Skip to content

Instantly share code, notes, and snippets.

@iceman91176

iceman91176/quickwit-openapi.yaml

Created November 24, 2025 11:44
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save iceman91176/5abdd914d02d3cdd64e9d6394a301999 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save iceman91176/5abdd914d02d3cdd64e9d6394a301999 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
quickwit-openapi.yaml
openapi: 3.0.3
info:
title: Quickwit
description: REST API server
contact:
name: Quickwit, Inc.
email: [email protected]
license:
name: AGPL-3.0-or-later
version: 0.8.2
paths:
/api/v1/_elastic:
get:
tags:
- Cluster Info
operationId: elastic_cluster_info_filter
responses: {}
/api/v1/cluster:
get:
tags:
- Cluster Info
summary: Get cluster information.
description: Get cluster information.
operationId: get_cluster
responses:
'200':
description: Successfully fetched cluster information.
content:
application/json:
schema:
$ref: '#/components/schemas/ClusterSnapshot'
/api/v1/config:
get:
tags:
- Node Info
operationId: node_config_handler
responses: {}
/api/v1/indexes:
get:
tags:
- Indexes
summary: Gets indexes metadata.
description: Gets indexes metadata.
operationId: list_indexes_metadata
parameters:
- name: index_id_patterns
in: query
required: false
schema:
type: array
items:
type: string
nullable: true
- name: index_id_patterns
in: path
description: The index ID pattern to retrieve indexes for.
required: true
schema:
type: string
responses:
'200':
description: Successfully fetched all indexes.
content:
application/json:
schema:
type: array
items:
$ref: '#/components/schemas/VersionedIndexMetadata'
post:
tags:
- Indexes
summary: Creates index.
description: Creates index.
operationId: create_index
parameters:
- name: overwrite
in: query
required: false
schema:
type: boolean
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/VersionedIndexConfig'
required: true
responses:
'200':
description: Successfully created index.
content:
application/json:
schema:
$ref: '#/components/schemas/VersionedIndexMetadata'
/api/v1/indexes/{index_id}:
delete:
tags:
- Indexes
summary: Deletes index.
description: Deletes index.
operationId: delete_index
parameters:
- name: dry_run
in: query
required: false
schema:
type: boolean
- name: index_id
in: path
description: The index ID to delete.
required: true
schema:
type: string
responses:
'200':
description: Successfully deleted index.
content:
application/json:
schema:
type: array
items:
$ref: '#/components/schemas/FileEntry'
/api/v1/indexes/{index_id}/clear:
put:
tags:
- Indexes
summary: Removes all of the data (splits, queued document) associated with the index, but keeps the index
description: |-
Removes all of the data (splits, queued document) associated with the index, but keeps the index
configuration. (See also, `delete-index`).
operationId: clear_index
parameters:
- name: index_id
in: path
description: The index ID to clear.
required: true
schema:
type: string
responses:
'200':
description: Successfully cleared index.
/api/v1/indexes/{index_id}/describe:
get:
tags:
- Indexes
summary: Describes an index.
description: Describes an index.
operationId: describe_index
parameters:
- name: index_id
in: path
description: The index ID to describe.
required: true
schema:
type: string
responses:
'200':
description: Successfully fetched stats about Index.
content:
application/json:
schema:
$ref: '#/components/schemas/IndexStats'
/api/v1/indexes/{index_id}/sources:
post:
tags:
- Sources
summary: Creates Source.
description: Creates Source.
operationId: create_source
parameters:
- name: index_id
in: path
description: The index ID to create a source for.
required: true
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/VersionedSourceConfig'
required: true
responses:
'200':
description: Successfully created source.
content:
application/json:
schema:
$ref: '#/components/schemas/VersionedSourceConfig'
/api/v1/indexes/{index_id}/sources/{source_id}:
delete:
tags:
- Sources
summary: Deletes source.
description: Deletes source.
operationId: delete_source
parameters:
- name: index_id
in: path
description: The index ID to remove the source from.
required: true
schema:
type: string
- name: source_id
in: path
description: The source ID to remove from the index.
required: true
schema:
type: string
responses:
'200':
description: Successfully deleted source.
/api/v1/indexes/{index_id}/sources/{source_id}/reset-checkpoint:
put:
tags:
- Sources
summary: Resets source checkpoint.
description: Resets source checkpoint.
operationId: reset_source_checkpoint
parameters:
- name: index_id
in: path
description: The index ID of the source.
required: true
schema:
type: string
- name: source_id
in: path
description: The source ID whose checkpoint is reset.
required: true
schema:
type: string
responses:
'200':
description: Successfully reset source checkpoint.
/api/v1/indexes/{index_id}/sources/{source_id}/toggle:
put:
tags:
- Sources
summary: Toggles source.
description: Toggles source.
operationId: toggle_source
parameters:
- name: index_id
in: path
description: The index ID of the source.
required: true
schema:
type: string
- name: source_id
in: path
description: The source ID to toggle.
required: true
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/ToggleSource'
required: true
responses:
'200':
description: Successfully toggled source.
/api/v1/indexes/{index_id}/splits:
get:
tags:
- Indexes
summary: Get splits.
description: Get splits.
operationId: list_splits
parameters:
- name: offset
in: query
description: If set, define the number of splits to skip
required: false
schema:
type: integer
nullable: true
minimum: 0
- name: limit
in: query
description: If set, restrict maximum number of splits to retrieve
required: false
schema:
type: integer
nullable: true
minimum: 0
- name: split_states
in: query
description: A specific split state(s) to filter by.
required: false
schema:
type: array
items:
$ref: '#/components/schemas/SplitState'
nullable: true
- name: start_timestamp
in: query
description: |-
If set, restrict splits to documents with a `timestamp >= start_timestamp`.
