mirror of
https://github.com/ruvnet/RuVector.git
synced 2026-06-01 23:00:37 +00:00
c1f89de337
- Add agentic-synth actor with TRM/SONA self-learning - Integrate 13 popular Apify scrapers for data grounding - Add 6 use case templates (lead-intelligence, competitor-monitor, etc.) - Include MCP server for AI agent integration - Add comprehensive README with tutorials and SEO optimization - Support generate/integrate/template modes - Add webhook and embedding generation support 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
469 lines
15 KiB
JSON
469 lines
15 KiB
JSON
{
|
|
"title": "Self-Learning Postgres DB Input",
|
|
"description": "A distributed vector database that learns. 30+ operations including semantic search, batch operations, RAG queries, clustering, deduplication, and GNN training.",
|
|
"type": "object",
|
|
"schemaVersion": 1,
|
|
"properties": {
|
|
"action": {
|
|
"title": "Action",
|
|
"type": "string",
|
|
"description": "The operation to perform on the vector database",
|
|
"default": "full_workflow",
|
|
"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"
|
|
],
|
|
"enumTitles": [
|
|
"Full Workflow - Demo: create + insert + search",
|
|
"Search - Semantic similarity search",
|
|
"Insert - Add documents with embeddings",
|
|
"Batch Insert - Add many documents efficiently",
|
|
"Get - Retrieve single document by ID",
|
|
"List - List documents with filters",
|
|
"Update - Modify existing document",
|
|
"Delete - Remove documents",
|
|
"Upsert - Insert or update documents",
|
|
"Hybrid Search - Vector + keyword combined",
|
|
"Multi Query Search - Multiple queries aggregated",
|
|
"MMR Search - Diverse results (Maximal Marginal Relevance)",
|
|
"Graph Search - Graph-based similarity",
|
|
"Range Search - All results within distance",
|
|
"Batch Search - Multiple queries at once",
|
|
"Create Table - Create new collection",
|
|
"Drop Table - Delete collection",
|
|
"List Tables - Show all vector collections",
|
|
"Table Stats - Collection statistics",
|
|
"Create Index - Add HNSW/IVFFlat index",
|
|
"Reindex - Rebuild indexes",
|
|
"Train GNN - Train Graph Neural Network",
|
|
"Optimize Index - Auto-tune parameters",
|
|
"Analyze Patterns - Analyze data patterns",
|
|
"SONA Learn - Trigger TRM/SONA self-learning cycle",
|
|
"SONA Status - Check SONA learning status",
|
|
"Cluster - K-means clustering",
|
|
"Find Duplicates - Detect similar documents",
|
|
"Deduplicate - Remove duplicates",
|
|
"Export - Export data to JSON/CSV",
|
|
"Import - Import data from JSON",
|
|
"RAG Query - Retrieval-Augmented Generation",
|
|
"Summarize - Document statistics",
|
|
"Ping - Test database connection",
|
|
"Version - Get version info",
|
|
"Embedding Models - List available models",
|
|
"Generate Embedding - Create embeddings only",
|
|
"Similarity - Compare two texts"
|
|
],
|
|
"editor": "select",
|
|
"prefill": "full_workflow",
|
|
"sectionCaption": "Core Settings",
|
|
"sectionDescription": "Choose the operation to perform"
|
|
},
|
|
"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.",
|
|
"editor": "textfield",
|
|
"isSecret": true,
|
|
"nullable": true,
|
|
"example": "postgresql://user:password@host:5432/database"
|
|
},
|
|
"tableName": {
|
|
"title": "Table/Collection Name",
|
|
"type": "string",
|
|
"description": "Name of the vector table (collection)",
|
|
"default": "documents",
|
|
"editor": "textfield"
|
|
},
|
|
"query": {
|
|
"title": "Search Query",
