Files
3f7468b504 Add agent framework/throttling/hidden model/OS assistant and update conversational search documentation (#6354)
* Add agent framework documentation

Signed-off-by: Fanit Kolchina <[email protected]>

* Add hidden model and API updates

Signed-off-by: Fanit Kolchina <[email protected]>

* Vale error

Signed-off-by: Fanit Kolchina <[email protected]>

* Updated field names

Signed-off-by: Fanit Kolchina <[email protected]>

* Add updating credentials

Signed-off-by: Fanit Kolchina <[email protected]>

* Added tools table

Signed-off-by: Fanit Kolchina <[email protected]>

* Add OpenSearch forum thread for OS Assistant

Signed-off-by: Fanit Kolchina <[email protected]>

* Add tech review for conv search

Signed-off-by: Fanit Kolchina <[email protected]>

* Fix links

Signed-off-by: Fanit Kolchina <[email protected]>

* Add tools

Signed-off-by: Fanit Kolchina <[email protected]>

* Add links to tools

Signed-off-by: Fanit Kolchina <[email protected]>

* More info about tools

Signed-off-by: Fanit Kolchina <[email protected]>

* Tool parameters

Signed-off-by: Fanit Kolchina <[email protected]>

* Update cat-index-tool.md

Signed-off-by: kolchfa-aws <[email protected]>

* Parameter clarification

Signed-off-by: Fanit Kolchina <[email protected]>

* Tech review feedback

Signed-off-by: Fanit Kolchina <[email protected]>

* Typo fix

Signed-off-by: Fanit Kolchina <[email protected]>

* More tech review feedback: RAG tool

Signed-off-by: Fanit Kolchina <[email protected]>

* Tech review feedback: memory APis

Signed-off-by: Fanit Kolchina <[email protected]>

* Update _ml-commons-plugin/agents-tools/index.md

Co-authored-by: Melissa Vagi <[email protected]>
Signed-off-by: kolchfa-aws <[email protected]>

* Update _ml-commons-plugin/agents-tools/tools/neural-sparse-tool.md

Co-authored-by: Melissa Vagi <[email protected]>
Signed-off-by: kolchfa-aws <[email protected]>

* Update _ml-commons-plugin/agents-tools/tools/neural-sparse-tool.md

Co-authored-by: Melissa Vagi <[email protected]>
Signed-off-by: kolchfa-aws <[email protected]>

* Update _ml-commons-plugin/agents-tools/tools/neural-sparse-tool.md

Co-authored-by: Melissa Vagi <[email protected]>
Signed-off-by: kolchfa-aws <[email protected]>

* Update _ml-commons-plugin/opensearch-assistant.md

Co-authored-by: Melissa Vagi <[email protected]>
Signed-off-by: kolchfa-aws <[email protected]>

* Update _ml-commons-plugin/agents-tools/tools/ppl-tool.md

Co-authored-by: Melissa Vagi <[email protected]>
Signed-off-by: kolchfa-aws <[email protected]>

* Apply suggestions from code review

Co-authored-by: Melissa Vagi <[email protected]>
Signed-off-by: kolchfa-aws <[email protected]>

* Separated search and get APIs and add conversational flow agent

Signed-off-by: Fanit Kolchina <[email protected]>

* More parameters for PPL tool

Signed-off-by: Fanit Kolchina <[email protected]>

* Added more parameters

Signed-off-by: Fanit Kolchina <[email protected]>

* Tech review feedback: PPL tool

Signed-off-by: Fanit Kolchina <[email protected]>

* Apply suggestions from code review

Co-authored-by: Nathan Bower <[email protected]>
Signed-off-by: kolchfa-aws <[email protected]>

