Still a work in progress. Some images and sections are on their way.
Aazim Haque.
Personal / Projects / Deep Dive
RAG · LLM Ongoing

Deep Dive

Like NotebookLM, but pointed at my own content: the podcasts I follow and any YouTube video I throw at it. It reads everything, hands back one consolidated take, then lets me ask questions to go deeper.

Deep Dive — the library: podcasts and YouTube channels, grouped by source, ready to pull into a session
The library — podcasts and YouTube channels, grouped by source, ready to pull into a session.
Deep Dive — a consolidated summary with a quick-reference table, then a back-and-forth to dig into the detail
A consolidated summary up top, then a back-and-forth to dig into whatever I want to understand better.

It runs on the home server, so there's no public instance, but I'm happy to give you a tour.

What it does

I get through a lot of podcasts and the odd long YouTube video, and the good bits never stick the first time round. This pulls a week's worth of that content into one place, writes a single consolidated analysis across all of it, and then lets me sit and talk to it (“what was the argument about X?”, “how does this connect to last week?”) until I actually understand the thing.

It's basically NotebookLM for my own feeds: same idea of grounding the model in a set of sources I chose, but built around the podcasts and videos I already follow rather than documents I have to upload.

How it works

Each source, whether a podcast feed or a YouTube link, gets transcribed and chunked into a vector store. When I start a session, the relevant passages are retrieved and a language model writes the consolidated summary, then answers follow-ups using only those sources, so the conversation stays anchored to what was actually said.

Sessions and bookmarks are saved, so I can come back to a topic later and keep pulling on the thread.