Add documentation on pointing llmengine client to self-hosted infrastructure

charts/llm-engine/values_sample.yaml

@@ -96,7 +96,7 @@ config:
       # k8s_cluster_name [required] is the name of the k8s cluster
       k8s_cluster_name: main_cluster
       # dns_host_domain [required] is the domain name of the k8s cluster
-      dns_host_domain: domain.llm-engine.com
+      dns_host_domain: llm-engine.domain.com
       # default_region [required] is the default AWS region for various resources (e.g ECR)
       default_region: us-east-1
       # aws_account_id [required] is the AWS account ID for various resources (e.g ECR)

docs/guides/self_hosting.md

@@ -200,4 +200,12 @@ $ curl -X POST 'http://localhost:5000/v1/llm/completions-sync?model_endpoint_nam
 You should get a response similar to:
 ```
 {"status":"SUCCESS","outputs":[{"text":". Tell me a joke about AI. Tell me a joke about AI. Tell me a joke about AI. Tell me","num_completion_tokens":30}],"traceback":null}
+```
+
+### Pointing LLM Engine client to use self-hosted infrastructure
+The `llmengine` client makes requests to Scale AI's hosted infrastructure by default. You can have `llmengine` client make requests to your own self-hosted infrastructure by setting the `LLM_ENGINE_BASE_PATH` environment variable to the URL of the `llm-engine` service. 
+
+The exact URL of `llm-engine` service depends on your Kubernetes cluster networking setup. The domain is specified at `config.values.infra.dns_host_domain` in the helm chart values config file. Using `charts/llm-engine/values_sample.yaml` as an example, you would do:
+```bash
+export LLM_ENGINE_BASE_PATH=https://llm-engine.domain.com
 ```