[skip ci]Update proxy reduce docs (#10256)

Signed-off-by: shiyu22 <shiyu.chen@zilliz.com>
pull/10304/head
shiyu22 2021-10-20 19:09:37 +08:00 committed by GitHub
parent 4d1e63470b
commit 11c9f86934
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions

View File

@ -4,7 +4,7 @@
For a specified Search request, with nq = 2 and topk = 10, Proxy received 4 search results from query nodes.
Each Search Result is nq \* topk two dimensional structureas the illustration below. The result indicates that the user has input NQ vectors and wants to obtain the TOPK most similar vectors to these NQ vectors respectively.
Each Search Result is nq \* topk two-dimensional structureas the illustration below. The result indicates that the user has input NQ vectors and wants to obtain the TOPK most similar vectors to these NQ vectors respectively.
![search_result_format](./figs/nq_topk_search_results.png)
@ -13,4 +13,4 @@ For each query, the top k hit results are in descending order of score. The larg
Therefore, we will only discuss how the proxy merges the results for one query result. For NQ query results, we can loop through NQ or process them in parallel.
So the problem degenerates to how to get the maximum number of 10 (TOPK) results from these four sorted arrays. As shown in the figure below:
![final_result](./figs/reduce_results.png)
![final_result](./figs/reduce_results.png)