You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository was archived by the owner on Jul 23, 2024. It is now read-only.
I have a requirement where I need to create a knowledgebase from documentation of two versions of a SaaS application we have developed. The AI chat solution I want to develop should be able to help people learn about the differences between the versions and find out about migration paths. Example: some features that exist in both versions of the application might have the same names but a different API. When searching embeddings from the documentation, can Azure AI Search differentiate between the two versions of the application? If not by default, how can I achieve it? Can I add metadata to the indexing and have AI Search use that to differentiate and return correct search results? An example question might be: "What is the difference between feature XYZ in v1.x compared to v2.x?"
The documentation of the two applications are quite different (PDF vs web pages).
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
Hi!
I have a requirement where I need to create a knowledgebase from documentation of two versions of a SaaS application we have developed. The AI chat solution I want to develop should be able to help people learn about the differences between the versions and find out about migration paths. Example: some features that exist in both versions of the application might have the same names but a different API. When searching embeddings from the documentation, can Azure AI Search differentiate between the two versions of the application? If not by default, how can I achieve it? Can I add metadata to the indexing and have AI Search use that to differentiate and return correct search results? An example question might be: "What is the difference between feature XYZ in v1.x compared to v2.x?"
The documentation of the two applications are quite different (PDF vs web pages).
Beta Was this translation helpful? Give feedback.
All reactions