SuperDuperDB / superduperdb

🔮 SuperDuperDB: Bring AI to your database! Build, deploy and manage any AI application directly with your existing data infrastructure, without moving your data. Including streaming inference, scalable model training and vector search.
https://superduperdb.com
Apache License 2.0
4.55k stars 445 forks source link

Optimization of Vector Search Interfaces #2105

Open jieguangzhou opened 1 month ago

jieguangzhou commented 1 month ago

In our vector search interface, we currently call

like({indexing_key: x}, vector_index=vector_index_name).

Should we consider removing the indexing_key in future iterations?

like({x, vector_index=vector_index_name).

This field corresponds to vector_index.listener.key, which means we are passing redundant information when calling the interface.