OpenAI

When using Google Gemini models, llm-exe will make POST requests to https://generativelanguage.googleapis.com/v1beta/models/{model}:generateContent. All models are supported if you pass google.chat.v1 as the first argument, and then specify a model in the options.

Basic Usage

Google Gemini Chat

const llm = useLlm("google.chat.v1", {
  model: "gemini-2.0-flash", // specify a model
});

Google Gemini Chat By Model

const llm = useLlm("google.gemini-2.0-flash", {
  // other options,
  // no model needed, using gemini-2.0-flash
});

INFO

You can use the following models using this shorthand:

google.gemini-2.0-flash
google.gemini-2.0-flash-lite
google.gemini-1.5-pro

Authentication

To authenticate, you need to provide an OpenAi API Key. You can provide the API key various ways, depending on your use case.

Pass in as execute options using geminiApiKey
Pass in as setup options using geminiApiKey
Use a default key by setting an environment variable of GEMINI_API_KEY

Generally you pass the LLM instance off to an LLM Executor and call that. However, it is possible to interact with the LLM object directly, if you wanted.

// given array of chat messages, calls chat completion
await llm.chat([]);

// given string prompt, calls completion
await llm.completion("");

Gemini-Specific Options

In addition to the generic options, the following options are OpenAi-specific and can be passed in when creating a llm function.

Option	Type	Default	Description
model	string	gemini-2.0-flash	The model to use. Can be any valid chat model. See OpenAI Docs
geminiApiKey	string	undefined	API key for Google. See authentication
temperature	number	undefined	Maps to temperature.*
maxTokens	number	undefined	Maps to max_tokens. See OpenAI Docs
topP	number	undefined	Maps to top_p. See OpenAI Docs

* OpenAI Docs: link

OpenAI ​

Basic Usage ​

Google Gemini Chat ​

Google Gemini Chat By Model ​