mirror of
https://github.com/qdrant/landing_page.git
synced 2026-10-04 10:28:29 +02:00
initial commit; Claude generated SEO descriptions
This commit is contained in:
kanungle
@@ -1,6 +1,7 @@
|
||||
---
|
||||
title: "Multi-Vector Search Course"
|
||||
page_title: "Qdrant Multi-Vector Search Course"
|
||||
short_description: "Master multi-vector search with ColBERT and ColPali: late interaction, MaxSim scoring, multi-stage retrieval, MUVERA indexing, and evaluation."
|
||||
description: Master late interaction models, ColPali, and production optimization. Build scalable multi-vector search pipelines.
|
||||
content:
|
||||
sidebarTitle: "Multi-Vector Search Course"
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: "Qdrant Multi-Vector Certification"
|
||||
short_description: "Validate your multi-vector search skills with an official Qdrant certification covering ColBERT, ColPali, MaxSim, and MUVERA pipelines."
|
||||
description: "Get officially certified in multi-vector search by Qdrant."
|
||||
url: /course/multi-vector-search/certification/
|
||||
isLesson: true
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: "Module 0: Setting Up Dependencies"
|
||||
short_description: "Module 0 of the Multi-Vector Search course: prepare your Qdrant environment and Python dependencies for late-interaction experiments."
|
||||
description: "Set up your development environment for multi-vector search. Install required dependencies and prepare your workspace for the course."
|
||||
isLesson: true
|
||||
weight: 10
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: "Installing Dependencies"
|
||||
short_description: "Set up a Python environment for multi-vector search with the Qdrant client and FastEmbed for late-interaction embeddings."
|
||||
description: Install Python dependencies including FastEmbed and Qdrant client.
|
||||
weight: 2
|
||||
isLesson: true
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: "Qdrant Setup"
|
||||
short_description: "Stand up Qdrant Cloud or a local Qdrant instance and configure credentials before running multi-vector search experiments."
|
||||
description: Set up Qdrant for multi-vector search. Learn how to create a collection and configure it for multi-vector embeddings.
|
||||
weight: 1
|
||||
isLesson: true
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: "Module 1: Multi-Vector Representations for Textual Data"
|
||||
short_description: "Module 1: late interaction with ColBERT, MaxSim scoring, multi-vector use cases, and the practical challenges of running them in Qdrant."
|
||||
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
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: "Late Interaction Basics"
|
||||
short_description: "Compare no-interaction, early-interaction, and late-interaction retrieval to see why ColBERT-style multivectors outperform single-vector search."
|
||||
description: Understand the late interaction paradigm and how it differs from traditional dense embeddings for text search.
|
||||
weight: 1
|
||||
isLesson: true
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: "MaxSim Distance Metric"
|
||||
short_description: "Understand the MaxSim distance metric for late interaction: how token-level matches aggregate into a single score for multi-vector retrieval."
|
||||
description: Learn about the MaxSim distance metric used in multi-vector search and how it computes similarity between multi-vector representations.
|
||||
weight: 2
|
||||
isLesson: true
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: "Multi-Vector Embeddings in Qdrant"
|
||||
short_description: "Configure Qdrant collections for multi-vector search: enable MaxSim, index ColBERT-style embeddings, and run late-interaction queries."
|
||||
description: Configure Qdrant collections for multi-vector embeddings and learn how to index and query multi-vector data.
|
||||
weight: 5
|
||||
isLesson: true
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: "Problems of Multi-Vector Search"
|
||||
short_description: "Understand the trade-offs of multi-vector search: HNSW incompatibility, asymmetric MaxSim, and the storage and compute overhead per document."
|
||||
description: Understand the challenges and limitations of multi-vector search at scale, including memory and performance considerations.
|
||||
weight: 4
|
||||
isLesson: true
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: "Use Cases for Multi-Vector Search"
|
||||
short_description: "See when multi-vector search outperforms single-vector embeddings: token-level matching for precise, fine-grained retrieval on complex queries."
