New release: 0.3.2 for Rhea: Latent Loom – self hosted LLM service

Rhea Embeddable Client
descriptionStandard

This update 0.3.2 introduces support for Text formats/Response formats support PyDantic JSON model schemas:

  • Refinements to endpoint: /v1/responses
    • Adds parameters for test_format (Response formats) supporting PyDantic model JSON schemas.
    • Adds response parameter: output_parsed.
  • Refinements to default parameters on endpoint: /v1/chat/completions
  • Additional schema models.
Continue reading

Unweaving the cloud: Local LLMs and Private RAG with Rhea: Latent Loom

Rhea: Latent Loom part of the Rhea Generative Framework
descriptionStandard

Data privacy and mounting cloud costs are driving a shift toward localised AI. Enterprises want the power of Large Language Models (LLMs), but they cannot afford to send sensitive files over public networks.

Here’s where the Rhea: Latent Loom project comes in to play, a self-hosted LLM service designed to keep your data local, secure, and instantly searchable.

Continue reading