search

PacktPublishing / Building-AI-Applications-with-Microsoft-Semantic-Kernel

Building AI Applications with Microsoft Semantic Kernel, published by Packt
MIT License
14 stars 8 forks source link

Chapter 7 - Create - Missing a step #1

Closed mnagatos101 closed 2 months ago

mnagatos101 commented 3 months ago

In the C# model for the ai search document, you specifically call out that the embedding field is not added like in python...that it will be added later dynamically during upload. However, i can't find any subsequent mention of this. When I upload, it says "The request is invalid. Details: Cannot find nested property 'Embedding' on the resource type 'search.documentFields'.". I will tinker with it more, but wanted to let you know.

Also, this example constrains me to searching a couple of strings. I would have liked to have seen a more robust example where I could search all document fields in a more robust index. In your example, how would you have also included the author field form the json objects?

mnagatos101 commented 3 months ago

Got it to work by adding the Embedding field via the Azure portal.

bsingha27 commented 2 months ago

Great to hear that you got it to work @mnagatos101, we're closing this issue! If you face any further issues on any chapter, please feel free to open a new one.