The API accepts 3 different authentication methods:
Elasticsearch APIs support key-based authentication. You must create an API key and use the encoded value in the request header. For example:
curl -X GET "${ES_URL}/_cat/indices?v=true" \
-H "Authorization: ApiKey ${API_KEY}"
To get API keys, use the /_security/api_key APIs.
Elasticsearch APIs support the use of bearer tokens in the Authorization HTTP header to authenticate with the API.
For examples, refer to Token-based authentication services
PUT _application/analytics/my_analytics_collection
resp = client.search_application.put_behavioral_analytics(
name="my_analytics_collection",
)const response = await client.searchApplication.putBehavioralAnalytics({
name: "my_analytics_collection",
});response = client.search_application.put_behavioral_analytics(
name: "my_analytics_collection"
)$resp = $client->searchApplication()->putBehavioralAnalytics([
"name" => "my_analytics_collection",
]);curl -X PUT -H "Authorization: ApiKey $ELASTIC_API_KEY" "$ELASTICSEARCH_URL/_application/analytics/my_analytics_collection"client.searchApplication().putBehavioralAnalytics(p -> p
.name("my_analytics_collection")
);
The name of the behavioral analytics collection.
The analytics event type.
Values are page_view, search, or search_click.
POST _application/analytics/my_analytics_collection/event/search_click
{
"session": {
"id": "1797ca95-91c9-4e2e-b1bd-9c38e6f386a9"
},
"user": {
"id": "5f26f01a-bbee-4202-9298-81261067abbd"
},
"search":{
"query": "search term",
"results": {
"items": [
{
"document": {
"id": "123",
"index": "products"
}
}
],
"total_results": 10
},
"sort": {
"name": "relevance"
},
"search_application": "website"
},
"document":{
"id": "123",
"index": "products"
}
}resp = client.search_application.post_behavioral_analytics_event(
collection_name="my_analytics_collection",
event_type="search_click",
payload={
"session": {
"id": "1797ca95-91c9-4e2e-b1bd-9c38e6f386a9"
},
"user": {
"id": "5f26f01a-bbee-4202-9298-81261067abbd"
},
"search": {
"query": "search term",
"results": {
"items": [
{
"document": {
"id": "123",
"index": "products"
}
}
],
"total_results": 10
},
"sort": {
"name": "relevance"
},
"search_application": "website"
},
"document": {
"id": "123",
"index": "products"
}
},
)const response = await client.searchApplication.postBehavioralAnalyticsEvent({
collection_name: "my_analytics_collection",
event_type: "search_click",
payload: {
session: {
id: "1797ca95-91c9-4e2e-b1bd-9c38e6f386a9",
},
user: {
id: "5f26f01a-bbee-4202-9298-81261067abbd",
},
search: {
query: "search term",
results: {
items: [
{
document: {
id: "123",
index: "products",
},
},
],
total_results: 10,
},
sort: {
name: "relevance",
},
search_application: "website",
},
document: {
id: "123",
index: "products",
},
},
});response = client.search_application.post_behavioral_analytics_event(
collection_name: "my_analytics_collection",
event_type: "search_click",
body: {
"session": {
"id": "1797ca95-91c9-4e2e-b1bd-9c38e6f386a9"
},
"user": {
"id": "5f26f01a-bbee-4202-9298-81261067abbd"
},
"search": {
"query": "search term",
"results": {
"items": [
{
"document": {
"id": "123",
"index": "products"
}
}
],
"total_results": 10
},
"sort": {
"name": "relevance"
},
"search_application": "website"
},
"document": {
"id": "123",
"index": "products"
}
}
)$resp = $client->searchApplication()->postBehavioralAnalyticsEvent([
"collection_name" => "my_analytics_collection",
"event_type" => "search_click",
"body" => [
"session" => [
"id" => "1797ca95-91c9-4e2e-b1bd-9c38e6f386a9",
],
"user" => [
"id" => "5f26f01a-bbee-4202-9298-81261067abbd",
],
"search" => [
"query" => "search term",
"results" => [
"items" => array(
[
"document" => [
"id" => "123",
"index" => "products",
],
],
),
"total_results" => 10,
],
"sort" => [
"name" => "relevance",
],
"search_application" => "website",
],
"document" => [
"id" => "123",
"index" => "products",
],
],
]);curl -X POST -H "Authorization: ApiKey $ELASTIC_API_KEY" -H "Content-Type: application/json" -d '{"session":{"id":"1797ca95-91c9-4e2e-b1bd-9c38e6f386a9"},"user":{"id":"5f26f01a-bbee-4202-9298-81261067abbd"},"search":{"query":"search term","results":{"items":[{"document":{"id":"123","index":"products"}}],"total_results":10},"sort":{"name":"relevance"},"search_application":"website"},"document":{"id":"123","index":"products"}}' "$ELASTICSEARCH_URL/_application/analytics/my_analytics_collection/event/search_click"client.searchApplication().postBehavioralAnalyticsEvent(p -> p
.collectionName("my_analytics_collection")
.eventType(EventType.SearchClick)
.payload(JsonData.fromJson("{\"session\":{\"id\":\"1797ca95-91c9-4e2e-b1bd-9c38e6f386a9\"},\"user\":{\"id\":\"5f26f01a-bbee-4202-9298-81261067abbd\"},\"search\":{\"query\":\"search term\",\"results\":{\"items\":[{\"document\":{\"id\":\"123\",\"index\":\"products\"}}],\"total_results\":10},\"sort\":{\"name\":\"relevance\"},\"search_application\":\"website\"},\"document\":{\"id\":\"123\",\"index\":\"products\"}}"))
);
{
"session": {
"id": "1797ca95-91c9-4e2e-b1bd-9c38e6f386a9"
},
"user": {
"id": "5f26f01a-bbee-4202-9298-81261067abbd"
},
"search":{
"query": "search term",
"results": {
"items": [
{
"document": {
"id": "123",
"index": "products"
}
}
],
"total_results": 10
},
"sort": {
"name": "relevance"
},
"search_application": "website"
},
"document":{
"id": "123",
"index": "products"
}
}All methods and paths for this operation:
Get a snapshot of the number of shards allocated to each data node and their disk space.
IMPORTANT: CAT APIs are only intended for human consumption using the command line or Kibana console. They are not intended for use by applications.
monitorA comma-separated list of node identifiers or names used to limit the returned information.
The unit used to display byte values.
Values are b, kb, mb, gb, tb, or pb.
A comma-separated list of columns names to display. It supports simple wildcards.
Supported values include:
shards (or s): The number of shards on the node.shards.undesired: The number of shards scheduled to be moved elsewhere in the cluster.write_load.forecast (or wlf, writeLoadForecast): The sum of index write load forecasts.disk.indices.forecast (or dif, diskIndicesForecast): The sum of shard size forecasts.disk.indices (or di, diskIndices): The disk space used by Elasticsearch indices.disk.used (or du, diskUsed): The total disk space used on the node.disk.avail (or da, diskAvail): The available disk space on the node.disk.total (or dt, diskTotal): The total disk capacity of all volumes on the node.disk.percent (or dp, diskPercent): The percentage of disk space used on the node.host (or h): IThe host of the node.ip: The IP address of the node.node (or n): The name of the node.node.role (or r, role, nodeRole): The roles assigned to the node.Values are shards, s, shards.undesired, write_load.forecast, wlf, writeLoadForecast, disk.indices.forecast, dif, diskIndicesForecast, disk.indices, di, diskIndices, disk.used, du, diskUsed, disk.avail, da, diskAvail, disk.total, dt, diskTotal, disk.percent, dp, diskPercent, host, h, ip, node, n, node.role, r, role, or nodeRole.
List of columns that determine how the table should be sorted.
Sorting defaults to ascending and can be changed by setting :asc
or :desc as a suffix to the column name.
If true, the request computes the list of selected nodes from the
local cluster state. If false the list of selected nodes are computed
from the cluster state of the master node. In both cases the coordinating
node will send requests for further information to each selected node.
Period to wait for a connection to the master node.
Values are -1 or 0.
GET /_cat/allocation?v=true&format=json
resp = client.cat.allocation(
v=True,
format="json",
)const response = await client.cat.allocation({
v: "true",
format: "json",
});response = client.cat.allocation(
v: "true",
format: "json"
)$resp = $client->cat()->allocation([
"v" => "true",
"format" => "json",
]);curl -X GET -H "Authorization: ApiKey $ELASTIC_API_KEY" "$ELASTICSEARCH_URL/_cat/allocation?v=true&format=json"client.cat().allocation();
[
{
"shards": "1",
"shards.undesired": "0",
"write_load.forecast": "0.0",
"disk.indices.forecast": "260b",
"disk.indices": "260b",
"disk.used": "47.3gb",
"disk.avail": "43.4gb",
"disk.total": "100.7gb",
"disk.percent": "46",
"host": "127.0.0.1",
"ip": "127.0.0.1",
"node": "CSUXak2",
"node.role": "himrst"
}
]Get a list of plugins running on each node of a cluster. IMPORTANT: cat APIs are only intended for human consumption using the command line or Kibana console. They are not intended for use by applications. For application consumption, use the nodes info API.
monitorList of columns to appear in the response. Supports simple wildcards.
List of columns that determine how the table should be sorted.
Sorting defaults to ascending and can be changed by setting :asc
or :desc as a suffix to the column name.
