Giter Site home page Giter Site logo

Comments (6)

RamanathanChinnappan-MSFT avatar RamanathanChinnappan-MSFT commented on July 20, 2024

@chkrause
Thanks for your feedback! We will investigate and update as appropriate.

from azure-docs.

HeidiSteen avatar HeidiSteen commented on July 20, 2024

@chkrause, to restate the question, you're not getting a chunk ID for your data chunks? Just curious if you've tried the import and vectorize data wizard to see how that index, skillset, and indexer configuration is set up because that wizard produces chunk ids and parent id, but I can't tell you how the chunk ID was generated. @Careyjmac for SME on index projections and split skills.

from azure-docs.

Careyjmac avatar Careyjmac commented on July 20, 2024

It sounds like you are asking if there is a way to select the value of the index and map it to a field in the index. Today, I don't think there is a way to do that. However, the value of the index is in the chunk key that we are already generating as part of index projections. For your example document, the chunk key that we generate will be "<hash>_<parent key value>_textItems_0", where the 0 at the end is the index. Is that sufficient for your use case?

from azure-docs.

chkrause avatar chkrause commented on July 20, 2024

Hi @Careyjmac, thanks for the hint, that the index key is generated with the chunk id. Is there a way to map the chunk id to a seperate field, maybe by function extractTokenAtPosition?

I just wondering why when using the playground in azure ai studio preview the chunk_id is generated as seperate field.

image

from azure-docs.

Careyjmac avatar Careyjmac commented on July 20, 2024

Unfortunately index projections don't offer support for field mapping functions today, so I don't think there is any way to extract the index from the key definition directly. I can definitely log that as a possible feature request though as it is an interesting idea.

I believe the Azure AI Studio experience is using a different process for chunking and indexing data outside of the built in integrated vectorization pipeline, hence why they have some additional fields and their key schema is defined differently.

from azure-docs.

RamanathanChinnappan-MSFT avatar RamanathanChinnappan-MSFT commented on July 20, 2024

@chkrause
We are going to close this thread. if there are any further questions regarding the documentation, please tag me in your reply and we will be happy to continue the conversation.

from azure-docs.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.