Embedder models
Read about what an embedder model is and how they are used for EbbotGPT to give answers based on your knowledge sourcs.
Last updated
Was this helpful?
Read about what an embedder model is and how they are used for EbbotGPT to give answers based on your knowledge sourcs.
Last updated
Was this helpful?
An AI embedder converts information into numerical representations that capture their meaning. This enables EbbotGPT to compare and match different pieces of information, such as identifying articles that contain the answer to a question asked in a chat.
In Ebbot, you can choose which embedder model to use for retrieving information from your knowledge sources. You can select a different embedder for each dataset, allowing flexibility in how data is processed. However, each dataset can only use one embedder model at a time.
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.
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.
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.