You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The Azure OpenAI vectorizer lacks the dimension parameter (configure-the-vectorizer), which allows the use of custom dimensions for the embeddings it generates.
This feature seems to have already been implemented in Weaviate: weaviate/weaviate#5987.
The text was updated successfully, but these errors were encountered:
Same problem here. We're migrating embeddings with dimension 3072 from pgvector and getting error – distance between entrypoint and query node: 3072 vs 1536: vector lengths don\'t match.
Model: text-embedding-3-large
The Azure OpenAI vectorizer lacks the dimension parameter (configure-the-vectorizer), which allows the use of custom dimensions for the embeddings it generates.
This feature seems to have already been implemented in Weaviate: weaviate/weaviate#5987.
The text was updated successfully, but these errors were encountered: