AI PAPERS/DAILY
Subscribe free Open sourceView on GitHub Star This project is open sourceRead the code or use it in your own project. If you like it, don’t forget to give it a ★ star on GitHub.
HubSpot
RAG and search

Building the AI Retrieval Infrastructure Behind 20 Billion+ Vectors at HubSpot

Our short summary of HubSpot’s engineering write-up. The full story, with all the detail, is on their blog.

Read the full write-up on product.hubspot.com (opens in a new tab)

Problem

Teams needed fast, accurate semantic search across billions of items for agents and other tools.

Solution

HubSpot built a centralized Vector-as-a-Service platform on Qdrant, adding API, access control, embedding generation, async writes, and cost‑saving features like quantization.

+ Suggest a write-up

Want the architecture, code and numbers? They’re in the original post.

Read the full write-up on product.hubspot.com (opens in a new tab)

More from RAG and search

All RAG and search write-ups