Skip to main content

Platform

RAG

Status: Planned

Retrieval-augmented generation: answers drawn from your own documents, not only from what a model was trained on. Planned; nothing is built yet.

What it is

RAG finds the passages of your documents that match a question and gives them to the model with the question, so the answer can rest on what you hold.

Where it stands today

Planned. It needs a model to answer and a place to keep your documents, and neither is available on the platform yet.

What comes next

In order, without dates: a date is published only once it is certain.

  1. Serving models through the inference API.
  2. Keeping your documents on the platform, under your account’s access controls.
  3. Then retrieval over them, with its status updated on this page.

Build with CloudFARM

Developer accounts open from the waitlist once capacity is connected. Until then, tell us what you want to build.