{ "openapi": "3.0.1", "info": { "title": "Self Learning Postgres DB", "description": "Self-learning vector database with GNN-powered index optimization. Features: vector search, RAG queries, embeddings, clustering, deduplication, batch ops, and data import/export. Scales with Raft consensus.", "version": "2.1", "x-build-id": "LfI2tK0RJa7uPN8NB" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ruv~self-learning-postgres-db/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ruv-self-learning-postgres-db", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ruv~self-learning-postgres-db/runs": { "post": { "operationId": "runs-sync-ruv-self-learning-postgres-db", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ruv~self-learning-postgres-db/run-sync": { "post": { "operationId": "run-sync-ruv-self-learning-postgres-db", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "action" ], "properties": { "action": { "title": "Action", "enum": [ "full_workflow", "search", "insert", "batch_insert", "get", "list", "update", "delete", "upsert", "hybrid_search", "multi_query_search", "mmr_search", "graph_search", "range_search", "batch_search", "create_table", "drop_table", "list_tables", "table_stats", "create_index", "reindex", "train_gnn", "optimize_index", "analyze_patterns", "sona_learn", "sona_status", "cluster", "find_duplicates", "deduplicate", "export", "import", "rag_query", "summarize", "ping", "version", "embedding_models", "generate_embedding", "similarity" ], "type": "string", "description": "The operation to perform on the vector database", "default": "full_workflow" }, "connectionString": { "title": "Database Connection", "type": "string", "description": "PostgreSQL connection URL. Leave empty for embedded database (non-persistent). For persistent storage, use your own PostgreSQL with ruvector/pgvector extension." }, "tableName": { "title": "Table/Collection Name", "type": "string", "description": "Name of the vector table (collection)", "default": "documents" }, "query": { "title": "Search Query", "type": "string", "description": "Natural language query for semantic search. The AI understands meaning, not just keywords." }, "queryVector": { "title": "Query Vector", "type": "array", "description": "Pre-computed embedding vector (alternative to query text). Use with external embedding APIs." }, "documents": { "title": "Documents", "type": "array", "description": "Documents to insert. Each should have 'content' and optional 'metadata' and 'embedding'." }, "topK": { "title": "Number of Results", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of results to return", "default": 10 }, "distanceMetric": { "title": "Distance Metric", "enum": [ "cosine", "l2", "inner_product", "manhattan" ], "type": "string", "description": "How to measure vector similarity", "default": "cosine" }, "filter": { "title": "Filter", "type": "string", "description": "SQL WHERE clause for filtering. Example: metadata->>'category' = 'AI'" }, "minScore": { "title": "Minimum Score", "minimum": 0, "maximum": 1, "type": "number", "description": "Minimum similarity score threshold (0-1)", "default": 0 }, "maxDistance": { "title": "Maximum Distance", "type": "number", "description": "Maximum distance threshold for range search" }, "includeEmbeddings": { "title": "Include Embeddings", "type": "boolean", "description": "Include embedding vectors in results (increases response size)", "default": false }, "includeMetadata": { "title": "Include Metadata", "type": "boolean", "description": "Include metadata in results", "default": true }, "embeddingModel": { "title": "Embedding Model", "enum": [ "all-MiniLM-L6-v2", "bge-small-en-v1.5", "bge-base-en-v1.5", "nomic-embed-text-v1", "gte-small", "e5-small-v2" ], "type": "string", "description": "AI model for generating text embeddings. No API key needed - runs locally!", "default": "all-MiniLM-L6-v2" }, "generateEmbeddings": { "title": "Generate Embeddings", "type": "boolean", "description": "Auto-generate embeddings for documents without them", "default": true }, "dimensions": { "title": "Vector Dimensions", "minimum": 64, "maximum": 4096, "type": "integer", "description": "Embedding dimensions (384 for MiniLM/BGE-small, 768 for larger models)", "default": 384 }, "indexType": { "title": "Index Type", "enum": [ "hnsw", "ivfflat", "none" ], "type": "string", "description": "Vector