mirror of
https://github.com/qdrant/landing_page.git
synced 2026-10-05 10:58:32 +02:00
Remove memory implications from Module 3
This commit is contained in:
@@ -15,11 +15,10 @@ Tackle the memory and performance challenges of production-scale multi-vector se
|
|||||||
|
|
||||||
## Today's path
|
## Today's path
|
||||||
|
|
||||||
1. Memory Usage Implications and Solutions
|
1. Multi-Stage Retrieval with Universal Query API
|
||||||
2. Vector Quantization Techniques
|
2. Vector Quantization Techniques
|
||||||
3. Pooling Techniques
|
3. Pooling Techniques
|
||||||
4. MUVERA
|
4. MUVERA
|
||||||
5. Multi-Stage Retrieval with Universal Query API
|
5. Evaluating Search Pipelines
|
||||||
6. Evaluating Search Pipelines
|
|
||||||
|
|
||||||
You'll master the optimization strategies needed to deploy multi-vector search at scale.
|
You'll master the optimization strategies needed to deploy multi-vector search at scale.
|
||||||
|
|||||||
@@ -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.
|
description: Learn how to evaluate different search configurations in terms of cost, latency, and retrieval quality.
|
||||||
weight: 6
|
weight: 5
|
||||||
---
|
---
|
||||||
|
|
||||||
{{< date >}} Module 3 {{< /date >}}
|
{{< date >}} Module 3 {{< /date >}}
|
||||||
|
|||||||
@@ -1,29 +0,0 @@
|
|||||||
---
|
|
||||||
title: "Memory Usage Implications"
|
|
||||||
description: Understand the memory challenges of multi-vector search and overview of optimization techniques.
|
|
||||||
weight: 1
|
|
||||||
---
|
|
||||||
|
|
||||||
{{< date >}} Module 3 {{< /date >}}
|
|
||||||
|
|
||||||
# Memory Usage Implications
|
|
||||||
|
|
||||||
Multi-vector search can consume 10-100x more memory than single-vector search. Before deploying to production, you need to understand why this happens and what you can do about it.
|
|
||||||
|
|
||||||
This lesson sets the stage for the optimization techniques we'll explore in the rest of Module 3.
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
<div class="video">
|
|
||||||
<iframe
|
|
||||||
src="https://www.youtube.com/embed/dQw4w9WgXcQ"
|
|
||||||
frameborder="0"
|
|
||||||
allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share"
|
|
||||||
referrerpolicy="strict-origin-when-cross-origin"
|
|
||||||
allowfullscreen>
|
|
||||||
</iframe>
|
|
||||||
</div>
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
Let's start optimizing. First up: vector quantization techniques to reduce memory usage.
|
|
||||||
@@ -1,7 +1,7 @@
|
|||||||
---
|
---
|
||||||
title: "Multi-Stage Retrieval with Universal Query API"
|
title: "Multi-Stage Retrieval with Universal Query API"
|
||||||
description: Combine multiple optimization techniques in multi-stage retrieval pipelines using Qdrant's Universal Query API.
|
description: Combine multiple optimization techniques in multi-stage retrieval pipelines using Qdrant's Universal Query API.
|
||||||
weight: 5
|
weight: 1
|
||||||
---
|
---
|
||||||
|
|
||||||
{{< date >}} Module 3 {{< /date >}}
|
{{< date >}} Module 3 {{< /date >}}
|
||||||
|
|||||||
Reference in New Issue
Block a user