LLM Support

Use various LLMs to handle your agents and tasks.

Overview The BeaconLabs framework allows you to use .env variable files or environment variables for LLM support. Once you provide the necessary keys for various services, you can easily select the LLM by using the model parameter within the agents.

The supported LLMs are:

• OpenAI

  • openai/gpt-4o

  • openai/o3-mini

• Azure

  • azure/gpt-4o

• Anthropic

  • claude/claude-3-5-sonnet

• AWS Bedrock

  • bedrock/claude-3-5-sonnet

• DeepSeek

  • deepseek/deepseek-chat

Setting up .env To use these LLMs, the example .env variable file is shown below. You can adjust the variables according to the LLM you want to use and fill in only the required ones. This .env file must be located in your working directory.

dotenvCopyEdit# OpenAI
OPENAI_API_KEY="sk-***"

# Anthropic
ANTHROPIC_API_KEY="sk-***"

# DeepSeek
DEEPSEEK_API_KEY="sk-**"

# AWS Bedrock
AWS_ACCESS_KEY_ID="**"
AWS_SECRET_ACCESS_KEY="***"
AWS_REGION="**-**"

# Azure
AZURE_OPENAI_ENDPOINT="https://**.com/"
AZURE_OPENAI_API_VERSION="****-**-**"
AZURE_OPENAI_API_KEY="***"

Using a Specific Model in Agent Using the model parameter, you can easily select which LLM each agent will use. Here's an example:

pythonCopyEditfrom beaconlabs import Agent

product_manager_agent = Agent(
    "Product Manager",

    model="openai/gpt-4o"  # Specify the model
)