Crate dakera_client

Expand description

Dakera Rust Client SDK

A high-level Rust client for interacting with Dakera AI Agent Memory Platform.

§Quick Start (HTTP)

use dakera_client::{DakeraClient, UpsertRequest, QueryRequest};

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    // Create a client
    let client = DakeraClient::new("http://localhost:3000")?;

    // Check health
    let health = client.health().await?;
    println!("Server healthy: {}", health.healthy);

    // Upsert vectors
    let request = UpsertRequest {
        vectors: vec![
            dakera_client::Vector {
                id: "vec1".to_string(),
                values: vec![0.1, 0.2, 0.3, 0.4],
                metadata: None,
            },
        ],
    };
    client.upsert("my-namespace", request).await?;

    // Query for similar vectors
    let query = QueryRequest {
        vector: vec![0.1, 0.2, 0.3, 0.4],
        top_k: 10,
        filter: None,
        include_metadata: true,
        include_vectors: false,
        distance_metric: Default::default(),
        consistency: Default::default(),
        staleness_config: None,
    };
    let results = client.query("my-namespace", query).await?;

    for match_ in results.results {
        println!("ID: {}, Score: {}", match_.id, match_.score);
    }

    Ok(())
}

§gRPC Client with Connection Pooling

Enable the grpc feature for high-performance gRPC communication:

use dakera_client::grpc::{GrpcClient, GrpcClientConfig, GrpcConnectionPool};

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    // Single client with HTTP/2 multiplexing
    let config = GrpcClientConfig::default()
        .with_endpoint("http://localhost:50051")
        .with_concurrency_limit(100);
    let client = GrpcClient::connect(config).await?;

    // Or use a connection pool for even higher throughput
    let pool = GrpcConnectionPool::new(GrpcClientConfig::default(), 4).await?;
    let client = pool.get();

    Ok(())
}

Re-exports§

pub use events::DakeraEvent;
pub use events::MemoryEvent;
pub use events::OpStatus;
pub use events::VectorMutationOp;
pub use admin::AutoPilotConfig;
pub use admin::AutoPilotConfigRequest;
pub use admin::AutoPilotConfigResponse;
pub use admin::AutoPilotConsolidationResult;
pub use admin::AutoPilotDedupResult;
pub use admin::AutoPilotStatusResponse;
pub use admin::AutoPilotTriggerAction;
pub use admin::AutoPilotTriggerRequest;
pub use admin::AutoPilotTriggerResponse;
pub use admin::BackupInfo;
pub use admin::BackupListResponse;
pub use admin::CacheStats;
pub use admin::ClusterStatus;
pub use admin::ConsolidationResultSnapshot;
pub use admin::CreateBackupRequest;
pub use admin::CreateBackupResponse;
pub use admin::DecayConfigResponse;
pub use admin::DecayConfigUpdateRequest;
pub use admin::DecayConfigUpdateResponse;
pub use admin::DecayStatsResponse;
pub use admin::DedupResultSnapshot;
pub use admin::FulltextReindexNamespaceResult;
pub use admin::FulltextReindexResponse;
pub use admin::IndexStats;
pub use admin::IndexStatsResponse;
pub use admin::KpiSnapshot;
pub use admin::LastDecayCycleStats;
pub use admin::NodeInfo;
pub use admin::NodeListResponse;
pub use admin::OpsStats;
pub use admin::QuotaConfig;
pub use admin::QuotaListResponse;
pub use admin::QuotaStatus;
pub use admin::RestoreBackupRequest;
pub use admin::RestoreBackupResponse;
pub use admin::RuntimeConfig;
pub use admin::SlowQueryListResponse;
pub use agents::AgentStats;
pub use agents::AgentSummary;
pub use agents::CompressResponse;
pub use agents::Memory;
pub use agents::WakeUpResponse;
pub use analytics::AnalyticsOverview;
pub use analytics::LatencyAnalytics;
pub use analytics::StorageAnalytics;
pub use analytics::ThroughputAnalytics;
pub use keys::ApiKeyUsageResponse;
pub use keys::CreateKeyRequest;
pub use keys::CreateKeyResponse;
pub use keys::CreateNamespaceKeyRequest;
pub use keys::CreateNamespaceKeyResponse;
pub use keys::KeyInfo;
pub use keys::ListKeysResponse;
pub use keys::ListNamespaceKeysResponse;
pub use keys::NamespaceKeyInfo;
pub use keys::NamespaceKeyUsageResponse;
pub use keys::RotateKeyResponse;
pub use knowledge::AgentNetworkEdge;
pub use knowledge::AgentNetworkInfo;
pub use knowledge::AgentNetworkNode;
pub use knowledge::AgentNetworkStats;
pub use knowledge::CrossAgentNetworkRequest;
pub use knowledge::CrossAgentNetworkResponse;
pub use knowledge::DeduplicateRequest;
pub use knowledge::DeduplicateResponse;
pub use knowledge::FullKnowledgeGraphRequest;
pub use knowledge::KnowledgeEdge;
pub use knowledge::KnowledgeGraphRequest;
pub use knowledge::KnowledgeGraphResponse;
pub use knowledge::KnowledgeNode;
pub use knowledge::SummarizeRequest;
pub use knowledge::SummarizeResponse;
pub use memory::AuditEvent;
pub use memory::AuditExportResponse;
pub use memory::AuditListResponse;
pub use memory::AuditQuery;
pub use memory::BatchForgetRequest;
pub use memory::BatchForgetResponse;
pub use memory::BatchMemoryFilter;
pub use memory::BatchRecallRequest;
pub use memory::BatchRecallResponse;
pub use memory::ConsolidationConfig;
pub use memory::ConsolidationLogEntry;
pub use memory::ExtractionProviderInfo;
pub use memory::ExtractionResult;
pub use memory::ForgetRequest;
pub use memory::ForgetResponse;
pub use memory::MemoryExportResponse;
pub use memory::MemoryImportResponse;
pub use memory::MemoryType;
pub use memory::RecallRequest;
pub use memory::RecallResponse;
pub use memory::RecalledMemory;
pub use memory::RotateEncryptionKeyRequest;
pub use memory::RotateEncryptionKeyResponse;
pub use memory::RoutingMode;
pub use memory::Session;
pub use memory::SessionEndResponse;
pub use memory::SessionStartResponse;
pub use memory::StoreMemoryRequest;
pub use memory::StoreMemoryResponse;
pub use reqwest;

