Ruvector Agentic Synth

@ruvector/agentic-synth

High-performance synthetic data generator designed for AI/ML training, RAG system evaluation, and agentic workflow testing. Generates realistic text, embeddings, Q&A pairs, conversations, and structured datasets.

Quick Reference

Installation

npx @ruvector/agentic-synth@latest

Quick Start

import {
  SynthGenerator,
  QAGenerator,
  ConversationGenerator,
  DatasetGenerator,
} from '@ruvector/agentic-synth';

const gen = new SynthGenerator({ seed: 42 });

// Generate Q&A pairs from documents (for RAG evaluation)
const qaPairs = await gen.generateQA(documents, {
  count: 100,
  difficulty: 'mixed',
  includeNegatives: true,
});

console.log(qaPairs[0]);
// { question: "What is the max retry count?",
//   answer: "The max retry count is 3",
//   context: "...",
//   difficulty: "easy",
//   isNegative: false }

// Generate synthetic embeddings (for testing vector search)
const embeddings = gen.generateEmbeddings({
  count: 10_000,
  dimensions: 1536,
  clusters: 50,
  noise: 0.1,
});

// Generate agent conversations (for training/eval)
const conversations = await gen.generateConversations({
  count: 50,
  turns: 5,
  agents: ['user', 'assistant'],
  topics: ['coding', 'debugging', 'architecture'],
});

// Generate structured dataset
const dataset = gen.generateDataset({
  count: 1000,
  schema: {
    name: { type: 'name' },
    email: { type: 'email' },
    score: { type: 'float', min: 0, max: 1 },
    category: { type: 'enum', values: ['A', 'B', 'C'] },
    embedding: { type: 'vector', dimensions: 384 },
  },
});

Core API

SynthGenerator

Main generator with all synthesis capabilities.

const gen = new SynthGenerator(config?: SynthConfig);

SynthConfig:

gen.generateQA(documents, options)

Generate question-answer pairs from source documents for RAG evaluation.

await gen.generateQA(
  documents: string[],
  options: QAOptions
): Promise<QAPair[]>

QAOptions:

QAPair:

gen.generateEmbeddings(options)

Generate synthetic embedding vectors with cluster structure.

gen.generateEmbeddings(options: EmbeddingOptions): EmbeddingDataset

EmbeddingOptions:

EmbeddingDataset:

gen.generateConversations(options)

Generate multi-turn agent conversations.

await gen.generateConversations(options: ConversationOptions): Promise<Conversation[]>

ConversationOptions:

Conversation:

gen.generateDataset(schema)

Generate structured tabular data.

gen.generateDataset(options: DatasetOptions): Record<string, unknown>[]

DatasetOptions:

Schema field types:

gen.generateText(options)

Generate synthetic text paragraphs.

await gen.generateText(options: TextOptions): Promise<string[]>

TextOptions:

CLI Usage

# Generate QA pairs
npx @ruvector/agentic-synth qa --input docs/ --count 100 --output qa.json

# Generate embeddings
npx @ruvector/agentic-synth embeddings --count 10000 --dims 384 --output embeds.npy

# Generate conversations
npx @ruvector/agentic-synth conversations --count 50 --turns 5 --output convos.json

# Generate dataset
npx @ruvector/agentic-synth dataset --count 1000 --schema schema.json --output data.csv

References

• API Reference
• npm