Appu (Apu) Shaji

speaker

101 appearances 1 recordings 1 series first heard Jul 2026 last heard 14 Jul

Appu (Apu) Shaji’s voice in public audio — every appearance, attributed to the second.

Trend

recordings per month · last 12 months

Recordings per month over the last 12 months — 1 in all, peaking in Jul 2026 with 1.

Appearances

newest first · ▶ plays the moment

Working Smarter · Building AI that can search inside videos (and photos and audio too) · 14 Jul 2026 podcast

And solving search for these users is very important.

So how do you do that?

When you think about search, you also have to think about different kinds of file types.

Typically, people have docs, they might have Jira tickets, they might have videos, they might have audio files, etc.

So search has

To work across all of these different uh files drives.

It's kind of hard to know what is inside what is happening inside a video document.

So we run certain models uh to look inside the video.

So if you think about video, it has various aspects.

It has the visuals that you see within the video.

Like uh I'm seeing you math, and that's kind of a very visual input.

We are talking to each other, that's essentially

An audio input, and then we are talking in some language, so that's contextual in nature.

So combining everything, this process is called multimodal input, where you have different modalities sort of merging, and you have to combine all of that things together and using some of the powerful sort of AI models that is coming up.

That's what we use.

And once this data has been extracted, this should be prepared for.

So typically we use techniques like sort of good embedding models.

So think about embedding models as creating a small summary of

what something happens in a dock so that the search engine can quickly go and uh retrieve that essentially.

And then there are other layers like personalization.

Showing 21–40 of 101 · page 2 of 6