# 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.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://help.twise.ai/content/the-basics-of-how-knowledge-retrieval-works.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.