Conversation
|
Note Reviews pausedIt looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the Use the following commands to manage reviews:
Use the checkboxes below for quick actions:
WalkthroughThis PR restructures AI/ML docs: adds KServe, Envoy AI Gateway, and LWS pages; removes legacy ai-generative content and certain Knative/GitLab migration sections; updates upgrade flow and target version (2.0 → 2.2); and adjusts multiple front-matter weights and a few headings. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Suggested reviewers
Poem
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 inconclusive)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
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. Comment |
Deploying alauda-ai with
|
| Latest commit: |
76217ba
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://6b8783a9.alauda-ai.pages.dev |
| Branch Preview URL: | https://upgrade-build-of-kserve.alauda-ai.pages.dev |
There was a problem hiding this comment.
Actionable comments posted: 6
🧹 Nitpick comments (3)
docs/en/lws/intro.mdx (1)
29-29: Consider adding.mdxextension to relative link for consistency.Same as the AI Gateway intro page - the link
../kserve/introlacks the.mdxextension. Consider updating for consistency with other relative links in the documentation.📝 Suggested fix
-- **KServe (Alauda Build)**: [../kserve/intro](../kserve/intro) — KServe uses LeaderWorkerSet as a required dependency for multi-node LLM inference workloads. +- **KServe (Alauda Build)**: [../kserve/intro](../kserve/intro.mdx) — KServe uses LeaderWorkerSet as a required dependency for multi-node LLM inference workloads.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/en/lws/intro.mdx` at line 29, Update the relative link target "../kserve/intro" in the "KServe (Alauda Build)" line to include the .mdx extension so it becomes "../kserve/intro.mdx" for consistency with other doc links; edit the anchor text near "KServe (Alauda Build)" in docs/en/lws/intro.mdx and ensure any other occurrences of "../kserve/intro" in this file are updated likewise.docs/en/kserve/install.mdx (1)
100-104: Clarify deployment mode choice in example.The example YAML shows
deploymentMode: Knative, butdocs/en/installation/ai-cluster.mdx(lines 9, 15-17) recommends Standard mode (RawKubernetes Deployment) for generative inference workloads. Consider either:
- Using
RawDeploymentas the example default to align with the recommendation, or- Adding a comment explaining when to choose each mode.
📝 Option 1: Change to RawDeployment with comment
kserve: controller: - deploymentMode: Knative # [!code callout] + deploymentMode: RawDeployment # [!code callout] # Use 'Knative' for serverless scale-to-zero, 'RawDeployment' for generative AI (recommended) gateway: domain: <inference-domain> # [!code callout]🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/en/kserve/install.mdx` around lines 100 - 104, The example sets kserve.controller.deploymentMode: Knative but the installation guide recommends Standard/RawKubernetes for generative inference; update the example to use RawDeployment (or RawKubernetes/Standard equivalent used in your docs) and add a short inline comment on kserve.controller.deploymentMode explaining when to prefer RawDeployment (low-latency, high-throughput/generative inference) vs Knative (scale-to-zero/event-driven). Locate and change the deploymentMode value in the kserve.controller block and add the one-line explanatory comment next to the deploymentMode and/or the gateway.domain entry so readers understand the recommended default and alternatives.docs/en/ai_gateway/intro.mdx (1)
33-33: Consider adding.mdxextension to relative link for consistency.The link
../kserve/introlacks the.mdxextension. Other documentation files in this PR (e.g.,docs/en/kserve/install.mdxat lines 16-17) use explicit.mdxextensions for relative links. Consider updating for consistency.📝 Suggested fix
-- **KServe (Alauda Build)**: [../kserve/intro](../kserve/intro) — KServe uses Envoy AI Gateway as a required dependency for exposing and routing inference services. +- **KServe (Alauda Build)**: [../kserve/intro](../kserve/intro.mdx) — KServe uses Envoy AI Gateway as a required dependency for exposing and routing inference services.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/en/ai_gateway/intro.mdx` at line 33, Update the relative link string "../kserve/intro" in docs/en/ai_gateway/intro.mdx (the line containing "**KServe (Alauda Build)**: [../kserve/intro]") to include the .mdx extension so it becomes "../kserve/intro.mdx" for consistency with other docs; ensure the displayed label remains unchanged and verify the link resolves after the edit.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@docs/en/ai_gateway/install.mdx`:
- Around line 35-36: Complete the truncated sentence in the upgrade
instructions: update the line mentioning "Administrator -> Clusters -> Target
Cluster -> Functional Components" and the `Upgrade` button so it reads something
like "click the `Upgrade` button, and you will see the `Alauda Build of Envoy AI
Gateway` can be upgraded — click it and follow the prompts to complete the
upgrade." Ensure the new wording replaces the incomplete ending and clearly
instructs the user to follow prompts to finish the upgrade.
