DocSynth
Sign In

SynthQA Generator

Last Update: 05/02/2025

Overview

SynthQA Generator enables the creation of synthetic question-answer (QA) pairs tailored for AI model training across various industries and use cases.

SynthQA Generator Overview

Configuration Options

Select Industry

Search or input a specific industry (e.g., Healthcare, Finance, E-commerce) to tailor QA generation to the domain.

Your Requirements (Optional)

Provide custom instructions, context, or specific needs to guide QA generation. This field helps define tone, complexity, or subject focus.

Categories

Organize your QA pairs by adding one or more categories (e.g., Customer Service, Product Features).

Example: Category 1 – Customer Service

Total QA Pairs to Generate

Default: 10

Specifies the total number of QA pairs to generate across all categories.

Auto-Download Dataset

Automatically downloads the generated QA pairs as a file when enabled.

Auto-Save to Database

Saves the generated QA pairs directly to a connected database when enabled.

Output Formats

Choose from the following supported formats:

DocSynth Single-Turn Format

Simple question-answer pairs in a single-turn structure.

Format: json

{
  "conversations": [
    {"from": "human", "value": "Q"},
    {"from": "assistant", "value": "A"}
  ]
}

OpenAI Format

Compatible with OpenAI's fine-tuning format, includes system-level guidance.

Format: json

{
  "messages": [
    {"role": "system", "content": "..."},
    {"role": "user", "content": "Q"},
    {"role": "assistant", "content": "A"}
  ]
}

QA Format

Minimalistic format with standalone QA pairs.

Format: json

{
  "question": "Q",
  "answer": "A"
}

OpenAI Format – System Message Configuration

Define the system role's content in the OpenAI format to control the tone, behavior, or focus of generated QA pairs. This message provides initial context for the assistant.

Example:

{
  "messages": [
    {
      "role": "system",
      "content": "Generate QA pairs for customer service scenarios, ensuring polite and professional responses."
    },
    {
      "role": "user",
      "content": "Q"
    },
    {
      "role": "assistant",
      "content": "A"
    }
  ]
}

This can either reference the content in Your Requirements or be uniquely crafted to suit OpenAI-specific training pipelines.

Actions

Generate QA Pairs

Initiates the generation process using the selected settings.

Start Over

Resets all configurations to their default values.