Updated multimodal vector search use case

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.

Apache License 2.0

4.55k stars 445 forks source link

Checklist

[ ] Is this code covered by new or existing unit tests or integration tests?

[ ] Did you run make unit_testing and make integration-testing successfully?

[ ] Do new classes, functions, methods and parameters all have docstrings?

[ ] Were existing docstrings updated, if necessary?

[ ] Was external documentation updated, if necessary?

AutoSchema ignores the table schema for MongoDB.
After removing the default values for the encoder and decoder in the Datatype, compatibility is not maintained.
When Ibis databackend saves an Artifact/File, it removes the _leaves/_blobs/_files information, making it impossible to restore during reading because the corresponding information cannot be found in _leaves.
When creating a table in Ibis, for Encodable datatypes using Artifact/File, it sets the attribute to bytes. This causes an issue during data insertion because, after encoding, the actual values for these data types are ?artifact/xxx or ?file/xxx.
During data decoding, the decode process is incorrect. It should first restore the leaf (Artifact/File) and then proceed with the schema decoding.

SuperDuperDB / superduperdb

Updated multimodal vector search use case #2121

Description

2074

Related Issues

Checklist

Additional Notes or Comments