In `@docs/en/kserve/install.mdx`:
- Around line 170-173: The upgrade instructions stop at clicking "Upgrade" and
need completion and verification steps: after the user clicks the **Upgrade**
button for "Alauda Build of KServe" (via `violet` upload and Administrator ->
Marketplace -> OperatorHub), add a sentence stating the operator will be updated
and the KServe CR will reconcile, then add a verification step such as running
the KServe status check (for example, using `kubectl get kserve default-kserve
-n kserve-operator`) and confirming the operator pod(s) and KServe CR reach the
Ready state; update the "Upgrading Alauda Build of KServe" section to include
these expected outcomes and the verification command(s).
In `@docs/en/kserve/intro.mdx`:
- Line 9: The sentence "**Alauda Build of KServe** is based on the
[KServe](https://kserve.github.io/website/) ." contains an extra space before
the period; remove the space so the closing parenthesis is immediately followed
by the period (i.e., change "...[KServe](https://kserve.github.io/website/)." in
docs/en/kserve/intro.mdx) to correct the typographical error.
In `@docs/en/upgrade/upgrade-from-previous-version.mdx`:
- Line 215: Update the verification expectation sentence in the docs text that
currently reads "Should returns `DEPLOYED: True`" to correct grammar by changing
it to "Should return `DEPLOYED: True`" (update the sentence in the
docs/en/upgrade/upgrade-from-previous-version.mdx where the expectation string
is defined).
- Around line 22-25: The second list item currently reads "Downloading" but
links to the upload section (`#upload-operator`); update the text and/or link so
they match: either change the visible verb to "Uploading" in the line containing
"2. [Downloading](../kserve/install.mdx#upload-operator) operator bundle
packages for `Alauda Build of KServe`." or change the link anchor to the correct
download anchor in ../kserve/install.mdx; ensure the list item’s visible verb
and the linked anchor (e.g., `#upload-operator`) are consistent.
- Around line 82-87: The surrounding explanatory text still refers to “both
operators” while the table header and rows are specific to “Alauda AI Operator”;
update the nearby copy to consistently reference the singular Alauda AI Operator
(or reword to “the operator” where appropriate), replacing occurrences of “both
operators” and any plural phrasing in the same section so headings, intro
sentences, and cross-references match the table labeled "Alauda AI Operator."
Ensure any subsequent mentions in this section and immediate neighboring
paragraphs use the singular form for clarity.
---
Nitpick comments:
In `@docs/en/ai_gateway/intro.mdx`:
- Line 33: Update the relative link string "../kserve/intro" in
docs/en/ai_gateway/intro.mdx (the line containing "**KServe (Alauda Build)**:
[../kserve/intro]") to include the .mdx extension so it becomes
"../kserve/intro.mdx" for consistency with other docs; ensure the displayed
label remains unchanged and verify the link resolves after the edit.
In `@docs/en/kserve/install.mdx`:
- Around line 100-104: The example sets kserve.controller.deploymentMode:
Knative but the installation guide recommends Standard/RawKubernetes for
generative inference; update the example to use RawDeployment (or
RawKubernetes/Standard equivalent used in your docs) and add a short inline
comment on kserve.controller.deploymentMode explaining when to prefer
RawDeployment (low-latency, high-throughput/generative inference) vs Knative
(scale-to-zero/event-driven). Locate and change the deploymentMode value in the
kserve.controller block and add the one-line explanatory comment next to the
deploymentMode and/or the gateway.domain entry so readers understand the
recommended default and alternatives.
