Dynamiq Docs
  • Welcome to Dynamiq
  • Low-Code Builder
    • Chat
    • Basics
    • Connecting Nodes
    • Conditional Nodes and Multiple Outputs
    • Input and Output Transformers
    • Error Handling and Retries
    • LLM Nodes
    • Validator Nodes
    • RAG Nodes
      • Indexing Workflow
        • Pre-processing Nodes
        • Document Splitting
        • Document Embedders
        • Document Writers
      • Inference RAG workflow
        • Text embedders
        • Document retrievers
          • Complex retrievers
        • LLM Answer Generators
    • LLM Agents
      • Basics
      • Guide to Implementing LLM Agents: ReAct and Simple Agents
      • Guide to Agent Orchestration: Linear and Adaptive Orchestrators
      • Guide to Advanced Agent Orchestration: Graph Orchestrator
    • Audio and voice
    • Tools and External Integrations
    • Python Code in Workflows
    • Memory
    • Guardrails
  • Deployments
    • Workflows
      • Tracing Workflow Execution
    • LLMs
      • Fine-tuned Adapters
      • Supported Models
    • Vector Databases
  • Prompts
    • Prompt Playground
  • Connections
  • LLM Fine-tuning
    • Basics
    • Using Adapters
    • Preparing Data
    • Supported Models
    • Parameters Guide
  • Knowledge Bases
  • Evaluations
    • Metrics
      • LLM-as-a-Judge
      • Predefined metrics
        • Faithfulness
        • Context Precision
        • Context Recall
        • Factual Correctness
        • Answer Correctness
      • Python Code Metrics
    • Datasets
    • Evaluation Runs
    • Examples
      • Build Accurate vs. Inaccurate Workflows
  • Examples
    • Building a Search Assistant
      • Approach 1: Single Agent with a Defined Role
      • Approach 2: Adaptive Orchestrator with Multiple Agents
      • Approach 3: Custom Logic Pipeline with a Straightforward Workflow
    • Building a Code Assistant
  • Platform Settings
    • Access Keys
    • Organizations
    • Settings
    • Billing
  • On-premise Deployment
    • AWS
    • IBM
  • Support Center
Powered by GitBook
On this page
  • Core Concepts
  • How Memory Systems Empower Agents
  1. Low-Code Builder

Memory

PreviousPython Code in WorkflowsNextGuardrails

Last updated 5 months ago

Memory systems are crucial for building sophisticated and context-aware AI agents. Dynamiq provides a robust and flexible memory management system that allows agents to learn from past interactions, maintain context, and reason more effectively. Below we'll outline the core concepts and functionalities of Dynamiq's memory system, including its various components and how they empower agents.

Core Concepts

Dynamiq's memory system is designed to provide a unified interface for interacting with various backend storage solutions. This abstraction simplifies development and enables flexibility in choosing the most suitable storage mechanism for your needs.

The central component is the Memory class, which handles the storage and retrieval of messages. It allows you to seamlessly switch between different implementations (in-memory, Pinecone, Qdrant, SQLite) without modifying your application's core logic.

How Memory Systems Empower Agents

  • Contextual Awareness: Memory allows agents to maintain context over conversations or task sequences, leading to more coherent and relevant responses.

  • Experience Accumulation: Agents can learn from past actions and improve future decision-making.

  • Entity Understanding: Agents can recognize and remember key entities, enhancing their ability to process and interact with complex information.