Replies: 1 comment 1 reply
-
I guess, you need embeddings for subsets. |
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hi,
I am trying to perform a search.
The initial data is in text form. An example of the data is
I generate embeddings for the above using
SentenceTransformer('bert-base-nli-mean-tokens')
Then I instantiate a
faiss.IndexFlatL2
and try a run the following queriesThe permutations of the full
interests
set result in the correctJohn Philip
being returned.However, the subsets do not.
What is the recommended way to perform this search ? Should I first produce the embeddings for subsets as well ?
Thanks
Beta Was this translation helpful? Give feedback.
All reactions