Skip to content

ai-database add embedding and vector search capabilities #146

Description

@nathanclevenger

https://ai-sdk.dev/docs/reference/ai-sdk-core/embed-many
https://ai-sdk.dev/docs/reference/ai-sdk-core/embed
https://docs.turso.tech/sdk/ts/orm/drizzle#vector-embeddings

We'll need to create a workflow that is triggered whenever Things are created or updated to create embeddings. (let's use OpenAI embed-3-large with 256 dimensions

We'll also probably need to create a embeddedAt field to track the updated at timestamp … and maybe a hash to see if the data has changed … we also only want to create a new job for the workflow if there isn't one running already… we'll need to figure out the right/best batch size … as well as how to perform search

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Fields

    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions