API Reference

Retrieves parameters from the specified collection.

Get collection details

Creates a new collection with the given parameters.

Wait for operation commit timeout in seconds.
If timeout is reached - request will return with service error.

Create a collection

Drops the specified collection and all associated data in it.

Delete a collection

Updates the parameters of the specified collection.

Update collection parameters

Returns a list of all existing collections.

List all collections

Checks whether the specified collection exists.

Check collection existence

Collections

Retrieves all details from multiple points.

Define read consistency guarantees for the operation

Retrieve points

Performs the insert + update action on specified points. Any point with an existing {id} will be overwritten.

If true, wait for changes to actually happen

define ordering guarantees for the operation

Upsert points

Retrieves all details from a single point.

Retrieve a point

Deletes specified points from the collection.

Delete points

Updates specified vectors on points. All other unspecified vectors will stay intact.

Update vectors

Deletes specified vectors from points. All other unspecified vectors will stay intact.

Delete vectors

Sets payload values for specified points.

Set payload

Replaces the entire payload of a specified point with a new payload.

Overwrite payload

Deletes a specified key payload for points.

Delete payload

Removes the entire payload for specified points.

Name of the collection to clear payload from

Clear payload

Batch updates points, including their respective vectors and payloads.

Name of the collection to apply operations on

Batch update points

Returns all points in a page-by-page manner.
By default, all resulting points are sorted by {id}.
To query the next page specify the last {id} in the offset field.
Additionally, you can specify filters and sorting options.

Scroll points

Counts the number of points that match a specified filtering condition.

Count points

Points

Retrieves the closest points based on vector similarity and given filtering conditions.

If set, overrides global timeout for this request. Unit is seconds.

Search points

Retrieves the closest points in batches based on vector similarity and given filtering conditions.

Search batch points

Retrieves the closest points based on vector similarity and given filtering conditions, grouped by a given payload field.

Search point groups

Retrieves points that are closer to stored positive examples and further from negative examples.

Recommend points

Retrieves points in batches that are closer to stored positive examples and further from negative examples.

Recommend batch points

Retrieves points that are closer to stored positive examples and further from negative examples. Results are grouped by the specified payload field.

Recommend point groups

Retrieves the most similar points to a given target, constrained by the provided context.
Context Search: When only the context is provided (without a target), pairs of points are used to generate a loss that guides the search towards the area where most positive examples overlap. The score minimizes finding points closer to a negative example than to a positive example. The maximum score a point can achieve is 0.0, meaning many points may have a score of 0.0.
Target Search: When a target is provided (with or without context), the score consists of two parts: the integer part represents the rank with respect to the context, and the decimal part relates to the distance to the target. The context score for each pair is +1 if the point is closer to a positive example than to a negative example, and -1 otherwise.

Discover points

Retrieves points in batches based on the target and/or positive and negative example pairs.

Discover batch points

Universally query points. This endpoint covers all capabilities of search, recommend, discover, filters. But also enables hybrid and multi-stage queries.

Query points

Universally query points in batch. This endpoint covers all capabilities of search, recommend, discover, filters. But also enables hybrid and multi-stage queries.

Query points in batch

Search

Creates a payload index for a field in the specified collection.

Create payload index

Deletes a payload index for a field in the specified collection.

Name of the field where to delete the index

Delete payload index

Indexes

Retrieves a list of all snapshots for a specified collection.

List all snapshots (collection)

Creates a new snapshot for a specified collection.

Name of the collection for which to create a snapshot

If true, wait for changes to actually happen. If false - let changes happen in background. Default is true.

Create a snapshot (collection)

Recovers local collection data from an uploaded snapshot. This will overwrite any collection data stored on the node. If the collection does not exist, it will be created.

Defines source of truth for snapshot recovery

Optional SHA256 checksum to verify snapshot integrity before recovery.

RecoverFromUploadedSnapshotRequest

Recover from an uploaded snapshot (collection)

Recovers local collection data from a snapshot. This will overwrite any collection data stored on the node. If the collection does not exist, it will be created.

Recover from a snapshot (collection)

Downloads the specified snapshot file from a collection.

Download a snapshot (collection)

Deletes the specified snapshot for a collection.