Include bootstrap plugins in the response
If true, the request computes the list of selected nodes from the
local cluster state. If false the list of selected nodes are computed
from the cluster state of the master node. In both cases the coordinating
node will send requests for further information to each selected node.
Period to wait for a connection to the master node.
Values are -1 or 0.
GET /_cat/plugins?v=true&s=component&h=name,component,version,description&format=json
resp = client.cat.plugins(
v=True,
s="component",
h="name,component,version,description",
format="json",
)const response = await client.cat.plugins({
v: "true",
s: "component",
h: "name,component,version,description",
format: "json",
});response = client.cat.plugins(
v: "true",
s: "component",
h: "name,component,version,description",
format: "json"
)$resp = $client->cat()->plugins([
"v" => "true",
"s" => "component",
"h" => "name,component,version,description",
"format" => "json",
]);curl -X GET -H "Authorization: ApiKey $ELASTIC_API_KEY" "$ELASTICSEARCH_URL/_cat/plugins?v=true&s=component&h=name,component,version,description&format=json"client.cat().plugins();
[
{ "name": "U7321H6", "component": "analysis-icu", "version": "8.17.0", "description": "The ICU Analysis plugin integrates the Lucene ICU module into Elasticsearch, adding ICU-related analysis components."},
{"name": "U7321H6", "component": "analysis-kuromoji", "verison": "8.17.0", description: "The Japanese (kuromoji) Analysis plugin integrates Lucene kuromoji analysis module into elasticsearch."},
{"name" "U7321H6", "component": "analysis-nori", "version": "8.17.0", "description": "The Korean (nori) Analysis plugin integrates Lucene nori analysis module into elasticsearch."},
{"name": "U7321H6", "component": "analysis-phonetic", "verison": "8.17.0", "description": "The Phonetic Analysis plugin integrates phonetic token filter analysis with elasticsearch."},
{"name": "U7321H6", "component": "analysis-smartcn", "verison": "8.17.0", "description": "Smart Chinese Analysis plugin integrates Lucene Smart Chinese analysis module into elasticsearch."},
{"name": "U7321H6", "component": "analysis-stempel", "verison": "8.17.0", "description": "The Stempel (Polish) Analysis plugin integrates Lucene stempel (polish) analysis module into elasticsearch."},
{"name": "U7321H6", "component": "analysis-ukrainian", "verison": "8.17.0", "description": "The Ukrainian Analysis plugin integrates the Lucene UkrainianMorfologikAnalyzer into elasticsearch."},
{"name": "U7321H6", "component": "discovery-azure-classic", "verison": "8.17.0", "description": "The Azure Classic Discovery plugin allows to use Azure Classic API for the unicast discovery mechanism"},
{"name": "U7321H6", "component": "discovery-ec2", "verison": "8.17.0", "description": "The EC2 discovery plugin allows to use AWS API for the unicast discovery mechanism."},
{"name": "U7321H6", "component": "discovery-gce", "verison": "8.17.0", "description": "The Google Compute Engine (GCE) Discovery plugin allows to use GCE API for the unicast discovery mechanism."},
{"name": "U7321H6", "component": "mapper-annotated-text", "verison": "8.17.0", "description": "The Mapper Annotated_text plugin adds support for text fields with markup used to inject annotation tokens into the index."},
{"name": "U7321H6", "component": "mapper-murmur3", "verison": "8.17.0", "description": "The Mapper Murmur3 plugin allows to compute hashes of a field's values at index-time and to store them in the index."},
{"name": "U7321H6", "component": "mapper-size", "verison": "8.17.0", "description": "The Mapper Size plugin allows document to record their uncompressed size at index time."},
{"name": "U7321H6", "component": "store-smb", "verison": "8.17.0", "description": "The Store SMB plugin adds support for SMB stores."}
]Update the cluster voting config exclusions by node IDs or node names. By default, if there are more than three master-eligible nodes in the cluster and you remove fewer than half of the master-eligible nodes in the cluster at once, the voting configuration automatically shrinks. If you want to shrink the voting configuration to contain fewer than three nodes or to remove half or more of the master-eligible nodes in the cluster at once, use this API to remove departing nodes from the voting configuration manually. The API adds an entry for each specified node to the cluster’s voting configuration exclusions list. It then waits until the cluster has reconfigured its voting configuration to exclude the specified nodes.
Clusters should have no voting configuration exclusions in normal operation.
Once the excluded nodes have stopped, clear the voting configuration exclusions with DELETE /_cluster/voting_config_exclusions.
This API waits for the nodes to be fully removed from the cluster before it returns.
If your cluster has voting configuration exclusions for nodes that you no longer intend to remove, use DELETE /_cluster/voting_config_exclusions?wait_for_removal=false to clear the voting configuration exclusions without waiting for the nodes to leave the cluster.
A response to POST /_cluster/voting_config_exclusions with an HTTP status code of 200 OK guarantees that the node has been removed from the voting configuration and will not be reinstated until the voting configuration exclusions are cleared by calling DELETE /_cluster/voting_config_exclusions.
If the call to POST /_cluster/voting_config_exclusions fails or returns a response with an HTTP status code other than 200 OK then the node may not have been removed from the voting configuration.
In that case, you may safely retry the call.
NOTE: Voting exclusions are required only when you remove at least half of the master-eligible nodes from a cluster in a short time period. They are not required when removing master-ineligible nodes or when removing fewer than half of the master-eligible nodes.
A comma-separated list of the names of the nodes to exclude from the voting configuration. If specified, you may not also specify node_ids.
A comma-separated list of the persistent ids of the nodes to exclude from the voting configuration. If specified, you may not also specify node_names.
Period to wait for a connection to the master node.
Values are -1 or 0.
When adding a voting configuration exclusion, the API waits for the specified nodes to be excluded from the voting configuration before returning. If the timeout expires before the appropriate condition is satisfied, the request fails and returns an error.
Values are -1 or 0.
curl \
--request POST 'http://api.example.com/_cluster/voting_config_exclusions' \
--header "Authorization: $API_KEY"By default, it returns only settings that have been explicitly defined.
monitorIf true, returns settings in flat format.
If true, also returns default values for all other cluster settings, reflecting the values
in the elasticsearch.yml file of one of the nodes in the cluster. If the nodes in your
cluster do not all have the same values in their elasticsearch.yml config files then the
values returned by this API may vary from invocation to invocation and may not reflect the
values that Elasticsearch uses in all situations. Use the GET _nodes/settings API to
fetch the settings for each individual node in your cluster.
Period to wait for a connection to the master node. If no response is received before the timeout expires, the request fails and returns an error.
Values are -1 or 0.
Period to wait for a response. If no response is received before the timeout expires, the request fails and returns an error.
Values are -1 or 0.
GET /_cluster/settings?filter_path=persistent.cluster.remote
resp = client.cluster.get_settings(
filter_path="persistent.cluster.remote",
)const response = await client.cluster.getSettings({
filter_path: "persistent.cluster.remote",
});response = client.cluster.get_settings(
filter_path: "persistent.cluster.remote"
)$resp = $client->cluster()->getSettings([
"filter_path" => "persistent.cluster.remote",
]);curl -X GET -H "Authorization: ApiKey $ELASTIC_API_KEY" "$ELASTICSEARCH_URL/_cluster/settings?filter_path=persistent.cluster.remote"Configure and update dynamic settings on a running cluster.
You can also configure dynamic settings locally on an unstarted or shut down node in elasticsearch.yml.
Updates made with this API can be persistent, which apply across cluster restarts, or transient, which reset after a cluster restart. You can also reset transient or persistent settings by assigning them a null value.
If you configure the same setting using multiple methods, Elasticsearch applies the settings in following order of precedence: 1) Transient setting; 2) Persistent setting; 3) elasticsearch.yml setting; 4) Default setting value.
For example, you can apply a transient setting to override a persistent setting or elasticsearch.yml setting.
However, a change to an elasticsearch.yml setting will not override a defined transient or persistent setting.
TIP: In Elastic Cloud, use the user settings feature to configure all cluster settings. This method automatically rejects unsafe settings that could break your cluster.
If you run Elasticsearch on your own hardware, use this API to configure dynamic cluster settings.
Only use elasticsearch.yml for static cluster settings and node settings.
The API doesn’t require a restart and ensures a setting’s value is the same on all nodes.
WARNING: Transient cluster settings are no longer recommended. Use persistent cluster settings instead. If a cluster becomes unstable, transient settings can clear unexpectedly, resulting in a potentially undesired cluster configuration.
Return settings in flat format (default: false)
Explicit operation timeout for connection to master node
Values are -1 or 0.
Explicit operation timeout
Values are -1 or 0.
