krzysztof/landing_page
1
0
Fork 0
mirror of https://github.com/qdrant/landing_page.git synced 2026-09-28 15:38:33 +02:00
Code Issues Packages Projects Releases Wiki Activity

Update qdrant-landing/content/blog/binary-quantization-openai.md

Browse Source
This commit is contained in:
Mike Jang
2024-02-21 06:03:03 -08:00
committed by GitHub
parent be8a401184
commit 7e9717f9e1
1 changed files with 0 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
qdrant-landing/content/blog/binary-quantization-openai.md
-4
View File
@@ -68,10 +68,6 @@ We use 100K random samples from the [OpenAI 1M](https://huggingface.co/datasets/
For each record, we run a parameter sweep over the number of oversampling, rescoring, and search limits. We can then understand the impact of these parameters on search accuracy and efficiency. Our experiment was designed to assess the impact of Binary Quantization under various conditions, based on the following parameters:
- Oversampling
- Rescoring
- Search limits
- **Oversampling**: By oversampling, we can limit the loss of information inherent in quantization. This also helps to preserve the semantic richness of your OpenAI embeddings. We experimented with different oversampling factors, and identified the impact on the accuracy and efficiency of search. Spoiler: higher oversampling factors tend to improve the accuracy of searches. However, they usually require more computational resources.
- **Rescoring**: Rescoring refines the first results of an initial binary search. This process leverages the original high-dimensional vectors to refine the search results, **always** improving accuracy. We toggled rescoring on and off to measure effectiveness, when combined with Binary Quantization. We also measured the impact on search performance.