mirror of
https://github.com/elastic/elasticsearch.git
synced 2025-06-29 01:44:36 -04:00
0059c59e25
Categorization jobs created once the entire cluster is upgraded to version 7.14 or higher will default to using the new ml_standard tokenizer rather than the previous default of the ml_classic tokenizer, and will incorporate the new first_non_blank_line char filter so that categorization is based purely on the first non-blank line of each message. The difference between the ml_classic and ml_standard tokenizers is that ml_classic splits on slashes and colons, so creates multiple tokens from URLs and filesystem paths, whereas ml_standard attempts to keep URLs, email addresses and filesystem paths as single tokens. It is still possible to config the ml_classic tokenizer if you prefer: just provide a categorization_analyzer within your analysis_config and whichever tokenizer you choose (which could be ml_classic or any other Elasticsearch tokenizer) will be used. To opt out of using first_non_blank_line as a default char filter, you must explicitly specify a categorization_analyzer that does not include it. If no categorization_analyzer is specified but categorization_filters are specified then the categorization filters are converted to char filters applied that are applied after first_non_blank_line. Closes elastic/ml-cpp#1724
128 lines
3.3 KiB
Text
128 lines
3.3 KiB
Text
[role="xpack"]
|
|
[testenv="platinum"]
|
|
[[get-ml-info]]
|
|
= Get machine learning info API
|
|
|
|
[subs="attributes"]
|
|
++++
|
|
<titleabbrev>Get {ml} info</titleabbrev>
|
|
++++
|
|
|
|
Returns defaults and limits used by machine learning.
|
|
|
|
[[get-ml-info-request]]
|
|
== {api-request-title}
|
|
|
|
`GET _ml/info`
|
|
|
|
[[get-ml-info-prereqs]]
|
|
== {api-prereq-title}
|
|
|
|
Requires the `monitor_ml` cluster privilege. This privilege is included in the
|
|
`machine_learning_user` built-in role.
|
|
|
|
[[get-ml-info-desc]]
|
|
== {api-description-title}
|
|
|
|
This endpoint is designed to be used by a user interface that needs to fully
|
|
understand machine learning configurations where some options are not specified,
|
|
meaning that the defaults should be used. This endpoint may be used to find out
|
|
what those defaults are. It also provides information about the maximum size
|
|
of {ml} jobs that could run in the current cluster configuration.
|
|
|
|
[[get-ml-info-example]]
|
|
== {api-examples-title}
|
|
|
|
The endpoint takes no arguments:
|
|
|
|
[source,console]
|
|
--------------------------------------------------
|
|
GET _ml/info
|
|
--------------------------------------------------
|
|
// TEST
|
|
|
|
This is a possible response:
|
|
|
|
[source,console-result]
|
|
----
|
|
{
|
|
"defaults" : {
|
|
"anomaly_detectors" : {
|
|
"categorization_analyzer" : {
|
|
"char_filter" : [
|
|
"first_non_blank_line"
|
|
],
|
|
"tokenizer" : "ml_standard",
|
|
"filter" : [
|
|
{
|
|
"type" : "stop",
|
|
"stopwords" : [
|
|
"Monday",
|
|
"Tuesday",
|
|
"Wednesday",
|
|
"Thursday",
|
|
"Friday",
|
|
"Saturday",
|
|
"Sunday",
|
|
"Mon",
|
|
"Tue",
|
|
"Wed",
|
|
"Thu",
|
|
"Fri",
|
|
"Sat",
|
|
"Sun",
|
|
"January",
|
|
"February",
|
|
"March",
|
|
"April",
|
|
"May",
|
|
"June",
|
|
"July",
|
|
"August",
|
|
"September",
|
|
"October",
|
|
"November",
|
|
"December",
|
|
"Jan",
|
|
"Feb",
|
|
"Mar",
|
|
"Apr",
|
|
"May",
|
|
"Jun",
|
|
"Jul",
|
|
"Aug",
|
|
"Sep",
|
|
"Oct",
|
|
"Nov",
|
|
"Dec",
|
|
"GMT",
|
|
"UTC"
|
|
]
|
|
}
|
|
]
|
|
},
|
|
"model_memory_limit" : "1gb",
|
|
"categorization_examples_limit" : 4,
|
|
"model_snapshot_retention_days" : 10,
|
|
"daily_model_snapshot_retention_after_days" : 1
|
|
},
|
|
"datafeeds" : {
|
|
"scroll_size" : 1000
|
|
}
|
|
},
|
|
"upgrade_mode": false,
|
|
"native_code" : {
|
|
"version": "7.0.0",
|
|
"build_hash": "99a07c016d5a73"
|
|
},
|
|
"limits" : {
|
|
"effective_max_model_memory_limit": "28961mb",
|
|
"total_ml_memory": "86883mb"
|
|
}
|
|
}
|
|
----
|
|
// TESTRESPONSE[s/"upgrade_mode": false/"upgrade_mode": $body.upgrade_mode/]
|
|
// TESTRESPONSE[s/"version": "7.0.0",/"version": "$body.native_code.version",/]
|
|
// TESTRESPONSE[s/"build_hash": "99a07c016d5a73"/"build_hash": "$body.native_code.build_hash"/]
|
|
// TESTRESPONSE[s/"effective_max_model_memory_limit": "28961mb"/"effective_max_model_memory_limit": "$body.limits.effective_max_model_memory_limit"/]
|
|
// TESTRESPONSE[s/"total_ml_memory": "86883mb"/"total_ml_memory": "$body.limits.total_ml_memory"/]
|