Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[DOCS] Update re-ranking intro to remove confusion about stages #114302

Merged
merged 2 commits into from
Oct 8, 2024
Merged

[DOCS] Update re-ranking intro to remove confusion about stages #114302

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3417e65
[DOCS] Update re-ranking intro to remove confusion about stages
leemthompo Oct 8, 2024
3dcac01
Kelsey Grammar
leemthompo Oct 8, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 7 additions & 7 deletions docs/reference/reranking/index.asciidoc
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,12 +1,12 @@
[[re-ranking-overview]]
= Re-ranking

Many search systems are built on two-stage retrieval pipelines.
Many search systems are built on multi-stage retrieval pipelines.

The first stage uses cheap, fast algorithms to find a broad set of possible matches.
Earlier stages use cheap, fast algorithms to find a broad set of possible matches.

The second stage uses a more powerful model, often machine learning-based, to reorder the documents.
This second step is called re-ranking.
Later stages use more powerful models, often machine learning-based, to reorder the documents.
This step is called re-ranking.
Because the resource-intensive model is only applied to the smaller set of pre-filtered results, this approach returns more relevant results while still optimizing for search performance and computational costs.

{es} supports various ranking and re-ranking techniques to optimize search relevance and performance.
Expand All @@ -18,7 +18,7 @@ Because the resource-intensive model is only applied to the smaller set of pre-f

[float]
[[re-ranking-first-stage-pipeline]]
=== First stage: initial retrieval
=== Initial retrieval

[float]
[[re-ranking-ranking-overview-bm25]]
Expand All @@ -45,7 +45,7 @@ Hybrid search techniques combine results from full-text and vector search pipeli

[float]
[[re-ranking-overview-second-stage]]
=== Second stage: Re-ranking
=== Re-ranking

When using the following advanced re-ranking pipelines, first-stage retrieval mechanisms effectively generate a set of candidates.
These candidates are funneled into the re-ranker to perform more computationally expensive re-ranking tasks.
Expand All @@ -67,4 +67,4 @@ Learning To Rank involves training a machine learning model to build a ranking f
LTR is best suited for when you have ample training data and need highly customized relevance tuning.

include::semantic-reranking.asciidoc[]
include::learning-to-rank.asciidoc[]
include::learning-to-rank.asciidoc[]
Loading