fix: add providerId, maxTokens and topk to ai spec

[samirtahir91]

Closes # #535

📑 Description

We need to set maxTokens, providerId and topk for backends like google gemini and googlevertexai, else they fail with related errors.

This PR adds new environment variables for K8SGPT_MAX_TOKENS (default 2048) and K8SGPT_TOP_K (default 50) into the k8sgpt deployment spec.

It optionally adds the env var K8SGPT_PROVIDER_ID to the deployment spec

The new K8SGPT CRD specs introduced for this are:

ai:
  providerId
  maxTokens
  topk

I have tested with vertex ai in GKE with a custom image of k8sgpt based off this PR k8sgpt-ai/k8sgpt#1280 with the example:

apiVersion: core.k8sgpt.ai/v1alpha1
kind: K8sGPT
metadata:
  name: k8sgpt-sample-vertexai
  namespace: k8sgpt-operator-system
spec:
  ai:
    model: gemini-1.5-pro-002
    backend: googlevertexai
    providerId: <my gcp project ID>
    enabled: true
    anonymized: true
    maxTokens: "2048"
    topk: "40"
  version: latest
  repository: samirtahir91076/k8sgpt
  noCache: false

✅ Checks

• My pull request adheres to the code style of this project
• My code requires changes to the documentation
• I have updated the documentation as required
• All the tests have passed

ℹ Additional Information

This PR depends on k8sgpt-ai/k8sgpt#1280 for K8SGPT_MAX_TOKENS env var to configure k8sgpt server config.

[samirtahir91]

@AlexsJones Could you review this please?

[samirtahir91]

@AlexsJones - Can this be reviewed pls?