Use embeddings and large language models on the edge with Supabase Edge Functions.| Supabase
Use Adaptive Retrieval to improve query performance with OpenAI's new embedding models| Supabase
pgvector 0.6.0 brings a significant improvement: parallel index builds for HNSW. Building an HNSW index is now up to 30x faster for unlogged tables.| Supabase
Direct performance comparison between pgvector and Pinecone.| Supabase
Increase performance in pgvector using HNSW indexes| Supabase
We've added support Hugging Face support in our Python Vector Client and Edge Functions.| Supabase