microsoft / kernel-memory

RAG architecture: index and query any data using LLM and natural language, track sources, show citations, asynchronous memory patterns.
https://microsoft.github.io/kernel-memory
MIT License
1.34k stars 252 forks source link

Update SearchClient to use webPageUrl instead of static fileName for webpages (fixes microsoft/kernel-memory#491) #521

Closed chaelli closed 1 month ago

chaelli commented 1 month ago

Update SearchClient to use webPageUrl instead of static fileName for webpages

Motivation and Context (Why the change? What's the scenario?)

When providing webpages as facts, the "filename" currently is a static "content.url" - this provides no value when asking the LLM to include sources directly in the response (e.g. to have per paragraph sources).

High level description (Approach, Design)

When creating the facts, instead of "content.url" the webpage url is added