Modules§

admin: Admin operations for the Dakera client.
agents: Agent management for the Dakera client.
analytics: Analytics operations for the Dakera client.
events: SSE streaming event types and client support (CE-1).
filter
keys: API Key management for the Dakera client.
knowledge: Knowledge graph operations for the Dakera client.
memory: Memory-oriented client methods for Dakera AI Agent Memory Platform

Structs§

ActualStats: Actual execution statistics (when execute=true)
AdminBackupInfo: Backup information.
AgentConsolidateResponse: Response from POST /v1/agents/{agent_id}/consolidate.
AgentConsolidationConfig: Response from consolidation config endpoints.
AgentConsolidationLogEntry: One entry in the agent consolidation log.
AgentFeedbackSummary: Response from GET /v1/agents/:id/feedback/summary (INT-1).
AggregationGroup: Single group in aggregation results
AggregationRequest: Request for aggregation query (Turbopuffer-inspired)
AggregationResponse: Response for aggregation query
BackupSchedule: Backup schedule configuration.
BatchQueryItem: A single query within a batch request
BatchQueryRequest: Batch query request - execute multiple queries in parallel
BatchQueryResponse: Batch query response
BatchQueryResult: Results for a single query within a batch
BatchQueryTextRequest: Request to execute multiple text queries with automatic embedding in a single call.
BatchQueryTextResponse: Response from a batch text query operation.
BulkDeleteRequest: Request for POST /v1/namespaces/{ns}/vectors/bulk-delete.
BulkDeleteResponse: Response from POST /v1/namespaces/{ns}/vectors/bulk-delete.
BulkUpdateRequest: Request for POST /v1/namespaces/{ns}/vectors/bulk-update.
BulkUpdateResponse: Response from POST /v1/namespaces/{ns}/vectors/bulk-update.
ColumnUpsertRequest: Column-based upsert request (Turbopuffer-inspired)
CompactionRequest: Compaction request
CompactionResponse: Compaction response
ComponentHealth: Component health status
ConfigureNamespaceRequest: Request body for PUT /v1/namespaces/:namespace — upsert semantics (v0.6.0).
ConfigureNamespaceResponse: Response from PUT /v1/namespaces/:namespace.
ConsolidationConfigPatch: Request for PATCH /v1/agents/{agent_id}/consolidation/config.
CostEstimate: Cost estimation
CountVectorsRequest: Request for POST /v1/namespaces/{ns}/vectors/count.
CountVectorsResponse: Response from POST /v1/namespaces/{ns}/vectors/count.
CreateNamespaceRequest: Request to create a new namespace.
DakeraClient: Dakera client for interacting with the vector database
DakeraClientBuilder: Builder for DakeraClient
DefaultQuotaResponse: Response from GET /admin/quotas/default.
DeleteRequest: Delete vectors request
DeleteResponse: Delete response
DisableMaintenanceRequest: Request for POST /admin/cluster/maintenance/disable.
Document: A document for full-text indexing
EnableMaintenanceRequest: Request for POST /admin/cluster/maintenance/enable.
EntityExtractionResponse: Response from POST /v1/memories/extract
ExecutionStage: A stage in query execution
ExportRequest: Request to export vectors from a namespace with pagination
ExportResponse: Response from export operation
ExportedVector: A single exported vector record
ExtractEntitiesRequest: Request body for POST /ode/extract (ODE-2).
ExtractEntitiesResponse: Response from POST /ode/extract on the ODE sidecar (ODE-2).
ExtractedEntity: A single extracted entity from GLiNER or rule-based pipeline.
FeedbackHealthResponse: Response from GET /v1/feedback/health (INT-1).
