Module models

Source

Expand description

Data models for the Vectorizer SDK

Re-exports§

pub use filter::QdrantCondition;
pub use filter::QdrantFilter;
pub use filter::QdrantGeoBoundingBox;
pub use filter::QdrantGeoPoint;
pub use filter::QdrantGeoRadius;
pub use filter::QdrantMatchValue;
pub use filter::QdrantRange;
pub use filter::QdrantValuesCount;
pub use hybrid_search::*;
pub use graph::*;
pub use file_upload::*;

Modules§

file_upload: File upload models for the Vectorizer SDK
filter: Typed Qdrant-compatible filter builder for delete_by_filter and bulk_update_metadata.
graph: Graph models for the Vectorizer SDK
hybrid_search: Hybrid search models for combining dense and sparse vectors

Structs§

AddPeerRequest: Request body for POST /cluster/peers.
AddWorkspaceRequest: Request body for add_workspace (POST /workspace/add). Server reads path and collection_name.
AnswerPlan: Response from build_answer_plan. Server: {sections: [...], total_bullets, sources}.
AnswerPlanRequest: Request for build_answer_plan (POST /discovery/build_answer_plan).
ApiKey: API key returned by POST /auth/keys.
ApiKeyScope: Per-collection scope attached to an API key.
ApiKeyUsageBucket: One day’s usage bucket from GET /auth/keys/{id}/usage.
ApiKeyUsageReport: Response body for GET /auth/keys/{id}/usage.
ApiKeyView: Flattened key view returned by update_api_key_permissions and get_api_key_usage. Mirrors the server’s ApiKeyView.
AuditEntry: One entry in the admin audit log returned by GET /auth/audit.
AuditQuery: Query parameters for GET /auth/audit.
BackupInfo: Metadata for one server-side backup file returned by GET /backups. Server shape: {id, name, date, size, collections}.
BatchConfig: Batch configuration
BatchDeleteRequest: Batch delete request
BatchInsertItem: One item in a batch_insert_texts call (POST /batch_insert).
BatchInsertReport: Aggregate outcome of a batch_insert_texts or insert_vectors call. Server response shape: {collection, inserted, failed, count, results}.
BatchInsertRequest: Batch insert request
BatchResponse: Batch response.
BatchResultEntry: One entry in BatchResponse::results as emitted by the v3 /insert_texts handler. Carries the client-provided id alongside the server-assigned vector UUID(s) so callers can round-trip the mapping when they need idempotency by client id.
BatchSearchQuery: One query in a batch_search call (POST /batch_search).
BatchSearchRequest: Batch search request
BatchSearchResponse: Batch search response
BatchTextRequest: Batch text request
BatchUpdateReport: Aggregate outcome of a batch_update_vectors call. Server response: {collection, count, updated, failed, results}.
BatchUpdateRequest: Batch update request
BatchVectorUpdate: Batch vector update
BroadDiscoveryRequest: Request for broad_discovery (POST /discovery/broad_discovery).
BroadDiscoveryResponse: Response from broad_discovery. Server: {chunks: [{collection, score, content_preview}], count}.
BulkUpdateReport: Aggregate outcome of a bulk_update_metadata call against POST /collections/{name}/vectors/bulk_update_metadata.
CleanupReport: Report returned by cleanup_empty_collections (DELETE /collections/cleanup).
Collection: Collection representation
CollectionInfo: Collection information.
CollectionProgress: Collection progress
CollectionStats: Collection statistics
CollectionsResponse: Collections list response
CompressEvidenceRequest: Request for compress_evidence (POST /discovery/compress_evidence).
CompressEvidenceResponse: Response from compress_evidence. Server: {bullets: [{text, source_id, category, score}], count}.
ConfigPatch: Patch applied to the server configuration by POST /config. The server accepts the full config as a JSON object and writes it to config.yml.
ConfigSnapshot: Server configuration snapshot returned by GET /config and POST /config.
ContextualSearchRequest: Contextual search request
ContextualSearchResponse: Contextual search response
CopyReport: Aggregate outcome of a copy_vectors call against POST /collections/{src}/vectors/copy.
CreateApiKeyRequest: Request body for create_api_key (POST /auth/keys).
CreateBackupRequest: Request body for create_backup (POST /backups/create).
CreateCollectionResponse: Create collection response
CreateScopedApiKeyRequest: Request body for POST /auth/keys — extended with optional per-collection scopes.
CreateUserBackupRequest: Request for create_user_backup (POST /hub/backups).
CreateUserRequest: Request body for create_user (POST /auth/users).
DatabaseStats: Database statistics
DeleteByFilterReport: Aggregate outcome of a delete_by_filter call against POST /collections/{name}/vectors/delete_by_filter.
DeleteReport: Aggregate outcome of a delete_vectors call against POST /batch_delete. Mirrors the server contract: {collection, count, deleted, failed, results}.
EmbeddingParameters: Embedding parameters
EmbeddingRequest: Embedding request
EmbeddingResponse: Embedding response
ExplainRequest: Request body for explain_search (POST /collections/{name}/explain).
ExplainResponse: Response from explain_search (POST /collections/{name}/explain).
ExplainTrace: Execution trace attached to an ExplainResponse.
FailoverReport: Report returned by POST /cluster/failover.
GetSummaryResponse: Get summary response
HealthStatus: Health status
HostConfig: Host configuration for master/replica topology.
HubApiKeyValidation: Validation result returned by POST /hub/validate-key.
IndexingProgress: Indexing progress
IndexingStatus: Indexing status.
IntelligentSearchRequest: Intelligent search request
