-
Notifications
You must be signed in to change notification settings - Fork 3.2k
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
Python: Weaviate vector store #9101
base: main
Are you sure you want to change the base?
Python: Weaviate vector store #9101
Conversation
for vector in data_model_definition.fields.values(): | ||
if isinstance(vector, VectorStoreRecordVectorField): | ||
named_vectors.append( | ||
Configure.NamedVectors.none( | ||
name=vector.name, | ||
vector_index_config=to_weaviate_vector_index_config(vector), | ||
) | ||
) |
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.
Should we return named_vectors
collection from this method after we populate it with vector-related info? Based on the usage of this method vectorizer_config=data_model_definition_to_weaviate_named_vectors(self.data_model_definition)
it looks like it should return something, but it doesn't have a return
statement.
case DistanceFunction.COSINE: | ||
return "cosine" | ||
case DistanceFunction.DOT_PROD: | ||
return "dot" | ||
case DistanceFunction.EUCLIDEAN: | ||
return "l2-squared" | ||
case DistanceFunction.MANHATTAN: | ||
return "manhattan" |
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.
There is also hamming
distance function: https://weaviate.io/developers/weaviate/config-refs/distances#available-distance-metrics
Motivation and Context
Add Weaviate DB to Semantic Kernel with the new vector store and vector collection interfaces.
Address: #6553
Description
Contribution Checklist