Embedding Vectors

This operation allows you to pass in text directly for inserting and searching vectors. The text is automatically embedded with an embedding model of your choice (can be defined in your config.hx.json file). The default embedding model is text-embedding-ada-002 from OpenAI. Make sure to set your OPENAI_API_KEY environment variable with your api key as well.

Embed

Embeds the input text and returns a vector

Embed(text)
AddV<Type>(Embed(text))

Example:

In schema.hx:

V::Document {
    content: String,
    created_at: I64
}

In query.hx:

QUERY InsertText(content: String, created_at: I64) =>
    // Create an empty user node
    basic_user <- AddV<Document>(Embed(content))
    // You could also write it like this with properties
    AddV<Document>(Embed(content), { content: content, created_at: created_at })
    RETURN basic_user

You can also use the Embed function in a search query:

QUERY SearchText(query: String, limit: I64) =>
    // Search for documents that are similar to the query
    results <- SearchV<Document>(Embed(query), limit)
    RETURN results