From c8718d2c5b1a4516b21e55d46cc8b508fa4d655d Mon Sep 17 00:00:00 2001 From: Vrushank Vyas Date: Tue, 15 Sep 2026 16:56:02 +0530 Subject: [PATCH] docs(aigw): repoint or unlink api-reference links that resolve to Latest Links under aigw/ that pointed at /api-reference/... were resolving against the Latest Portkey-branded version, so nothing flagged them as broken while a Prisma AIRS reader silently left the Prisma AIRS docs. Three classes, handled individually rather than by bulk prefix: - Targets that exist under aigw/ -- repointed (inference-api/headers, inference-api/config-object, inference-api/open-api-specification, integrations/libraries/microsoft-semantic-kernel). - Targets that will never exist -- /api-reference/sdk (no SDK reference is carried into aigw) and the Workspaces / Users / Log Exports Admin API groups (dropped from the spec). Cards removed, prose unlinked with the text kept. - Targets never carried into aigw -- gateway-for-other-apis, anthropic-transform, a Messages API reference. Unlinked, text kept. Also fixes open-api-specification.mdx, whose frontmatter still redirected to https://github.com/Portkey-AI/openapi instead of the PaloAltoNetworks repo. Roughly 90 links remain. Those all target generated operation pages and are blocked on x-mint.href being set upstream in the spec. Co-Authored-By: Claude Opus 5 --- aigw/api-reference/admin-api/introduction.mdx | 17 ++--------------- .../inference-api/agentic-usage.mdx | 6 ------ .../inference-api/open-api-specification.mdx | 2 +- aigw/changelog/data-service.mdx | 2 +- aigw/changelog/enterprise.mdx | 2 +- aigw/integrations/cloud/azure.mdx | 2 +- aigw/integrations/libraries.mdx | 2 +- aigw/integrations/libraries/vercel.mdx | 2 +- aigw/integrations/llms/aws-sagemaker.mdx | 4 ---- aigw/integrations/llms/azure-foundry.mdx | 4 ---- .../llms/azure-openai/azure-openai.mdx | 5 ----- aigw/integrations/llms/bedrock/aws-bedrock.mdx | 4 ---- aigw/integrations/llms/gemini.mdx | 4 ---- aigw/integrations/llms/oracle.mdx | 5 ----- aigw/integrations/llms/vertex-ai.mdx | 4 ---- .../tracing-providers/honeyhive.mdx | 1 - .../integrations/tracing-providers/langfuse.mdx | 1 - .../tracing-providers/langsmith.mdx | 1 - ...e-workspace-budget-limts-and-rate-limits.mdx | 6 ------ aigw/product/ai-gateway.mdx | 2 +- .../ai-gateway/cache-simple-and-semantic.mdx | 4 ++-- aigw/product/ai-gateway/messages-api.mdx | 9 +-------- aigw/product/ai-gateway/universal-api.mdx | 2 +- .../org-management/api-keys-authn-and-authz.mdx | 4 ++-- .../user-roles-and-permissions.mdx | 2 +- .../org-management/workspaces.mdx | 4 ---- aigw/product/observability/logs-export.mdx | 2 -- 27 files changed, 16 insertions(+), 87 deletions(-) diff --git a/aigw/api-reference/admin-api/introduction.mdx b/aigw/api-reference/admin-api/introduction.mdx index fffad83b1..5d489e27f 100644 --- a/aigw/api-reference/admin-api/introduction.mdx +++ b/aigw/api-reference/admin-api/introduction.mdx @@ -43,19 +43,6 @@ Once your resources are configured, you'll want to measure performance and usage -### User and Workspace Administration - -Beyond resources and analytics, you'll need to manage who has access to your AI Gateway environment: - - - - Manage user accounts, permissions, and access. Send and manage user invitations. - - - Create workspaces and manage team membership and permissions within workspaces. - - - ## Authentication Strategy Now that you understand what the Admin API can do, let's explore how to authenticate your requests. The AI Gateway uses a sophisticated access control system with two types of API keys, each designed for different use cases: @@ -199,8 +186,8 @@ Now that you understand the Admin API ecosystem, authentication, and permissions For developers looking to integrate with the Admin API, we provide a complete OpenAPI