-
Notifications
You must be signed in to change notification settings - Fork 0
ASM-21890 LLM-external-access #8
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: master
Are you sure you want to change the base?
Conversation
Signed-off-by: Yuan Fang <[email protected]>
WalkthroughA new documentation file was introduced, providing a comprehensive, step-by-step guide on configuring external access to inference services. The guide details procedures for setting up domains, configuring load balancers, and verifying external connectivity, including troubleshooting steps and references to related documentation. Changes
Suggested reviewers
Poem
📜 Recent review detailsConfiguration used: CodeRabbit UI 📒 Files selected for processing (1)
✅ Files skipped from review due to trivial changes (1)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Actionable comments posted: 0
🧹 Nitpick comments (5)
docs/en/model_inference/inference_service/how_to/external_access_inference_service.mdx (5)
1-7
: Front-matter lacks a canonical slug and description
Most docs pages includeslug:
and (optionally)description:
in the front-matter so that the static site generator produces predictable URLs and richer metadata for SEO. Add them to keep the page consistent with the rest of the docs set.--- weight: 10 +i18n: + # … +slug: external-access-inference-service +description: Step-by-step instructions for exposing Alauda inference services to the Internet. i18n: title: en: Configure External Access for Inference Services zh: 配置推理服务外部访问 ---
19-22
: Include a CLI one-liner for quickly retrievingstatus.url
Docs consumers often work purely from a terminal. A concretekubectl
command removes guesswork and speeds up validation.### 1. View External Access Address of the Inference Service @@ -To find the external access address of your inference service, navigate to the inference service details page. You can find the address in the **Access Method** card, or by viewing the **YAML** card and checking the address under `status.url`. +You can: +1. Navigate to the service details page and copy the address from the **Access Method** card, **or** +2. Run + ```bash + kubectl get inferenceservice <SERVICE_NAME> -o jsonpath='{.status.url}' + ``` + which prints the `status.url` field directly.
30-33
: Ambiguous parenthetical note
“(Multiple projects can share, create as needed)” reads awkwardly and may confuse non-native speakers. Re-phrase for clarity.-### 3. Create a Load Balancer (Multiple projects can share, create as needed) +### 3. Create a Load Balancer +(*One load balancer can be shared by multiple projects; create a new one only if necessary.*)
38-46
: Terminology & cross-product mapping could trip readers
A first-time ACP user might not know that “ServiceGroup” ≈ KubernetesService
. Add a short parenthetical to anchor the concept.-* **ServiceGroup**: Select the service named `knative-ingressgateway` under the `istio-system` namespace, and choose port **80**. +* **ServiceGroup** (Kubernetes **Service**): Select `knative-ingressgateway` in the `istio-system` namespace and choose port **80**.
51-56
:curl
example omits the HTTPS pathway and may mislead
The preceding steps configure both 80/HTTP and 443/HTTPS. Show the secure variant or explicitly state that the example targets HTTP to avoid doubt.-curl -v --resolve "your-inference-service-domain.com:your-port:your-load-balancer-ip" http://your-inference-service-domain.com/v1/models +# For HTTP +curl -v --resolve "your-inference-service-domain.com:80:your-load-balancer-ip" \ + http://your-inference-service-domain.com/v1/models + +# For HTTPS (skip `-k` if you have a valid certificate) +curl -vk --resolve "your-inference-service-domain.com:443:your-load-balancer-ip" \ + https://your-inference-service-domain.com/v1/models
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
docs/en/model_inference/inference_service/how_to/external_access_inference_service.mdx
(1 hunks)
close #ASM-21890
LLM-external-access
Summary by CodeRabbit