Basic RAG chat

This workflow demonstrates a simple Retrieval-Augmented Generation (RAG) pipeline in n8n, split into two main sections:

🔹 Part 1: Load Data into Vector Store Reads files from disk (or Google Drive).

Splits content into manageable chunks using a recursive text splitter.

Generates embeddings using the Cohere Embedding API.

Stores the vectors into an In-Memory Vector Store (for simplicity; can be replaced with Pinecone, Qdrant, etc.).

🔹 Part 2: Chat with the Vector Store Takes user input from a chat UI or trigger node.

Embeds the query using the same Cohere embedding model.

Retrieves similar chunks from the vector store via similarity search.