PUT /_cluster/settings
{
"persistent" : {
"indices.recovery.max_bytes_per_sec" : "50mb"
}
}resp = client.cluster.put_settings(
persistent={
"indices.recovery.max_bytes_per_sec": "50mb"
},
)const response = await client.cluster.putSettings({
persistent: {
"indices.recovery.max_bytes_per_sec": "50mb",
},
});response = client.cluster.put_settings(
body: {
"persistent": {
"indices.recovery.max_bytes_per_sec": "50mb"
}
}
)$resp = $client->cluster()->putSettings([
"body" => [
"persistent" => [
"indices.recovery.max_bytes_per_sec" => "50mb",
],
],
]);curl -X PUT -H "Authorization: ApiKey $ELASTIC_API_KEY" -H "Content-Type: application/json" -d '{"persistent":{"indices.recovery.max_bytes_per_sec":"50mb"}}' "$ELASTICSEARCH_URL/_cluster/settings"client.cluster().putSettings(p -> p
.persistent("indices.recovery.max_bytes_per_sec", JsonData.fromJson("\"50mb\""))
);
{
"persistent" : {
"indices.recovery.max_bytes_per_sec" : "50mb"
}
}{
"persistent": {
"action.auto_create_index": "my-index-000001,index10,-index1*,+ind*"
}
}Get repositories metering information for a cluster. This API exposes monotonically non-decreasing counters and it is expected that clients would durably store the information needed to compute aggregations over a period of time. Additionally, the information exposed by this API is volatile, meaning that it will not be present after node restarts.
monitor,managecurl \
--request GET 'http://api.example.com/_nodes/{node_id}/_repositories_metering' \
--header "Authorization: $API_KEY"All methods and paths for this operation:
Get statistics for nodes in a cluster. By default, all stats are returned. You can limit the returned information by using metrics.
monitor,manageComma-separated list of node IDs or names used to limit returned information.
Limit the information returned to the specified metrics
Limit the information returned for indices metric to the specific index metrics. It can be used only if indices (or all) metric is specified.
Comma-separated list or wildcard expressions of fields to include in fielddata and suggest statistics.
Comma-separated list or wildcard expressions of fields to include in fielddata statistics.
Comma-separated list or wildcard expressions of fields to include in the statistics.
Comma-separated list of search groups to include in the search statistics.
If true, the call reports the aggregated disk usage of each one of the Lucene index files (only applies if segment stats are requested).
Indicates whether statistics are aggregated at the cluster, index, or shard level.
Values are cluster, indices, or shards.
Period to wait for a response. If no response is received before the timeout expires, the request fails and returns an error.
Values are -1 or 0.
A comma-separated list of document types for the indexing index metric.
If true, the response includes information from segments that are not loaded into memory.
GET _nodes/stats/process?filter_path=**.max_file_descriptors
resp = client.nodes.stats(
metric="process",
filter_path="**.max_file_descriptors",
)const response = await client.nodes.stats({
metric: "process",
filter_path: "**.max_file_descriptors",
});response = client.nodes.stats(
metric: "process",
filter_path: "**.max_file_descriptors"
)$resp = $client->nodes()->stats([
"metric" => "process",
"filter_path" => "**.max_file_descriptors",
]);curl -X GET -H "Authorization: ApiKey $ELASTIC_API_KEY" "$ELASTICSEARCH_URL/_nodes/stats/process?filter_path=**.max_file_descriptors"Removes a connector and associated sync jobs. This is a destructive action that is not recoverable. NOTE: This action doesn’t delete any API keys, ingest pipelines, or data indices associated with the connector. These need to be removed manually.
DELETE _connector/my-connector-id&delete_sync_jobs=true
resp = client.connector.delete(
connector_id="my-connector-id&delete_sync_jobs=true",
)const response = await client.connector.delete({
connector_id: "my-connector-id&delete_sync_jobs=true",
});response = client.connector.delete(
connector_id: "my-connector-id&delete_sync_jobs=true"
)$resp = $client->connector()->delete([
"connector_id" => "my-connector-id&delete_sync_jobs=true",
]);curl -X DELETE -H "Authorization: ApiKey $ELASTIC_API_KEY" "$ELASTICSEARCH_URL/_connector/my-connector-id&delete_sync_jobs=true"client.connector().delete(d -> d
.connectorId("my-connector-id&delete_sync_jobs=true")
);
{
"acknowledged": true
}This action updates the job status to in_progress and sets the last_seen and started_at timestamps to the current time.
Additionally, it can set the sync_cursor property for the sync job.
This API is not intended for direct connector management by users. It supports the implementation of services that utilize the connector protocol to communicate with Elasticsearch.
To sync data using self-managed connectors, you need to deploy the Elastic connector service on your own infrastructure. This service runs automatically on Elastic Cloud for Elastic managed connectors.
PUT _connector/_sync_job/my-connector-sync-job-id/_claim
{
"worker_hostname": "some-machine"
}resp = client.connector.sync_job_claim(
connector_sync_job_id="my-connector-sync-job-id",
worker_hostname="some-machine",
)const response = await client.connector.syncJobClaim({
connector_sync_job_id: "my-connector-sync-job-id",
worker_hostname: "some-machine",
});response = client.connector.sync_job_claim(
connector_sync_job_id: "my-connector-sync-job-id",
body: {
"worker_hostname": "some-machine"
}
)$resp = $client->connector()->syncJobClaim([
"connector_sync_job_id" => "my-connector-sync-job-id",
"body" => [
"worker_hostname" => "some-machine",
],
]);curl -X PUT -H "Authorization: ApiKey $ELASTIC_API_KEY" -H "Content-Type: application/json" -d '{"worker_hostname":"some-machine"}' "$ELASTICSEARCH_URL/_connector/_sync_job/my-connector-sync-job-id/_claim"client.connector().syncJobClaim(s -> s
.connectorSyncJobId("my-connector-sync-job-id")
.workerHostname("some-machine")
);
{
"worker_hostname": "some-machine"
}Set the error field for a connector sync job and set its status to error.
To sync data using self-managed connectors, you need to deploy the Elastic connector service on your own infrastructure. This service runs automatically on Elastic Cloud for Elastic managed connectors.
PUT _connector/_sync_job/my-connector-sync-job/_error
{
"error": "some-error"
}resp = client.connector.sync_job_error(
connector_sync_job_id="my-connector-sync-job",
error="some-error",
)const response = await client.connector.syncJobError({
connector_sync_job_id: "my-connector-sync-job",
error: "some-error",
});response = client.connector.sync_job_error(
connector_sync_job_id: "my-connector-sync-job",
body: {
"error": "some-error"
}
)$resp = $client->connector()->syncJobError([
"connector_sync_job_id" => "my-connector-sync-job",
"body" => [
"error" => "some-error",
],
]);curl -X PUT -H "Authorization: ApiKey $ELASTIC_API_KEY" -H "Content-Type: application/json" -d '{"error":"some-error"}' "$ELASTICSEARCH_URL/_connector/_sync_job/my-connector-sync-job/_error"client.connector().syncJobError(s -> s
.connectorSyncJobId("my-connector-sync-job")
.error("some-error")
);
{
"error": "some-error"
}Stats include: deleted_document_count, indexed_document_count, indexed_document_volume, and total_document_count.
You can also update last_seen.
This API is mainly used by the connector service for updating sync job information.
To sync data using self-managed connectors, you need to deploy the Elastic connector service on your own infrastructure. This service runs automatically on Elastic Cloud for Elastic managed connectors.
The number of documents the sync job deleted.
The number of documents the sync job indexed.
The total size of the data (in MiB) the sync job indexed.
The timestamp to use in the last_seen property for the connector sync job.
The connector-specific metadata.
The total number of documents in the target index after the sync job finished.
PUT _connector/_sync_job/my-connector-sync-job/_stats
{
"deleted_document_count": 10,
"indexed_document_count": 20,
"indexed_document_volume": 1000,
"total_document_count": 2000,
"last_seen": "2023-01-02T10:00:00Z"
}resp = client.connector.sync_job_update_stats(
connector_sync_job_id="my-connector-sync-job",
deleted_document_count=10,
indexed_document_count=20,
indexed_document_volume=1000,
total_document_count=2000,
last_seen="2023-01-02T10:00:00Z",
)const response = await client.connector.syncJobUpdateStats({
connector_sync_job_id: "my-connector-sync-job",
deleted_document_count: 10,
indexed_document_count: 20,
indexed_document_volume: 1000,
total_document_count: 2000,
last_seen: "2023-01-02T10:00:00Z",
});response = client.connector.sync_job_update_stats(
connector_sync_job_id: "my-connector-sync-job",
body: {
"deleted_document_count": 10,
"indexed_document_count": 20,
"indexed_document_volume": 1000,
"total_document_count": 2000,
"last_seen": "2023-01-02T10:00:00Z"
}
)$resp = $client->connector()->syncJobUpdateStats([
"connector_sync_job_id" => "my-connector-sync-job",
"body" => [
"deleted_document_count" => 10,
"indexed_document_count" => 20,
"indexed_document_volume" => 1000,
"total_document_count" => 2000,
"last_seen" => "2023-01-02T10:00:00Z",
],
]);curl -X PUT -H "Authorization: ApiKey $ELASTIC_API_KEY" -H "Content-Type: application/json" -d '{"deleted_document_count":10,"indexed_document_count":20,"indexed_document_volume":1000,"total_document_count":2000,"last_seen":"2023-01-02T10:00:00Z"}' "$ELASTICSEARCH_URL/_connector/_sync_job/my-connector-sync-job/_stats"client.connector().syncJobUpdateStats(s -> s
.connectorSyncJobId("my-connector-sync-job")
.deletedDocumentCount(10L)
.indexedDocumentCount(20L)
.indexedDocumentVolume(1000L)
.lastSeen(l -> l
.time("2023-01-02T10:00:00Z")
)
.totalDocumentCount(2000)
);
{
"deleted_document_count": 10,
"indexed_document_count": 20,
"indexed_document_volume": 1000,
"total_document_count": 2000,
"last_seen": "2023-01-02T10:00:00Z"
}Update the configuration field in the connector document.