FeedbackHistoryEntry: A single recorded feedback event stored in memory metadata (INT-1).
FeedbackHistoryResponse: Response from GET /v1/memories/:id/feedback (INT-1).
FeedbackResponse: Response from POST /v1/memories/:id/feedback and PATCH /v1/memories/:id/importance (INT-1).
FetchRequest: Request to fetch vectors by their IDs.
FetchResponse: Response from a fetch-by-ID operation.
FullTextMatch: Full-text search result
FullTextSearchRequest: Full-text search request
FullTextSearchResponse: Full-text search response
FullTextStats: Full-text index statistics
GraphEdge: A directed edge in the memory knowledge graph.
GraphExport: Agent graph export from GET /v1/agents/{id}/graph/export.
GraphLinkRequest: Request body for POST /v1/memories/{id}/links.
GraphLinkResponse: Response from POST /v1/memories/{id}/links.
GraphNode: A node (memory) in the knowledge graph traversal result.
GraphOptions: Options for [DakeraClient::memory_graph].
GraphPath: Shortest path between two memories from GET /v1/memories/{id}/path.
HealthResponse: Health check response
HealthStatus: Health status for a component
HybridSearchRequest: Hybrid search request combining vector and full-text search.
HybridSearchResponse: Hybrid search response
ImportJobStatus: Status of an import job returned by GET /v1/import/{job_id}/status.
IndexAlternative: Alternative index that was considered
IndexDocumentsRequest: Index documents request
IndexDocumentsResponse: Index documents response
IndexSelection: Index selection details
IndexStatistics: Index statistics
JobInfo: Background job information
KgExportResponse: Response from GET /v1/knowledge/export with format=json (KG-2).
KgPathResponse: Response from GET /v1/knowledge/path (KG-2).
KgQueryResponse: Response from GET /v1/knowledge/query (KG-2).
ListNamespacesResponse: List namespaces response
MaintenanceStatus: Response from GET /admin/cluster/maintenance.
Match: A match result from a query
MemoryEntitiesResponse: Response from GET /v1/memory/entities/:id
MemoryFeedbackBody: Request body for POST /v1/memories/:id/feedback (INT-1).
MemoryGraph: Graph traversal result from GET /v1/memories/{id}/graph.
MemoryImportancePatch: Request body for PATCH /v1/memories/:id/importance (INT-1).
MemoryPolicy: Per-namespace memory lifecycle policy (COG-1).
MemoryTypeStatsResponse: Per-type memory statistics from GET /admin/memory-type-stats.
MigrateDimensionsResponse: Response from POST /admin/namespaces/migrate-dimensions.
MigrateNamespaceDimensionsRequest: Request for POST /admin/namespaces/migrate-dimensions.
MultiVectorSearchRequest: Request for multi-vector search with positive and negative vectors
MultiVectorSearchResponse: Response from multi-vector search
MultiVectorSearchResult: Single result from multi-vector search
NamespaceEntityConfig: Response from GET /v1/namespaces/{ns}/config.
NamespaceExtractorConfig: Response from GET /v1/namespaces/{ns}/extractor.
NamespaceInfo: Namespace information
NamespaceMigrationResult: Per-namespace migration result.
NamespaceNerConfig: Configuration for namespace-level entity extraction (CE-4).
NodeReplicationLag: Per-node replication lag entry.
OdeEntity: A single entity extracted by the GLiNER model (ODE-2).
QueryExplainRequest: Query explain request
QueryExplainResponse: Query explain response - detailed execution plan
QueryParams: Query parameters for reference
QueryRequest: Query request for vector similarity search
QueryResponse: Query response
QueryTextRequest: Request to query using natural language text with automatic embedding.
