Buffer Memory

​

Node Details

• Name: bufferMemory
• Type: BufferMemory
• Version: 2.0
• Version: 2.0
• Category: Memory

​

Base Classes

• BufferMemory
• BufferMemoryExtended

​

Base Classes

• BufferMemory
• BufferMemoryExtended

​

Parameters

​

Inputs

1. Session Id (optional)

​

Inputs

1. Session Id (optional)

   • Type: string
   • Default: ” (empty string)
   • Description: Unique identifier for the chat session. If not specified, a random id will be used
   • Description: Unique identifier for the chat session. If not specified, a random id will be used

2. Memory Key

   • Type: string
   • Default: ‘chat_history’
   • Description: Key used to store and retrieve the chat history in memory
   • Description: Key used to store and retrieve the chat history in memory

​

Input/Output

This node doesn’t have specific input/output ports. Instead, it initializes a BufferMemoryExtended instance that can be used by other nodes in the flow to manage chat history.

​

Functionality

1. Initialization:

   • Creates a BufferMemoryExtended instance with the provided session ID, memory key, and database connection details.

2. getChatMessages:

   • Retrieves chat messages from the database for a given session ID.
   • Can optionally return messages as BaseMessage objects or IMessage interfaces.
   • Allows prepending additional messages to the retrieved history.

3. addChatMessages and clearChatMessages:

   • These methods are placeholders and don’t perform any actions, as message management is handled at the server level.

​

Database Integration

• Uses TypeORM’s DataSource for database operations.
• Retrieves chat messages from a ‘ChatMessage’ entity in the database.
• Filters messages by session ID and chatflow ID.
• Orders messages by creation date in ascending order.

​

Use Cases

• Maintaining conversation context in chatbots or conversational AI systems.
• Retrieving past interactions for context-aware responses.
• Supporting multi-turn conversations with persistent memory.

​

Notes

• This node is designed to work within a larger system that handles the actual storage and management of chat messages.
• It’s part of a modular architecture where memory management is separated from other conversational AI components.