Skip to content
FloTorch

LangGraph Plugin: Agent

The FlotorchLangGraphAgent serves as the primary component for integrating FloTorch-managed agent configurations with LangGraph. It enables developers to define agent configurations centrally in the FloTorch Console and instantiate them with minimal code, eliminating the need for complex in-code configuration management.

Prerequisites

Section titled “Prerequisites”

Before using FlotorchLangGraphAgent, ensure you have completed the general prerequisites outlined in the LangGraph Plugin Overview, including installation and environment configuration.

Configuration

Section titled “Configuration”

Parameters

Section titled “Parameters”

Configure your agent using the following parameters:

FlotorchLangGraphAgent(
    agent_name: str,                    # Agent name from FloTorch Console (required)
    custom_tools: list = None,          # List of custom user-defined tools
    base_url: str = None,               # FloTorch Gateway URL
    api_key: str = None,                # FloTorch API key
    checkpointer: BaseCheckpointSaver = None,  # Optional checkpointer for session persistence
    store: BaseStore = None             # Optional store for long-term memory
)

Parameter Details:

  • agent_name - Must match an existing agent name in your FloTorch Console
  • custom_tools - List of custom LangGraph tools to add to the agent’s capabilities
  • base_url - FloTorch Gateway endpoint (defaults to environment variable FLOTORCH_BASE_URL)
  • api_key - Authentication key (defaults to environment variable FLOTORCH_API_KEY)
  • checkpointer - Optional LangGraph checkpointer for session-based state persistence
  • store - Optional LangGraph store for long-term memory storage

Note: Tools include custom tools and MCP tools from Console configuration. The agent is compatible with LangGraph workflows and create_react_agent.

Features

Section titled “Features”

Automatic Configuration Loading

Section titled “Automatic Configuration Loading”

The agent automatically loads comprehensive configuration from FloTorch Console, including:

  • Agent name and description (goal)
  • System instructions and prompts
  • LLM model configuration
  • Input/output schemas
  • MCP tools configuration
  • Synchronization settings

Configuration Synchronization

Section titled “Configuration Synchronization”

Supports automatic configuration updates based on:

  • syncEnabled - Enables automatic configuration reloading
  • syncInterval - Defines the synchronization interval in seconds

This ensures your agent stays up-to-date with changes made in the FloTorch Console without requiring code redeployment.

Tool Integration

Section titled “Tool Integration”

Automatically integrates tools configured in FloTorch Console:

  • MCP Tools - Loaded directly from agent configuration
  • Custom Tools - Add your own LangGraph tools via the custom_tools parameter
  • Tool Management - Handles authentication and connection automatically
  • LangGraph Compatibility - Seamlessly integrates with LangGraph’s tool framework

Memory Integration

Section titled “Memory Integration”

Supports LangGraph’s memory patterns:

  • Checkpointer - Use checkpointer parameter for session-based state persistence
  • Store - Use store parameter for long-term memory storage
  • State Management - Handles state persistence automatically

Logging Configuration

Section titled “Logging Configuration”

FloTorch LangGraph Plugin supports configurable logging to help you monitor and debug your agents. For comprehensive logging configuration details, including environment variables and programmatic setup, refer to the SDK Logging Configuration documentation.

Quick Setup:

Terminal window
# Enable debug logging to console
export FLOTORCH_LOG_DEBUG=true
export FLOTORCH_LOG_PROVIDER="console"

Or configure programmatically:

from flotorch.sdk.logger.global_logger import configure_logger


configure_logger(debug=True, log_provider="console")

For detailed logging configuration options, see the SDK Logging Configuration guide.

Usage Example

Section titled “Usage Example”

Basic Agent Setup

Section titled “Basic Agent Setup”
from flotorch.langgraph.agent import FlotorchLangGraphAgent


# Initialize the agent manager
agent_manager = FlotorchLangGraphAgent(
    agent_name="my-agent",  # Must exist in FloTorch Console
    base_url="https://gateway.flotorch.cloud",
    api_key="your_api_key"
    # Note: Agent goal and system prompt are configured
    # in the FloTorch Console during agent creation
)


# Get the configured agent
agent = agent_manager.get_agent()

Agent with Custom Tools

Section titled “Agent with Custom Tools”
from flotorch.langgraph.agent import FlotorchLangGraphAgent


# Define a custom weather tool
def get_weather(location: str) -> str:
    """
    Get the current weather for a specific location.
    Args:
        location: The city or location name to get weather for
    Returns:
        A string describing the current weather conditions
    """
    return f"The weather in {location} is sunny with a temperature of 72°F (22°C)."


# Initialize agent with custom weather tool
agent_manager = FlotorchLangGraphAgent(
    agent_name="weather-agent",
    custom_tools=[get_weather],  # Add the custom weather tool
    base_url="https://gateway.flotorch.cloud",
    api_key="your_api_key"
)


# Get the configured agent
agent = agent_manager.get_agent()

Best Practices

Section titled “Best Practices”
  1. Configuration Management - Define agent configurations in FloTorch Console rather than in code
  2. Environment Variables - Use environment variables for credentials to avoid hardcoding sensitive information
  3. Configuration Sync - Enable synchronization in the Console to receive updates without redeployment
  4. Custom Tools - Define custom tools with clear descriptions and proper error handling for robust agent behavior
  5. Logging - Configure logging based on your environment: use console logging for development and file logging for production. See SDK Logging Configuration for details

Next Steps

Section titled “Next Steps”