# Embedder Models

## What is an embedder? <a href="#what-is-an-embedder" id="what-is-an-embedder"></a>

An AI embedder converts information into numerical representations that capture their meaning. This enables your AI agent to compare and match different pieces of information, such as identifying articles that contain the answer to a question asked in a chat.

## Embedder models in Ebbot <a href="#embedder-models-in-ebbot" id="embedder-models-in-ebbot"></a>

In EbbotGPT Knowledge, you can choose which embedder model to use for retrieving information from your knowledge sources. You can select a different embedder for each data set, allowing flexibility in how data is processed. However, each dataset can only use one embedder model at a time.

<figure><img src="https://2117387010-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F3rWESGvwA3vHJ3zNiAG1%2Fuploads%2Fl5eQpRsBU7yp2QJdDsgZ%2Fimage.png?alt=media&#x26;token=5236f3ce-7837-4c8a-b1f1-68225b596ffc" alt=""><figcaption></figcaption></figure>

### Our embedder models <a href="#our-embedder-models" id="our-embedder-models"></a>

1. **Vector Search**

A vector search model finds similar items by comparing numerical representations (vectors) of text, images, or other data. Instead of matching exact words, it looks at meaning and context, making it useful for AI-powered search and recommendations.

2. **Vector Search Hybrid**

A vector search hybrid combines vector search with traditional keyword or database searches. This approach improves accuracy by using both deep understanding (from AI embeddings) and precise keyword matching, ensuring better and more relevant results.

## Deciding on what embedder to use <a href="#what-embedder-to-use" id="what-embedder-to-use"></a>

If you're unsure which embedder to choose, we recommend using **Vector Search Hybrid**. While both options perform well in most cases, Hybrid Search is particularly effective when keywords are key to retrieving the right information. It's especially useful when dealing with many sources that contain similar content.


---

# 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://docs.ebbot.ai/ebbot-docs/core-capabilities/ebbotgpt/ebbotgpt-knowledge/embedder-models.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.