Chat Memory Node

The chat memory takes the past conversation history and passes it to connected nodes. Chat memory nodes are often connected to LLM nodes, as LLMs do not inherently have memory. This allows the LLM to reference previous conversation history.

​

Node Inputs

The chat memory node does not have any inputs.

​

Node Parameters

1. Memory Type: select the memory type
   • Type: Dropdown

Overview of Memory Types

1. Full - Formatted: Returns all previous chat history, with user messages prepended with “Human” and output messages prepended with “AI”. Useful for handling short conversations, but may run into token limits once conversations start becoming longer.
2. Full - Raw: Returns a Python list with elements in the following format: {"type": type, "message": message}, where type is “input” (i.e., Human) or “output” (i.e., AI) and message contains the contents of the message. Useful for developers looking to execute custom logic with their chat history using Transformations.
3. Message Buffer: Returns a set number of previous consecutive messages. This number defaults to 10 and can be changed by right-clicking the Chat Memory node and clicking “Details”. Both Human messages and AI messages count toward the limit.
4. Token Buffer: Returns previous consecutive messages until adding an additional message would cause the total history size to be larger than the Max Tokens. The default number of Max Tokens is 2048 and can be changed by right-clicking the Chat Memory node and clicking “Details”.

​

Node Outputs

1. Memory: The conversation history in the selected memory type
   • Type: Text
   • Example usage: {{chat_memory_0.memory}}

​

Example

The below example is a simple chatbot pipeline. The chat memory node passes the chat history to the LLM, allowing the LLM to reference previous message as necessary.

1. Input Node: Represents the user message
2. Knowledge Base Reader Node: Queries the knowledge base semantically
   • Search Query: {{input_0.text}}
3. Chat Memory Node: Passes the conversation history to the LLM
   • Memory Type: Token Buffer
4. LLM Node: Responds to the user question
   • System (Instructions): Answer the question based on the context in a friendly but professional manner. Use conversation history when relevant.
   • Prompt: Question: {{input_0.text}} Context: {{knowledge_base_1.chunks}} Conversation History: {{chat_memory_0.memory}}
5. Output Node: Displays the response
   • Output: {{openai_0.response}}