This timestamp is in seconds.
required: false
schema:
type: integer
format: int64
nullable: true
- name: end_timestamp
in: query
description: |-
If set, restrict splits to documents with a `timestamp < end_timestamp`.
This timestamp is in seconds.
required: false
schema:
type: integer
format: int64
nullable: true
- name: end_create_timestamp
in: query
description: If set, restrict splits whose creation dates are before this date.
required: false
schema:
type: integer
format: int64
nullable: true
- name: index_id
in: path
description: The index ID to retrieve splits for.
required: true
schema:
type: string
responses:
'200':
description: Successfully fetched splits.
content:
application/json:
schema:
$ref: '#/components/schemas/ListSplitsResponse'
/api/v1/indexes/{index_id}/splits/mark-for-deletion:
put:
tags:
- Splits
summary: Marks splits for deletion.
description: Marks splits for deletion.
operationId: mark_splits_for_deletion
parameters:
- name: index_id
in: path
description: The index ID to mark splits for deletion for.
required: true
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/SplitsForDeletion'
required: true
responses:
'200':
description: Successfully marked splits for deletion.
/api/v1/indexing:
get:
tags:
- Indexing
summary: Observe Indexing Pipeline
description: Observe Indexing Pipeline
operationId: indexing_endpoint
responses:
'200':
description: Successfully observed indexing pipelines.
content:
application/json:
schema:
$ref: '#/components/schemas/IndexingStatistics'
/api/v1/templates:
get:
tags:
- Templates
summary: Retrieves all the index templates stored in the metastore.
description: Retrieves all the index templates stored in the metastore.
operationId: list_index_templates
responses:
'200':
description: The index template was successfuly retrieved.
post:
tags:
- Templates
summary: Creates a new index template.
description: Creates a new index template.
operationId: create_index_template
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/VersionedIndexTemplate'
required: true
responses:
'200':
description: The index template was successfuly created.
/api/v1/templates/{template_id}:
get:
tags:
- Templates
summary: Retrieves the index template identified by `template_id`.
description: Retrieves the index template identified by `template_id`.
operationId: get_index_template
responses:
'200':
description: The index template was successfuly retrieved.
'404':
description: The index template was not found.
put:
tags:
- Templates
summary: Updates the index template identified by `template_id`.
description: Updates the index template identified by `template_id`.
operationId: update_index_template
responses:
'200':
description: The index template was successfuly retrieved.
'404':
description: The index template was not found.
delete:
tags:
- Templates
summary: Deletes the index template identified by the provided `template_id`.
description: Deletes the index template identified by the provided `template_id`.
operationId: delete_index_template
responses:
'200':
description: The index template was successfuly deleted.
'404':
description: The index template was not found.
/api/v1/version:
get:
tags:
- Node Info
operationId: node_version_handler
responses: {}
/api/v1/{index_id}/delete-tasks:
get:
tags:
- Delete Tasks
summary: Get Delete Tasks
description: |-
Get Delete Tasks
Returns delete tasks in json format for a given `index_id`.
operationId: get_delete_tasks
parameters:
- name: index_id
in: path
description: The index ID to retrieve delete tasks for.
required: true
schema:
type: string
responses:
'200':
description: Successfully fetched delete tasks.
content:
application/json:
schema:
type: array
items:
$ref: '#/components/schemas/DeleteTask'
post:
tags:
- Delete Tasks
summary: Create Delete Task
description: |-
Create Delete Task
This operation will not be immediately executed, instead it will be added to a queue
and cleaned up in the near future.
operationId: post_delete_request
parameters:
- name: index_id
in: path
description: The index ID to add the delete task to.
required: true
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/DeleteQueryRequest'
required: true
responses:
'200':
description: Successfully added a new delete task.
content:
application/json:
schema:
$ref: '#/components/schemas/DeleteTask'
/api/v1/{index_id}/ingest:
post:
tags:
- Ingest
summary: Ingest documents
description: Ingest documents
operationId: ingest
parameters:
- name: index_id
in: path
description: The index ID to add docs to.
required: true
schema:
type: string
- name: commit
in: query
description: Force or wait for commit at the end of the indexing operation.
required: false
schema:
allOf:
- $ref: '#/components/schemas/CommitType'
nullable: true
requestBody:
description: Documents to ingest in NDJSON format and limited to 10MB
content:
application/json:
schema:
type: string
required: true
responses:
'200':
description: Successfully ingested documents.
content:
application/json:
schema:
$ref: '#/components/schemas/IngestResponse'
/api/v1/{index_id}/search:
get:
tags:
- Search
summary: Search Index (GET Variant)
description: |-
Search Index (GET Variant)
Parses the search request from the request query string.
operationId: search_get_handler
parameters:
- name: query
in: query
description: Query text. The query language is that of tantivy.
required: true
schema:
type: string
- name: aggs
in: query
description: The aggregation JSON string.
required: false
schema:
type: object
- name: search_field
in: query
required: false
schema:
type: array
items:
type: string
nullable: true
- name: snippet_fields
in: query
description: Fields to extract snippets on.
required: false
schema:
type: array
items:
type: string
nullable: true
- name: start_timestamp
in: query
description: |-
If set, restrict search to documents with a `timestamp >= start_timestamp`.
This timestamp is expressed in seconds.
required: false
schema:
type: integer
format: int64
nullable: true
- name: end_timestamp
in: query
description: |-
If set, restrict search to documents with a `timestamp < end_timestamp``.
This timestamp is expressed in seconds.
required: false
schema:
type: integer
format: int64
nullable: true
- name: max_hits
in: query
description: Maximum number of hits to return (by default 20).
required: false
schema:
type: integer
format: int64
minimum: 0
- name: start_offset
in: query
description: |-
First hit to return. Together with num_hits, this parameter
can be used for pagination.
E.g.
