Need a way to get the index of an string array

[chkrause]

Need a way to get the index of an string array

[RamanathanChinnappan-MSFT]

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

[HeidiSteen]

@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.

[Careyjmac]

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?

[chkrause]

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.

[Careyjmac]

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.

[RamanathanChinnappan-MSFT]

@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.