[deepersprout]

I usually feed all the documentation to an llm and ask the question to the llm that fetches the info with rag. For example:

> how do i configure Traefik to proxy traffic to two backend services?

Configuring Traefik to proxy traffic to multiple backend services is a common use case. You can achieve this by defining multiple entry points and routers in Traefik's configuration, each pointing to a different backend service. Here's a basic example of how you can configure Traefik to proxy traffic to two backend services:

  yaml
  
  # traefik.yaml
  
  # Enable API and Dashboard
  api:
    dashboard: true
  
  # Define entry points
  entryPoints:
    web:
      address: ":80"
    app1:
      address: ":8081"
    app2:
      address: ":8082"

[...more stuff...]

[freedomben]

Can you describe more on your process? Which LLM are you using? Are you doing soething specific to make it us RAG or is that automagic (might be obvious depending on which LLM you are using but)? How do you feed the documentation in? for example, when the documentation has more than one page, how do you get that content in to the LLM? Is it part of the prompt or something you've tuned it on? have to clone the docs site, turn it into plan text and feed that in to the prompt or can you pass a URL and have it crawl ahead of time or something?

This is the system I've been dreaming about but haven't had time to dig into yet. I've got ollama and openwebui set up now though, and with OpenAI getting bigger context windows it seems like it might be possible to inject the whole set of docs into the prompt, but I'm not sure how to go about that

[san-fran]

This might be an additional way to quickly iterate on the content of the documentation itself. If I were the one writing, an easy test is passing the documentation to a lay person and asking them if they have what they need to perform X by following the documentation.

Perhaps having a focused LLM generate the steps could help catch some documentation deficiencies.

[freedomben]

> If I were the one writing, an easy test is passing the documentation to a lay person and asking them if they have what they need to perform X by following the documentation.

What kind of documentation is this though? Is this how to bake a cake or tie a necktie, or is it how to setup a reverse proxy for the services in your k8s cluster?

If it's something a lay-person could do then I think this is a good strategy (though depending on the size/scope of the project/documentaiton it does seem like a pretty big effort to undertake without compensation), but if it's something highly technical like Traefik, I expect a lay-person to not even understand half the words/vocabulary in the documentation, let alone be able to perform X by reading it and following it.

[all2]

If we push this into the software development domain, my expectation would be something like "documentation should allow a software developer to do this thing without knowing the underlying tooling".

> how to setup a reverse proxy for the services in your k8s cluster

Going off this specifically. I don't know how to do this. I actually have a k8s cluster on a home server waiting for me to do exactly this. Ideally there would be a doc that would start with ingress selection, and then guide a user through how to get it set up with common use-cases. Or something like that. Like others in this conversation, I've been leveraging LLMs with varying degrees of success to try and navigate this.

[bsenftner]

I did this with Tailscale, which I have endless problems getting to work reliably. Their documentation is a joke. The process is pretty simple: scrape, than concatenate into a large text file and submit.