The results with rank [start_offset..start_offset + max_hits) are returned
required: false
schema:
type: integer
format: int64
minimum: 0
- name: format
in: query
description: The output format.
required: false
schema:
$ref: '#/components/schemas/BodyFormat'
- name: sort_by
in: query
description: Specifies how documents are sorted.
required: false
schema:
type: string
- name: count_all
in: query
required: false
schema:
type: boolean
- name: index_id
in: path
description: The index ID to search.
required: true
schema:
type: string
responses:
'200':
description: Successfully executed search.
content:
application/json:
schema:
$ref: '#/components/schemas/SearchResponseRest'
post:
tags:
- Search
summary: Search Index (POST Variant)
description: |-
Search Index (POST Variant)
REST POST search handler.
Parses the search request from the request body.
operationId: search_post_handler
parameters:
- name: index_id
in: path
description: The index ID to search.
required: true
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/SearchRequestQueryString'
required: true
responses:
'200':
description: Successfully executed search.
content:
application/json:
schema:
$ref: '#/components/schemas/SearchResponseRest'
/api/v1/{index_id}/search/stream:
get:
tags:
- Search
summary: Stream Search Index
description: Stream Search Index
operationId: search_stream_handler
parameters:
- name: query
in: query
description: Query text. The query language is that of tantivy.
required: true
schema:
type: string
- name: search_field
in: query
required: false
schema:
type: array
items:
type: string
nullable: true
- name: snippet_fields
in: query
description: Fields to extract snippet on
required: false
schema:
type: array
items:
type: string
nullable: true
- name: start_timestamp
in: query
description: If set, restricts search to documents with a `timestamp >= start_timestamp`.
required: false
schema:
type: integer
format: int64
nullable: true
- name: end_timestamp
in: query
description: If set, restricts search to documents with a `timestamp < end_timestamp``.
required: false
schema:
type: integer
format: int64
nullable: true
- name: fast_field
in: query
description: The fast field to extract.
required: true
schema:
type: string
- name: output_format
in: query
description: The requested output format.
required: false
schema:
$ref: '#/components/schemas/OutputFormat'
- name: partition_by_field
in: query
required: false
schema:
type: string
nullable: true
- name: index_id
in: path
description: The index ID to search.
required: true
schema:
type: string
responses:
'200':
description: Successfully executed search.
/api/v1/{index_id}/tail:
get:
tags:
- Ingest
summary: Returns the last few ingested documents.
description: Returns the last few ingested documents.
operationId: tail_endpoint
parameters:
- name: index_id
in: path
description: The index ID to tail.
required: true
schema:
type: string
responses:
'200':
description: Successfully fetched documents.
content:
application/json:
schema:
$ref: '#/components/schemas/FetchResponse'
/api/v1/{otel-traces-index-id}/jaeger/api/services:
get:
tags:
- Jaeger
operationId: jaeger_services_handler
parameters:
- name: otel-traces-index-id
in: path
description: The name of the index to get services for.
required: true
schema:
type: string
responses:
'200':
description: Successfully fetched services names.
content:
application/json:
schema:
$ref: '#/components/schemas/JaegerResponseBody'
/api/v1/{otel-traces-index-id}/jaeger/api/services/{service}/operations:
get:
tags:
- Jaeger
operationId: jaeger_service_operations_handler
parameters:
- name: otel-traces-index-id
in: path
description: The name of the index to get operations for.
required: true
schema:
type: string
- name: service
in: path
description: The name of the service to get operations for.
required: true
schema:
type: string
responses:
'200':
description: Successfully fetched operations names the given service.
content:
application/json:
schema:
$ref: '#/components/schemas/JaegerResponseBody'
/api/v1/{otel-traces-index-id}/jaeger/api/traces:
get:
tags:
- Jaeger
operationId: jaeger_traces_search_handler
parameters:
- name: otel-traces-index-id
in: path
description: The name of the index to get traces for.
required: true
schema:
type: string
- name: service
in: query
description: The service name.
required: false
schema:
type: string
nullable: true
- name: operation
in: query
description: The operation name.
required: false
schema:
type: string
nullable: true
- name: start
in: query
description: The start time in nanoseconds.
required: false
schema:
type: integer
format: int64
nullable: true
- name: end
in: query
description: The end time in nanoseconds.
required: false
schema:
type: integer
format: int64
nullable: true
- name: tags
in: query
description: Sets tags with values in the logfmt format, such as error=true status=200.
required: false
schema:
type: string
nullable: true
- name: min_duration
in: query
description: Filters all traces with a duration higher than the set value. Possible values are 1.2s, 100ms, 500us.
required: false
schema:
type: string
nullable: true
- name: max_duration
in: query
description: Filters all traces with a duration lower than the set value. Possible values are 1.2s, 100ms, 500us.
required: false
schema:
type: string
nullable: true
- name: limit
in: query
description: Limits the number of traces returned.
required: false
schema:
type: integer
format: int32
nullable: true
responses:
'200':
description: Successfully fetched traces information.
content:
application/json:
schema:
$ref: '#/components/schemas/JaegerResponseBody'
/api/v1/{otel-traces-index-id}/jaeger/api/traces/{id}:
get:
tags:
- Jaeger
operationId: jaeger_traces_handler
parameters:
- name: otel-traces-index-id
in: path
description: The name of the index to get traces for.
required: true
schema:
type: string
- name: id
in: path
description: The ID of the trace to get spans for.
required: true
schema:
type: string
responses:
'200':
description: Successfully fetched traces spans for the provided trace ID.
content:
application/json:
schema:
$ref: '#/components/schemas/JaegerResponseBody'
/debugging:
get:
tags:
- Get debug information for node
summary: Get Node debug information.
description: |-
Get Node debug information.
