How to use RAG effectively

By dbracho, 1 April, 2026

19. Technical specifications for RAG

RAG allows your agent to respond using real information (documents) instead of relying only on general knowledge. This helps limit responsibilities and prevents the agent from hallucinating answers or falling short when it lacks sufficient information.

 

19.1. Supported file types

Currently, you can use:

  • Word documents (.docx)
  • PDFs
  • Images

 

19.2. Important considerations

A RAG is the set of additional information that the agent uses as context to generate more accurate and realistic responses. It works with text-based content, has no strict page limit, and allows you to include all relevant information needed, preventing the agent from giving incomplete or insufficient answers.

 

The model performs best with:

  • Clear text
  • Well-structured paragraphs

 

It may struggle with:

  • Complex tables
  • Scanned PDFs
  • Highly visual layouts

 

19.3. Document quality = response quality

 Good RAG:

  • Clear information
  • Well-structured
  • Noise-free

 

 Poor RAG:

  • Disorganized text
  • Duplicate information
  • Very long documents without structure

 

19.4. Be specific with your content

 Better:

  • FAQs
  • Scripts
  • Clear policies
  • Concrete information

 

Worse:

  • Generic documents
  • Ambiguous information

Tags