"Import and vectorize data" -- vector or hybrid index?

Barry Briggs 80 Reputation points
2024-12-18T15:20:57.8366667+00:00

When using the "Import and Vectorize Data" option (say, on JSON documents), are the original text fields preserved in the index with vectors added (for example, "body:" and "bodyVector:") or is the document simply vectorized as a whole? If the latter, is it possible in some way to extract specific fields in Azure OpenAI for example for citations?

Azure AI Search
Azure AI Search
An Azure search service with built-in artificial intelligence capabilities that enrich information to help identify and explore relevant content at scale.
1,142 questions
{count} votes

Accepted answer
  1. Laxman Reddy Revuri 1,525 Reputation points Microsoft Vendor
    2024-12-26T04:09:53.2833333+00:00

    Hi @Barry Briggs
    You are correct! Using the "Import and Vectorize Data" wizard in Azure Cognitive Search with a dataset like JSON documents containing fields such as title, author, and body results in the creation of a hybrid index.
    Please accept as "Yes" if the answer provided is useful , so that you can help others in the community looking for remediation for similar issues.

    1 person found this answer helpful.

0 additional answers

Sort by: Most helpful

Your answer

Answers can be marked as Accepted Answers by the question author, which helps users to know the answer solved the author's problem.