The format is not guaranteed to ever be stable, and is meant to provide some introspection to
help with debugging.
operationId: debugging_handler
responses:
'200':
description: Successfully fetched debugging info.
content:
application/json:
schema:
$ref: '#/components/schemas/GetDebugStateRequestResponse'
/health/livez:
get:
tags:
- Node Health
summary: Get Node Liveliness
description: Get Node Liveliness
operationId: get_liveness
responses:
'200':
description: The service is live.
content:
text/plain:
schema:
type: boolean
'503':
description: The service is not live.
content:
text/plain:
schema:
type: boolean
/health/readyz:
get:
tags:
- Node Health
summary: Get Node Readiness
description: Get Node Readiness
operationId: get_readiness
responses:
'200':
description: The service is ready.
content:
text/plain:
schema:
type: boolean
'503':
description: The service is not ready.
content:
text/plain:
schema:
type: boolean
/metrics:
get:
tags:
- Get Metrics
summary: Get Node Metrics
description: |-
Get Node Metrics
These are in the form of prometheus metrics.
operationId: metrics_handler
responses:
'200':
description: Successfully fetched metrics.
content:
text/plain:
schema:
type: string
components:
schemas:
BodyFormat:
type: string
description: Body output format used for the REST API.
enum:
- json
- pretty_json
ClusterSnapshot:
type: object
required:
- cluster_id
- self_node_id
- ready_nodes
- live_nodes
- dead_nodes
- chitchat_state_snapshot
properties:
chitchat_state_snapshot:
type: object
description: A complete snapshot of the Chitchat cluster state.
cluster_id:
type: string
description: The ID of the cluster that the node is a part of.
example: qw-cluster-1
dead_nodes:
type: array
items:
$ref: '#/components/schemas/NodeIdSchema'
description: The set of cluster node IDs flagged as dead or faulty.
live_nodes:
type: array
items:
$ref: '#/components/schemas/NodeIdSchema'
description: The set of cluster node IDs that are alive but not ready.
ready_nodes:
type: array
items:
$ref: '#/components/schemas/NodeIdSchema'
description: The set of cluster node IDs that are ready to handle requests.
self_node_id:
$ref: '#/components/schemas/NodeIdSchema'
CommitType:
type: string
description: Specifies if the ingest request should block waiting for the records to be committed.
enum:
- auto
- wait_for
- force
ConstWriteAmplificationMergePolicyConfig:
type: object
properties:
maturation_period:
type: string
description: |-
Duration relative to `split.created_timestamp` after which a split
becomes mature.
If `now() >= split.created_timestamp + maturation_period` then
the split is considered mature.
max_merge_factor:
type: integer
description: Maximum number of splits that can be merged together in a single merge operation.
minimum: 0
max_merge_ops:
type: integer
description: Maximum number of merges that a given split should undergo.
minimum: 0
merge_factor:
type: integer
description: Number of splits to merge together in a single merge operation.
minimum: 0
additionalProperties: false
CpuCapacity:
type: integer
format: int32
description: |-
The CpuCapacity represents an amount of CPU resource available.
It is usually expressed in CPU millis (For instance, one full CPU thread is
displayed as `1000m`).
minimum: 0
DeleteQuery:
type: object
required:
- index_uid
- query_ast
properties:
end_timestamp:
type: integer
format: int64
description: If set, restrict search to documents with a `timestamp < end_timestamp``.
nullable: true
index_uid:
type: string
description: Index ID.
query_ast:
type: string
description: |-
Query text. The query language is that of tantivy.
Query AST serialized in JSON
start_timestamp:
type: integer
format: int64
description: If set, restrict search to documents with a `timestamp >= start_timestamp`.
nullable: true
DeleteQueryRequest:
type: object
description: |-
This struct represents the delete query passed to
the rest API.
required:
- query
properties:
end_timestamp:
type: integer
format: int64
description: If set, restrict delete to documents with a `timestamp < end_timestamp``.
nullable: true
query:
type: string
description: Query text. The query language is that of tantivy.
search_fields:
type: array
items:
type: string
start_timestamp:
type: integer
format: int64
description: If set, restrict delete to documents with a `timestamp >= start_timestamp`.
nullable: true
additionalProperties: false
DeleteTask:
type: object
required:
- create_timestamp
- opstamp
properties:
create_timestamp:
type: integer
format: int64
delete_query:
allOf:
- $ref: '#/components/schemas/DeleteQuery'
nullable: true
opstamp:
type: integer
format: int64
minimum: 0
DocBatch:
type: object
required:
- index_id
- doc_buffer
- doc_lengths
properties:
doc_buffer:
type: string
format: binary
doc_lengths:
type: array
items:
type: integer
format: int32
minimum: 0
index_id:
type: string
DocMapping:
type: object
properties:
dynamic_mapping:
allOf:
- $ref: '#/components/schemas/QuickwitJsonOptions'
nullable: true
field_mappings:
type: array
items:
$ref: '#/components/schemas/FieldMappingEntryForSerialization'
description: |-
The mapping of the index schema fields.
This defines the name, type and other information about the field(s).
Properties are determined by the specified type, for more information
please see: <https://quickwit.io/docs/configuration/index-config#field-types>
index_field_presence:
type: boolean
max_num_partitions:
type: integer
format: int32
minimum: 0
mode:
$ref: '#/components/schemas/ModeType'
partition_key:
type: string
nullable: true
store_source:
type: boolean
tag_fields:
type: array
items:
type: string
timestamp_field:
type: string
nullable: true
tokenizers:
type: array
items:
$ref: '#/components/schemas/TokenizerEntry'
additionalProperties: false
FastFieldOptions:
oneOf:
- type: string
enum:
- Disabled
- type: object
required:
- EnabledWithNormalizer
properties:
EnabledWithNormalizer:
type: object
required:
- normalizer
properties:
normalizer:
$ref: '#/components/schemas/QuickwitTextNormalizer'
FetchResponse:
type: object
properties:
doc_batch:
allOf:
- $ref: '#/components/schemas/DocBatch'
nullable: true
first_position:
type: integer
format: int64
nullable: true
minimum: 0
FieldMappingEntryForSerialization:
type: object
description: |-
A `FieldMappingEntry` defines how a field is indexed, stored,
and mapped from a JSON document to the related index fields.
