root
/
elasticsearch
mirror of https://github.com/elastic/elasticsearch.git
1
0
Fork 0
Code Issues Actions 1 Packages Projects Releases Wiki Activity
elasticsearch/docs/reference/ml/df-analytics/apis/ml-df-analytics-apis.asciidoc

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

40 lines
1.4 KiB
Plaintext
Raw Normal View History

[DOCS] Changes level offset in data frame analytics APIs (#59919)
2020-07-21 03:11:47 +08:00
[role="xpack"]
[[ml-df-analytics-apis]]
= {ml-cap} {dfanalytics} APIs
[DOCS] Drafts trained model deployment APIs (#75497)
2021-07-27 00:49:37 +08:00
You can use the following APIs to perform {ml} {dfanalytics} activities:
[DOCS] Changes level offset in data frame analytics APIs (#59919)
2020-07-21 03:11:47 +08:00
* <<put-dfanalytics,Create {dfanalytics-jobs}>>
* <<delete-dfanalytics,Delete {dfanalytics-jobs}>>
* <<get-dfanalytics,Get {dfanalytics-jobs} info>>
* <<get-dfanalytics-stats,Get {dfanalytics-jobs} statistics>>
* <<evaluate-dfanalytics,Evaluate {dfanalytics}>>
* <<explain-dfanalytics,Explain {dfanalytics}>>
[DOCS] Drafts trained model deployment APIs (#75497)
2021-07-27 00:49:37 +08:00
* <<preview-dfanalytics,Preview {dfanalytics}>>
* <<start-dfanalytics,Start {dfanalytics-jobs}>>
* <<stop-dfanalytics,Stop {dfanalytics-jobs}>>
* <<update-dfanalytics,Update {dfanalytics-jobs}>>
[DOCS] Changes level offset in data frame analytics APIs (#59919)
2020-07-21 03:11:47 +08:00
[DOCS] Drafts trained model deployment APIs (#75497)
2021-07-27 00:49:37 +08:00
You can use the following APIs to perform {infer} operations:
[DOCS] Changes level offset in data frame analytics APIs (#59919)
2020-07-21 03:11:47 +08:00
[ML] renames */inference* apis to */trained_models* (#63097) This commit renames all `inference` CRUD APIs to `trained_models`. This aligns with internal terminology, documentation, and use-cases.
2020-10-02 00:13:49 +08:00
* <<put-trained-models>>
[ML] creating new PUT model definition part API (#76987) This commit simplifies the interactions for uploading chunked model definitions and model vocabulary.
2021-09-07 20:22:52 +08:00
* <<put-trained-model-definition-part>>
[ML] adding new PUT trained model vocabulary endpoint (#77387) This commit removes the ability to set the vocabulary location in the model config. This opts instead for sane defaults to be set and used. Wrapping this up in an API. The index is now always the internally managed .ml-inference-native index and the document ID is always <model_id>_vocabulary This API only works for pytorch/nlp type models.
2021-09-08 22:21:45 +08:00
* <<put-trained-model-vocabulary>>
[ML] adds new trained model alias API to simplify trained model updates and deployments (#68922) A `model_alias` allows trained models to be referred by a user defined moniker. This not only improves the readability and simplicity of numerous API calls, but it allows for simpler deployment and upgrade procedures for trained models. Previously, if you referenced a model ID directly within an ingest pipeline, when you have a new model that performs better than an earlier referenced model, you have to update the pipeline itself. If this model was used in numerous pipelines, ALL those pipelines would have to be updated. When using a `model_alias` in an ingest pipeline, only that `model_alias` needs to be updated. Then, the underlying referenced model will change in place for all ingest pipelines automatically. An additional benefit is that the model referenced is not changed until it is fully loaded into cache, this way throughput is not hampered by changing models.
2021-02-18 22:41:50 +08:00
* <<put-trained-models-aliases>>
[DOCS] Drafts trained model deployment APIs (#75497)
2021-07-27 00:49:37 +08:00
* <<delete-trained-models>>
[ML] add new delete trained model aliases API (#69195) In addition to creating and re-assigning model aliases, users should be able to delete existing and unused model aliases.
2021-02-19 02:12:07 +08:00
* <<delete-trained-models-aliases>>
[DOCS] Drafts trained model deployment APIs (#75497)
2021-07-27 00:49:37 +08:00
* <<get-trained-models>>
* <<get-trained-models-stats>>
[DOCS] Changes level offset in data frame analytics APIs (#59919)
2020-07-21 03:11:47 +08:00
[ML] adds new trained model alias API to simplify trained model updates and deployments (#68922) A `model_alias` allows trained models to be referred by a user defined moniker. This not only improves the readability and simplicity of numerous API calls, but it allows for simpler deployment and upgrade procedures for trained models. Previously, if you referenced a model ID directly within an ingest pipeline, when you have a new model that performs better than an earlier referenced model, you have to update the pipeline itself. If this model was used in numerous pipelines, ALL those pipelines would have to be updated. When using a `model_alias` in an ingest pipeline, only that `model_alias` needs to be updated. Then, the underlying referenced model will change in place for all ingest pipelines automatically. An additional benefit is that the model referenced is not changed until it is fully loaded into cache, this way throughput is not hampered by changing models.
2021-02-18 22:41:50 +08:00
You can deploy a trained model to make predictions in an ingest pipeline or in
[DOCS] Drafts trained model deployment APIs (#75497)
2021-07-27 00:49:37 +08:00
an aggregation. Refer to the following documentation to learn more:
[DOCS] Improves inference processor linking and docs (#66119)
2021-01-05 16:42:06 +08:00
* <<search-aggregations-pipeline-inference-bucket-aggregation,{infer-cap} bucket aggregation>>
[DOCS] Drafts trained model deployment APIs (#75497)
2021-07-27 00:49:37 +08:00
* <<inference-processor,{infer-cap} processor>>
* <<infer-trained-model-deployment>>
* <<start-trained-model-deployment>>
* <<stop-trained-model-deployment>>
[DOCS] Improves inference processor linking and docs (#66119)
2021-01-05 16:42:06 +08:00
[DOCS] Changes level offset in data frame analytics APIs (#59919)
2020-07-21 03:11:47 +08:00
See also <<ml-apis>>.