PUT _connector/my-spo-connector/_configuration
{
"values": {
"tenant_id": "my-tenant-id",
"tenant_name": "my-sharepoint-site",
"client_id": "foo",
"secret_value": "bar",
"site_collections": "*"
}
}resp = client.connector.update_configuration(
connector_id="my-spo-connector",
values={
"tenant_id": "my-tenant-id",
"tenant_name": "my-sharepoint-site",
"client_id": "foo",
"secret_value": "bar",
"site_collections": "*"
},
)const response = await client.connector.updateConfiguration({
connector_id: "my-spo-connector",
values: {
tenant_id: "my-tenant-id",
tenant_name: "my-sharepoint-site",
client_id: "foo",
secret_value: "bar",
site_collections: "*",
},
});response = client.connector.update_configuration(
connector_id: "my-spo-connector",
body: {
"values": {
"tenant_id": "my-tenant-id",
"tenant_name": "my-sharepoint-site",
"client_id": "foo",
"secret_value": "bar",
"site_collections": "*"
}
}
)$resp = $client->connector()->updateConfiguration([
"connector_id" => "my-spo-connector",
"body" => [
"values" => [
"tenant_id" => "my-tenant-id",
"tenant_name" => "my-sharepoint-site",
"client_id" => "foo",
"secret_value" => "bar",
"site_collections" => "*",
],
],
]);curl -X PUT -H "Authorization: ApiKey $ELASTIC_API_KEY" -H "Content-Type: application/json" -d '{"values":{"tenant_id":"my-tenant-id","tenant_name":"my-sharepoint-site","client_id":"foo","secret_value":"bar","site_collections":"*"}}' "$ELASTICSEARCH_URL/_connector/my-spo-connector/_configuration"client.connector().updateConfiguration(u -> u
.connectorId("my-spo-connector")
.values(Map.of("tenant_id", JsonData.fromJson("\"my-tenant-id\""),"tenant_name", JsonData.fromJson("\"my-sharepoint-site\""),"secret_value", JsonData.fromJson("\"bar\""),"client_id", JsonData.fromJson("\"foo\""),"site_collections", JsonData.fromJson("\"*\"")))
);
{
"values": {
"tenant_id": "my-tenant-id",
"tenant_name": "my-sharepoint-site",
"client_id": "foo",
"secret_value": "bar",
"site_collections": "*"
}
}{
"values": {
"secret_value": "foo-bar"
}
}{
"result": "updated"
}Update the connector features in the connector document. This API can be used to control the following aspects of a connector:
Normally, the running connector service automatically manages these features. However, you can use this API to override the default behavior.
To sync data using self-managed connectors, you need to deploy the Elastic connector service on your own infrastructure. This service runs automatically on Elastic Cloud for Elastic managed connectors.
PUT _connector/my-connector/_features
{
"features": {
"document_level_security": {
"enabled": true
},
"incremental_sync": {
"enabled": true
},
"sync_rules": {
"advanced": {
"enabled": false
},
"basic": {
"enabled": true
}
}
}
}resp = client.connector.update_features(
connector_id="my-connector",
features={
"document_level_security": {
"enabled": True
},
"incremental_sync": {
"enabled": True
},
"sync_rules": {
"advanced": {
"enabled": False
},
"basic": {
"enabled": True
}
}
},
)const response = await client.connector.updateFeatures({
connector_id: "my-connector",
features: {
document_level_security: {
enabled: true,
},
incremental_sync: {
enabled: true,
},
sync_rules: {
advanced: {
enabled: false,
},
basic: {
enabled: true,
},
},
},
});response = client.connector.update_features(
connector_id: "my-connector",
body: {
"features": {
"document_level_security": {
"enabled": true
},
"incremental_sync": {
"enabled": true
},
"sync_rules": {
"advanced": {
"enabled": false
},
"basic": {
"enabled": true
}
}
}
}
)$resp = $client->connector()->updateFeatures([
"connector_id" => "my-connector",
"body" => [
"features" => [
"document_level_security" => [
"enabled" => true,
],
"incremental_sync" => [
"enabled" => true,
],
"sync_rules" => [
"advanced" => [
"enabled" => false,
],
"basic" => [
"enabled" => true,
],
],
],
],
]);curl -X PUT -H "Authorization: ApiKey $ELASTIC_API_KEY" -H "Content-Type: application/json" -d '{"features":{"document_level_security":{"enabled":true},"incremental_sync":{"enabled":true},"sync_rules":{"advanced":{"enabled":false},"basic":{"enabled":true}}}}' "$ELASTICSEARCH_URL/_connector/my-connector/_features"client.connector().updateFeatures(u -> u
.connectorId("my-connector")
.features(f -> f
.documentLevelSecurity(d -> d
.enabled(true)
)
.incrementalSync(i -> i
.enabled(true)
)
.syncRules(s -> s
.advanced(a -> a
.enabled(false)
)
.basic(b -> b
.enabled(true)
)
)
)
);
{
"features": {
"document_level_security": {
"enabled": true
},
"incremental_sync": {
"enabled": true
},
"sync_rules": {
"advanced": {
"enabled": false
},
"basic": {
"enabled": true
}
}
}
}{
"features": {
"document_level_security": {
"enabled": true
}
}
}{
"result": "updated"
}PUT _connector/my-connector/_name
{
"name": "Custom connector",
"description": "This is my customized connector"
}resp = client.connector.update_name(
connector_id="my-connector",
name="Custom connector",
description="This is my customized connector",
)const response = await client.connector.updateName({
connector_id: "my-connector",
name: "Custom connector",
description: "This is my customized connector",
});response = client.connector.update_name(
connector_id: "my-connector",
body: {
"name": "Custom connector",
"description": "This is my customized connector"
}
)$resp = $client->connector()->updateName([
"connector_id" => "my-connector",
"body" => [
"name" => "Custom connector",
"description" => "This is my customized connector",
],
]);curl -X PUT -H "Authorization: ApiKey $ELASTIC_API_KEY" -H "Content-Type: application/json" -d '{"name":"Custom connector","description":"This is my customized connector"}' "$ELASTICSEARCH_URL/_connector/my-connector/_name"client.connector().updateName(u -> u
.connectorId("my-connector")
.description("This is my customized connector")
.name("Custom connector")
);
{
"name": "Custom connector",
"description": "This is my customized connector"
}{
"result": "updated"
}Pause a cross-cluster replication auto-follow pattern. When the API returns, the auto-follow pattern is inactive. New indices that are created on the remote cluster and match the auto-follow patterns are ignored.
You can resume auto-following with the resume auto-follow pattern API. When it resumes, the auto-follow pattern is active again and automatically configures follower indices for newly created indices on the remote cluster that match its patterns. Remote indices that were created while the pattern was paused will also be followed, unless they have been deleted or closed in the interim.
manage_ccrPOST /_ccr/auto_follow/my_auto_follow_pattern/pause
resp = client.ccr.pause_auto_follow_pattern(
name="my_auto_follow_pattern",
)const response = await client.ccr.pauseAutoFollowPattern({
name: "my_auto_follow_pattern",
});response = client.ccr.pause_auto_follow_pattern(
name: "my_auto_follow_pattern"
)$resp = $client->ccr()->pauseAutoFollowPattern([
"name" => "my_auto_follow_pattern",
]);curl -X POST -H "Authorization: ApiKey $ELASTIC_API_KEY" "$ELASTICSEARCH_URL/_ccr/auto_follow/my_auto_follow_pattern/pause"client.ccr().pauseAutoFollowPattern(p -> p
.name("my_auto_follow_pattern")
);
{
"acknowledged" : true
}Resume a cross-cluster replication auto-follow pattern that was paused. The auto-follow pattern will resume configuring following indices for newly created indices that match its patterns on the remote cluster. Remote indices created while the pattern was paused will also be followed unless they have been deleted or closed in the interim.
manage_ccrPOST /_ccr/auto_follow/my_auto_follow_pattern/resume
resp = client.ccr.resume_auto_follow_pattern(
name="my_auto_follow_pattern",
)const response = await client.ccr.resumeAutoFollowPattern({
name: "my_auto_follow_pattern",
});response = client.ccr.resume_auto_follow_pattern(
name: "my_auto_follow_pattern"
)$resp = $client->ccr()->resumeAutoFollowPattern([
"name" => "my_auto_follow_pattern",
]);curl -X POST -H "Authorization: ApiKey $ELASTIC_API_KEY" "$ELASTICSEARCH_URL/_ccr/auto_follow/my_auto_follow_pattern/resume"client.ccr().resumeAutoFollowPattern(r -> r
.name("my_auto_follow_pattern")
);
{
"acknowledged" : true
}Comma-separated list of data stream names used to limit the request.
Wildcard (*) expressions are supported. If omitted, all data streams are returned.
Type of data stream that wildcard patterns can match.
Supports comma-separated values, such as open,hidden.
Supported values include:
all: Match any data stream or index, including hidden ones.open: Match open, non-hidden indices. Also matches any non-hidden data stream.closed: Match closed, non-hidden indices. Also matches any non-hidden data stream. Data streams cannot be closed.hidden: Match hidden data streams and hidden indices. Must be combined with open, closed, or both.none: Wildcard expressions are not accepted.Values are all, open, closed, hidden, or none.
If true, returns all relevant default configurations for the index template.
Period to wait for a connection to the master node. If no response is received before the timeout expires, the request fails and returns an error.
Values are -1 or 0.
Whether the maximum timestamp for each data stream should be calculated and returned.
