This n8n workflow enables an AI assistant to remember, retrieve, and utilize past conversations across user sessions by integrating advanced embedding, vector search, and language models. It combines OpenAI for embeddings and chat, Qdrant for long-term memory storage, and Cohere for relevance reranking. The system processes real-time chat messages, chunks texts for semantic understanding, and manages memory storage and retrieval seamlessly. Practical for customer support bots, personal AI assistants, educational tools, and knowledge bases, this workflow enhances conversational continuity, personalization, and efficiency while reducing token costs.
AI-Powered Long-Term Memory Chat Workflow
Node Count | >20 Nodes |
---|---|
Nodes Used | @n8n/n8n-nodes-langchain.agent, @n8n/n8n-nodes-langchain.chatTrigger, @n8n/n8n-nodes-langchain.documentDefaultDataLoader, @n8n/n8n-nodes-langchain.embeddingsOpenAi, @n8n/n8n-nodes-langchain.lmChatOpenAi, @n8n/n8n-nodes-langchain.outputParserStructured, @n8n/n8n-nodes-langchain.rerankerCohere, @n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter, @n8n/n8n-nodes-langchain.vectorStoreQdrant, set, stickyNote |
Reviews
There are no reviews yet.