IntelligentSearchResponse: Intelligent search response
IntelligentSearchResult: Intelligent search result
JwtToken: JWT token returned by POST /auth/refresh. Server shape: {access_token, token_type, expires_in}.
ListSummariesResponse: List summaries response
LlmPrompt: Response from render_llm_prompt. Server: {prompt, length, estimated_tokens}.
LogEntry: One log entry returned by GET /logs.
LogsQuery: Query parameters for get_logs (GET /logs).
MoveReport: Aggregate outcome of a move_to_collection call against POST /collections/{src}/vectors/move (issue #265).
MultiCollectionSearchRequest: Multi-collection search request
MultiCollectionSearchResponse: Multi-collection search response
NativeSnapshotInfo: Native snapshot metadata returned by create_native_snapshot and each entry in list_native_snapshots.
PasswordPolicyReport: Password policy report returned by POST /auth/validate-password. Server shape: {valid, errors, strength, strength_label}.
PeerInfo: Information about a newly added cluster peer.
PromoteReadmeRequest: Request for promote_readme (POST /discovery/promote_readme). chunks is an array of ScoredChunk-compatible objects.
PromoteReadmeResponse: Response from promote_readme. Server: {promoted_chunks: [...], count}.
QuotaInfo: Quota information returned by GET /hub/usage/quota.
RawVectorInsert: One vector entry in an insert_vectors call (POST /insert_vectors).
ReadOptions: Options that can be passed to read operations for per-operation override.
RebalanceJob: Job descriptor returned by POST /cluster/rebalance.
ReencodeJob: Job descriptor returned by reencode_collection against POST /collections/{name}/reencode.
ReindexJob: Job descriptor returned by reindex_collection (POST /collections/{name}/reindex).
ReindexParams: Parameters for reindex_collection (POST /collections/{name}/reindex).
RenderPromptRequest: Request for render_llm_prompt (POST /discovery/render_llm_prompt).
ReplicaInfo: Information about a replica node
ReplicaListResponse: Response for listing replicas
ReplicationConfig: Request body for configure_replication (POST /replication/configure).
ReplicationStats: Statistics for replication status
ReplicationStatus: Replication status returned by GET /replication/status. Server: {role, enabled, stats?, replicas?}.
ReplicationStatusResponse: Response for replication status endpoint
RestoreBackupRequest: Request body for restore_backup (POST /backups/restore).
RestoreUserBackupRequest: Request for restore_user_backup (POST /hub/backups/restore).
ResyncJob: Report returned by POST /cluster/replicas/{id}/resync.
RotatedKey: Response from POST /auth/keys/{id}/rotate.
RouteStats: Per-route latency + QPS line in RuntimeMetrics.throughput_by_route.
RuntimeMetrics: Runtime metrics snapshot returned by GET /metrics/runtime (phase25). Single JSON object refreshed once per second on the server. Every field defaults so the SDK tolerates older servers that do not emit the route.
SearchByFileRequest: Request for search_by_file (POST /collections/{name}/search/file).
SearchResponse: Search response.
SearchResult: Search result
SemanticFocusRequest: Request for semantic_focus (POST /discovery/semantic_focus).
SemanticFocusResponse: Response from semantic_focus. Server: {chunks: [...], count}.
SemanticSearchRequest: Semantic search request
SemanticSearchResponse: Semantic search response
ServerStatus: Server status returned by GET /status. Server: {online, version, uptime_seconds, collections_count}.
SlowQueryConfig: Slow-query ring-buffer configuration returned by POST /slow_queries/config.
SlowQueryEntry: One entry in the slow-query ring buffer returned by GET /slow_queries.
Stats: Server statistics returned by GET /stats.
SummarizeContextRequest: Summarize context request
SummarizeContextResponse: Summarize context response
SummarizeTextRequest: Summarize text request
SummarizeTextResponse: Summarize text response
SummaryInfo: Summary info
TokenIntrospection: RFC 7662 token introspection response from POST /auth/introspect.
TokenScope: Per-collection permission scope sent in CreateScopedApiKeyRequest.
UpdateApiKeyPermissionsRequest: Request body for PUT /auth/keys/{id}/permissions.
UpdateVectorRequest: Request body for update_vector (POST /update).
UploadUserBackupRequest: Request for upload_user_backup (POST /hub/backups/upload).
UsageStatistics: Usage statistics returned by GET /hub/usage/statistics.
User: User record returned by auth endpoints. Server shape: {user_id, username, roles}.
UserBackup: A user-scoped backup entry returned by GET /hub/backups. Mirrors vectorizer::hub::backup::UserBackupInfo.
Vector: Vector representation
VectorCountSample: One sample in the per-collection vector-count history (phase25 §6).
VectorOpResult: Per-vector outcome for a delete_vectors or move_to_collection call. The status string is one of:
VectorPage: Paginated vector listing returned by GET /collections/{name}/vectors.
VectorUpdate: One entry in a batch_update_vectors call (POST /batch_update).
WalSnapshot: WAL state surfaced inside RuntimeMetrics.wal (phase25 §3).
WorkspaceConfig: Workspace config entry returned by GET /workspace/config and GET /workspace/list.

Enums§

ReadPreference: Read preference for routing read operations. Similar to MongoDB’s read preferences.
ReplicaStatus: Status of a replica node
SimilarityMetric: Vector similarity metrics
SummarizationMethod: Summarization methods

Module models

Module models Copy item path

Re-exports§

Modules§

Structs§

Enums§

Module models