---
title: "Reconstructed Slides: Stop Using RAG as Memory — Daniel Chalef, Zep"
category: "slides"
video_id: "T5IMo5ntyhA"
sourceLabels: ["Cropped public YouTube video frames", "Local OpenCV slide-region detection", "Local RapidOCR"]
---

# Reconstructed Slides: Stop Using RAG as Memory — Daniel Chalef, Zep

## Source Video
[Stop Using RAG as Memory — Daniel Chalef, Zep](https://www.youtube.com/watch?v=T5IMo5ntyhA)

## Method
This deck is reconstructed from the existing video frame captures by detecting likely slide regions with OpenCV, cropping/upscaling those regions, deduplicating similar crops, and OCRing the cropped slide images locally. It is a cleaner companion to the full-stage frame deck.

## Reconstructed Slides
![[assets/reconstructed-slides/T5IMo5ntyhA/slide-001.jpg]]

- Source frame: `slide-001.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `160.13`
![[assets/reconstructed-slides/T5IMo5ntyhA/slide-002.jpg]]

- Source frame: `slide-002.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `175.96`
![[assets/reconstructed-slides/T5IMo5ntyhA/slide-003.jpg]]

- Source frame: `slide-003.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `156.99`
![[assets/reconstructed-slides/T5IMo5ntyhA/slide-004.jpg]]

- Source frame: `slide-004.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `177.34`
## Dense Scene-Detected Slide Candidates
- [[youtube-T5IMo5ntyhA-dense-slides]]