Property parameters which defines the way the value must be indexed.
Properties are determined by the specified type, for more information
please see: <https://quickwit.io/docs/configuration/index-config#field-types>
required:
- name
- type
properties:
name:
type: string
description: Field name in the index schema.
type:
type: string
additionalProperties:
type: object
FileSourceParams:
type: object
properties:
filepath:
type: string
description: Path of the file to read. Assume stdin if None.
additionalProperties: false
IndexConfigV0_8:
type: object
required:
- index_id
- doc_mapping
properties:
doc_mapping:
$ref: '#/components/schemas/DocMapping'
index_id:
type: string
index_uri:
type: string
indexing_settings:
$ref: '#/components/schemas/IndexingSettings'
retention:
allOf:
- $ref: '#/components/schemas/RetentionPolicy'
nullable: true
search_settings:
$ref: '#/components/schemas/SearchSettings'
additionalProperties: false
IndexMetadataV0_8:
type: object
required:
- index_config
- checkpoint
- sources
properties:
checkpoint:
type: object
create_timestamp:
type: integer
format: int64
index_config:
$ref: '#/components/schemas/VersionedIndexConfig'
index_uid:
type: string
sources:
type: array
items:
$ref: '#/components/schemas/VersionedSourceConfig'
IndexRecordOptionSchema:
type: string
enum:
- basic
- freq
- position
IndexStats:
type: object
description: Describes an index with its main information and statistics.
required:
- index_id
- index_uri
- num_published_splits
- size_published_splits
- num_published_docs
- size_published_docs_uncompressed
properties:
index_id:
type: string
index_uri:
type: string
max_timestamp:
type: integer
format: int64
nullable: true
min_timestamp:
type: integer
format: int64
nullable: true
num_published_docs:
type: integer
format: int64
minimum: 0
num_published_splits:
type: integer
minimum: 0
size_published_docs_uncompressed:
type: integer
format: int64
minimum: 0
size_published_splits:
type: integer
format: int64
minimum: 0
timestamp_field_name:
type: string
nullable: true
IndexTemplateV0_8:
type: object
required:
- template_id
- index_id_patterns
- doc_mapping
properties:
description:
type: string
nullable: true
doc_mapping:
$ref: '#/components/schemas/DocMapping'
index_id_patterns:
type: array
items:
type: string
index_root_uri:
type: string
indexing_settings:
$ref: '#/components/schemas/IndexingSettings'
priority:
type: integer
minimum: 0
retention:
allOf:
- $ref: '#/components/schemas/RetentionPolicy'
nullable: true
search_settings:
$ref: '#/components/schemas/SearchSettings'
template_id:
type: string
additionalProperties: false
IndexingResources:
type: object
properties:
heap_size:
type: string
default: 2 GB
additionalProperties: false
IndexingSettings:
type: object
properties:
commit_timeout_secs:
type: integer
default: 60
minimum: 0
docstore_blocksize:
type: integer
default: 1000000
minimum: 0
docstore_compression_level:
type: integer
format: int32
default: 8
merge_policy:
$ref: '#/components/schemas/MergePolicyConfig'
resources:
$ref: '#/components/schemas/IndexingResources'
split_num_docs_target:
type: integer
description: |-
The merge policy aims to eventually produce mature splits that have a larger size but
are within close range of `split_num_docs_target`.
In other words, splits that contain a number of documents greater than or equal to
`split_num_docs_target` are considered mature and never merged.
minimum: 0
additionalProperties: false
IndexingStatistics:
type: object
description: A Struct that holds all statistical data about indexing
required:
- num_docs
- num_invalid_docs
- num_local_splits
- num_staged_splits
- num_uploaded_splits
- num_published_splits
- num_empty_splits
- total_bytes_processed
- total_size_splits
- generation
- num_spawn_attempts
- shard_ids
properties:
generation:
type: integer
description: Pipeline generation.
minimum: 0
num_docs:
type: integer
format: int64
description: Number of document processed (valid or not)
minimum: 0
num_empty_splits:
type: integer
format: int64
description: Number of empty batches
minimum: 0
num_invalid_docs:
type: integer
format: int64
description: Number of document parse error, or missing timestamps
minimum: 0
num_local_splits:
type: integer
format: int64
description: Number of created split
minimum: 0
num_published_splits:
type: integer
format: int64
description: Number of published splits
minimum: 0
num_spawn_attempts:
type: integer
description: Number of successive pipeline spawn attempts.
minimum: 0
num_staged_splits:
type: integer
format: int64
description: Number of staged splits
minimum: 0
num_uploaded_splits:
type: integer
format: int64
description: Number of uploaded splits
minimum: 0
pipeline_metrics_opt:
allOf:
- $ref: '#/components/schemas/PipelineMetrics'
nullable: true
shard_ids:
type: array
items:
type: integer
format: int64
minimum: 0
total_bytes_processed:
type: integer
format: int64
description: Size in byte of document processed
minimum: 0
total_size_splits:
type: integer
format: int64
description: Size in bytes of resulting split
minimum: 0
IngestResponse:
type: object
required:
- num_docs_for_processing
properties:
num_docs_for_processing:
type: integer
format: int64
minimum: 0
KafkaSourceParams:
type: object
required:
- topic
properties:
client_log_level:
type: string
description: Kafka client log level. Possible values are `debug`, `info`, `warn`, and `error`.
client_params:
type: object
description: Kafka client configuration parameters.
enable_backfill_mode:
type: boolean
description: When backfill mode is enabled, the source exits after reaching the end of the topic.
topic:
type: string
description: Name of the topic that the source consumes.
