Description: You can store multiple vectors in a vector field of a document for data query. For example, if 128-dimensional vectors are generated from your data, you can store multiple 128-dimensional vectors in the vector field. Then, if one of the vectors in the document is retrieved, the document can be retrieved.
Scenario: After a piece of long text is segmented and vectorized, you can store the vectors of all segments in a vector field for data query.
Example:
In this example, 128-dimensional vectors are used.
The vector field is named vector. The Vector Dimension parameter of the vector index is 128. To retrieve a document by retrieving one or more vectors in the document, you need to push 128-dimensional vectors to the vector field and separate the vectors with the delimiter that is used to separate the elements in a vector in the vector field. The following figure shows the format of three vectors to be stored in a vector field if the delimiter is a comma (,).
When you perform a query, specify 128-dimensional vectors as the vectors to be queried. If one of the vectors in a document is retrieved, the document is retrieved.
When the retrieval results are sorted by score, if more than one vector in a document is retrieved, the score of the most relevant vector is used as the score of the document. If vector similarity is calculated based on Euclidean instance, a lower score indicates higher relevance. If vector similarity is calculated based on inner product, a higher score indicates higher relevance.