Skip to content
FloTorch

LangGraph Plugin: Memory

FloTorch LangGraph Memory services enable persistent memory capabilities for your agents, allowing them to store and retrieve information across sessions. The memory system integrates seamlessly with LangGraph’s store framework and provides long-term persistent storage for agent state and conversation history.

Important: Memory services require prior setup in the FloTorch Console. Memory capabilities are not built-in and must be explicitly configured.

Prerequisites

Section titled “Prerequisites”

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

Quick Setup

Section titled “Quick Setup”

Store Service

Section titled “Store Service”
from flotorch.langgraph.memory import FlotorchStore


# Initialize memory store (requires prior registration in FloTorch Console)
memory = FlotorchStore(
    provider_name="your-memory-provider",
    api_key="your_api_key",
    base_url="https://gateway.flotorch.cloud",
    userId="user_123",
    appId="app_123"
)

Configuration

Section titled “Configuration”

Parameters

Section titled “Parameters”

Configure your memory store with the following parameters:

FlotorchStore(
    provider_name: str,    # Memory provider name (from FloTorch Console) - required
    api_key: str,          # FloTorch API key for authentication (required)
    base_url: str,         # FloTorch Gateway URL (required)
    userId: str,            # User identifier for memory isolation (required)
    appId: str              # Application identifier for memory isolation (required)
)

Parameter Details:

  • provider_name - The name of the memory provider configured in FloTorch Console
  • api_key - Authentication key for accessing FloTorch Gateway (can be set via environment variable)
  • base_url - FloTorch Gateway endpoint URL (can be set via environment variable)
  • userId - User identifier for isolating memory per user
  • appId - Application identifier for isolating memory per application

Features

Section titled “Features”

BaseStore Interface

Section titled “BaseStore Interface”

Fully implements LangGraph’s BaseStore interface:

  • Store Operations - Supports put, get, and search operations
  • State Persistence - Persists agent state and conversation history
  • LangGraph Compatibility - Works seamlessly with LangGraph’s store framework

Automatic Content Management

Section titled “Automatic Content Management”

Memory store provides automatic content management:

  • Content Extraction - Automatically extracts content from LangGraph state
  • State Persistence - Persists agent state to FloTorch Memory
  • Metadata Storage - Stores conversations with associated metadata
  • History Formatting - Formats history for agent context

Search Capabilities

Section titled “Search Capabilities”

Provides comprehensive memory search:

  • Keyword-Based Search - Performs traditional text-based searches
  • User/App Filtering - Filters results by user ID and application name
  • Metadata Filtering - Supports custom metadata filtering
  • Date Range Queries - Allows filtering by time ranges

Usage Example

Section titled “Usage Example”

Basic Memory Setup

Section titled “Basic Memory Setup”
from flotorch.langgraph.agent import FlotorchLangGraphAgent
from flotorch.langgraph.memory import FlotorchStore


# Initialize memory store
memory = FlotorchStore(
    provider_name="your-memory-provider",
    api_key="your_api_key",
    base_url="https://gateway.flotorch.cloud",
    userId="user_123",
    appId="app_123"
)


# Use with agent
agent_manager = FlotorchLangGraphAgent(
    agent_name="customer-support",
    store=memory,  # Add memory store
    base_url="https://gateway.flotorch.cloud",
    api_key="your_api_key"
)


agent = agent_manager.get_agent()

Store Operations

Section titled “Store Operations”
from flotorch.langgraph.memory import FlotorchStore


# Initialize memory store
memory = FlotorchStore(
    provider_name="your-memory-provider",
    api_key="your_api_key",
    base_url="https://gateway.flotorch.cloud",
    userId="user_123",
    appId="app_123"
)


# Store data
await memory.aput("key", "value")


# Retrieve data
value = await memory.aget("key")


# Search memory
results = await memory.asearch("query")

Best Practices

Section titled “Best Practices”
  1. Memory Provider Setup - Always configure memory providers in FloTorch Console before using them in code
  2. User/App Isolation - Use appropriate userId and appId values to isolate memory per user and application
  3. Store Operations - Use store operations (put, get, search) for managing agent state and conversation history
  4. Error Handling - Implement proper error handling for memory operations in production environments
  5. Memory Cleanup - Consider implementing memory cleanup strategies for long-running applications

Next Steps

Section titled “Next Steps”