|
|
"type": "string",
|
|
"description": "Natural language query for semantic search. The AI understands meaning, not just keywords.",
|
|
"editor": "textarea",
|
|
"example": "How does machine learning work?",
|
|
"sectionCaption": "Search Settings"
|
|
},
|
|
"queryVector": {
|
|
"title": "Query Vector",
|
|
"type": "array",
|
|
"description": "Pre-computed embedding vector (alternative to query text). Use with external embedding APIs.",
|
|
"editor": "json",
|
|
"nullable": true
|
|
},
|
|
"documents": {
|
|
"title": "Documents",
|
|
"type": "array",
|
|
"description": "Documents to insert. Each should have 'content' and optional 'metadata' and 'embedding'.",
|
|
"editor": "json",
|
|
"prefill": [
|
|
{"content": "Machine learning is a type of AI that learns patterns from data to make predictions.", "metadata": {"category": "AI"}},
|
|
{"content": "PostgreSQL is a powerful open-source relational database.", "metadata": {"category": "Database"}},
|
|
{"content": "Neural networks are inspired by the human brain and consist of layers of nodes.", "metadata": {"category": "AI"}},
|
|
{"content": "Vector databases store data as mathematical embeddings for similarity search.", "metadata": {"category": "Database"}}
|
|
],
|
|
"sectionCaption": "Document Input"
|
|
},
|
|
"topK": {
|
|
"title": "Number of Results",
|
|
"type": "integer",
|
|
"description": "Maximum number of results to return",
|
|
"default": 10,
|
|
"minimum": 1,
|
|
"maximum": 1000,
|
|
"editor": "number"
|
|
},
|
|
"distanceMetric": {
|
|
"title": "Distance Metric",
|
|
"type": "string",
|
|
"description": "How to measure vector similarity",
|
|
"default": "cosine",
|
|
"enum": ["cosine", "l2", "inner_product", "manhattan"],
|
|
"enumTitles": [
|
|
"Cosine - Angular similarity (recommended)",
|
|
"L2 (Euclidean) - Straight-line distance",
|
|
"Inner Product - Dot product",
|
|
"Manhattan (L1) - City-block distance"
|
|
],
|
|
"editor": "select"
|
|
},
|
|
"filter": {
|
|
"title": "Filter",
|
|
"type": "string",
|
|
"description": "SQL WHERE clause for filtering. Example: metadata->>'category' = 'AI'",
|
|
"editor": "textfield",
|
|
"nullable": true,
|
|
"example": "metadata->>'category' = 'AI'"
|
|
},
|
|
"minScore": {
|
|
"title": "Minimum Score",
|
|
"type": "number",
|
|
"description": "Minimum similarity score threshold (0-1)",
|
|
"default": 0,
|
|
"minimum": 0,
|
|
"maximum": 1,
|
|
"editor": "number"
|
|
},
|
|
"maxDistance": {
|
|
"title": "Maximum Distance",
|
|
"type": "number",
|
|
"description": "Maximum distance threshold for range search",
|
|
"nullable": true,
|
|
"editor": "number"
|
|
},
|
|
"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",
|
|
"type": "string",
|
|
"description": "AI model for generating text embeddings. No API key needed - runs locally!",
|
|
"default": "all-MiniLM-L6-v2",
|
|
"enum": [
|
|
"all-MiniLM-L6-v2",
|
|
"bge-small-en-v1.5",
|
|
"bge-base-en-v1.5",
|
|
"nomic-embed-text-v1",
|
|
"gte-small",
|
|
"e5-small-v2"
|
|
],
|
|
"enumTitles": [
|
|
"all-MiniLM-L6-v2 (384d) - Fast, general purpose",
|
|
"bge-small-en-v1.5 (384d) - MTEB benchmark #1",
|
|
"bge-base-en-v1.5 (768d) - Higher accuracy",
|
|
"nomic-embed-text-v1 (768d) - Long documents (8K)",
|
|
"gte-small (384d) - Good quality, fast",
|
|
"e5-small-v2 (384d) - Multilingual"
|
|
],
|
|
"editor": "select",
|
|
"sectionCaption": "Embedding Settings"
|
|
},
|
|
"generateEmbeddings": {
|
|
