Torus.Embeddings.Gemini (Torus v0.5.2)

Generates dense vector embeddings through the Gemini API.

How to use

1. Select the embedding backend

   # config.exs
   config :torus, embedding_module: Torus.Embeddings.Gemini

2. Add req to your dependencies

   def deps do
     [
       {:req, "~> 0.5"}
     ]
   end

3. Put your Gemini API token in runtime config

   # runtime.exs
   config :torus, Torus.Embeddings.Gemini,
     token: System.get_env("GEMINI_API_KEY"),
     # optional – defaults to "text-embedding-004"
     model: "gemini-embedding-exp-03-07"

By default, it uses text-embedding-004 model, but you can specify a different model by explicitly passing model to the config:

config :torus, Torus.Embeddings.Gemini, model: "your/model"

See Torus.semantic/5 on how to use this module to introduce semantic search in your application.