←back to thread

Ask HN: Best way to create a searchable knowledge base?

20 points aljgz | 1 comments | 16 Oct 25 17:36 UTC | HN request time: 0.2s | source

Have you had the experience of using/developing knowledge bases? Here is my scenario:

My team is dealing with a lot of information: Wikis, Code repos, Monitoring dashboards, internal chat messages, emails, Task tickets, related systems, etc.

There are many cases when we need to do ad-hoc searches for anything related to a concept. For instance, imagine if someone makes a change to a metric, there is a need to find all dashboards that might be using this metric to make sure they are still valid after the change.

I don't want to just fix this problem, but create the ability to find related information in ad-hoc cases.

The ramp-up time is not important, as long as some positive value can be created with a small initial effort.

Any existing products (Paid/Free/Open Source, etc) and any references to existing knowledge (designs, discussions) about this would be really appreciated.

1. asim ◴[17 Oct 25 11:24 UTC] No.45615423[source]▶
So I just started doing this using LLM embeddings for semantic search. It actually works quite well. You index every piece of data with metadata and it's content. Then you choose specific metadata fields you might want to correlate on e.g knowing two pieces of data are of type "product" or "design" and then the query will return the related items. OpenAI gets used for turning your query into what can then be used against your index which is basically a vector dB. If you are using Go then chromem-go does this quite easily and has examples.