krzysztof/landing_page
1
0
Fork 0
mirror of https://github.com/qdrant/landing_page.git synced 2026-10-04 10:28:29 +02:00
Code Issues Packages Projects Releases Wiki Activity

Remove placeholder video

Browse Source
This commit is contained in:
Kacper Łukawski
2026-01-02 11:18:01 +01:00
parent 561f93e480
commit 0b2fae05ea
13 changed files with 14 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files
qdrant-landing/content/course/multi-vector-search/module-2/colpali-family.md
+1 -1
View File
@@ -16,7 +16,7 @@ Let's explore what each model offers and when to use it.
<div class="video">
<iframe
src="https://www.youtube.com/embed/dQw4w9WgXcQ"
src="https://www.youtube.com/embed/xK9mV7zR4pL"
frameborder="0"
allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share"
referrerpolicy="strict-origin-when-cross-origin"
qdrant-landing/content/course/multi-vector-search/module-2/how-colpali-works.md
+2 -2
View File
@@ -16,7 +16,7 @@ Understanding ColPali's architecture helps you leverage its full potential for m
<div class="video">
<iframe
src="https://www.youtube.com/embed/dQw4w9WgXcQ"
src="https://www.youtube.com/embed/xK9mV7zR4pL"
frameborder="0"
allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share"
referrerpolicy="strict-origin-when-cross-origin"
@@ -92,7 +92,7 @@ For text inputs, there isn't any additional preprocessing step, but it is tokeni
Vision transformers, the foundation of ColPali, don't process entire images at once. Instead, they divide images into a grid of fixed-size patches - think of it like a checkerboard overlaid on your document.
ColPali pipeline starts with a document. It is usually a screenshot of a single PDF page, or anything you want to encode. While you might convert a PDF page to a high-resolution screenshot to preserve visual details during conversion, **the ColPali preprocessing itself resizes images to a fixed resolution** of **448×448 pixels** before processing.
The ColPali pipeline starts with a document. It is usually a screenshot of a single PDF page, or anything you want to encode. While you might convert a PDF page to a high-resolution screenshot to preserve visual details during conversion, **the ColPali preprocessing itself resizes images to a fixed resolution** of **448×448 pixels** before processing.
This fixed-size input is then divided into patches:
- **Patch size**: 14×14 pixels per patch
qdrant-landing/content/course/multi-vector-search/module-2/visual-interpretability.md
+1 -1
View File
@@ -16,7 +16,7 @@ This transparency is invaluable for building trust in multi-modal search systems
<div class="video">
<iframe
src="https://www.youtube.com/embed/dQw4w9WgXcQ"
src="https://www.youtube.com/embed/xK9mV7zR4pL"
frameborder="0"
allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share"
referrerpolicy="strict-origin-when-cross-origin"