-
Notifications
You must be signed in to change notification settings - Fork 11
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add OpenAI Embeddings Primitive #251
base: main
Are you sure you want to change the base?
Conversation
Adds a primitive for natural language logical types that uses the OpenAI Embeddings API to calculate embeddings features. The model to use is configurable, but text-embedding-ada-002 is used by default.
|
||
def can_fit_in_batch(tokens) -> bool: | ||
return ( | ||
len(elements_in_batch) < 2048 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Is 2048 the maximum number of elements per batch?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
yeah, here's the limit in the openai client: https://github.com/openai/openai-python/blob/main/openai/embeddings_utils.py#L43
|
||
# can this element fit in the batch? | ||
if can_fit_in_batch(next_tokens): | ||
# can't fit -- construct a request with existing elements |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Not sure if I am misunderstanding this, but does this block cover the case where it can fit?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Good call. Fixed. I need to add tests for all of this to catch stuff like this 😅
Co-authored-by: Shripad Badithe <[email protected]>
Adds a primitive for natural language logical types that uses the OpenAI Embeddings API to calculate embeddings features.
The model to use is configurable, but
text-embedding-ada-002
is used by default.