How to Build a No-Code RAG System (Pinecone + Make.com)

👉 Get all of our make.com templates here (including this one): https://www.theaiautomators.com/?utm_source=youtube&utm_medium=video&utm_campaign=tutorial&utm_content=rag_pinecone

In this video, I’ll show you how to build a no-code retrieval augmented generation (RAG) system using Make.com and Pinecone. This system demonstrates how to load an e-commerce store’s knowledge base into a vector database, improving the accuracy of AI-generated content. Whether you're generating articles for clients or your business, this method ensures the text is highly accurate and personalized to your data.

We’ll start by embedding your data into Pinecone and then use a large language model to create content based on the most relevant information. This RAG system automates the process, so you don’t need to manually provide context every time, leading to more precise, useful results.

JSON Safe Code

Here's the code I used to make the text JSON Safe

{{replace(replace(replace(replace(replace(replace(replace(4.fullRecord; "/\n/g"; space); "/\r/g"; space); "/\t/g"; space); "/\f/g"; space); "/\//g"; "/"); "/\\/g"; "\\"); "/""/g"; "\""")}}

🛠️ Tools & Platforms Used:

Make: https://www.make.com/en/register?pc=aiauto
Pinecone - https://www.pinecone.io/
OpenAI Assistant and GPT-4o - https://platform.openai.com/

👋 Connect with Us: Have any questions or want to discuss more about AI automation? Drop your thoughts in the comments below or join our community to collaborate with other automation enthusiasts!

Chapters

00:00 Intro
01:20 Demo
01:51 What we're building
06:06 Loading Knowledgebase into Pinecone
22:02 Building RAG Flow
30:30 End to End Demo