logo
  • Develop
  • Deploy
  • Ecosystem
  • Learn
  • API Reference
Log in Start Free
logo
  • Develop
  • Deploy
  • Ecosystem
  • Learn
  • API Reference
Multi-Vector Search Course
  • Qdrant Multi-Vector Certification
  • Module 0: Setting Up Dependencies
    • Qdrant Setup
    • Installing Dependencies
  • Module 1: Multi-Vector Representations for Textual Data
    • Late Interaction Basics
    • MaxSim Distance Metric
    • Use Cases for Multi-Vector Search
    • Problems of Multi-Vector Search
    • Multi-Vector Embeddings in Qdrant
  • Module 2: Multi-Vector Representations for Multi-Modal Data
    • How ColPali Models Work
    • ColPali Family Overview
    • Visual Interpretability of ColPali
  • Module 3: Scalability and Optimization
    • Multi-Stage Retrieval with Universal Query API
    • Vector Quantization Techniques
    • Pooling Techniques
    • MUVERA
    • Evaluating Search Pipelines
    • Final Project: Build Your Own Multi-Vector Search System
Qdrant Essentials Course
  • Day 0: Setup and First Steps
    • Qdrant Setup
    • Implementing a Basic Vector Search
    • Project: Building Your First Vector Search System
  • Day 1: Vector Search Fundamentals
    • Points, Vectors and Payloads
    • Distance Metrics
    • Text Chunking Strategies
    • Demo: Semantic Movie Search
    • Project: Building a Semantic Search Engine
  • Day 2: Indexing and Performance
    • HNSW Indexing Fundamentals
    • Combining Vector Search and Filtering
    • Demo: HNSW Performance Tuning
    • Project: HNSW Performance Benchmarking
  • Day 3: Hybrid Search
    • Sparse Vectors and Inverted Indexes
    • Demo: Keyword Search with Sparse Vectors
    • Hybrid Search and the Universal Query API
    • Demo: Implementing a Hybrid Search System
    • Project: Building a Hybrid Search Engine
  • Day 4: Optimization and Scale
    • Vector Quantization Methods
    • Accuracy Recovery with Rescoring
    • Large-Scale Data Ingestion
    • Project: Quantization Performance Optimization
  • Day 5: Advanced APIs
    • Multivectors for Late Interaction Models
    • The Universal Query API
    • Demo: Universal Query for Hybrid Retrieval
    • Project: Building a Recommendation System
  • Day 6: Final Project - Building a Production-Grade Search Engine
    • Final Project: Production-Ready Documentation Search Engine
    • Course Completion and Next Steps
  • Day 7: Partner Ecosystem Integrations (Bonus)
    • Integrating with Haystack
    • Integrating with Unstructured.io
    • Integrating with Tensorlake
    • Integrating with Superlinked
    • Integrating with LlamaIndex
    • Integrating with Quotient
    • Integrating with Camel AI
    • Integrating with Jina AI
  • Qdrant Essentials Certification
    • Qdrant Essentials FAQs

      Multi-Vector Search Course

      48%

      Course Overview
      Module 0: Setting Up Dependencies
        Qdrant Setup
        Installing Dependencies
      Module 1: Multi-Vector Representations for Textual Data
        Late Interaction Basics
        MaxSim Distance Metric
        Use Cases for Multi-Vector Search
        Problems of Multi-Vector Search
        Multi-Vector Embeddings in Qdrant
      Module 2: Multi-Vector Representations for Multi-Modal Data
        How ColPali Models Work
        ColPali Family Overview
        Visual Interpretability of ColPali
      Module 3: Scalability and Optimization
        Multi-Stage Retrieval with Universal Query API
        Vector Quantization Techniques
        Pooling Techniques
        MUVERA
        Evaluating Search Pipelines
        Final Project: Build Your Own Multi-Vector Search System
      Qdrant Multi-Vector Certification
      • Qdrant Academy
      • Multi-Vector Search Course
      • Module 2: Multi-Vector Representations for Multi-Modal Data
      Calendar Module 2

      Multi-Vector Representations for Multi-Modal Data

      Extend multi-vector representations beyond text to unlock powerful multi-modal search capabilities.


      Today’s path

      1. How ColPali Models Work
      2. ColPali Family Overview
      3. Visual Interpretability of ColPali

      You’ll learn to build multi-modal search systems that understand both images and text.

      Continue to Next Step

      On this page:

      • Multi-Vector Representations for Multi-Modal Data
        • Today’s path
      © 2026 Qdrant.
      Terms Privacy Policy Impressum Recruitment Privacy Policy Cookie Consent