"title": "Generate Embeddings",
|
|
"type": "boolean",
|
|
"description": "Auto-generate embeddings for documents without them",
|
|
"default": true
|
|
},
|
|
"dimensions": {
|
|
"title": "Vector Dimensions",
|
|
"type": "integer",
|
|
"description": "Embedding dimensions (384 for MiniLM/BGE-small, 768 for larger models)",
|
|
"default": 384,
|
|
"minimum": 64,
|
|
"maximum": 4096,
|
|
"editor": "number"
|
|
},
|
|
"indexType": {
|
|
"title": "Index Type",
|
|
"type": "string",
|
|
"description": "Vector index algorithm for faster search",
|
|
"default": "hnsw",
|
|
"enum": ["hnsw", "ivfflat", "none"],
|
|
"enumTitles": [
|
|
"HNSW - Fastest search, uses more memory",
|
|
"IVFFlat - Balanced speed and memory",
|
|
"None - No index, exact search"
|
|
],
|
|
"editor": "select",
|
|
"sectionCaption": "Index Settings"
|
|
},
|
|
"hnswM": {
|
|
"title": "HNSW M Parameter",
|
|
"type": "integer",
|
|
"description": "Max connections per node. Higher = better recall, more memory",
|
|
"default": 16,
|
|
"minimum": 4,
|
|
"maximum": 64,
|
|
"editor": "number"
|
|
},
|
|
"hnswEfConstruction": {
|
|
"title": "HNSW ef_construction",
|
|
"type": "integer",
|
|
"description": "Index build quality. Higher = better index, slower build",
|
|
"default": 64,
|
|
"minimum": 16,
|
|
"maximum": 512,
|
|
"editor": "number"
|
|
},
|
|
"hnswEfSearch": {
|
|
"title": "HNSW ef_search",
|
|
"type": "integer",
|
|
"description": "Search quality. Higher = better recall, slower search",
|
|
"default": 100,
|
|
"minimum": 16,
|
|
"maximum": 512,
|
|
"editor": "number"
|
|
},
|
|
"ivfLists": {
|
|
"title": "IVF Lists",
|
|
"type": "integer",
|
|
"description": "Number of IVF partitions for IVFFlat index",
|
|
"default": 100,
|
|
"minimum": 10,
|
|
"maximum": 1000,
|
|
"editor": "number"
|
|
},
|
|
"hybridWeight": {
|
|
"title": "Hybrid Weight",
|
|
"type": "number",
|
|
"description": "Balance between vector (1.0) and keyword (0.0) search",
|
|
"default": 0.7,
|
|
"minimum": 0,
|
|
"maximum": 1,
|
|
"editor": "number",
|
|
"sectionCaption": "Hybrid Search"
|
|
},
|
|
"batchSize": {
|
|
"title": "Batch Size",
|
|
"type": "integer",
|
|
"description": "Documents per batch for batch operations",
|
|
"default": 100,
|
|
"minimum": 1,
|
|
"maximum": 1000,
|
|
"editor": "number",
|
|
"sectionCaption": "Batch Settings"
|
|
},
|
|
"documentId": {
|
|
"title": "Document ID",
|
|
"type": "integer",
|
|
"description": "Single document ID for get/update/delete operations",
|
|
"nullable": true,
|
|
"editor": "number",
|
|
"sectionCaption": "Document Operations"
|
|
},
|
|
"documentIds": {
|
|
"title": "Document IDs",
|
|
"type": "array",
|
|
"description": "Multiple document IDs for batch delete",
|
|
"editor": "json",
|
|
"nullable": true
|
|
},
|
|
"updates": {
|
|
"title": "Updates",
|
|
"type": "object",
|
|
"description": "Fields to update: {content, metadata, embedding}",
|
|
"editor": "json",
|
|
"nullable": true
|
|
},
|
|
"enableLearning": {
|
|
"title": "Enable Learning",
|
|
"type": "boolean",
|
|
"description": "Enable self-learning index optimization",
|
|
"default": false,
|
|
"sectionCaption": "Self-Learning / GNN"
|
|
},
|
|
"learningRate": {
|
|
"title": "Learning Rate",
|
|
"type": "number",
|
|
"description": "GNN training learning rate",
|
|
"default": 0.01,
|
|
"minimum": 0.0001,
|
|
"maximum": 1,
|
|
"editor": "number"
|
|
},
|
|
"gnnLayers": {
|
|
"title": "GNN Layers",
|
|
"type": "integer",
|
|