Name of the collection for which to delete a snapshot

Delete a snapshot (collection)

Returns a list of all snapshots for the entire storage.

List all snapshots (storage)

Creates a new snapshot of the entire storage.

Create a snapshot (storage)

Downloads the specified snapshot of the entire storage as a file.

Download a snapshot (storage)

Deletes the specified snapshot of the entire storage.

Delete a snapshot (storage)

Recovers the shard of a local collection from an uploaded snapshot. This will overwrite any collection data, which is stored in this shard.

RecoverShardFromUploadedSnapshotRequest

Recover from an uploaded snapshot (shard)

Recovers the shard of a local collection from a snapshot. This will overwrite any collection data, which is stored in this shard.

Recover from a snapshot (shard)

Returns a list of all snapshots for a shard from a collection.

List all snapshots (shard)

Creates a new snapshot of a shard from a collection.

Create a snapshot (shard)

Downloads the specified snapshot of a shard from a collection as a file.

Download a snapshot (shard)

Deletes the specified snapshot of a shard from a collection.

Delete a snapshot (shard)

Snapshots

Updates aliases for the specified collections.

Update collection aliases

Retrieves a list of all aliases for the specified collection.

List collection aliases

Retrieves a list of all existing aliases.

List all aliases

Aliases

Returns information about the cluster's current state and composition.

Check cluster status

Creates one or more shard keys for a specified collection.

Name of the collection to create shards for

Create a shard key

Deletes one or more shard keys for a specified collection.

Delete a shard key

Attempts to restore or synchronize the node's current state with that of its peers.

Recover cluster state

Attempts to remove the node from the cluster. This endpoint returns an error if the node (peer) has shards on it.

If true - removes peer even if it has shards/replicas on it.

Remove peer from cluster

Retrieves cluster details for a specified collection.

Name of the collection to retrieve the cluster info for

Retrieve cluster details

Updates the cluster configuration for a specified collection.

Name of the collection on which to to apply the cluster update operation

Update cluster setup

Distributed

Collects telemetry data, such as: application info, system info, collection info, cluster info, configs and statistics.

Collect telemetry data

Returns details about the running Qdrant instance.

Retrieve instance details

Collect metrics data, such as: application info, collection info, cluster info and statistics.

Collect Prometheus metrics data

Retrieves the current lock setting. If write is false, all write operations and collection creation are restricted.

Check write protection

Restricts all write operations and forbids collection creation. This endpoint also returns previous lock options.

Set write protection

Checks the health of individual instance.

Kubernetes health check

Monitors the container responsiveness and alerts in case of failure.

Kubernetes liveness probe

Checks the instance to see when it can start accepting traffic.

Kubernetes readiness probe

Service

Retrieves a report of performance issues and configuration suggestions.

Report issues

Clear issues

Beta

AbortShardTransfer

AbortTransferOperation

AliasDescription

Group of all the possible operations related to collection aliases

AliasOperations

AnyVariants

AppBuildTelemetry

AppBuildTelemetryFeatures

AppBuildTelemetrySystem

AppFeaturesTelemetry

Batch

BatchPayloadsItem

BatchVectorStruct

BinaryQuantization

BinaryQuantizationConfig

ClearPayloadOperation

ClusterConfigTelemetry

ClusterOperations

Information about current cluster status and structure

ClusterStatus

ClusterStatusDisabled

ClusterStatusEnabled

Peers composition of the cluster with main information

Consequent failures of message send operations in consensus by peer address. On the first success to send to that peer - entry is removed from this hashmap.

ClusterStatusTelemetry

ClusterStatusTelemetryRole

ClusterTelemetry

ClusterTelemetryConfig

ClusterTelemetryStatus

Current clustering distribution for the collection

CollectionClusterInfo

CollectionConfig

CollectionConfigQuantizationConfig

CollectionDescription

State of existence of a collection, true = exists, false = does not exist

CollectionExistence

Current statistics and configuration of the collection

CollectionInfo

Approximate number of indexed vectors in the collection. Indexed vectors in large segments are faster to query, as it is stored in a specialized vector index.

1	curl -X POST http://localhost:6333/cluster/recover \
2	-H "api-key: <apiKey>"

1	{
2	"time": 1.1,
3	"status": "status",
4	"result": true
5	}

Recover cluster state

Response