Getting an OpenAI API Key:
- Visit the OpenAI website at https://platform.openai.com/account/api-keys.
- If you don’t have an account, click on “Sign Up” to create one. If you do, click “Log In”.
- Once logged in, navigate to your API key management page.
- Click on “Create new secret key”.
- Enter a name for your new key, then click “Create secret key”.
- Your new API key will be displayed. Use this key to interact with the OpenAI API.
Note: Your API key is sensitive information. Do not share it with anyone.
Frequently Asked Questions
Why don’t we get the same answer when specifying a temperature field of 0 and asking the same question?
Even when specifying a temperature field of 0, it doesn’t guarantee that you’ll always get the same response. Several factors come into play.
- Go OpenAI Behavior: When you specify a temperature field of 0 in Go OpenAI, the omitempty tag causes that field to be removed from the request. Consequently, the OpenAI API applies the default value of 1.
- Token Count for Input/Output: If there’s a large number of tokens in the input and output, setting the temperature to 0 can still result in non-deterministic behavior. In particular, when using around 32k tokens, the likelihood of non-deterministic behavior becomes highest even with a temperature of 0.
Due to the factors mentioned above, different answers may be returned even for the same question.
Workarounds:
- As of November 2023, use the new
seed
parameter in conjunction with thesystem_fingerprint
response field, alongside Temperature management. - Try using
math.SmallestNonzeroFloat32
: By specifyingmath.SmallestNonzeroFloat32
in the temperature field instead of 0, you can mimic the behavior of setting it to 0. - Limiting Token Count: By limiting the number of tokens in the input and output and especially avoiding large requests close to 32k tokens, you can reduce the risk of non-deterministic behavior.
By adopting these strategies, you can expect more consistent results.
Related Issues:
omitempty option of request struct will generate incorrect request when parameter is 0.
Does Go OpenAI provide a method to count tokens?
No, Go OpenAI does not offer a feature to count tokens, and there are no plans to provide such a feature in the future. However, if there’s a way to implement a token counting feature with zero dependencies, it might be possible to merge that feature into Go OpenAI. Otherwise, it would be more appropriate to implement it in a dedicated library or repository.
For counting tokens, you might find the following links helpful:
Related Issues:
Is it possible to join the implementation of GPT3 Tokenizer
Thank you
We want to take a moment to express our deepest gratitude to the contributors and sponsors of this project:
To all of you: thank you. You’ve helped us achieve more than we ever imagined possible. Can’t wait to see where we go next, together!