In `@docs/en/lws/intro.mdx`:
- Line 29: Update the relative link target "../kserve/intro" in the "KServe
(Alauda Build)" line to include the .mdx extension so it becomes
"../kserve/intro.mdx" for consistency with other doc links; edit the anchor text
near "KServe (Alauda Build)" in docs/en/lws/intro.mdx and ensure any other
occurrences of "../kserve/intro" in this file are updated likewise.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 8102ca3a-1ddb-4c98-8b7f-49f2bcdc9a6a
📒 Files selected for processing (18)
docs/en/ai_gateway/index.mdxdocs/en/ai_gateway/install.mdxdocs/en/ai_gateway/intro.mdxdocs/en/installation/ai-cluster.mdxdocs/en/installation/ai-generative.mdxdocs/en/kserve/index.mdxdocs/en/kserve/install.mdxdocs/en/kserve/intro.mdxdocs/en/kubeflow/index.mdxdocs/en/kueue/index.mdxdocs/en/kueue/install.mdxdocs/en/llama_stack/index.mdxdocs/en/lws/index.mdxdocs/en/lws/install.mdxdocs/en/lws/intro.mdxdocs/en/trustyai/index.mdxdocs/en/upgrade/migrating-to-knative-operator.mdxdocs/en/upgrade/upgrade-from-previous-version.mdx
💤 Files with no reviewable changes (1)
- docs/en/installation/ai-generative.mdx
There was a problem hiding this comment.
🧹 Nitpick comments (1)
docs/en/envoy_ai_gateway/intro.mdx (1)
29-33: Consider reducing repeated “Envoy …” starts in the resource list.Lines 29–33 read slightly repetitive due to repeated lead wording. Optional polish: vary labels a bit for faster scanning.
✍️ Optional wording tweak
-- **Envoy AI Gateway Documentation**: [https://aigateway.envoyproxy.io/](https://aigateway.envoyproxy.io/) — Official documentation covering architecture, configuration, and API references. -- **Envoy AI Gateway GitHub**: [https://github.com/envoyproxy/ai-gateway](https://github.com/envoyproxy/ai-gateway) — Source code, release notes, and issues. -- **Envoy Gateway**: [https://gateway.envoyproxy.io/](https://gateway.envoyproxy.io/) — The underlying gateway infrastructure that Envoy AI Gateway extends. +- **Official Docs (Envoy AI Gateway)**: [https://aigateway.envoyproxy.io/](https://aigateway.envoyproxy.io/) — Architecture, configuration, and API references. +- **GitHub Repository (Envoy AI Gateway)**: [https://github.com/envoyproxy/ai-gateway](https://github.com/envoyproxy/ai-gateway) — Source code, release notes, and issues. +- **Underlying Gateway (Envoy Gateway)**: [https://gateway.envoyproxy.io/](https://gateway.envoyproxy.io/) — Base gateway infrastructure extended by Envoy AI Gateway.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/en/envoy_ai_gateway/intro.mdx` around lines 29 - 33, The resource list in the intro.mdx block repeats the phrase "Envoy ..." at the start of several list items; change the visible labels to reduce repetition (e.g., "Official docs — Envoy AI Gateway", "GitHub repo — Envoy AI Gateway", "Underlying gateway — Envoy Gateway", "Gateway API Inference Extension (GIE)", "KServe (Alauda Build)") while keeping the same href targets so links are unchanged; update the five list item labels shown in the diff to be more varied and scannable without altering URLs.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Nitpick comments:
In `@docs/en/envoy_ai_gateway/intro.mdx`:
- Around line 29-33: The resource list in the intro.mdx block repeats the phrase
"Envoy ..." at the start of several list items; change the visible labels to
reduce repetition (e.g., "Official docs — Envoy AI Gateway", "GitHub repo —
Envoy AI Gateway", "Underlying gateway — Envoy Gateway", "Gateway API Inference
Extension (GIE)", "KServe (Alauda Build)") while keeping the same href targets
so links are unchanged; update the five list item labels shown in the diff to be
more varied and scannable without altering URLs.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 7ae32a6e-16b3-4e79-afac-1674da8d245f
📒 Files selected for processing (4)
docs/en/envoy_ai_gateway/index.mdxdocs/en/envoy_ai_gateway/install.mdxdocs/en/envoy_ai_gateway/intro.mdxdocs/en/kserve/install.mdx
✅ Files skipped from review due to trivial changes (3)
- docs/en/envoy_ai_gateway/index.mdx
- docs/en/envoy_ai_gateway/install.mdx
- docs/en/kserve/install.mdx
There was a problem hiding this comment.
Actionable comments posted: 1
♻️ Duplicate comments (1)
docs/en/upgrade/upgrade-from-previous-version.mdx (1)
23-23:⚠️ Potential issue | 🟡 MinorAlign visible action text with the linked anchor.