additionalProperties: false
KinesisSourceParams:
allOf:
- allOf:
- $ref: '#/components/schemas/RegionOrEndpoint'
nullable: true
- type: object
required:
- stream_name
properties:
enable_backfill_mode:
type: boolean
description: When backfill mode is enabled, the source exits after reaching the end of the stream.
stream_name:
type: string
MergePolicyConfig:
oneOf:
- type: object
required:
- type
properties:
type:
type: string
enum:
- no_merge
- allOf:
- $ref: '#/components/schemas/ConstWriteAmplificationMergePolicyConfig'
- type: object
required:
- type
properties:
type:
type: string
enum:
- limit_merge
- allOf:
- $ref: '#/components/schemas/StableLogMergePolicyConfig'
- type: object
required:
- type
properties:
type:
type: string
enum:
- stable_log
discriminator:
propertyName: type
ModeType:
type: string
description: '`Mode` describing how the unmapped field should be handled.'
enum:
- lenient
- strict
- dynamic
NgramTokenizerOption:
type: object
required:
- min_gram
- max_gram
properties:
max_gram:
type: integer
minimum: 0
min_gram:
type: integer
minimum: 0
prefix_only:
type: boolean
additionalProperties: false
NodeIdSchema:
type: object
required:
- node_id
- generation_id
- gossip_advertise_addr
properties:
generation_id:
type: integer
format: int64
description: A numeric identifier incremented every time the node leaves and rejoins the cluster.
example: '1683736537'
minimum: 0
gossip_advertise_addr:
type: string
description: The socket address peers should use to gossip with the node.
example: 127.0.0.1:8000
node_id:
type: string
description: The unique identifier of the node in the cluster.
example: node-1
OutputFormat:
type: string
enum:
- csv
- click_house_row_binary
PipelineMetrics:
type: object
required:
- cpu_millis
- throughput_mb_per_sec
properties:
cpu_millis:
$ref: '#/components/schemas/CpuCapacity'
throughput_mb_per_sec:
type: integer
format: int32
minimum: 0
PubSubSourceParams:
type: object
required:
- subscription
properties:
credentials_file:
type: string
description: |-
GCP service account credentials (`None` will use default via
GOOGLE_APPLICATION_CREDENTIALS)
Path to a google_cloud_auth::credentials::CredentialsFile serialized in JSON. See also
`<https://cloud.google.com/docs/authentication/application-default-credentials>` and
`<https://github.com/yoshidan/google-cloud-rust/tree/main/pubsub#automatically>` and
`<https://docs.rs/google-cloud-auth/0.12.0/google_cloud_auth/credentials/struct.CredentialsFile.html>`.
nullable: true
enable_backfill_mode:
type: boolean
description: When backfill mode is enabled, the source exits after reaching the end of the topic.
max_messages_per_pull:
type: integer
format: int32
description: Maximum number of messages returned by a pull request (default 1,000)
nullable: true
project_id:
type: string
description: GCP project ID (Defaults to credentials file project ID).
nullable: true
subscription:
type: string
description: Name of the subscription that the source consumes.
additionalProperties: false
PulsarSourceAuth:
oneOf:
- type: object
required:
- token
properties:
token:
type: string
- type: object
required:
- oauth2
properties:
oauth2:
type: object
required:
- issuer_url
- credentials_url
properties:
audience:
type: string
nullable: true
credentials_url:
type: string
issuer_url:
type: string
scope:
type: string
nullable: true
PulsarSourceParams:
type: object
required:
- topics
- address
properties:
address:
type: string
description: The connection URI for pulsar.
authentication:
allOf:
- $ref: '#/components/schemas/PulsarSourceAuth'
nullable: true
consumer_name:
type: string
description: The name to register with the pulsar source.
default: quickwit
topics:
type: array
items:
type: string
description: List of the topics that the source consumes.
additionalProperties: false
QuickwitJsonOptions:
type: object
description: |-
Options associated to a json field.
`QuickwitJsonOptions` is also used to configure
the dynamic mapping.
properties:
description:
type: string
description: Optional description of JSON object.
nullable: true
expand_dots:
type: boolean
description: If true, the '.' in json keys will be expanded.
fast:
$ref: '#/components/schemas/FastFieldOptions'
indexed:
type: boolean
description: If true, all of the element in the json object will be indexed.
record:
$ref: '#/components/schemas/IndexRecordOptionSchema'
stored:
type: boolean
description: If true, the field will be stored in the doc store.
tokenizer:
allOf:
- $ref: '#/components/schemas/QuickwitTextTokenizer'
nullable: true
additionalProperties: false
QuickwitTextNormalizer:
type: string
enum:
- raw
- lowercase
QuickwitTextTokenizer:
type: string
RegexTokenizerOption:
type: object
required:
- pattern
properties:
pattern:
type: string
additionalProperties: false
RegionOrEndpoint:
oneOf:
- type: object
required:
- region
properties:
region:
type: string
- type: object
required:
- endpoint
properties:
endpoint:
type: string
RetentionPolicy:
type: object
required:
- period
properties:
period:
type: string
description: |-
Duration of time for which the splits should be retained, expressed in a human-friendly way
(`1 hour`, `3 days`, `a week`, ...).
schedule:
type: string
description: |-
Defines the frequency at which the retention policy is evaluated and applied, expressed in
a human-friendly way (`hourly`, `daily`, ...) or as a cron expression (`0 0 * * * *`,
`0 0 0 * * *`).
additionalProperties: false
SearchRequestQueryString:
type: object
description: |-
This struct represents the QueryString passed to
the rest API.
required:
- query
properties:
aggs:
type: object
description: The aggregation JSON string.
count_all:
type: boolean
end_timestamp:
type: integer
format: int64
description: |-
If set, restrict search to documents with a `timestamp < end_timestamp``.
