class Memo::Providers::Bus

• Memo::Providers::Bus
• Reference
• Object

Overview

Bus-based embedding provider.

Routes embedding requests through the Arcana bus to a remote embedding service (e.g. openai:embed, voyage:embed).

Requires an Arcana::Client to be available — typically set once at process startup via Memo::Providers::Bus.client = ....

Bus responses don't include per-text token counts, only total_tokens. We distribute the total evenly across texts (same approach as Memo::Providers::OpenAI when the API doesn't itemize).

Included Modules

• Memo::Providers::Base

Defined in:

memo/providers/bus.cr

Constant Summary

DEFAULT_TIMEOUT = 60.seconds

Constructors

• .new(target : String, model : String = "", from_address : String = "memo:rag", timeout : Time::Span = DEFAULT_TIMEOUT)

Class Method Summary

• .client : ::Arcana::Client | Nil

  Process-wide Arcana::Client used by all Bus providers.

• .client=(client : ::Arcana::Client | Nil)

  Process-wide Arcana::Client used by all Bus providers.

Instance Method Summary

• #embed_text(text : String, input_type : String | Nil = nil) : Tuple(Array(Float64), Int32)

  Embed a single text

• #embed_texts(texts : Array(String), input_type : String | Nil = nil) : EmbedResult

  Embed multiple texts in a batch

• #from_address : String
• #model : String
• #target : String

Constructor Detail

Class Method Detail

Instance Method Detail