Line 23 says Downloading but links to
#upload-operator, which is inconsistent in the step flow.📝 Proposed fix
-2. [Downloading](../kserve/install.mdx#upload-operator) operator bundle packages for `Alauda Build of KServe`. +2. [Uploading](../kserve/install.mdx#upload-operator) operator bundle packages for `Alauda Build of KServe`.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/en/upgrade/upgrade-from-previous-version.mdx` at line 23, The visible link text "Downloading" is inconsistent with the anchor target "#upload-operator"; update the step so the action text matches the linked anchor — either change the link text to "Upload operator" (to match `#upload-operator`) or change the anchor target to a download-related anchor; edit the markdown line containing the link (the text "Downloading" and the anchor "#upload-operator") so they accurately reflect the intended action and remain consistent with the step flow.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@docs/en/upgrade/upgrade-from-previous-version.mdx`:
- Line 203: Replace the awkward sentence "Check the status field from the
`KServe` resource which named `default-kserve`" with a grammatically correct
version; update the text to read "Check the status field of the `KServe`
resource named `default-kserve`" so it is clear and natural (locate the existing
phrase "Check the status field from the `KServe` resource which named
`default-kserve`" and replace it).
---
Duplicate comments:
In `@docs/en/upgrade/upgrade-from-previous-version.mdx`:
- Line 23: The visible link text "Downloading" is inconsistent with the anchor
target "#upload-operator"; update the step so the action text matches the linked
anchor — either change the link text to "Upload operator" (to match
`#upload-operator`) or change the anchor target to a download-related anchor; edit
the markdown line containing the link (the text "Downloading" and the anchor
"#upload-operator") so they accurately reflect the intended action and remain
consistent with the step flow.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 99461863-40ef-41c4-bddb-ed59f857941d
📒 Files selected for processing (4)
docs/en/envoy_ai_gateway/install.mdxdocs/en/kserve/install.mdxdocs/en/kserve/intro.mdxdocs/en/upgrade/upgrade-from-previous-version.mdx
✅ Files skipped from review due to trivial changes (2)
- docs/en/envoy_ai_gateway/install.mdx
- docs/en/kserve/install.mdx
7e7003d to
334d281
Compare
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
docs/en/installation/ai-cluster.mdx (1)
235-237:⚠️ Potential issue | 🟡 MinorAvoid hard-coding ACP 4.0 Knative version in a shared example.
Line 237 currently defaults to
1.18.1, but Line 263-Line 264 states ACP 4.1+ should use1.19.6. This is easy to copy-paste incorrectly.📝 Suggested doc fix
- version: "1.18.1" # [!code callout] + version: "<knative-serving-version>" # [!code callout] @@ -1. Specify the version of Knative Serving to be deployed. +1. Set `<knative-serving-version>` based on ACP version: + - ACP 4.0: `1.18.1` + - ACP 4.1 and above: `1.19.6`Also applies to: 262-265, 269-269
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/en/installation/ai-cluster.mdx` around lines 235 - 237, Replace the hard-coded Knative version string (e.g., the line containing version: "1.18.1") with a neutral placeholder or a clearly annotated conditional note (e.g., "KNATIVE_VERSION" or "use 1.18.1 for ACP 4.0, 1.19.6 for ACP 4.1+") and update the surrounding examples so they don't default to a specific release; ensure you change all other occurrences referenced (the other instances around the 262-265 and 269 ranges) so the doc shows a single source of truth for choosing between 1.18.1 and 1.19.6 rather than embedding one as the default.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Outside diff comments:
In `@docs/en/installation/ai-cluster.mdx`:
- Around line 235-237: Replace the hard-coded Knative version string (e.g., the
line containing version: "1.18.1") with a neutral placeholder or a clearly
annotated conditional note (e.g., "KNATIVE_VERSION" or "use 1.18.1 for ACP 4.0,
1.19.6 for ACP 4.1+") and update the surrounding examples so they don't default
to a specific release; ensure you change all other occurrences referenced (the
other instances around the 262-265 and 269 ranges) so the doc shows a single
source of truth for choosing between 1.18.1 and 1.19.6 rather than embedding one