GET _data_stream/my-data-stream
resp = client.indices.get_data_stream(
name="my-data-stream",
)const response = await client.indices.getDataStream({
name: "my-data-stream",
});response = client.indices.get_data_stream(
name: "my-data-stream"
)$resp = $client->indices()->getDataStream([
"name" => "my-data-stream",
]);curl -X GET -H "Authorization: ApiKey $ELASTIC_API_KEY" "$ELASTICSEARCH_URL/_data_stream/my-data-stream"client.indices().getDataStream(g -> g
.name("my-data-stream")
);
{
"data_streams": [
{
"name": "my-data-stream",
"timestamp_field": {
"name": "@timestamp"
},
"indices": [
{
"index_name": ".ds-my-data-stream-2099.03.07-000001",
"index_uuid": "xCEhwsp8Tey0-FLNFYVwSg",
"prefer_ilm": true,
"ilm_policy": "my-lifecycle-policy",
"managed_by": "Index Lifecycle Management"
},
{
"index_name": ".ds-my-data-stream-2099.03.08-000002",
"index_uuid": "PA_JquKGSiKcAKBA8DJ5gw",
"prefer_ilm": true,
"ilm_policy": "my-lifecycle-policy",
"managed_by": "Index Lifecycle Management"
}
],
"generation": 2,
"_meta": {
"my-meta-field": "foo"
},
"status": "GREEN",
"next_generation_managed_by": "Index Lifecycle Management",
"prefer_ilm": true,
"template": "my-index-template",
"ilm_policy": "my-lifecycle-policy",
"hidden": false,
"system": false,
"allow_custom_routing": false,
"replicated": false,
"rollover_on_write": false
},
{
"name": "my-data-stream-two",
"timestamp_field": {
"name": "@timestamp"
},
"indices": [
{
"index_name": ".ds-my-data-stream-two-2099.03.08-000001",
"index_uuid": "3liBu2SYS5axasRt6fUIpA",
"prefer_ilm": true,
"ilm_policy": "my-lifecycle-policy",
"managed_by": "Index Lifecycle Management"
}
],
"generation": 1,
"_meta": {
"my-meta-field": "foo"
},
"status": "YELLOW",
"next_generation_managed_by": "Index Lifecycle Management",
"prefer_ilm": true,
"template": "my-index-template",
"ilm_policy": "my-lifecycle-policy",
"hidden": false,
"system": false,
"allow_custom_routing": false,
"replicated": false,
"rollover_on_write": false
}
]
}Comma-separated list of data streams to delete. Wildcard (*) expressions are supported.
Period to wait for a connection to the master node. If no response is received before the timeout expires, the request fails and returns an error.
Values are -1 or 0.
Type of data stream that wildcard patterns can match. Supports comma-separated values,such as open,hidden.
Supported values include:
all: Match any data stream or index, including hidden ones.open: Match open, non-hidden indices. Also matches any non-hidden data stream.closed: Match closed, non-hidden indices. Also matches any non-hidden data stream. Data streams cannot be closed.hidden: Match hidden data streams and hidden indices. Must be combined with open, closed, or both.none: Wildcard expressions are not accepted.Values are all, open, closed, hidden, or none.
DELETE _data_stream/my-data-stream
resp = client.indices.delete_data_stream(
name="my-data-stream",
)const response = await client.indices.deleteDataStream({
name: "my-data-stream",
});response = client.indices.delete_data_stream(
name: "my-data-stream"
)$resp = $client->indices()->deleteDataStream([
"name" => "my-data-stream",
]);curl -X DELETE -H "Authorization: ApiKey $ELASTIC_API_KEY" "$ELASTICSEARCH_URL/_data_stream/my-data-stream"client.indices().deleteDataStream(d -> d
.name("my-data-stream")
);
Get the data stream lifecycle configuration of one or more data streams.
Comma-separated list of data streams to limit the request.
Supports wildcards (*).
To target all data streams, omit this parameter or use * or _all.
Type of data stream that wildcard patterns can match.
Supports comma-separated values, such as open,hidden.
Supported values include:
all: Match any data stream or index, including hidden ones.open: Match open, non-hidden indices. Also matches any non-hidden data stream.closed: Match closed, non-hidden indices. Also matches any non-hidden data stream. Data streams cannot be closed.hidden: Match hidden data streams and hidden indices. Must be combined with open, closed, or both.none: Wildcard expressions are not accepted.Values are all, open, closed, hidden, or none.
If true, return all default settings in the response.
Period to wait for a connection to the master node. If no response is received before the timeout expires, the request fails and returns an error.
Values are -1 or 0.
GET /_data_stream/{name}/_lifecycle?human&pretty
resp = client.indices.get_data_lifecycle(
name="{name}",
human=True,
pretty=True,
)const response = await client.indices.getDataLifecycle({
name: "{name}",
human: "true",
pretty: "true",
});response = client.indices.get_data_lifecycle(
name: "{name}",
human: "true",
pretty: "true"
)$resp = $client->indices()->getDataLifecycle([
"name" => "{name}",
"human" => "true",
"pretty" => "true",
]);curl -X GET -H "Authorization: ApiKey $ELASTIC_API_KEY" "$ELASTICSEARCH_URL/_data_stream/%7Bname%7D/_lifecycle?human&pretty"{
"data_streams": [
{
"name": "my-data-stream-1",
"lifecycle": {
"enabled": true,
"data_retention": "7d"
}
},
{
"name": "my-data-stream-2",
"lifecycle": {
"enabled": true,
"data_retention": "7d"
}
}
]
}Update the data stream lifecycle of the specified data streams.
Comma-separated list of data streams used to limit the request.
Supports wildcards (*).
To target all data streams use * or _all.
Type of data stream that wildcard patterns can match.
Supports comma-separated values, such as open,hidden.
Supported values include:
all: Match any data stream or index, including hidden ones.open: Match open, non-hidden indices. Also matches any non-hidden data stream.closed: Match closed, non-hidden indices. Also matches any non-hidden data stream. Data streams cannot be closed.hidden: Match hidden data streams and hidden indices. Must be combined with open, closed, or both.none: Wildcard expressions are not accepted.Values are all, open, closed, hidden, or none.
Period to wait for a connection to the master node. If no response is received before the timeout expires, the request fails and returns an error.
Values are -1 or 0.
Period to wait for a response. If no response is received before the timeout expires, the request fails and returns an error.
Values are -1 or 0.
If defined, every document added to this data stream will be stored at least for this time frame. Any time after this duration the document could be deleted. When empty, every document in this data stream will be stored indefinitely.
The downsampling configuration to execute for the managed backing index after rollover.
If defined, it turns data stream lifecycle on/off (true/false) for this data stream. A data stream lifecycle
that's disabled (enabled: false) will have no effect on the data stream.
Default value is true.
PUT _data_stream/my-data-stream/_lifecycle
{
"data_retention": "7d"
}resp = client.indices.put_data_lifecycle(
name="my-data-stream",
data_retention="7d",
)const response = await client.indices.putDataLifecycle({
name: "my-data-stream",
data_retention: "7d",
});response = client.indices.put_data_lifecycle(
name: "my-data-stream",
body: {
"data_retention": "7d"
}
)$resp = $client->indices()->putDataLifecycle([
"name" => "my-data-stream",
"body" => [
"data_retention" => "7d",
],
]);curl -X PUT -H "Authorization: ApiKey $ELASTIC_API_KEY" -H "Content-Type: application/json" -d '{"data_retention":"7d"}' "$ELASTICSEARCH_URL/_data_stream/my-data-stream/_lifecycle"client.indices().putDataLifecycle(p -> p
.dataRetention(d -> d
.time("7d")
)
.name("my-data-stream")
);
{
"data_retention": "7d"
}{
"downsampling": [
{
"after": "1d",
"fixed_interval": "10m"
},
{
"after": "7d",
"fixed_interval": "1d"
}
]
}{
"acknowledged": true
}Aggregate a time series (TSDS) index and store pre-computed statistical summaries (min, max, sum, value_count and avg) for each metric field grouped by a configured time interval.
For example, a TSDS index that contains metrics sampled every 10 seconds can be downsampled to an hourly index.
All documents within an hour interval are summarized and stored as a single document in the downsample index.
NOTE: Only indices in a time series data stream are supported.
Neither field nor document level security can be defined on the source index.
The source index must be read only (index.blocks.write: true).
POST /my-time-series-index/_downsample/my-downsampled-time-series-index
{
"fixed_interval": "1d"
}resp = client.indices.downsample(
index="my-time-series-index",
target_index="my-downsampled-time-series-index",
config={
"fixed_interval": "1d"
},
)const response = await client.indices.downsample({
index: "my-time-series-index",
target_index: "my-downsampled-time-series-index",
config: {
fixed_interval: "1d",
},
});response = client.indices.downsample(
index: "my-time-series-index",
target_index: "my-downsampled-time-series-index",
body: {
"fixed_interval": "1d"
}
)$resp = $client->indices()->downsample([
"index" => "my-time-series-index",
"target_index" => "my-downsampled-time-series-index",
"body" => [
"fixed_interval" => "1d",
],
]);curl -X POST -H "Authorization: ApiKey $ELASTIC_API_KEY" -H "Content-Type: application/json" -d '{"fixed_interval":"1d"}' "$ELASTICSEARCH_URL/my-time-series-index/_downsample/my-downsampled-time-series-index"client.indices().downsample(d -> d
.index("my-time-series-index")
.targetIndex("my-downsampled-time-series-index")
.config(c -> c
.fixedInterval(f -> f
.time("1d")
)
)
);
{
"fixed_interval": "1d"
}All methods and paths for this operation:
Get multiple term vectors with a single request.
