# Inference processor PUT error

**URL:** <https://discuss.elastic.co/t/inference-processor-put-error/228674>\
**Category:** Elasticsearch\
**Tags:** elastic-stack-machine-learning\
**Created:** [April 18, 2020, 7:07pm UTC](https://discuss.elastic.co/t/inference-processor-put-error/228674 "2020-04-18T19:07:43Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![Cain310](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/cain310/32/53115_2.png) [@Cain310](https://discuss.elastic.co/u/Cain310)\
**Post date:** [April 18, 2020, 7:07pm UTC](https://discuss.elastic.co/t/inference-processor-put-error/228674/1 "2020-04-18T19:07:43Z")

</div>

I am trying to create a pipeline with the inference processor using my ML model for a continuous transform and i keep getting 400 error.

version: 7.6.2

```auto
PUT /_ingest/pipeline/ml_pipeline
{
  "pipeline": {
    "description" : "ml_pipeline",
    "processors": [
      {
        "inference": {
          "model_id": "ml_analysis-xxx",
          "inference_config": {
            "classification": {
              "num_top_classes": 2,
              "results_field": "prediction",
              "top_classes_results_field": "probabilities"
            }
          },
          "field_mappings": {}
        }
      }
    ]
  }
}

```

```auto
{
  "error" : {
    "root_cause" : [
      {
        "type" : "parse_exception",
        "reason" : "[processors] required property is missing",
        "property_name" : "processors"
      }
    ],
    "type" : "parse_exception",
    "reason" : "[processors] required property is missing",
    "property_name" : "processors"
  },
  "status" : 400
}

```

---

<div class="post-metadata">

**Author:** ![Cain310](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/cain310/32/53115_2.png) [@Cain310](https://discuss.elastic.co/u/Cain310)\
**Post date:** [April 19, 2020, 3:42pm UTC](https://discuss.elastic.co/t/inference-processor-put-error/228674/2 "2020-04-19T15:42:01Z")

</div>

The solution is to remove the pipeline wrapper object.

```auto
PUT /_ingest/pipeline/ml_pipeline
{
  "description": "ml_pipeline",
  "processors": [
    {
      "inference": {
        "model_id": "ml_analysis-xxx",
        "field_mappings": {},
        "inference_config": {
          "classification": {
            "num_top_classes": 2,
            "results_field": "prediction",
            "top_classes_results_field": "probabilities"
          }
        }
      }
    }
  ]
}

```

---

<div class="post-metadata">

**Author:** ![system](https://us1.discourse-cdn.com/elastic/original/3X/1/a/1ac57faf039f6b580b3f104ef42a2a89e41014de.png) [@system](https://discuss.elastic.co/u/system)\
**Post date:** [May 17, 2020, 3:42pm UTC](https://discuss.elastic.co/t/inference-processor-put-error/228674/3 "2020-05-17T15:42:02Z")

</div>

This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.