diff --git a/qdrant-landing/content/documentation/advanced-tutorials/using-multivector-representations.md b/qdrant-landing/content/documentation/advanced-tutorials/using-multivector-representations.md index 415efc993..67ae23822 100644 --- a/qdrant-landing/content/documentation/advanced-tutorials/using-multivector-representations.md +++ b/qdrant-landing/content/documentation/advanced-tutorials/using-multivector-representations.md @@ -14,7 +14,7 @@ In most vector engines, each document is represented by a single vector - an app Multivector representations offer a more fine-grained alternative where a single document is represented using multiple vectors, often at the token or phrase level. This enables more precise matching between specific query terms and relevant parts of the document. Matching is especially effective in Late Interaction models like [ColBERT](https://qdrant.tech/documentation/fastembed/fastembed-colbert/), which retain token-level embeddings and perform interaction during query time leading to relevance scoring. -![Multivector Representations](/documentation/advanced-tutorials/multivector.png) +![Multivector Representations](/documentation/advanced-tutorials/multivectors.png) As you will see later in the tutorial, Qdrant supports multivectors and thus late interaction models natively. diff --git a/qdrant-landing/static/documentation/advanced-tutorials/multivector.png b/qdrant-landing/static/documentation/advanced-tutorials/multivector.png deleted file mode 100644 index 169c42fab..000000000 Binary files a/qdrant-landing/static/documentation/advanced-tutorials/multivector.png and /dev/null differ diff --git a/qdrant-landing/static/documentation/advanced-tutorials/multivectors.png b/qdrant-landing/static/documentation/advanced-tutorials/multivectors.png new file mode 100644 index 000000000..966d5820d Binary files /dev/null and b/qdrant-landing/static/documentation/advanced-tutorials/multivectors.png differ