as the default.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 56bf01ac-ddc6-439b-a5ed-88892118a781
📒 Files selected for processing (18)
docs/en/envoy_ai_gateway/index.mdxdocs/en/envoy_ai_gateway/install.mdxdocs/en/envoy_ai_gateway/intro.mdxdocs/en/installation/ai-cluster.mdxdocs/en/installation/ai-generative.mdxdocs/en/kserve/index.mdxdocs/en/kserve/install.mdxdocs/en/kserve/intro.mdxdocs/en/kubeflow/index.mdxdocs/en/kueue/index.mdxdocs/en/kueue/install.mdxdocs/en/llama_stack/index.mdxdocs/en/lws/index.mdxdocs/en/lws/install.mdxdocs/en/lws/intro.mdxdocs/en/trustyai/index.mdxdocs/en/upgrade/migrating-to-knative-operator.mdxdocs/en/upgrade/upgrade-from-previous-version.mdx
💤 Files with no reviewable changes (1)
- docs/en/installation/ai-generative.mdx
✅ Files skipped from review due to trivial changes (13)
- docs/en/kueue/install.mdx
- docs/en/lws/install.mdx
- docs/en/kserve/index.mdx
- docs/en/envoy_ai_gateway/index.mdx
- docs/en/llama_stack/index.mdx
- docs/en/trustyai/index.mdx
- docs/en/kueue/index.mdx
- docs/en/kubeflow/index.mdx
- docs/en/lws/index.mdx
- docs/en/envoy_ai_gateway/install.mdx
- docs/en/upgrade/migrating-to-knative-operator.mdx
- docs/en/kserve/install.mdx
- docs/en/upgrade/upgrade-from-previous-version.mdx
334d281 to
e7cf92c
Compare
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@docs/en/envoy_ai_gateway/intro.mdx`:
- Around line 1-33: The internal cross-directory link at the bottom of
docs/en/envoy_ai_gateway/intro.mdx uses ../kserve/intro without the .mdx
extension; update that link to ../kserve/intro.mdx so it matches the repository
convention used elsewhere (e.g., ../installation/ai-cluster.mdx and
../kserve/install.mdx) by editing the markdown link in the file (search for the
anchor referencing KServe or the text "KServe (Alauda Build)").
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 91a253a4-0c3f-41d9-a564-6db743a14480
📒 Files selected for processing (18)
docs/en/envoy_ai_gateway/index.mdxdocs/en/envoy_ai_gateway/install.mdxdocs/en/envoy_ai_gateway/intro.mdxdocs/en/installation/ai-cluster.mdxdocs/en/installation/ai-generative.mdxdocs/en/kserve/index.mdxdocs/en/kserve/install.mdxdocs/en/kserve/intro.mdxdocs/en/kubeflow/index.mdxdocs/en/kueue/index.mdxdocs/en/kueue/install.mdxdocs/en/llama_stack/index.mdxdocs/en/lws/index.mdxdocs/en/lws/install.mdxdocs/en/lws/intro.mdxdocs/en/trustyai/index.mdxdocs/en/upgrade/migrating-to-knative-operator.mdxdocs/en/upgrade/upgrade-from-previous-version.mdx
💤 Files with no reviewable changes (1)
- docs/en/installation/ai-generative.mdx
✅ Files skipped from review due to trivial changes (12)
- docs/en/kueue/install.mdx
- docs/en/lws/install.mdx
- docs/en/trustyai/index.mdx
- docs/en/kubeflow/index.mdx
- docs/en/kserve/index.mdx
- docs/en/kueue/index.mdx
- docs/en/lws/index.mdx
- docs/en/envoy_ai_gateway/index.mdx
- docs/en/llama_stack/index.mdx
- docs/en/envoy_ai_gateway/install.mdx
- docs/en/upgrade/migrating-to-knative-operator.mdx
- docs/en/kserve/install.mdx
🚧 Files skipped from review as they are similar to previous changes (1)
- docs/en/upgrade/upgrade-from-previous-version.mdx
| --- | ||
| weight: 10 | ||
| --- | ||
|
|
||
| # Introduction | ||
|
|
||
| ## Envoy AI Gateway | ||
|
|
||
| **Alauda Build of Envoy AI Gateway** is based on the [Envoy AI Gateway](https://aigateway.envoyproxy.io/) project. | ||
| Envoy AI Gateway is a Kubernetes-native, AI-specific gateway layer built on top of [Envoy Gateway](https://gateway.envoyproxy.io/), providing intelligent traffic management, routing, and policy enforcement for AI inference workloads. | ||
|
|
||
| Main components and capabilities include: | ||
|
|
||
| - **AI-Aware Routing**: Routes inference requests to the appropriate backend model service based on request content, model name, and backend availability — enabling transparent multi-model serving behind a single endpoint. | ||
| - **OpenAI-Compatible API**: Exposes a unified, OpenAI-compatible API surface (`/v1/chat/completions`, `/v1/completions`, `/v1/models`) for all downstream inference services, regardless of the underlying runtime. | ||
| - **Per-Model Rate Limiting & Policies**: Enforces fine-grained rate limiting, token quotas, and traffic policies at the individual model level, preventing resource starvation and ensuring fair usage across tenants. | ||