This timestamp is expressed in seconds.
nullable: true
format:
$ref: '#/components/schemas/BodyFormat'
max_hits:
type: integer
format: int64
description: Maximum number of hits to return (by default 20).
minimum: 0
query:
type: string
description: Query text. The query language is that of tantivy.
search_field:
type: array
items:
type: string
nullable: true
snippet_fields:
type: array
items:
type: string
description: Fields to extract snippets on.
nullable: true
sort_by:
$ref: '#/components/schemas/SortBy'
start_offset:
type: integer
format: int64
description: |-
First hit to return. Together with num_hits, this parameter
can be used for pagination.
E.g.
The results with rank [start_offset..start_offset + max_hits) are returned
minimum: 0
start_timestamp:
type: integer
format: int64
description: |-
If set, restrict search to documents with a `timestamp >= start_timestamp`.
This timestamp is expressed in seconds.
nullable: true
additionalProperties: false
SearchResponseRest:
type: object
description: |-
SearchResponseRest represents the response returned by the REST search API
and is meant to be serialized into JSON.
required:
- num_hits
- hits
- elapsed_time_micros
- errors
properties:
aggregations:
type: object
description: Aggregations.
elapsed_time_micros:
type: integer
format: int64
description: Elapsed time.
minimum: 0
errors:
type: array
items:
type: string
description: Search errors.
hits:
type: array
items:
type: object
description: List of hits returned.
num_hits:
type: integer
format: int64
description: Overall number of documents matching the query.
minimum: 0
snippets:
type: array
items:
type: object
description: List of snippets
SearchSettings:
type: object
properties:
default_search_fields:
type: array
items:
type: string
additionalProperties: false
SortBy:
type: object
required:
- sort_fields
properties:
sort_fields:
type: array
items:
$ref: '#/components/schemas/SortField'
description: Fields to sort on.
SortField:
type: object
required:
- field_name
- sort_order
properties:
field_name:
type: string
sort_datetime_format:
type: integer
format: int32
description: |-
Optional sort value format for datetime field only.
If none, the default output format for datetime field is
unix_timestamp_nanos.
nullable: true
sort_order:
type: integer
format: int32
SortOrder:
type: string
enum:
- asc
- desc
SourceConfigV0_7:
allOf:
- $ref: '#/components/schemas/SourceParams'
- type: object
required:
- source_id
properties:
desired_num_pipelines:
type: integer
minimum: 0
enabled:
type: boolean
input_format:
$ref: '#/components/schemas/SourceInputFormat'
max_num_pipelines_per_indexer:
type: integer
minimum: 0
source_id:
type: string
transform:
allOf:
- $ref: '#/components/schemas/TransformConfig'
nullable: true
SourceConfigV0_8:
allOf:
- $ref: '#/components/schemas/SourceParams'
- type: object
required:
- source_id
properties:
enabled:
type: boolean
input_format:
$ref: '#/components/schemas/SourceInputFormat'
num_pipelines:
type: integer
minimum: 0
source_id:
type: string
transform:
allOf:
- $ref: '#/components/schemas/TransformConfig'
nullable: true
SourceInputFormat:
type: string
enum:
- json
- otlp_logs_json
- otlp_logs_protobuf
- otlp_traces_json
- otlp_traces_protobuf
- plain_text
SourceParams:
oneOf:
- type: object
required:
- source_type
- params
properties:
params:
$ref: '#/components/schemas/FileSourceParams'
source_type:
type: string
enum:
- file
- type: object
required:
- source_type
properties:
source_type:
type: string
enum:
- ingest
- type: object
required:
- source_type
properties:
source_type:
type: string
enum:
- ingest-api
- type: object
required:
- source_type
properties:
source_type:
type: string
enum:
- ingest-cli
- type: object
required:
- source_type
- params
properties:
params:
$ref: '#/components/schemas/KafkaSourceParams'
source_type:
type: string
enum:
- kafka
- type: object
required:
- source_type
- params
properties:
params:
$ref: '#/components/schemas/KinesisSourceParams'
source_type:
type: string
enum:
- kinesis
- type: object
required:
- source_type
- params
properties:
params:
$ref: '#/components/schemas/PubSubSourceParams'
source_type:
type: string
enum:
- pubsub
- type: object
required:
- source_type
- params
properties:
params:
$ref: '#/components/schemas/PulsarSourceParams'
source_type:
type: string
enum:
- pulsar
- type: object
required:
- source_type
- params
properties:
params:
$ref: '#/components/schemas/VecSourceParams'
source_type:
type: string
enum:
- vec
- type: object
required:
- source_type
- params
properties:
params:
$ref: '#/components/schemas/VoidSourceParams'
source_type:
type: string
enum:
- void
discriminator:
propertyName: source_type
Split:
allOf:
- $ref: '#/components/schemas/VersionedSplitMetadata'
- type: object
required:
- split_state
- update_timestamp
properties:
publish_timestamp:
type: integer
format: int64
description: Timestamp for tracking when the split was published.
nullable: true
split_state:
$ref: '#/components/schemas/SplitState'
update_timestamp:
type: integer
format: int64
description: Timestamp for tracking when the split was last updated.
description: Carries split metadata.
SplitInfo:
type: object
description: A summarized version of the split metadata for display purposes.
required:
- split_id
- num_docs
- uncompressed_docs_size_bytes
- file_name
- file_size_bytes
properties:
file_name:
type: string
description: The name of the split file on disk.
file_size_bytes:
type: integer
format: int64
description: The size of the split file on disk in bytes.
minimum: 0
num_docs:
type: integer
description: The number of documents in the split.
minimum: 0
split_id:
type: string
description: The split ID.
uncompressed_docs_size_bytes:
type: integer
format: int64
description: The sum of the sizes of the original JSON payloads in bytes.
minimum: 0
SplitMetadataV0_8:
type: object
required:
- split_id
- index_uid
- num_docs
- uncompressed_docs_size_in_bytes
- footer_offsets
properties:
create_timestamp:
type: integer
format: int64
description: Timestamp for tracking when the split was created.
delete_opstamp:
type: integer
format: int64
description: Split delete opstamp.
minimum: 0
footer_offsets:
type: object
description: |-
Contains the range of bytes of the footer that needs to be downloaded
in order to open a split.
