elasticsearch/docs/reference/tab-widgets/inference-api/infer-api-reindex.asciidoc

// tag::cohere[]

[source,console]
----
POST _reindex?wait_for_completion=false
{
  "source": {
    "index": "test-data",
    "size": 50 <1>
  },
  "dest": {
    "index": "cohere-embeddings",
    "pipeline": "cohere_embeddings_pipeline"
  }
}
----
// TEST[skip:TBD]
<1> The default batch size for reindexing is 1000. Reducing `size` to a smaller
number makes the update of the reindexing process quicker which enables you to
follow the progress closely and detect errors early.

NOTE: The
https://dashboard.cohere.com/billing[rate limit of your Cohere account]
may affect the throughput of the reindexing process.

// end::cohere[]

// tag::elser[]

[source,console]
----
POST _reindex?wait_for_completion=false
{
  "source": {
    "index": "test-data",
    "size": 50 <1>
  },
  "dest": {
    "index": "elser-embeddings",
    "pipeline": "elser_embeddings_pipeline"
  }
}
----
// TEST[skip:TBD]
<1> The default batch size for reindexing is 1000. Reducing `size` to a smaller
number makes the update of the reindexing process quicker which enables you to
follow the progress closely and detect errors early.

// end::elser[]

// tag::hugging-face[]

[source,console]
----
POST _reindex?wait_for_completion=false
{
  "source": {
    "index": "test-data",
    "size": 50 <1>
  },
  "dest": {
    "index": "hugging-face-embeddings",
    "pipeline": "hugging_face_embeddings_pipeline"
  }
}
----
// TEST[skip:TBD]
<1> The default batch size for reindexing is 1000. Reducing `size` to a smaller
number makes the update of the reindexing process quicker which enables you to
follow the progress closely and detect errors early.

// end::hugging-face[]


// tag::openai[]

[source,console]
----
POST _reindex?wait_for_completion=false
{
  "source": {
    "index": "test-data",
    "size": 50 <1>
  },
  "dest": {
    "index": "openai-embeddings",
    "pipeline": "openai_embeddings_pipeline"
  }
}
----
// TEST[skip:TBD]
<1> The default batch size for reindexing is 1000. Reducing `size` to a smaller
number makes the update of the reindexing process quicker which enables you to
follow the progress closely and detect errors early.

NOTE: The
https://platform.openai.com/account/limits[rate limit of your OpenAI account]
may affect the throughput of the reindexing process. If this happens, change
`size` to `3` or a similar value in magnitude.

// end::openai[]

// tag::azure-openai[]

[source,console]
----
POST _reindex?wait_for_completion=false
{
  "source": {
    "index": "test-data",
    "size": 50 <1>
  },
  "dest": {
    "index": "azure-openai-embeddings",
    "pipeline": "azure_openai_embeddings_pipeline"
  }
}
----
// TEST[skip:TBD]
<1> The default batch size for reindexing is 1000. Reducing `size` to a smaller
number makes the update of the reindexing process quicker which enables you to
follow the progress closely and detect errors early.

NOTE: The
https://learn.microsoft.com/en-us/azure/ai-services/openai/quotas-limits#quotas-and-limits-reference[rate limit of your Azure OpenAI account]
may affect the throughput of the reindexing process. If this happens, change
`size` to `3` or a similar value in magnitude.

// end::azure-openai[]

// tag::azure-ai-studio[]

[source,console]
----
POST _reindex?wait_for_completion=false
{
  "source": {
    "index": "test-data",
    "size": 50 <1>
  },
  "dest": {
    "index": "azure-ai-studio-embeddings",
    "pipeline": "azure_ai_studio_embeddings_pipeline"
  }
}
----
// TEST[skip:TBD]
<1> The default batch size for reindexing is 1000. Reducing `size` to a smaller
number makes the update of the reindexing process quicker which enables you to
follow the progress closely and detect errors early.

NOTE: Your Azure AI Studio model deployment may have rate limits in place that
might affect the throughput of the reindexing process. If this happens, change
`size` to `3` or a similar value in magnitude.

// end::azure-ai-studio[]

// tag::google-vertex-ai[]

[source,console]
----
POST _reindex?wait_for_completion=false
{
  "source": {
    "index": "test-data",
    "size": 50 <1>
  },
  "dest": {
    "index": "google-vertex-ai-embeddings",
    "pipeline": "google_vertex_ai_embeddings_pipeline"
  }
}
----
// TEST[skip:TBD]
<1> The default batch size for reindexing is 1000. Reducing `size` will make updates to the reindexing process faster. This enables you to
follow the progress closely and detect errors early.

// end::google-vertex-ai[]

// tag::mistral[]

[source,console]
----
POST _reindex?wait_for_completion=false
{
  "source": {
    "index": "test-data",
    "size": 50 <1>
  },
  "dest": {
    "index": "mistral-embeddings",
    "pipeline": "mistral_embeddings_pipeline"
  }
}
----
// TEST[skip:TBD]
<1> The default batch size for reindexing is 1000. Reducing `size` to a smaller
number makes the update of the reindexing process quicker which enables you to
follow the progress closely and detect errors early.

// end::mistral[]

// tag::amazon-bedrock[]

[source,console]
----
POST _reindex?wait_for_completion=false
{
  "source": {
    "index": "test-data",
    "size": 50 <1>
  },
  "dest": {
    "index": "amazon-bedrock-embeddings",
    "pipeline": "amazon_bedrock_embeddings_pipeline"
  }
}
----
// TEST[skip:TBD]
<1> The default batch size for reindexing is 1000. Reducing `size` to a smaller
number makes the update of the reindexing process quicker which enables you to
follow the progress closely and detect errors early.

// end::amazon-bedrock[]

// tag::alibabacloud-ai-search[]

[source,console]
----
POST _reindex?wait_for_completion=false
{
  "source": {
    "index": "test-data",
    "size": 50 <1>
  },
  "dest": {
    "index": "alibabacloud-ai-search-embeddings",
    "pipeline": "alibabacloud_ai_search_embeddings_pipeline"
  }
}
----
// TEST[skip:TBD]
<1> The default batch size for reindexing is 1000. Reducing `size` to a smaller
number makes the update of the reindexing process quicker which enables you to
follow the progress closely and detect errors early.

// end::alibabacloud-ai-search[]