9 Comments
User's avatar
Tom De Villiers's avatar

i love these deep dives into how entire specific apps/sites work

Expand full comment
Anabel's avatar

I love using Perplexity but knowing how the business made architectural decisions to optimize the business but also deliver the best user experience is enlightening. I feel like I learned so much about RAG and Perplexity as a business, thank you!

Expand full comment
Wei Ren's avatar

If Perplexity uses Amazon Bedrock to easily plug these different third-party models into their system, it is not clear to me why they need to have their own inference stack, for hosting those models not available in Amazon Bedrock?

Expand full comment
SJ's avatar

Thank you, this was so enlightening!

a noob question - "Perplexity’s crawling and indexing infrastructure tracks over 200 billion unique URLs / how Vespa db is used as the index". Does it mean that they don't rely on any search api (ex: Bing api) to retrieve? I'm just amazed at this part b/c in addition to the scale problem, the data / human labeling to build this search ranking model would be huge effort

Expand full comment
Merenia Marin's avatar

Have been using Perplexity for about a year now- really happy I have a lot on at work I have used it to build out whole community development models and programs , great to understand a bit of how it works and why it really seems more intuitive than other AI tools like co pilot etc

Expand full comment
Sumanta Boral's avatar

This is a good deep dive. Not just Perplexity, coming from Amazon/Alexa background I could relate to most of the content in here.

Expand full comment
Neural Foundry's avatar

Your technical breakdown of Perplexity's RAG pipeline really highlights why Google is facing such intesne competition now. The fact that Perplexity can build a competitive search experience with just 38 engineers by leveraging Vespa shows how much the infrastructure playing field has leveled. What strikes me is that Google's massive web index and PageRank algorithms might not be the moat they once were if the real value shifts to retrieval quality and LLM orchestration.

Expand full comment
Bit Prompt's avatar

Perplexity’s innovative approach to real-time, cited answers truly sets a new standard for AI-powered search.

Expand full comment
Ravi's avatar

Is step 3 missing from the "how RAG works" diagram? Or am I not following it correctly?

Expand full comment