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

Minor fixes

Browse Source
This commit is contained in:
Kacper Łukawski
2026-01-22 14:39:14 +01:00
parent 3d5fa5da35
commit d51e2b40b2
3 changed files with 5 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
qdrant-landing/content/course/multi-vector-search/module-3/_index.md
+2 -1
View File
@@ -20,5 +20,6 @@ Tackle the memory and performance challenges of production-scale multi-vector se
3. Pooling Techniques 3. Pooling Techniques
4. MUVERA 4. MUVERA
5. Evaluating Search Pipelines 5. Evaluating Search Pipelines
6. Final Project
You'll master the optimization strategies needed to deploy multi-vector search at scale. Eventually, you will utilize all the learned skills to build a real-world project implementing multi-vector search for multi-modal data. You'll master the optimization strategies needed to deploy multi-vector search at scale. The module concludes with a final project where you'll apply all the learned skills to build a real-world multi-vector search system for multi-modal data.
qdrant-landing/content/course/multi-vector-search/module-3/evaluating-pipelines.md
+1 -1
View File
@@ -1,7 +1,7 @@
--- ---
title: "Evaluating Search Pipelines" title: "Evaluating Search Pipelines"
description: Learn how to evaluate different search configurations in terms of cost, latency, and retrieval quality using ground truth datasets and standardized metrics. description: Learn how to evaluate different search configurations in terms of cost, latency, and retrieval quality using ground truth datasets and standardized metrics.
weight: 6 weight: 5
--- ---
{{< date >}} Module 3 {{< /date >}} {{< date >}} Module 3 {{< /date >}}
qdrant-landing/content/course/multi-vector-search/module-3/pooling-techniques.md
+2 -2
View File
@@ -164,7 +164,7 @@ from scipy.cluster.vq import kmeans2
# Embed a document image # Embed a document image
image_path = "images/financial-report.png" image_path = "images/financial-report.png"
embeddings = list(model.embed_images([image_path]))[0] embeddings = list(model.embed_image([image_path]))[0]
def hierarchical_pool(embeddings: np.ndarray, k: int) -> np.ndarray: def hierarchical_pool(embeddings: np.ndarray, k: int) -> np.ndarray:
"""Pool embeddings using k-means clustering.""" """Pool embeddings using k-means clustering."""
@@ -187,7 +187,7 @@ for k in [16, 32, 64, 128]:
## What's Next ## What's Next
You've learned two complementary strategies for reducing the number of vectors per document: This lesson covered two complementary strategies for reducing the number of vectors per document:
- **Row/column pooling**: Exploits spatial structure in image embeddings for a fixed reduction (32x for ColPali) - **Row/column pooling**: Exploits spatial structure in image embeddings for a fixed reduction (32x for ColPali)
- **Hierarchical pooling**: Content-adaptive clustering that works for any multi-vector representation - **Hierarchical pooling**: Content-adaptive clustering that works for any multi-vector representation