0

I am trying to build a chat experience on private data in Azure OpenAI. Currently in OpenAI Studio I can deploy a web app against private data housed in Azure Cognitive Search. I'd like that Search to be a vector embedding search, but cannot see any reasonable way to achieve that out of the box. The DataSources property on the api request doesn't seem to accept anything that would perform a vector search.

I can build this manually by doing the embeddings query manually, then doing the search query manually, and finally prompt engineering the Chat request. However, this seems like it should be something out of the box. This is all pretty new, and documentation is sparse on the Azure OpenAI stuff so im trying to decide if this is a feature gap or a documentation gap.

user19771002
  • 21
  • 2
  • Some links to get you started: https://learn.microsoft.com/en-us/shows/azure-friday/introducing-vector-search-in-azure-cognitive-search & https://python.langchain.com/docs/integrations/vectorstores/azuresearch. – Gaurav Mantri Aug 22 '23 at 14:58
  • @GauravMantri - thanks for these. I'm aware of the underlying tech. I'm more asking if this is a feature already built in to the Azure Open AI Extensions Chat Completions API: /openai/deployments/{deployment-id}/extensions/chat/completions?api-version={api-version} This api accepts a Data Source like Azure Cognitive Services search index, but I can't seem to find where to tell it to do a vector embeddings search against it. – user19771002 Aug 22 '23 at 15:56

1 Answers1

0

For those curious about this, just yesterday (the day before the question was posted) a PR was accepted into the sample app repository which demonstrates the Vector Search capability.

user19771002
  • 21
  • 2