* Rename to automating configurations

Signed-off-by: Fanit Kolchina <[email protected]>

* Editorial comments on the new text

Signed-off-by: Fanit Kolchina <[email protected]>

* Add parameter to PPl tool

Signed-off-by: Fanit Kolchina <[email protected]>

* Changed link to configurations

Signed-off-by: Fanit Kolchina <[email protected]>

* Rate limiter feedback and added warning

Signed-off-by: Fanit Kolchina <[email protected]>

---------

Signed-off-by: Fanit Kolchina <[email protected]>
Signed-off-by: kolchfa-aws <[email protected]>
Co-authored-by: Melissa Vagi <[email protected]>
Co-authored-by: Nathan Bower <[email protected]>
2024-02-20 12:09:31 -05:00

4.5 KiB

layout, title, parent, grand_parent, nav_order
layout title parent grand_parent nav_order
default Train and predict Train and Predict APIs ML Commons APIs 10

Train and predict

Use to train and then immediately predict against the same training dataset. Can only be used with unsupervised learning models and the following algorithms:

  • BATCH_RCF
  • FIT_RCF
  • k-means

Example request: Train and predict with indexed data

POST /_plugins/_ml/_train_predict/kmeans
{
    "parameters": {
        "centroids": 2,
        "iterations": 10,
        "distance_type": "COSINE"
    },
    "input_query": {
        "query": {
            "bool": {
                "filter": [
                    {
                        "range": {
                            "k1": {
                                "gte": 0
                            }
                        }
                    }
                ]
            }
        },
        "size": 10
    },
    "input_index": [
        "test_data"
    ]
}

{% include copy-curl.html %}

Example request: Train and predict with data directly

POST /_plugins/_ml/_train_predict/kmeans
{
    "parameters": {
        "centroids": 2,
        "iterations": 1,
        "distance_type": "EUCLIDEAN"
    },
    "input_data": {
        "column_metas": [
            {
                "name": "k1",
                "column_type": "DOUBLE"
            },
            {
                "name": "k2",
                "column_type": "DOUBLE"
            }
        ],
        "rows": [
            {
                "values": [
                    {
                        "column_type": "DOUBLE",
                        "value": 1.00
                    },
                    {
                        "column_type": "DOUBLE",
                        "value": 2.00
                    }
                ]
            },
            {
                "values": [
                    {
                        "column_type": "DOUBLE",
                        "value": 1.00
                    },
                    {
                        "column_type": "DOUBLE",
                        "value": 4.00
                    }
                ]
            },
            {
                "values": [
                    {
                        "column_type": "DOUBLE",
                        "value": 1.00
                    },
                    {
                        "column_type": "DOUBLE",
                        "value": 0.00
                    }
                ]
            },
            {
                "values": [
                    {
                        "column_type": "DOUBLE",
                        "value": 10.00
                    },
                    {
                        "column_type": "DOUBLE",
                        "value": 2.00
                    }
                ]
            },
            {
                "values": [
                    {
                        "column_type": "DOUBLE",
                        "value": 10.00
                    },
                    {
                        "column_type": "DOUBLE",
                        "value": 4.00
                    }
                ]
            },
            {
                "values": [
                    {
                        "column_type": "DOUBLE",
                        "value": 10.00
                    },
                    {
                        "column_type": "DOUBLE",
                        "value": 0.00
                    }
                ]
            }
        ]
    }
}

{% include copy-curl.html %}

Example response

{
  "status" : "COMPLETED",
  "prediction_result" : {
    "column_metas" : [
      {
        "name" : "ClusterID",
        "column_type" : "INTEGER"
      }
    ],
    "rows" : [
      {
        "values" : [
          {
            "column_type" : "INTEGER",
            "value" : 1
          }
        ]
      },
      {
        "values" : [
          {
            "column_type" : "INTEGER",
            "value" : 1
          }
        ]
      },
      {
        "values" : [
          {
            "column_type" : "INTEGER",
            "value" : 1
          }
        ]
      },
      {
        "values" : [
          {
            "column_type" : "INTEGER",
            "value" : 0
          }
        ]
      },
      {
        "values" : [
          {
            "column_type" : "INTEGER",
            "value" : 0
          }
        ]
      },
      {
        "values" : [
          {
            "column_type" : "INTEGER",
            "value" : 0
          }
        ]
      }
    ]
  }
}