Create Namespace
Creates a new namespace with specified feature extractors and payload indexes.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
Request schema for creating a new namespace.
Name of the namespace to create
3 - 64"product-search"
Optional namespace ID override. Used for recovery/migration when recreating a namespace with a known ID. If not provided, a new ID is auto-generated.
Namespace mode. 'managed' (default) uses Mixpeek feature extractors. 'standalone' allows BYO vectors without extractors. If omitted and ONLY vector_configs is provided (no features/feature_extractors), standalone is inferred.
Type of namespace. STANDARD for regular namespaces, MARKETPLACE for curated datasets.
standard, marketplace Ownership scope. ORG (default) creates an org-scoped namespace. SYSTEM requires Mixpeek admin privileges and creates a namespace visible read-only to every org — used for curated sample corpora.
org, system Description of the namespace
"This namespace contains playlists from Spotify"
Modality+features config (contract v2 §6.2, D9): feature keys from GET /v1/collections/features (e.g. ['image_search', 'faces'] or ['custom:']). Resolved server-side to the UNION of feature extractors the namespace needs — the preferred alternative to feature_extractors (extractor names are internal implementation). A namespace hosts many collections, so multiple features spanning multiple extractors are fine here. May be combined with feature_extractors (the two merge as a union). If neither is provided, the namespace gets the standard baseline (same as the scaffolded default namespace). Managed mode only.
List of feature extractors to configure for this namespace. DEPRECATED for direct use: prefer features: [...] (contract v2 §6.2, D9) — extractor names are internal implementation. Not used for standalone mode. If neither features nor feature_extractors is provided, the namespace defaults to the standard baseline. Each extractor requires 'feature_extractor_name' and 'version'. Optional 'params' can be specified for extractors with configurable settings (e.g., model selection) that affect vector dimensions. These params are locked at namespace creation time. Example: [{"feature_extractor_name": "multimodal_extractor", "version": "v1"}]
Optional vector index configurations for standalone mode. Each entry defines a named vector index with dimension and distance metric. If omitted, indexes are auto-created on first upsert (schema-on-write).
Optional list of custom payload index configurations. Indexes required by selected feature extractors will be added automatically.
Enable automatic creation of Qdrant payload indexes based on filter usage patterns. When enabled, the system tracks which fields are most frequently filtered (>100 queries/24h) and automatically creates indexes to improve query performance. Background task runs every 6 hours. Expected performance improvement: 50-90% latency reduction for filtered queries. Defaults: managed namespaces off, standalone namespaces on. Set explicitly to false to opt out (including for standalone, so an agent can manage indexes itself).
true
Time-to-live in seconds. Namespace will be auto-deleted after this duration.
x >= 60Optional dedicated infrastructure configuration for this namespace. Required for custom plugins and custom models (Enterprise tier). If None, uses shared infrastructure or organization-level infrastructure.
Response
Successful Response
Namespace model.
Name of the namespace
64"product-search"
Resource type identifier, always 'namespace'.
Unique identifier for the namespace. Format: ns_.
Type of namespace. STANDARD for regular namespaces, MARKETPLACE for curated datasets that can be subscribed to.
standard, marketplace Ownership scope. ORG (default) is org-scoped — only visible to members of the owning organization. SYSTEM is Mixpeek-owned and visible read-only to every authenticated org; used for curated sample corpora. Mutations on SYSTEM namespaces require admin auth.
org, system Infrastructure configuration for the namespace.
Infrastructure cluster ID for this namespace (Enterprise only). When set, this namespace uses a dedicated compute and vector cluster. If None, uses shared infrastructure or organization-level infrastructure. Format: iclstr_xxx
"iclstr_abc123xyz"
Description of the namespace
List of feature extractors configured for this namespace
Custom payload indexes configured for this namespace
Total number of documents in this namespace
Total number of buckets in this namespace
Total number of collections in this namespace
Total number of objects across all buckets in this namespace
Enable automatic creation of Qdrant payload indexes based on filter usage patterns. When enabled, the system tracks which fields are most frequently filtered (>100 queries/24h) and automatically creates indexes to improve query performance. Background task runs every 6 hours. Expected performance improvement: 50-90% latency reduction for filtered queries.
Mapping of vector index names to inference service names. Built at namespace creation based on extractor configurations. Used by feature search to determine correct inference service for queries. Example: {'image_extractor_v1_embedding': 'google_siglip_base_v1'}
Creation-time marker for BYO vector-name handling (SP-263). False = the namespace was created with EXPLICIT vector_configs, so upserting a vector name outside those configs is rejected (422) instead of silently auto-indexed under a name nothing searches. True = fully dynamic BYO namespace (created without vector_configs): new vector names keep being inferred on first upsert. Null (namespaces that predate the marker) behaves as True so existing flows are unchanged.
Namespace mode: 'managed' (Mixpeek manages vector schemas and inference) or 'standalone' (bring-your-own vectors). Populated from the stored mvs_mode; null for namespaces that predate BYOV.
For standalone / promoted (BYO-vector) namespaces, the per-vector configs: name, dimension, metric. Populated from the stored mvs_vector_configs; null for managed namespaces with no BYO vectors.
Live vector collection status. Populated when retrieving a namespace. Includes: status (green/yellow/red), points_count, indexed_vectors_count, segments_count. None if vector collection does not exist or is unreachable.
Deep-clone / scaffold sample-data progress: 'cloning' (in flight), 'ready' (completed), 'failed' (see clone_error). Null for namespaces that were never cloned. Poll this after a scaffold instantiate with include_sample_data=true.
Error detail when clone_status='failed'; null otherwise.
For a cloned namespace, the source (golden/sample) namespace id it was cloned from.
When the namespace was created
When the namespace was last updated
UTC timestamp after which the namespace is auto-deleted by the hourly cleanup_expired_namespaces reaper. Computed at create time from CreateNamespaceRequest.ttl_seconds; null means the namespace never expires.