index algorithm for faster search", "default": "hnsw" }, "hnswM": { "title": "HNSW M Parameter", "minimum": 4, "maximum": 64, "type": "integer", "description": "Max connections per node. Higher = better recall, more memory", "default": 16 }, "hnswEfConstruction": { "title": "HNSW ef_construction", "minimum": 16, "maximum": 512, "type": "integer", "description": "Index build quality. Higher = better index, slower build", "default": 64 }, "hnswEfSearch": { "title": "HNSW ef_search", "minimum": 16, "maximum": 512, "type": "integer", "description": "Search quality. Higher = better recall, slower search", "default": 100 }, "ivfLists": { "title": "IVF Lists", "minimum": 10, "maximum": 1000, "type": "integer", "description": "Number of IVF partitions for IVFFlat index", "default": 100 }, "hybridWeight": { "title": "Hybrid Weight", "minimum": 0, "maximum": 1, "type": "number", "description": "Balance between vector (1.0) and keyword (0.0) search", "default": 0.7 }, "batchSize": { "title": "Batch Size", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Documents per batch for batch operations", "default": 100 }, "documentId": { "title": "Document ID", "type": "integer", "description": "Single document ID for get/update/delete operations" }, "documentIds": { "title": "Document IDs", "type": "array", "description": "Multiple document IDs for batch delete" }, "updates": { "title": "Updates", "type": "object", "description": "Fields to update: {content, metadata, embedding}" }, "enableLearning": { "title": "Enable Learning", "type": "boolean", "description": "Enable self-learning index optimization", "default": false }, "learningRate": { "title": "Learning Rate", "minimum": 0.0001, "maximum": 1, "type": "number", "description": "GNN training learning rate", "default": 0.01 }, "gnnLayers": { "title": "GNN Layers", "minimum": 1, "maximum": 10, "type": "integer", "description": "Number of Graph Neural Network layers", "default": 2 }, "trainEpochs": { "title": "Training Epochs", "minimum": 1, "maximum": 100, "type": "integer", "description": "Number of GNN training epochs", "default": 10 }, "numClusters": { "title": "Number of Clusters", "minimum": 2, "maximum": 100, "type": "integer", "description": "K-means cluster count", "default": 10 }, "clusteringAlgorithm": { "title": "Clustering Algorithm", "enum": [ "kmeans", "hierarchical" ], "type": "string", "description": "Clustering method", "default": "kmeans" }, "similarityThreshold": { "title": "Similarity Threshold", "minimum": 0.5, "maximum": 1, "type": "number", "description": "Threshold for duplicate detection (0-1, higher = stricter)", "default": 0.95 }, "exportFormat": { "title": "Export Format", "enum": [ "json", "csv" ], "type": "string", "description": "Data export format", "default": "json" }, "importData": { "title": "Import Data", "type": "array", "description": "Data to import (array of documents with content and optional metadata)" }, "ragMaxTokens": { "title": "RAG Max Tokens", "minimum": 100, "maximum": 10000, "type": "integer", "description": "Maximum context tokens for RAG query", "default": 2000 }, "ragContext": { "title": "RAG Context", "type": "string", "description": "Additional context to prepend to RAG results" }, "sonaEnabled": { "title": "Enable SONA Learning", "type": "boolean", "description": "Enable TRM/SONA self-learning with trajectory tracking and pattern recognition", "default": true }, "ewcLambda": { "title": "EWC Lambda", "minimum": 100, "maximum": 10000, "type": "number", "description": "Elastic Weight Consolidation strength for anti-forgetting protection. Higher values preserve more learned knowledge.", "default": 2000 }, "patternThreshold": { "title": "Pattern Threshold", "minimum": 0.1, "maximum": 1, "type": "number", "description": "Minimum confidence threshold for pattern recognition (0-1)", "default": 0.7 }, "maxTrajectories": { "title": "Max Trajectories", "minimum": 10, "maximum": 1000, "type": "integer", "description": "Maximum number of trajectory steps to track for learning", "default": 100 }, "sonaLearningTiers": { "title": "Learning Tiers", "type": "array", "description": "SONA learning tiers to enable (instant=real-time, background=async, deep=comprehensive)", "default": [ "instant", "background" ] } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }