Twise Help Center
  • Welcome 👋
    • Quick start guide
    • [Video] Beginners guide on how to edit and share a twise
    • [Video] Tips, tricks and admin walk through
  • Content
    • How twise learns from your content
    • Knowledge cards
    • Best practise for adding content
    • Understanding how twise works with your content
    • How to match answers with visuals
    • Include links in answers
    • What kind of content can be uploaded?
    • Video and audio files
    • Adding lists and structured content
    • The basics of how knowledge retrieval works
    • Bulk import content via CSV or XML file
  • Content - Collections
    • What are collections?
  • Collections API - Events
  • Importing a collection via a Twise XML Feed
  • SHARING
    • [Video tutorial] How to get twise onto your website
    • How to share a twise
    • Website widget
    • Embed onto your site
    • Access rights
  • OTHER
    • Understand the Visitor: Setting Up Twise for Personalized Engagement
    • Lead capturing
    • Contact form & CTA
    • Insights
    • Voices
    • Privacy and security
    • Zapier Integration
    • How to iterate and improve answer quality
    • How do I upgrade to a paid plan?
    • How do credits work and what happens if you run out?
    • Delete a twise
    • API Guide
    • Enterprise plan onboarding
  • DESIGN
    • How to add a menu & navigation
    • Custom design
Powered by GitBook
On this page
  1. Content

The basics of how knowledge retrieval works

Categorical Search: This traditional method uses predefined categories and keywords to find information. It's simple but limited to exact matches.

Semantic Search with Twise: When you upload your structured data (like a people or product database) into Twise, it converts this data into a question-and-answer format using advanced techniques. Semantic search understands the context and meaning behind queries, not just exact words.

RAG (Retrieval-Augmented Generation): Twise combines finding relevant data (semantic search) with generating accurate responses. When users ask questions, Twise retrieves the most relevant information and generates precise answers.

Benefits: This makes your data more accessible and user-friendly, providing accurate and intuitive responses to user queries.

Things to Consider: Semantic search may not always find every answer within a specific category, especially if the data is sparse or not well-defined. It’s important to ensure your data is comprehensive and well-organized to maximize the effectiveness of Twise's semantic capabilities.

PreviousAdding lists and structured contentNextBulk import content via CSV or XML file

Last updated 1 year ago