You can specify existing documents by index and ID or provide artificial documents in the body of the request.
You can specify the index in the request body or request URI.
The response contains a docs array with all the fetched termvectors.
Each element has the structure provided by the termvectors API.
Artificial documents
You can also use mtermvectors to generate term vectors for artificial documents provided in the body of the request.
The mapping used is determined by the specified _index.
readA comma-separated list of documents ids. You must define ids as parameter or set "ids" or "docs" in the request body
A comma-separated list or wildcard expressions of fields to include in the statistics.
It is used as the default list unless a specific field list is provided in the completion_fields or fielddata_fields parameters.
If true, the response includes the document count, sum of document frequencies, and sum of total term frequencies.
If true, the response includes term offsets.
If true, the response includes term payloads.
If true, the response includes term positions.
The node or shard the operation should be performed on. It is random by default.
If true, the request is real-time as opposed to near-real-time.
A custom value used to route operations to a specific shard.
If true, the response includes term frequency and document frequency.
If true, returns the document version as part of a hit.
The version type.
Supported values include:
internal: Use internal versioning that starts at 1 and increments with each update or delete.external: Only index the document if the specified version is strictly higher than the version of the stored document or if there is no existing document.external_gte: Only index the document if the specified version is equal or higher than the version of the stored document or if there is no existing document.
NOTE: The external_gte version type is meant for special use cases and should be used with care.
If used incorrectly, it can result in loss of data.force: This option is deprecated because it can cause primary and replica shards to diverge.Values are internal, external, external_gte, or force.
POST /my-index-000001/_mtermvectors
{
"docs": [
{
"_id": "2",
"fields": [
"message"
],
"term_statistics": true
},
{
"_id": "1"
}
]
}resp = client.mtermvectors(
index="my-index-000001",
docs=[
{
"_id": "2",
"fields": [
"message"
],
"term_statistics": True
},
{
"_id": "1"
}
],
)const response = await client.mtermvectors({
index: "my-index-000001",
docs: [
{
_id: "2",
fields: ["message"],
term_statistics: true,
},
{
_id: "1",
},
],
});response = client.mtermvectors(
index: "my-index-000001",
body: {
"docs": [
{
"_id": "2",
"fields": [
"message"
],
"term_statistics": true
},
{
"_id": "1"
}
]
}
)$resp = $client->mtermvectors([
"index" => "my-index-000001",
"body" => [
"docs" => array(
[
"_id" => "2",
"fields" => array(
"message",
),
"term_statistics" => true,
],
[
"_id" => "1",
],
),
],
]);curl -X POST -H "Authorization: ApiKey $ELASTIC_API_KEY" -H "Content-Type: application/json" -d '{"docs":[{"_id":"2","fields":["message"],"term_statistics":true},{"_id":"1"}]}' "$ELASTICSEARCH_URL/my-index-000001/_mtermvectors"client.mtermvectors(m -> m
.docs(List.of(MultiTermVectorsOperation.of(mu -> mu
.id("2")
.fields("message")
.termStatistics(true)),MultiTermVectorsOperation.of(mu -> mu
.id("1"))))
.index("my-index-000001")
);
{
"docs": [
{
"_id": "2",
"fields": [
"message"
],
"term_statistics": true
},
{
"_id": "1"
}
]
}{
"ids": [ "1", "2" ],
"fields": [
"message"
],
"term_statistics": true
}{
"docs": [
{
"_index": "my-index-000001",
"doc" : {
"message" : "test test test"
}
},
{
"_index": "my-index-000001",
"doc" : {
"message" : "Another test ..."
}
}
]
}Updates documents that match the specified query. If no query is specified, performs an update on every document in the data stream or index without modifying the source, which is useful for picking up mapping changes.
If the Elasticsearch security features are enabled, you must have the following index privileges for the target data stream, index, or alias:
readindex or writeYou can specify the query criteria in the request URI or the request body using the same syntax as the search API.
When you submit an update by query request, Elasticsearch gets a snapshot of the data stream or index when it begins processing the request and updates matching documents using internal versioning.
When the versions match, the document is updated and the version number is incremented.
If a document changes between the time that the snapshot is taken and the update operation is processed, it results in a version conflict and the operation fails.
You can opt to count version conflicts instead of halting and returning by setting conflicts to proceed.
Note that if you opt to count version conflicts, the operation could attempt to update more documents from the source than max_docs until it has successfully updated max_docs documents or it has gone through every document in the source query.
NOTE: Documents with a version equal to 0 cannot be updated using update by query because internal versioning does not support 0 as a valid version number.
While processing an update by query request, Elasticsearch performs multiple search requests sequentially to find all of the matching documents. A bulk update request is performed for each batch of matching documents. Any query or update failures cause the update by query request to fail and the failures are shown in the response. Any update requests that completed successfully still stick, they are not rolled back.
Throttling update requests
To control the rate at which update by query issues batches of update operations, you can set requests_per_second to any positive decimal number.
This pads each batch with a wait time to throttle the rate.
Set requests_per_second to -1 to turn off throttling.
Throttling uses a wait time between batches so that the internal scroll requests can be given a timeout that takes the request padding into account.
The padding time is the difference between the batch size divided by the requests_per_second and the time spent writing.
By default the batch size is 1000, so if requests_per_second is set to 500:
target_time = 1000 / 500 per second = 2 seconds
wait_time = target_time - write_time = 2 seconds - .5 seconds = 1.5 seconds
Since the batch is issued as a single _bulk request, large batch sizes cause Elasticsearch to create many requests and wait before starting the next set. This is "bursty" instead of "smooth".
Slicing
Update by query supports sliced scroll to parallelize the update process. This can improve efficiency and provide a convenient way to break the request down into smaller parts.
Setting slices to auto chooses a reasonable number for most data streams and indices.
This setting will use one slice per shard, up to a certain limit.
If there are multiple source data streams or indices, it will choose the number of slices based on the index or backing index with the smallest number of shards.
Adding slices to _update_by_query just automates the manual process of creating sub-requests, which means it has some quirks:
slices only contains the status of completed slices.slices will rethrottle the unfinished sub-request proportionally.requests_per_second and max_docs on a request with slices are distributed proportionally to each sub-request. Combine that with the point above about distribution being uneven and you should conclude that using max_docs with slices might not result in exactly max_docs documents being updated.If you're slicing manually or otherwise tuning automatic slicing, keep in mind that:
Whether query or update performance dominates the runtime depends on the documents being reindexed and cluster resources.
Update the document source
Update by query supports scripts to update the document source.
As with the update API, you can set ctx.op to change the operation that is performed.
Set ctx.op = "noop" if your script decides that it doesn't have to make any changes.
The update by query operation skips updating the document and increments the noop counter.
Set ctx.op = "delete" if your script decides that the document should be deleted.
The update by query operation deletes the document and increments the deleted counter.
Update by query supports only index, noop, and delete.
Setting ctx.op to anything else is an error.
Setting any other field in ctx is an error.
This API enables you to only modify the source of matching documents; you cannot move them.
read,writeA comma-separated list of data streams, indices, and aliases to search.
It supports wildcards (*).
To search all data streams or indices, omit this parameter or use * or _all.
If false, the request returns an error if any wildcard expression, index alias, or _all value targets only missing or closed indices.
This behavior applies even if the request targets other open indices.
For example, a request targeting foo*,bar* returns an error if an index starts with foo but no index starts with bar.
The analyzer to use for the query string.
This parameter can be used only when the q query string parameter is specified.
If true, wildcard and prefix queries are analyzed.
This parameter can be used only when the q query string parameter is specified.
The preferred behavior when update by query hits version conflicts: abort or proceed.
Supported values include:
abort: Stop reindexing if there are conflicts.proceed: Continue reindexing even if there are conflicts.Values are abort or proceed.
The default operator for query string query: AND or OR.
This parameter can be used only when the q query string parameter is specified.
Values are and, AND, or, or OR.
The field to use as default where no field prefix is given in the query string.
This parameter can be used only when the q query string parameter is specified.
The type of index that wildcard patterns can match.
If the request can target data streams, this argument determines whether wildcard expressions match hidden data streams.
It supports comma-separated values, such as open,hidden.
Supported values include:
all: Match any data stream or index, including hidden ones.open: Match open, non-hidden indices. Also matches any non-hidden data stream.closed: Match closed, non-hidden indices. Also matches any non-hidden data stream. Data streams cannot be closed.hidden: Match hidden data streams and hidden indices. Must be combined with open, closed, or both.none: Wildcard expressions are not accepted.Values are all, open, closed, hidden, or none.
Skips the specified number of documents.
If true, format-based query failures (such as providing text to a numeric field) in the query string will be ignored.
This parameter can be used only when the q query string parameter is specified.
The maximum number of documents to process.
It defaults to all documents.
When set to a value less then or equal to scroll_size then a scroll will not be used to retrieve the results for the operation.
The ID of the pipeline to use to preprocess incoming documents.
If the index has a default ingest pipeline specified, then setting the value to _none disables the default ingest pipeline for this request.
If a final pipeline is configured it will always run, regardless of the value of this parameter.
The node or shard the operation should be performed on. It is random by default.
A query in the Lucene query string syntax.
If true, Elasticsearch refreshes affected shards to make the operation visible to search after the request completes.
