Jenna Pederson

developer relations leader bringing business, community, and technology together

Everyone says their agent "has memory"

Everyone uses the word "memory" but I feel like they all mean something different by it. What do you mean?

Stop over-engineering your n8n RAG pipeline before you've shipped anything

When building RAG workflows in n8n, you have two primary options for working with Pinecone: the Pinecone Assistant node and the Pinecone Vector Store node.

n8n

Build a multi-assistant workflow with Pinecone Assistant in n8n

An n8n workflow using multiple, specialized knowledge bases because sometimes you need knowledge isolation between clients, locations, or even products in your RAG workflows.

n8n

Build a simple RAG workflow to chat with your docs in n8n

The new n8n community node for Pinecone Assistant handles the entire RAG pipeline in a single node so you don't have to think about file storage, chunking your data, creating embeddings, query planning, vector search, and reranking.

Diagram showing traditional RAG from user query to output

What is RAG?

I've been working to build out resources for people to learn more about retrieval-augmented generation (RAG) — and to learn more about it myself. This post covers what RAG is, what I found and suggestions for how to tackle the resources.