search

Azure-Samples / azure-search-openai-demo

A sample app for the Retrieval-Augmented Generation pattern running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences.
https://azure.microsoft.com/products/search
MIT License
6.15k stars 4.18k forks source link

Documentation of the feature "Use query-contextual summaries instead of whole documents" #1294

Closed giuliotosato closed 3 weeks ago

giuliotosato commented 8 months ago

Please provide us with the following information:

This issue is for a: (mark with an x)

- [ ] bug report -> please search issues before submitting
- [ ] feature request
- [X ] documentation issue or request
- [ ] regression (a behavior that used to work and stopped in a new release)

Minimal steps to reproduce

Is there any explanation of "Use query-contextual summaries instead of whole documents" feature? It seems that it's related to semantic search and changes the output with semantic results. But I cannot determine the complete idea of this.

image
pamelafox commented 8 months ago

Good question! It uses semantic captions for the answers, which are described here: https://techcommunity.microsoft.com/t5/ai-azure-ai-services-blog/introducing-semantic-search-bringing-more-meaningful-results-to/ba-p/2175636

You should be able to see the difference in the "supporting content", the answers would be relevant subsets of the cited sources. I haven't personally used this for my deployments, but if you do use it, please share whether it works well for you. The semantic captions team would love feedback about the caption generation.

pamelafox commented 3 weeks ago

We now have tooltips that explain this better, closing this issue.