The footer offsets
make it possible to download the footer in a single call to `.get_slice(...)`.
index_uid:
type: string
description: Uid of the index this split belongs to.
maturity:
description: Split maturity either `Mature` or `Immature` with a given maturation period.
node_id:
type: string
nullable: true
num_docs:
type: integer
description: Number of records (or documents) in the split.
minimum: 0
num_merge_ops:
type: integer
minimum: 0
partition_id:
type: integer
format: int64
minimum: 0
source_id:
type: string
nullable: true
split_id:
type: string
description: |-
Split ID. Joined with the index URI (<index URI>/<split ID>), this ID
should be enough to uniquely identify a split.
In reality, some information may be implicitly configured
in the storage resolver: for instance, the Amazon S3 region.
tags:
type: array
items:
type: string
description: A set of tags for categorizing and searching group of splits.
time_range:
type: object
description: |-
If a timestamp field is available, the min / max timestamp in
the split.
nullable: true
uncompressed_docs_size_in_bytes:
type: integer
format: int64
description: |-
Sum of the size (in bytes) of the raw documents in this split.
Note this is not the split file size. It is the size of the original
JSON payloads.
minimum: 0
SplitState:
type: string
description: A split state.
enum:
- Staged
- Published
- MarkedForDeletion
SplitsForDeletion:
type: object
required:
- split_ids
properties:
split_ids:
type: array
items:
type: string
additionalProperties: false
StableLogMergePolicyConfig:
type: object
properties:
maturation_period:
type: string
description: |-
Duration relative to `split.created_timestamp` after which a split
becomes mature.
If `now() >= split.created_timestamp + maturation_period` then
the split is mature.
max_merge_factor:
type: integer
description: Maximum number of splits that can be merged together in a single merge operation.
minimum: 0
merge_factor:
type: integer
description: Number of splits to merge together in a single merge operation.
minimum: 0
min_level_num_docs:
type: integer
description: Number of docs below which all splits are considered as belonging to the same level.
minimum: 0
additionalProperties: false
ToggleSource:
type: object
required:
- enable
properties:
enable:
type: boolean
additionalProperties: false
TokenFilterType:
type: string
enum:
- remove_long
- lower_caser
- ascii_folding
TokenizerConfig:
allOf:
- $ref: '#/components/schemas/TokenizerType'
- type: object
properties:
filters:
type: array
items:
$ref: '#/components/schemas/TokenFilterType'
description: Tokenizer configuration.
TokenizerEntry:
allOf:
- $ref: '#/components/schemas/TokenizerConfig'
- type: object
required:
- name
properties:
name:
type: string
description: Tokenizer name.
description: A `TokenizerEntry` defines a custom tokenizer with its name and configuration.
TokenizerType:
oneOf:
- type: object
required:
- type
properties:
type:
type: string
enum:
- multilang
- allOf:
- $ref: '#/components/schemas/NgramTokenizerOption'
- type: object
required:
- type
properties:
type:
type: string
enum:
- ngram
- allOf:
- $ref: '#/components/schemas/RegexTokenizerOption'
- type: object
required:
- type
properties:
type:
type: string
enum:
- regex
- type: object
required:
- type
properties:
type:
type: string
enum:
- simple
- type: object
required:
- type
properties:
type:
type: string
enum:
- source_code
discriminator:
propertyName: type
TransformConfig:
type: object
required:
- script
properties:
script:
type: string
description: |-
[VRL] source code of the transform compiled to a VRL [`Program`](vrl::compiler::Program).
[VRL]: https://vector.dev/docs/reference/vrl/
timezone:
type: string
description: |-
Timezone used in the VRL [`Program`](vrl::compiler::Program) for date and time
manipulations. Defaults to `UTC` if not timezone is specified.
additionalProperties: false
VecSourceParams:
type: object
required:
- docs
- batch_num_docs
properties:
batch_num_docs:
type: integer
minimum: 0
docs:
type: array
items:
type: string
partition:
type: string
additionalProperties: false
VersionedIndexConfig:
oneOf:
- allOf:
- $ref: '#/components/schemas/IndexConfigV0_8'
- type: object
required:
- version
properties:
version:
type: string
enum:
- '0.8'
discriminator:
propertyName: version
VersionedIndexMetadata:
oneOf:
- allOf:
- $ref: '#/components/schemas/IndexMetadataV0_8'
- type: object
required:
- version
properties:
version:
type: string
enum:
- '0.8'
discriminator:
propertyName: version
VersionedIndexTemplate:
oneOf:
- allOf:
- $ref: '#/components/schemas/IndexTemplateV0_8'
- type: object
required:
- version
properties:
version:
type: string
enum:
- '0.8'
discriminator:
propertyName: version
VersionedSourceConfig:
oneOf:
- allOf:
- $ref: '#/components/schemas/SourceConfigV0_7'
- type: object
required:
- version
properties:
version:
type: string
enum:
- '0.7'
- allOf:
- $ref: '#/components/schemas/SourceConfigV0_8'
- type: object
required:
- version
properties:
version:
type: string
enum:
- '0.8'
discriminator:
propertyName: version
VersionedSplitMetadata:
oneOf:
- allOf:
- $ref: '#/components/schemas/SplitMetadataV0_8'
- type: object
required:
- version
properties:
version:
type: string
enum:
- '0.8'
discriminator:
propertyName: version
VoidSourceParams:
default: null
nullable: true
tags:
- name: Search
- name: Indexes
- name: Ingest
- name: Delete Tasks
- name: Node Health
- name: Sources
- name: Get Metrics
- name: Cluster Info
- name: Node Info
- name: Indexing
- name: Splits
- name: Jaeger
- name: Debugging
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment