Chunking

The process of splitting long documents into smaller, meaningful pieces so an AI can retrieve exactly the right section to answer a question, not the entire document.

Technical definition

Chunking strategies include fixed-size (e.g. 500 tokens with overlap), semantic (splitting at paragraph or section boundaries), and recursive (progressively splitting large sections into smaller ones). Chunk size affects retrieval precision: smaller chunks are more specific but may lose context; larger chunks preserve context but reduce precision. Metadata (source, section title) is preserved per chunk.

How Verabase uses Chunking

Verabase uses intelligent chunking when you add sources to your knowledge base. PDFs, web pages, and documents are split at natural boundaries — headings, paragraphs, and list items — rather than at arbitrary character counts. Each chunk retains its source URL, page number, and section title as metadata. For visual documents, charts and diagrams are chunked separately with AI-generated descriptions.

Why it matters for support teams

Poor chunking is the most common reason RAG systems give wrong answers. If your 50-page manual is chunked into 10-page blocks, the AI retrieves too much irrelevant text. If it's chunked into single sentences, the AI loses context. Good chunking gives the AI the Goldilocks amount of information — just enough to answer accurately without drowning in noise.

Related terms

How Verabase Handles Self-Healing Knowledge

The standard industry approach relies on support agents manually flagging stale content and technical writers updating documentation weeks later. Verabase completely upends this model through an autonomous AI platform that identifies knowledge gaps the moment an AI agent encounters a question it cannot answer.

Rather than requiring manual intervention, our visual RAG engine drafts a proposed fix. It analyzes the context of the user's question, reviews your existing knowledge base for conflicts, and creates a clear, structured article or snippet. All you need to do is click 'Approve'. This ensures your AI agents continually get smarter over time without adding to your support team's workload.

Security First Architecture

Many legacy platforms bolt AI onto their existing infrastructure, creating potential data leaks between tenants or exposing sensitive internal documents to end-users. Verabase is built from the ground up with a Bring Your Own Key (BYOK) architecture, enterprise-grade access controls, and strict semantic boundaries. This means your private engineering documents never accidentally leak into customer-facing agent responses.