This change adds the recall@k metric and refactors precision@k to match
the new metric.
Recall@k is an important metric to use for learning to rank (LTR)
use-cases. Candidate generation or first ranking phase ranking functions
are often optimized for high recall, in order to generate as many
relevant candidates in the top-k as possible for a second phase of
ranking. Adding this metric allows tuning that base query for LTR.
See: https://github.com/elastic/elasticsearch/issues/51676
Backports: https://github.com/elastic/elasticsearch/pull/52577
Add default value to each one of the usages of `allow_no_indices`
since it differs between different APIs.
Relates to: #52534
(cherry picked from commit 2eb986488ac326d6da6ab8ad0203a94e08684a36)
Several files in the REST APIs nav section are included using
:leveloffset: tags. This increments headings (h2 -> h3, h3 -> h4, etc.)
in those files and removes the :leveloffset: tags.
Other supporting changes:
* Alphabetizes top-level REST API nav items.
* Change 'indices APIs' heading to 'index APIs.'
* Changes 'Snapshot lifecycle management' heading to sentence case.
The notion of "quality" is an overloaded term in the search ranking evaluation
context. Its usually used to decribe certain levels of "good" vs. "bad" of a
seach result with respect to the users information need. We currently report the
result of the ranking evaluation as `quality_level` which is a bit missleading.
This changes the response parameter name to `metric_score` which fits better.
Currently the ranking evaluation response contains a 'unknown_docs' section
for each search use case in the evaluation set. It contains document ids for
results in the search hits that currently don't have a quality rating.
This change renames it to `unrated_docs`, which better reflects its purpose.
The rank_eval documentation was missing an explanation of the parameter
`k` that controls the number of top hits that are used in the ranking evaluation.
Closes#29205
This change adds support for the new ranking evaluation API to the High Level Rest Client.
This mostly means adding support for parsing the various response objects back from the
REST representation. It includes one change to the response syntax where previously we didn't
print the type of the metric details section but we now need it to pick the right parser to
parse this section back.
Closes#28198
Problem: So far all rank eval requests are being executed in parallel. If there
are more than the search thread pool can handle, or if there are other search
requests executed in parallel rank eval can fail.
Solution: Make number of max_concurrent_searches configurable.
Name of configuration parameter is analogous to msearch. Default
max_concurrent_searches set to 10: Rank_eval isn't particularly time critical so
trying to avoid being more clever than probably needed here. Can set this value
through the API to a higher value anytime.
Fixes#21403
Problem: We introduced the ability to shorten the rank eval request by using a
template in #20231. When playing with the API it turned out that there might be
use cases where - e.g. due to various heuristics - folks might want to translate
the original user query into more than just one type of Elasticsearch query.
Solution: Give each template an id that can later be referenced in the
actual requests.
Closes#21257
* Reference documentation for rank evaluation API
This adds a first page of reference documentation to the current state of the
rank evaluation API.
Closes to #21402
* Add default values for precision metric.
Add information on default relevant_rating_threshold and ignore_unlabeled
settings.
Relates to #21304
* Move under search request docs, fix formatting
Also removes some detail where it seemed unneeded for reference docs
James Rodewig
James Rodewig
Lisa Cawley
Josh Devins
Marios Trivyzas
Jess
Christoph Büscher
István Zoltán Szabó
Jesse Wright
Josh Soref
Christoph Büscher
Christoph Büscher
Christoph Büscher
Isabel Drost-Fromm
Isabel Drost-Fromm