(df: pd.DataFrame) -> Dict[Tuple[str, str], List[float]]:

Seems to be working now though! Much appreciated!