Replies: 1 comment
-
@aza1200 No OpenAI embeddings are fixed in their dimensions. They are designed to be general purpose, but you might find more specific open source embedding models better for your use-case depending on what you are embedding. Rather than experiment on embedding dimensions, experiment on different embedding models that LangChain supports. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
I'm using langchain's embedding providing library
I want to test at which embedding dimension is best for my program.
while Increasing and decreasing the number of embedding dimensions,
Is there a way to experiment with which dimension perform best while experimenting?
Beta Was this translation helpful? Give feedback.
All reactions