View Source Rag.Generation.Nx (rag v0.1.0)

Functions to generate responses using Nx.Serving.batched_run/2.

Summary

Functions

Passes prompt from generation to serving to generate a response. Then, puts response in generation.

Functions

generate_response(generation, serving \\ Rag.LLMServing)

@spec generate_response(Rag.Generation.t(), Nx.Serving.t()) :: Rag.Generation.t()

Passes prompt from generation to serving to generate a response. Then, puts response in generation.