Integration with the Rhea Generation Framework

Part of the Rhea Generative Suite and optional project with rich integrations in to Luna WMS.

The Rhea: Latent Loom project is Oddineers Ltd. locally deployable LLM (AI) service that can run standalone or integrate deeply with the broader Rhea Generative Framework. Built on an OpenAPI specification, it mimics cloud infrastructure but operates locally entirely within your own perimeter.

Designed to be a drop-in replacement to swap out common cloud providers using standardised endpoints. It is compatible with standard Chat Completion and Responses object types.

Luna WMS Integration

Looking for the Rest API schema?

• Rhea Generative Framework - Rest API Schema
  
• Rhea Latent Loom - Rest API Schema

Overview

Luna's use of Rhea operates as follows:

graph TD
  %% System 1: Luna
  subgraph Luna_Env [Luna WMS Environment]
    A[Luna Core App]
    B[Trigger Event / Webhook]
    A --> B
  end

  %% System 2: Latent Loom
  subgraph Loom_Env [Latent Loom Environment]
    C[Rhea Generative Framework]

    subgraph Loom_Core [Latent Loom Dual Engine]
      D1[Embedding Engine]
      D2[Inference Generator]
    end

    C <--> D1
    C <--> D2
  end

  %% System 3: Vector DB
  subgraph Vector_Env [Vector Infrastructure]
    E[(Vector Database)]
  end

  %% The Inter-API Data Flow
  B -->|1. HTTP Request<br>Prompts / Text / Context| C

  %% Vector Path
  D1 -->|2a. Generate Embeddings<br>Vector Matrix| E
  E -->|3a. Return Vector Matches / Index Status| D1

  %% Inference Path (using context if needed)
  D2 -.->|2b. Read Context / Matches| D1

  C -->|4. JSON Response Payload<br>Generated Text + Vectors| A