QuotaCheckRequest: Request for POST /admin/quotas/{namespace}/check.
QuotaCheckResult: Response from POST /admin/quotas/{namespace}/check.
QuotaUsage: Quota usage for a namespace.
RateLimitHeaders: Rate-limit and quota headers present on every API response (OPS-1).
ReadinessResponse: Readiness check response
Recommendation: Performance recommendation
ReplicationStatus: Response from GET /admin/cluster/replication.
ResourceUsage: Resource usage metrics
RetryConfig: Configuration for request retry behavior with exponential backoff.
RouteMatch: A single route match returned by POST /v1/route.
RouteRequest: Request for POST /v1/route.
RouteResponse: Response from POST /v1/route.
SetDefaultQuotaRequest: Request for PUT /admin/quotas/default.
SetQuotaRequest: Request for PUT /admin/quotas/{namespace}.
SetQuotaResponse: Response from PUT /admin/quotas.
ShardInfo: Shard information.
ShardListResponse: Response from GET /admin/cluster/shards.
ShardMove: A planned shard move.
ShardRebalanceRequest: Request for POST /admin/cluster/shards/rebalance.
ShardRebalanceResponse: Response from POST /admin/cluster/shards/rebalance.
StalenessConfig: Configuration for bounded staleness reads
StorageTierOverview: Overview of the tiered storage system from GET /admin/storage/tiers.
SystemDiagnostics: System diagnostics
SystemInfo: System information
TextDocument: A text document to upsert with automatic embedding generation.
TextQueryResponse: Response from a text query operation.
TextSearchResult: A single text search result.
TextUpsertResponse: Response from a text upsert operation.
TierActivity: Tier movement activity counters.
TierConfig: Tiered storage configuration parameters.
TierInfo: Information about a single storage tier.
UnifiedQueryRequest: Unified query request with flexible ranking options (Turbopuffer-inspired)
UnifiedQueryResponse: Unified query response
UnifiedSearchResult: Single result from unified query
UpdateBackupScheduleRequest: Request for POST /admin/backups/schedule.
UpsertRequest: Upsert vectors request
UpsertResponse: Upsert response
UpsertTextRequest: Request to upsert text documents with automatic embedding.
Vector: A vector with ID and optional metadata
WarmCacheRequest: Cache warming request with priority hints
WarmCacheResponse: Cache warming response

Enums§

AccessPatternHint: Access pattern hint for cache optimization
AggregateFunction: Aggregate function for computing values across documents
ClientError: Errors that can occur when using the Dakera client
DistanceMetric: Distance metric for similarity search
EdgeType: Edge type for memory knowledge graph relationships (CE-5).
EmbeddingModel: Supported embedding models for text-based operations.
ExplainQueryType: Query type for explain
FeedbackSignal: Feedback signal for memory active learning (INT-1).
RankBy: Ranking function for unified query API Supports vector search (ANN/kNN), full-text BM25, and attribute ordering
ReadConsistency: Read consistency level for queries (Turbopuffer-inspired)
SortDirection: Sort direction for attribute ordering
VectorSearchMethod: Vector search method for unified query
WarmingPriority: Priority level for cache warming operations
WarmingTargetTier: Target cache tier for warming

Type Aliases§

Result: Result type alias for Dakera client operations

Crate dakera_client

Crate dakera_client Copy item path

§Quick Start (HTTP)

§gRPC Client with Connection Pooling

Re-exports§

Modules§

Structs§

Enums§

Type Aliases§

Crate dakera_client