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"
  }
}
----
// 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::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"
  }
}
----
// 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"
  }
}
----
// 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[]