Overview

Store your organization’s content to ground synthetic data generation and evaluations in real source material.

About

A Knowledge Base (KB) is a store of your organization’s content: FAQs, documentation, SOPs, manuals, policies, and product specs. Future AGI indexes this content and makes it available across the platform. When you generate synthetic data or run evaluations, the platform pulls from your KB so outputs stay grounded in real source material instead of drifting into wrong terminology, invented procedures, or generic answers.

How Knowledge Base Connects to Other Features

  • Synthetic data generation: When creating a synthetic dataset, you can optionally select a KB. The generator uses your documents as context, producing examples that reflect your domain and terminology. Learn more
  • Evaluation: Run hallucination detection and grounding evals that compare model outputs against what your documents actually say. Learn more
  • Protect: Use KB content as reference material for guardrails that check whether responses align with your organization’s knowledge. Learn more

Getting Started

Understanding Knowledge Base

What a KB is, what content types are supported, and how files are processed.

Create KB Using UI

Create and manage a KB from the platform with drag-and-drop or bulk file upload.

Create KB Using SDK

Create and update knowledge bases programmatically with the Python SDK.

Next Steps

Was this page helpful?

Questions & Discussion