Overview
Together AI provides access to Llama 2 and Llama 3 models including instruction-tuned models through their inference API. These models are multilingual and text-only, making them suitable for a variety of agent applications.
Usage
Install the OpenAI plugin to add Together AI support:
pip install "livekit-agents[openai]~=1.2"
pnpm add@livekit/agents-plugin-openai@1.x
Set the following environment variable in your .env file:
TOGETHER_API_KEY=<your-together-api-key>
Create a Together AI LLM using the with_together method:
from livekit.plugins import openaisession = AgentSession(llm=openai.LLM.with_together(model="meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",),# ... tts, stt, vad, turn_detection, etc.)
import * as openai from '@livekit/agents-plugin-openai';const session = new voice.AgentSession(llm: new openai.LLM.withTogether(model: "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",),// ... tts, stt, vad, turn_detection, etc.);
Parameters
This section describes some of the available parameters. For a complete reference of all available parameters, see the plugin reference links in the Additional resources section.
Model to use for inference. To learn more, see supported models.
Controls the randomness of the model's output. Higher values, for example 0.8, make the output more random, while lower values, for example 0.2, make it more focused and deterministic.
Valid values are between 0 and 1.
Controls whether the model can make multiple tool calls in parallel. When enabled, the model can make multiple tool calls simultaneously, which can improve performance for complex tasks.
Controls how the model uses tools. Set to 'auto' to let the model decide, 'required' to force tool usage, or 'none' to disable tool usage.
Additional resources
The following links provide more information about the Together AI LLM integration.