| - **Backend Load Balancing**: Distributes inference requests across multiple replicas of the same model using configurable load-balancing strategies, with health checking and automatic failover. | ||
| - **Envoy Gateway Integration**: Runs as an extension of Envoy Gateway, inheriting its Kubernetes Gateway API-native control plane, TLS termination, and observability features (metrics, access logs, distributed tracing). | ||
| - **Gateway API Inference Extension (GIE)**: Integrates with the Kubernetes SIG Gateway API Inference Extension for advanced, inference-aware scheduling and load balancing decisions based on real-time backend state. | ||
|
|
||
| Envoy AI Gateway is a required dependency of **Alauda Build of KServe** for exposing inference services. | ||
|
|
||
| For installation on the platform, see [Install Envoy AI Gateway](./install). | ||
|
|
||
| ## Documentation | ||
|
|
||
| Envoy AI Gateway upstream documentation and related resources: | ||
|
|
||
| - **Envoy AI Gateway Documentation**: [https://aigateway.envoyproxy.io/](https://aigateway.envoyproxy.io/) — Official documentation covering architecture, configuration, and API references. | ||
| - **Envoy AI Gateway GitHub**: [https://github.com/envoyproxy/ai-gateway](https://github.com/envoyproxy/ai-gateway) — Source code, release notes, and issues. | ||
| - **Envoy Gateway**: [https://gateway.envoyproxy.io/](https://gateway.envoyproxy.io/) — The underlying gateway infrastructure that Envoy AI Gateway extends. | ||
| - **Gateway API Inference Extension (GIE)**: [https://gateway-api-inference-extension.sigs.k8s.io/](https://gateway-api-inference-extension.sigs.k8s.io/) — Kubernetes SIG project for AI-aware routing integrated with Envoy AI Gateway. | ||
| - **KServe (Alauda Build)**: [../kserve/intro](../kserve/intro) — KServe uses Envoy AI Gateway as a required dependency for exposing and routing inference services. |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# Description: Check if the referenced kserve intro file exists and verify link format consistency
fd -t f "intro.mdx" docs/en/kserve/
# Check how other files in this repo reference cross-directory MDX files
rg -n '\]\(\.\./.*intro\)' docs/en/ --type mdx | head -10Repository: alauda/aml-docs
Length of output: 128
🏁 Script executed:
#!/bin/bash
# Find actual internal link patterns in the documentation to see if .mdx extension is typically included or omitted
rg '\]\(\.\./[^)]+\)' docs/en/ -A 1 | head -30
# Also check documentation index/nav files that might show link format conventions
find docs/en -name "*nav*" -o -name "*config*" -o -name "*sidebar*" -o -name "index.mdx" | head -10Repository: alauda/aml-docs
Length of output: 3854
Fix internal link format to match repository convention.
The link on line 33 ../kserve/intro should include the .mdx extension as ../kserve/intro.mdx — all other cross-directory links in the documentation consistently use this format (e.g., ../installation/ai-cluster.mdx, ../kserve/install.mdx).
Otherwise, the documentation is well-structured, clearly explains Envoy AI Gateway's purpose and capabilities, and provides good upstream context.
🧰 Tools
🪛 LanguageTool
[style] ~30-~30: Three successive sentences begin with the same word. Consider rewording the sentence or use a thesaurus to find a synonym.
Context: ... configuration, and API references. - Envoy AI Gateway GitHub: [https://github.co...
(ENGLISH_WORD_REPEAT_BEGINNING_RULE)
[style] ~31-~31: Three successive sentences begin with the same word. Consider rewording the sentence or use a thesaurus to find a synonym.
Context: ...ce code, release notes, and issues. - Envoy Gateway: [https://gateway.envoyproxy....
(ENGLISH_WORD_REPEAT_BEGINNING_RULE)
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@docs/en/envoy_ai_gateway/intro.mdx` around lines 1 - 33, The internal
cross-directory link at the bottom of docs/en/envoy_ai_gateway/intro.mdx uses
../kserve/intro without the .mdx extension; update that link to
../kserve/intro.mdx so it matches the repository convention used elsewhere
(e.g., ../installation/ai-cluster.mdx and ../kserve/install.mdx) by editing the
markdown link in the file (search for the anchor referencing KServe or the text
"KServe (Alauda Build)").
refactor install and upgrade resort menu fix preview path problem take advice
e7cf92c to
76217ba
Compare
refactor install and upgrade
resort menu
Summary by CodeRabbit