How to get from which page number of uploaded document , the Azure ai search chunk is coming?

Hadjmbarek Nadia 0 Reputation points
2024-10-04T14:05:24.96+00:00

I am using Import and vectorize data on Azure AI search to index my documents. Next, I use this index in Azure OpenAI Service (From your own data). I want the answers of the OpenAI service to contain the reference to the relevant chunk but also to **the number of page from the relevant document from which the chunk has come.
**
Anyone has an idea on how to do this? I have selected: GenerateNormalizedimagesPerPage to configure my indexer but all I got is an array of the pages numbers in the document (Ex: [1,2,3]) not just the relevant one related to the retrieved chunk.

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.
1,001 questions
Azure OpenAI Service
Azure OpenAI Service
An Azure service that provides access to OpenAI’s GPT-3 models with enterprise capabilities.
3,054 questions
Azure AI services
Azure AI services
A group of Azure services, SDKs, and APIs designed to make apps more intelligent, engaging, and discoverable.
2,840 questions
0 comments

1 answer

Sort by: Most helpful
Most helpful Newest Oldest
  1. Vahid Ghafarpour 21,325 Reputation points
    2024-10-04T16:09:37.3666667+00:00

    Thanks for posting your question in the Microsoft Q&A forum.

    You can create a custom skill that processes each chunk and extracts the page number. This skill should add the page number as a metadata field to each chunk.

    Ensure this metadata is indexed so that it can be retrieved during searches.

    [https://video2.skills-academy.com/en-us/azure/search/vector-search-how-to-chunk-documents

    ](https://video2.skills-academy.com/en-us/azure/search/vector-search-how-to-chunk-documents

    )** Please don't forget to close up the thread here by upvoting and accept it as an answer if it is helpful **

    0 comments

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.