Announcing the Rhea: Latent Loom project a locally hosted LLM services that can be ran independently or with the Rhea Generative Framework. This post introduces the Rhea: Latent Loom API specification in OpenAPI (3.0.1) format. A Swagger UI Bundle is used to explore the API.
Please note that no active endpoints are provided; if you would like to test this further with a active/real deployment please get in touch with us.
The Swagger UI Bundle is configured to enable the server endpoint url to be defined as a URI parameter: `<host>/?server=https://oddineers.co.uk` .
View the documentation here: Rhea: Latent Loom API Explorer – GitLab Pages
Links
Learn more about the Rhea Generative Framework.
Purpose
This project is intended to allow users to take back control of their data and host LLM’s locally on their own hardware. It’s focused on Google’s Gemma model supporting Gemma 3 and RAG based knowledge inference. RAG support allows users to build vector databases from their own fata/knowledge and use said data to with queries from the AI model.
Responses from the LLM can be fine-tuned and used to either; improve model output and queried against in the future or reused in model training.
More to come soon!