This is different than the update API's refresh parameter, which causes just the shard that received the request to be refreshed.
If true, the request cache is used for this request.
It defaults to the index-level setting.
The throttle for this request in sub-requests per second.
A custom value used to route operations to a specific shard.
The period to retain the search context for scrolling.
Values are -1 or 0.
The size of the scroll request that powers the operation.
An explicit timeout for each search request. By default, there is no timeout.
Values are -1 or 0.
The type of the search operation. Available options include query_then_fetch and dfs_query_then_fetch.
Supported values include:
query_then_fetch: Documents are scored using local term and document frequencies for the shard. This is usually faster but less accurate.dfs_query_then_fetch: Documents are scored using global term and document frequencies across all shards. This is usually slower but more accurate.Values are query_then_fetch or dfs_query_then_fetch.
The number of slices this task should be divided into.
Value is auto.
A comma-separated list of : pairs.
The specific tag of the request for logging and statistical purposes.
The maximum number of documents to collect for each shard. If a query reaches this limit, Elasticsearch terminates the query early. Elasticsearch collects documents before sorting.
IMPORTANT: Use with caution. Elasticsearch applies this parameter to each shard handling the request. When possible, let Elasticsearch perform early termination automatically. Avoid specifying this parameter for requests that target data streams with backing indices across multiple data tiers.
The period each update request waits for the following operations: dynamic mapping updates, waiting for active shards. By default, it is one minute. This guarantees Elasticsearch waits for at least the timeout before failing. The actual wait time could be longer, particularly when multiple waits occur.
Values are -1 or 0.
If true, returns the document version as part of a hit.
Should the document increment the version number (internal) on hit or not (reindex)
The number of shard copies that must be active before proceeding with the operation.
Set to all or any positive integer up to the total number of shards in the index (number_of_replicas+1).
The timeout parameter controls how long each write request waits for unavailable shards to become available.
Both work exactly the way they work in the bulk API.
Values are all or index-setting.
If true, the request blocks until the operation is complete.
If false, Elasticsearch performs some preflight checks, launches the request, and returns a task ID that you can use to cancel or get the status of the task.
Elasticsearch creates a record of this task as a document at .tasks/task/${taskId}.
The maximum number of documents to update.
The documents to update using the Query DSL.
The script to run to update the document source or metadata when updating.
Slice the request manually using the provided slice ID and total number of slices.
The preferred behavior when update by query hits version conflicts: abort or proceed.
Supported values include:
abort: Stop reindexing if there are conflicts.proceed: Continue reindexing even if there are conflicts.Values are abort or proceed.
POST my-index-000001/_update_by_query?conflicts=proceed
{
"query": {
"term": {
"user.id": "kimchy"
}
}
}resp = client.update_by_query(
index="my-index-000001",
conflicts="proceed",
query={
"term": {
"user.id": "kimchy"
}
},
)const response = await client.updateByQuery({
index: "my-index-000001",
conflicts: "proceed",
query: {
term: {
"user.id": "kimchy",
},
},
});response = client.update_by_query(
index: "my-index-000001",
conflicts: "proceed",
body: {
"query": {
"term": {
"user.id": "kimchy"
}
}
}
)$resp = $client->updateByQuery([
"index" => "my-index-000001",
"conflicts" => "proceed",
"body" => [
"query" => [
"term" => [
"user.id" => "kimchy",
],
],
],
]);curl -X POST -H "Authorization: ApiKey $ELASTIC_API_KEY" -H "Content-Type: application/json" -d '{"query":{"term":{"user.id":"kimchy"}}}' "$ELASTICSEARCH_URL/my-index-000001/_update_by_query?conflicts=proceed"client.updateByQuery(u -> u
.conflicts(Conflicts.Proceed)
.index("my-index-000001")
.query(q -> q
.term(t -> t
.field("user.id")
.value(FieldValue.of("kimchy"))
)
)
);
{
"query": {
"term": {
"user.id": "kimchy"
}
}
}{
"script": {
"source": "ctx._source.count++",
"lang": "painless"
},
"query": {
"term": {
"user.id": "kimchy"
}
}
}{
"slice": {
"id": 0,
"max": 2
},
"script": {
"source": "ctx._source['extra'] = 'test'"
}
}{
"script": {
"source": "ctx._source['extra'] = 'test'"
}
}Change the number of requests per second for a particular update by query operation. Rethrottling that speeds up the query takes effect immediately but rethrotting that slows down the query takes effect after completing the current batch to prevent scroll timeouts.
POST _update_by_query/r1A2WoRbTwKZ516z6NEs5A:36619/_rethrottle?requests_per_second=-1
resp = client.update_by_query_rethrottle(
task_id="r1A2WoRbTwKZ516z6NEs5A:36619",
requests_per_second="-1",
)const response = await client.updateByQueryRethrottle({
task_id: "r1A2WoRbTwKZ516z6NEs5A:36619",
requests_per_second: "-1",
});response = client.update_by_query_rethrottle(
task_id: "r1A2WoRbTwKZ516z6NEs5A:36619",
requests_per_second: "-1"
)$resp = $client->updateByQueryRethrottle([
"task_id" => "r1A2WoRbTwKZ516z6NEs5A:36619",
"requests_per_second" => "-1",
]);curl -X POST -H "Authorization: ApiKey $ELASTIC_API_KEY" "$ELASTICSEARCH_URL/_update_by_query/r1A2WoRbTwKZ516z6NEs5A:36619/_rethrottle?requests_per_second=-1"client.updateByQueryRethrottle(u -> u
.requestsPerSecond(-1.0F)
.taskId("r1A2WoRbTwKZ516z6NEs5A:36619")
);
All methods and paths for this operation:
Returns information about an enrich policy.
Comma-separated list of enrich policy names used to limit the request. To return information for all enrich policies, omit this parameter.
GET /_enrich/policy/my-policy
resp = client.enrich.get_policy(
name="my-policy",
)const response = await client.enrich.getPolicy({
name: "my-policy",
});response = client.enrich.get_policy(
name: "my-policy"
)$resp = $client->enrich()->getPolicy([
"name" => "my-policy",
]);curl -X GET -H "Authorization: ApiKey $ELASTIC_API_KEY" "$ELASTICSEARCH_URL/_enrich/policy/my-policy"client.enrich().getPolicy(g -> g
.name("my-policy")
);
Get the current global checkpoints for an index. This API is designed for internal use by the Fleet server project.
A boolean value which controls whether to wait (until the timeout) for the global checkpoints
to advance past the provided checkpoints.
A boolean value which controls whether to wait (until the timeout) for the target index to exist
and all primary shards be active. Can only be true when wait_for_advance is true.
A comma separated list of previous global checkpoints. When used in combination with wait_for_advance,
the API will only return once the global checkpoints advances past the checkpoints. Providing an empty list
will cause Elasticsearch to immediately return the current global checkpoints.
Period to wait for a global checkpoints to advance past checkpoints.
Values are -1 or 0.
curl \
--request GET 'http://api.example.com/{index}/_fleet/global_checkpoints' \
--header "Authorization: $API_KEY"If Elasticsearch encounters index data that is absent from the current cluster state, those indices are considered to be dangling.
For example, this can happen if you delete more than cluster.indices.tombstones.size indices while an Elasticsearch node is offline.
manageDELETE /_dangling/<index-uuid>?accept_data_loss=true
resp = client.dangling_indices.delete_dangling_index(
index_uuid="<index-uuid>",
accept_data_loss=True,
)const response = await client.danglingIndices.deleteDanglingIndex({
index_uuid: "<index-uuid>",
accept_data_loss: "true",
});response = client.dangling_indices.delete_dangling_index(
index_uuid: "<index-uuid>",
accept_data_loss: "true"
)$resp = $client->danglingIndices()->deleteDanglingIndex([
"index_uuid" => "<index-uuid>",
"accept_data_loss" => "true",
]);curl -X DELETE -H "Authorization: ApiKey $ELASTIC_API_KEY" "$ELASTICSEARCH_URL/_dangling/<index-uuid>?accept_data_loss=true"client.danglingIndices().deleteDanglingIndex(d -> d
.acceptDataLoss(true)
.indexUuid("<index-uuid>")
);
If Elasticsearch encounters index data that is absent from the current cluster state, those indices are considered to be dangling.
For example, this can happen if you delete more than cluster.indices.tombstones.size indices while an Elasticsearch node is offline.
Use this API to list dangling indices, which you can then import or delete.
manageGET /_dangling
resp = client.dangling_indices.list_dangling_indices()const response = await client.danglingIndices.listDanglingIndices();response = client.dangling_indices.list_dangling_indices$resp = $client->danglingIndices()->listDanglingIndices();curl -X GET -H "Authorization: ApiKey $ELASTIC_API_KEY" "$ELASTICSEARCH_URL/_dangling"client.danglingIndices().listDanglingIndices();
{
"dangling_indices": [
{
"index_name": "my-index-000001",
"index_uuid": "zmM4e0JtBkeUjiHD-MihPQ",
"creation_date_millis": 1589414451372,
"node_ids": [
"pL47UN3dAb2d5RCWP6lQ3e"
]
}
]
}Add an index block to an index. Index blocks limit the operations allowed on an index by blocking specific operation types.
A comma-separated list or wildcard expression of index names used to limit the request.
By default, you must explicitly name the indices you are adding blocks to.
To allow the adding of blocks to indices with _all, *, or other wildcard expressions, change the action.destructive_requires_name setting to false.