|
||||
description: Discover scenarios where multi-vector search outperforms single-vector embeddings and provides better retrieval quality.
|
||||
weight: 3
|
||||
isLesson: true
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: "Module 2: Multi-Vector Representations for Multi-Modal Data"
|
||||
short_description: "Module 2: extend multi-vector search to images and PDFs with ColPali, vision-language models, and visual interpretability."
|
||||
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
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: "ColPali Family Overview"
|
||||
short_description: "Compare ColPali variants for visual document retrieval, from compact ColSmol and ColFlor to multilingual models, and pick the right fit."
|
||||
description: Explore the ColPali model family and their capabilities for multi-modal document understanding and retrieval.
|
||||
weight: 2
|
||||
isLesson: true
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: "How ColPali Models Work"
|
||||
short_description: "Learn how ColPali turns document images into multi-vector representations, retrieving from PDFs, charts, and tables without an OCR step."
|
||||
description: Understand the inner workings of ColPali models and how they generate multi-vector representations for images and documents.
|
||||
weight: 1
|
||||
isLesson: true
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: "Visual Interpretability of ColPali"
|
||||
short_description: "Visualize ColPali matches by mapping query tokens to image patches, making multi-modal retrieval results inspectable and debuggable."
|
||||
description: Learn how to visualize and interpret ColPali embeddings to understand what the model focuses on in images.
|
||||
weight: 3
|
||||
isLesson: true
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: "Module 3: Scalability and Optimization"
|
||||
short_description: "Module 3: scale multi-vector search with quantization, pooling, MUVERA indexing, multi-stage retrieval, and pipeline evaluation."
|
||||
description: "Address scalability challenges in multi-vector search. Learn optimization techniques including quantization, pooling, MUVERA, and multi-stage retrieval."
|
||||
isLesson: true
|
||||
weight: 40
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: "Evaluating Search Pipelines"
|
||||
short_description: "Evaluate retrieval pipelines with Recall@k, NDCG, and MRR using qrels to balance cost, latency, and search quality across configurations."
|
||||
description: Learn how to evaluate different search configurations in terms of cost, latency, and retrieval quality using ground truth datasets and standardized metrics.
|
||||
weight: 5
|
||||
isLesson: true
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: "Final Project: Build Your Own Multi-Vector Search System"
|
||||
short_description: "Capstone project: build an end-to-end multi-vector search system with ColPali, optimization techniques, and a measurable quality benchmark."
|
||||
description: Apply everything you've learned to build a multi-vector search system that solves a real problem of your choosing.
|
||||
weight: 7
|
||||
isLesson: true
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: "Multi-Stage Retrieval with Universal Query API"
|
||||
short_description: "Build multi-stage retrieval with the Universal Query API: prefetch with fast vectors, then rerank with ColBERT for high-quality results."
|
||||
description: Combine multiple optimization techniques in multi-stage retrieval pipelines using Qdrant's Universal Query API.
|
||||
weight: 1
|
||||
isLesson: true
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: "MUVERA"
|
||||
short_description: "Use MUVERA to approximate multi-vector documents as single vectors so HNSW can index them, enabling fast late-interaction retrieval at scale."
|
||||
description: Understand MUVERA and how it enables HNSW indexing for multi-vector search despite MaxSim asymmetry.
|
||||
weight: 4
|
||||
isLesson: true
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: "Pooling Techniques"
|
||||
short_description: "Apply pooling to multi-vector documents to cut the number of vectors per document while preserving late-interaction retrieval quality."
|
||||
description: Reduce the number of vectors per document using row/column pooling and hierarchical token pooling strategies.
|
||||
weight: 3
|
||||
isLesson: true
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: "Vector Quantization Techniques"
|
||||
short_description: "Compress multi-vector embeddings with scalar, binary, and product quantization in Qdrant to slash memory cost without losing retrieval quality."
|
||||
description: Learn how to reduce memory usage with scalar quantization, binary quantization, and other compression methods.
|
||||
weight: 2
|
||||
isLesson: true
|
||||
|
||||
Reference in New Issue
Block a user