"description": "Number of Graph Neural Network layers",
|
|
"default": 2,
|
|
"minimum": 1,
|
|
"maximum": 10,
|
|
"editor": "number"
|
|
},
|
|
"trainEpochs": {
|
|
"title": "Training Epochs",
|
|
"type": "integer",
|
|
"description": "Number of GNN training epochs",
|
|
"default": 10,
|
|
"minimum": 1,
|
|
"maximum": 100,
|
|
"editor": "number"
|
|
},
|
|
"numClusters": {
|
|
"title": "Number of Clusters",
|
|
"type": "integer",
|
|
"description": "K-means cluster count",
|
|
"default": 10,
|
|
"minimum": 2,
|
|
"maximum": 100,
|
|
"editor": "number",
|
|
"sectionCaption": "Clustering & Deduplication"
|
|
},
|
|
"clusteringAlgorithm": {
|
|
"title": "Clustering Algorithm",
|
|
"type": "string",
|
|
"description": "Clustering method",
|
|
"default": "kmeans",
|
|
"enum": ["kmeans", "hierarchical"],
|
|
"editor": "select"
|
|
},
|
|
"similarityThreshold": {
|
|
"title": "Similarity Threshold",
|
|
"type": "number",
|
|
"description": "Threshold for duplicate detection (0-1, higher = stricter)",
|
|
"default": 0.95,
|
|
"minimum": 0.5,
|
|
"maximum": 1,
|
|
"editor": "number"
|
|
},
|
|
"exportFormat": {
|
|
"title": "Export Format",
|
|
"type": "string",
|
|
"description": "Data export format",
|
|
"default": "json",
|
|
"enum": ["json", "csv"],
|
|
"editor": "select",
|
|
"sectionCaption": "Export/Import"
|
|
},
|
|
"importData": {
|
|
"title": "Import Data",
|
|
"type": "array",
|
|
"description": "Data to import (array of documents with content and optional metadata)",
|
|
"editor": "json",
|
|
"nullable": true
|
|
},
|
|
"ragMaxTokens": {
|
|
"title": "RAG Max Tokens",
|
|
"type": "integer",
|
|
"description": "Maximum context tokens for RAG query",
|
|
"default": 2000,
|
|
"minimum": 100,
|
|
"maximum": 10000,
|
|
"editor": "number",
|
|
"sectionCaption": "RAG Settings"
|
|
},
|
|
"ragContext": {
|
|
"title": "RAG Context",
|
|
"type": "string",
|
|
"description": "Additional context to prepend to RAG results",
|
|
"editor": "textarea",
|
|
"nullable": true
|
|
},
|
|
"sonaEnabled": {
|
|
"title": "Enable SONA Learning",
|
|
"type": "boolean",
|
|
"description": "Enable TRM/SONA self-learning with trajectory tracking and pattern recognition",
|
|
"default": true,
|
|
"sectionCaption": "SONA / TRM Self-Learning",
|
|
"sectionDescription": "Self-Optimizing Neural Architecture with Tiny Recursive Models"
|
|
},
|
|
"ewcLambda": {
|
|
"title": "EWC Lambda",
|
|
"type": "number",
|
|
"description": "Elastic Weight Consolidation strength for anti-forgetting protection. Higher values preserve more learned knowledge.",
|
|
"default": 2000,
|
|
"minimum": 100,
|
|
"maximum": 10000,
|
|
"editor": "number"
|
|
},
|
|
"patternThreshold": {
|
|
"title": "Pattern Threshold",
|
|
"type": "number",
|
|
"description": "Minimum confidence threshold for pattern recognition (0-1)",
|
|
"default": 0.7,
|
|
"minimum": 0.1,
|
|
"maximum": 1,
|
|
"editor": "number"
|
|
},
|
|
"maxTrajectories": {
|
|
"title": "Max Trajectories",
|
|
"type": "integer",
|
|
"description": "Maximum number of trajectory steps to track for learning",
|
|
"default": 100,
|
|
"minimum": 10,
|
|
"maximum": 1000,
|
|
"editor": "number"
|
|
},
|
|
"sonaLearningTiers": {
|
|
"title": "Learning Tiers",
|
|
"type": "array",
|
|
"description": "SONA learning tiers to enable (instant=real-time, background=async, deep=comprehensive)",
|
|
"default": ["instant", "background"],
|
|
"editor": "json"
|
|
}
|
|
},
|
|
"required": ["action"]
|
|
}
|