You can update this setting in the elasticsearch.yml file or by using the cluster update settings API.
The block type to add to the index.
Supported values include:
metadata: Disable metadata changes, such as closing the index.read: Disable read operations.read_only: Disable write operations and metadata changes.write: Disable write operations. However, metadata changes are still allowed.Values are metadata, read, read_only, or write.
If false, the request returns an error if any wildcard expression, index alias, or _all value targets only missing or closed indices.
This behavior applies even if the request targets other open indices.
For example, a request targeting foo*,bar* returns an error if an index starts with foo but no index starts with bar.
The type of index that wildcard patterns can match.
If the request can target data streams, this argument determines whether wildcard expressions match hidden data streams.
It supports comma-separated values, such as open,hidden.
Supported values include:
all: Match any data stream or index, including hidden ones.open: Match open, non-hidden indices. Also matches any non-hidden data stream.closed: Match closed, non-hidden indices. Also matches any non-hidden data stream. Data streams cannot be closed.hidden: Match hidden data streams and hidden indices. Must be combined with open, closed, or both.none: Wildcard expressions are not accepted.Values are all, open, closed, hidden, or none.
The period to wait for the master node.
If the master node is not available before the timeout expires, the request fails and returns an error.
It can also be set to -1 to indicate that the request should never timeout.
Values are -1 or 0.
The period to wait for a response from all relevant nodes in the cluster after updating the cluster metadata.
If no response is received before the timeout expires, the cluster metadata update still applies but the response will indicate that it was not completely acknowledged.
It can also be set to -1 to indicate that the request should never timeout.
Values are -1 or 0.
PUT /my-index-000001/_block/write
resp = client.indices.add_block(
index="my-index-000001",
block="write",
)const response = await client.indices.addBlock({
index: "my-index-000001",
block: "write",
});response = client.indices.add_block(
index: "my-index-000001",
block: "write"
)$resp = $client->indices()->addBlock([
"index" => "my-index-000001",
"block" => "write",
]);curl -X PUT -H "Authorization: ApiKey $ELASTIC_API_KEY" "$ELASTICSEARCH_URL/my-index-000001/_block/write"client.indices().addBlock(a -> a
.block(IndicesBlockOptions.Write)
.index("my-index-000001")
);
{
"acknowledged" : true,
"shards_acknowledged" : true,
"indices" : [ {
"name" : "my-index-000001",
"blocked" : true
} ]
}Comma-separated list of data streams, indices, and index aliases used to limit the request. Wildcard expressions (*) are supported.
If false, the request returns an error if any wildcard expression, index alias, or _all value targets only missing or closed indices. This behavior applies even if the request targets other open indices. For example, a request targeting foo*,bar* returns an error if an index starts with foo but no index starts with bar.
Type of index that wildcard expressions can match. If the request can target data streams, this argument determines whether wildcard expressions match hidden data streams. Supports comma-separated values, such as open,hidden.
Supported values include:
all: Match any data stream or index, including hidden ones.open: Match open, non-hidden indices. Also matches any non-hidden data stream.closed: Match closed, non-hidden indices. Also matches any non-hidden data stream. Data streams cannot be closed.hidden: Match hidden data streams and hidden indices. Must be combined with open, closed, or both.none: Wildcard expressions are not accepted.Values are all, open, closed, hidden, or none.
If true, returns settings in flat format.
If true, return all default settings in the response.
If true, the request retrieves information from the local node only. Defaults to false, which means information is retrieved from the master node.
Period to wait for a connection to the master node. If no response is received before the timeout expires, the request fails and returns an error.
Values are -1 or 0.
Return only information on specified index features
Supported values include: aliases, mappings, settings
Values are aliases, mappings, or settings.
GET /my-index-000001
resp = client.indices.get(
index="my-index-000001",
)const response = await client.indices.get({
index: "my-index-000001",
});response = client.indices.get(
index: "my-index-000001"
)$resp = $client->indices()->get([
"index" => "my-index-000001",
]);curl -X GET -H "Authorization: ApiKey $ELASTIC_API_KEY" "$ELASTICSEARCH_URL/my-index-000001"client.indices().get(g -> g
.index("my-index-000001")
);
All methods and paths for this operation:
Adds a data stream or index to an alias.
Comma-separated list of data streams or indices to add.
Supports wildcards (*).
Wildcard patterns that match both data streams and indices return an error.
Alias to update. If the alias doesn’t exist, the request creates it. Index alias names support date math.
Period to wait for a connection to the master node. If no response is received before the timeout expires, the request fails and returns an error.
Values are -1 or 0.
Period to wait for a response. If no response is received before the timeout expires, the request fails and returns an error.
Values are -1 or 0.
Query used to limit documents the alias can access.
Value used to route indexing operations to a specific shard.
If specified, this overwrites the routing value for indexing operations.
Data stream aliases don’t support this parameter.
If true, sets the write index or data stream for the alias.
If an alias points to multiple indices or data streams and is_write_index isn’t set, the alias rejects write requests.
If an index alias points to one index and is_write_index isn’t set, the index automatically acts as the write index.
Data stream aliases don’t automatically set a write data stream, even if the alias points to one data stream.
Value used to route indexing and search operations to a specific shard. Data stream aliases don’t support this parameter.
Value used to route search operations to a specific shard.
If specified, this overwrites the routing value for search operations.
Data stream aliases don’t support this parameter.
POST _aliases
{
"actions": [
{
"add": {
"index": "my-data-stream",
"alias": "my-alias"
}
}
]
}resp = client.indices.update_aliases(
actions=[
{
"add": {
"index": "my-data-stream",
"alias": "my-alias"
}
}
],
)const response = await client.indices.updateAliases({
actions: [
{
add: {
index: "my-data-stream",
alias: "my-alias",
},
},
],
});response = client.indices.update_aliases(
body: {
"actions": [
{
"add": {
"index": "my-data-stream",
"alias": "my-alias"
}
}
]
}
)$resp = $client->indices()->updateAliases([
"body" => [
"actions" => array(
[
"add" => [
"index" => "my-data-stream",
"alias" => "my-alias",
],
],
),
],
]);curl -X POST -H "Authorization: ApiKey $ELASTIC_API_KEY" -H "Content-Type: application/json" -d '{"actions":[{"add":{"index":"my-data-stream","alias":"my-alias"}}]}' "$ELASTICSEARCH_URL/_aliases"client.indices().updateAliases(u -> u
.actions(a -> a
.add(ad -> ad
.alias("my-alias")
.index("my-data-stream")
)
)
);
{
"actions": [
{
"add": {
"index": "my-data-stream",
"alias": "my-alias"
}
}
]
}Removes the data stream lifecycle from a data stream, rendering it not managed by the data stream lifecycle.
A comma-separated list of data streams of which the data stream lifecycle will be deleted; use * to get all data streams
Whether wildcard expressions should get expanded to open or closed indices (default: open)
Supported values include:
all: Match any data stream or index, including hidden ones.open: Match open, non-hidden indices. Also matches any non-hidden data stream.closed: Match closed, non-hidden indices. Also matches any non-hidden data stream. Data streams cannot be closed.hidden: Match hidden data streams and hidden indices. Must be combined with open, closed, or both.none: Wildcard expressions are not accepted.Values are all, open, closed, hidden, or none.
Specify timeout for connection to master
Values are -1 or 0.
Explicit timestamp for the document
Values are -1 or 0.
DELETE _data_stream/my-data-stream/_lifecycle
resp = client.indices.delete_data_lifecycle(
name="my-data-stream",
)const response = await client.indices.deleteDataLifecycle({
name: "my-data-stream",
});response = client.indices.delete_data_lifecycle(
name: "my-data-stream"
)$resp = $client->indices()->deleteDataLifecycle([
"name" => "my-data-stream",
]);curl -X DELETE -H "Authorization: ApiKey $ELASTIC_API_KEY" "$ELASTICSEARCH_URL/_data_stream/my-data-stream/_lifecycle"client.indices().deleteDataLifecycle(d -> d
.name("my-data-stream")
);
{
"acknowledged": true
}Comma-separated list of index template names used to limit the request. Wildcard (*) expressions are supported.
If true, the request retrieves information from the local node only. Defaults to false, which means information is retrieved from the master node.
If true, returns settings in flat format.
Period to wait for a connection to the master node. If no response is received before the timeout expires, the request fails and returns an error.
Values are -1 or 0.
If true, returns all relevant default configurations for the index template.
GET _index_template/*?filter_path=index_templates.name,index_templates.index_template.index_patterns,index_templates.index_template.data_stream
resp = client.indices.get_index_template(
name="*",
filter_path="index_templates.name,index_templates.index_template.index_patterns,index_templates.index_template.data_stream",
)const response = await client.indices.getIndexTemplate({
name: "*",
filter_path:
"index_templates.name,index_templates.index_template.index_patterns,index_templates.index_template.data_stream",
});response = client.indices.get_index_template(
name: "*",
filter_path: "index_templates.name,index_templates.index_template.index_patterns,index_templates.index_template.data_stream"
)$resp = $client->indices()->getIndexTemplate([
"name" => "*",
"filter_path" => "index_templates.name,index_templates.index_template.index_patterns,index_templates.index_template.data_stream",
]);curl -X GET -H "Authorization: ApiKey $ELASTIC_API_KEY" "$ELASTICSEARCH_URL/_index_template/*?filter_path=index_templates.name,index_templates.index_template.index_patterns,index_templates.index_template.data_stream"