Course modules division

qdrant-landing/content/course/multi-vector-search/module-0/_index.md

@@ -0,0 +1,23 @@
+---
+title: "Module 0: Setting Up Dependencies"
+description: Set up your development environment for multi-vector search. Install required dependencies and prepare your workspace for the course.
+isLesson: true
+weight: 10
+---
+
+{{< date >}} Module 0 {{< /date >}}
+
+# Setting Up Dependencies
+
+Get your environment ready for exploring multi-vector search with Qdrant.
+
+---
+
+## Today's path
+
+1. Python Environment Setup
+2. Installing Qdrant and FastEmbed
+3. Preparing Your Workspace
+4. Verifying Your Installation
+
+By the end, you'll have a working development environment ready for multi-vector search experiments.

qdrant-landing/content/course/multi-vector-search/module-1/_index.md

@@ -0,0 +1,23 @@
+---
+title: "Module 1: Multi-Vector Representations for Textual Data"
+description: Learn about multi-vector representations for text with ColBERT. Understand how they differ from single vector embeddings and when to use them.
+isLesson: true
+weight: 20
+---
+
+{{< date >}} Module 1 {{< /date >}}
+
+# Multi-Vector Representations for Textual Data
+
+Dive into multi-vector text representations and discover how ColBERT changes the vector search landscape.
+
+---
+
+## Today's path
+
+1. ColBERT Basics
+2. Comparison to Regular Dense Embedding Models
+3. Use Cases for Multi-Vector Search
+4. MaxSim Distance Metric
+
+You'll understand when multi-vector representations outperform traditional single-vector embeddings.

qdrant-landing/content/course/multi-vector-search/module-2/_index.md

@@ -0,0 +1,23 @@
+---
+title: "Module 2: Multi-Vector Representations for Multi-Modal Data"
+description: Explore multi-modal multi-vector search with ColPali. Learn how to search across images and text, and configure Qdrant for multi-vector embeddings.
+isLesson: true
+weight: 30
+---
+
+{{< date >}} Module 2 {{< /date >}}
+
+# Multi-Vector Representations for Multi-Modal Data
+
+Extend multi-vector representations beyond text to unlock powerful multi-modal search capabilities.
+
+---
+
+## Today's path
+
+1. ColPali Family Overview
+2. How ColPali Models Work
+3. Visual Interpretability of ColPali
+4. Configuring Qdrant for Multi-Vector Embeddings
+
+You'll learn to build multi-modal search systems that understand both images and text.

qdrant-landing/content/course/multi-vector-search/module-3/_index.md

@@ -0,0 +1,25 @@
+---
+title: "Module 3: Scalability and Optimization"
+description: Address scalability challenges in multi-vector search. Learn optimization techniques including quantization, pooling, MUVERA, and multi-stage retrieval.
+isLesson: true
+weight: 40
+---
+
+{{< date >}} Module 3 {{< /date >}}
+
+# Scalability and Optimization
+
+Tackle the memory and performance challenges of production-scale multi-vector search.
+
+---
+
+## Today's path
+
+1. Memory Usage Implications and Solutions
+2. Vector Quantization Techniques (Scalar, Binary, +1.5/2-bit)
+3. Pooling Techniques (Row/Column, Hierarchical Token Pooling)
+4. MUVERA for HNSW Compatibility
+5. Multi-Stage Retrieval with Universal Query API
+6. Evaluating Search Pipelines (Cost vs. Latency)
+
+You'll master the optimization strategies needed to deploy multi-vector search at scale.

qdrant-landing/content/course/multi-vector-search/plan.md

@@ -4,17 +4,18 @@ This document is a proposal for another Qdrant course. I suggest covering both t
 
 # Outline
 
-1. **Module 1:** Multi-vector representations for textual data  
+1. **Module 0:** Setting up dependencies
+2. **Module 1:** Multi-vector representations for textual data  
    * ColBERT basics  
    * Comparison to regular dense embedding models  
    * Examples when multi-vectors may work better than single vectors  
    * MaxSim distance  
-2. **Module 2:** Multi-vector representations for multi-modal data (image \+ text)  
+3. **Module 2:** Multi-vector representations for multi-modal data (image \+ text)  
    * ColPali family  
    * Inner workings of the ColPali models  
    * Visual interpretability of ColPali representations  
    * Setting up Qdrant for multi-vector embeddings  
-3. **Module 3:** Scalability issues caused by multi-vector representations  
+4. **Module 3:** Scalability issues caused by multi-vector representations  
    * The implications of high memory usage and ways to solve it  
      * Vector quantization: scalar, binary, \+1.5/2-bit  
      * Pooling techniques: row/column pooling, hierarchical token pooling