Update multimodal-search-overview.md

Author: gmndrg

articles/search/multimodal-search-overview.md

@@ -11,7 +11,7 @@ ms.author: gimondra
 
 # Multimodal search in Azure AI Search
 
-Multimodal search refers to the ability to ingest, understand, and retrieve content across multiple data types, including text, images, and other modalities such as video and audio. In Azure AI Search, multimodal search supports natively the ingestion and retrieval of documents containing text and images, enabling users to perform searches that combine these modalities. In practice, this capability means an application using multimodal search can answer a question such as, "What is the process to have an HR form approved?" even when the only authoritative description of the workflow lives inside an embedded diagram of a PDF file.  
+Multimodal search refers to the ability to ingest, understand, and retrieve content across multiple data types, including text, images, and other modalities such as video and audio. In Azure AI Search, multimodal search natively supports the ingestion of documents containing text and images, as well as the retrieval of their content, enabling users to perform searches that combine these modalities. In practice, this capability means an application using multimodal search can answer a question such as, "What is the process to have an HR form approved?" even when the only authoritative description of the workflow lives inside an embedded diagram of a PDF file.  
 
 Diagrams, scanned forms, screenshots, and infographics often contain the decisive details that make or break an answer. Multimodal search helps close the gap by integrating visual content into the same retrieval pipeline as text. This approach reduces the likelihood that your AI agent or RAG application might overlook important images and enables your users to trace every provided answer back to its original source.