What is the main purpose of a text embedding?
Why D is the answer
Representing meaning as a vector so similarity can be measured
Embeddings map text to vectors where similar meanings sit close together.
In detail
- An embedding represents meaning as a vector, so similarity can be measured.
- Close vectors mean similar meaning.
Use case
An illustrative scenario, not a real incident.
A help desk compares a question's vector with article vectors, and finds matches that share no keywords.
See it in different ways
flowchart LR A["Text"] --> B["Embedding model"] B --> C["Vector"] C --> D["Vector database"] E["Query vector"] --> D D --> F["Nearest passages"]
sequenceDiagram participant U as Query participant E as Embedding model participant V as Vector database U->>E: Text E-->>U: Vector U->>V: Find the nearest V-->>U: Similar passages
flowchart LR S0["Text"] --> S1["Embedding"] --> S2["Measure similarity"]
Key point: Embeddings make similarity measurable.
Why the other options are wrong
- A. Checking grammar before the text reaches the model
- It is not a grammar check.
- B. Compressing a file so it takes less storage on disk
- It is not file compression.
- C. Encrypting a prompt so providers cannot read the text
- It is not encryption.