specification that you can use with your API development tools: - - Download the OpenAPI spec for the Admin API + + A single specification covers both the gateway and the Admin API ## Need Support? diff --git a/aigw/api-reference/inference-api/agentic-usage.mdx b/aigw/api-reference/inference-api/agentic-usage.mdx index f8d40ff06..73c5f5c95 100644 --- a/aigw/api-reference/inference-api/agentic-usage.mdx +++ b/aigw/api-reference/inference-api/agentic-usage.mdx @@ -178,12 +178,6 @@ The skill source is available at: [github.com/portkey-ai/skills](https://github. Contributions and feedback are welcome. - - Full Python SDK documentation - - - Full TypeScript SDK documentation - View the skills source on GitHub diff --git a/aigw/api-reference/inference-api/open-api-specification.mdx b/aigw/api-reference/inference-api/open-api-specification.mdx index fcb264bb2..e7321254a 100644 --- a/aigw/api-reference/inference-api/open-api-specification.mdx +++ b/aigw/api-reference/inference-api/open-api-specification.mdx @@ -1,4 +1,4 @@ --- title: "OpenAPI Specification" -url: "https://github.com/Portkey-AI/openapi" +url: "https://github.com/PaloAltoNetworks/openapi" --- diff --git a/aigw/changelog/data-service.mdx b/aigw/changelog/data-service.mdx index dbd924d80..c92c2de7e 100644 --- a/aigw/changelog/data-service.mdx +++ b/aigw/changelog/data-service.mdx @@ -291,7 +291,7 @@ rss: true --- ### Data exports -- Added support for [Data exports](/api-reference/admin-api/data-plane/logs/log-exports-beta/start-a-log-export) for hybrid deployments. +- Added support for Data exports for hybrid deployments. ### Fixes and Improvements - Fixed issue with custom batches for small batch files diff --git a/aigw/changelog/enterprise.mdx b/aigw/changelog/enterprise.mdx index 71bd986e1..5ee101b82 100644 --- a/aigw/changelog/enterprise.mdx +++ b/aigw/changelog/enterprise.mdx @@ -2662,7 +2662,7 @@ Added new condition keys for fine-grained budget and rate limit policies: ### Log Exports available on Data Plane - Log exports are now available on Data Plane -- Export logs without them being sent to Management Plane [Docs Link](/api-reference/admin-api/data-plane/logs/log-exports-beta) +- Export logs without them being sent to Management Plane - Please note that, `Dataservice` is required for log exports to work via Data Plane. ### Fixes And Improvements diff --git a/aigw/integrations/cloud/azure.mdx b/aigw/integrations/cloud/azure.mdx index 73a0aab0b..23d80a5a2 100644 --- a/aigw/integrations/cloud/azure.mdx +++ b/aigw/integrations/cloud/azure.mdx @@ -34,7 +34,7 @@ Bring any model deployed via Azure AI Studio (formerly AI Foundry) under the AI Apply robust, configurable content moderation and PII detection to every AI request—no code changes required in your applications. - + Developers can continue using familiar Microsoft tooling. The AI Gateway transparently adds value by handling routing, cost attribution, observability, and guardrails. diff --git a/aigw/integrations/libraries.mdx b/aigw/integrations/libraries.mdx index 58f5c0573..5b3438853 100644 --- a/aigw/integrations/libraries.mdx +++ b/aigw/integrations/libraries.mdx @@ -45,7 +45,7 @@ title: "Overview" - + diff --git a/aigw/integrations/libraries/vercel.mdx b/aigw/integrations/libraries/vercel.mdx index ddda28848..c0e64d732 100644 --- a/aigw/integrations/libraries/vercel.mdx +++ b/aigw/integrations/libraries/vercel.mdx @@ -410,7 +410,7 @@ const openai = createOpenAI({ - + ## Using AI Providers & Model Catalog diff --git a/aigw/integrations/llms/aws-sagemaker.mdx b/aigw/integrations/llms/aws-sagemaker.mdx index 54dac28c0..c3826b7a0 100644 --- a/aigw/integrations/llms/aws-sagemaker.mdx +++ b/aigw/integrations/llms/aws-sagemaker.mdx @@ -133,10 +133,6 @@ curl https://aigw.portkey.ai/v1/endpoints/{endpoint_name}/invocations \ - -Complete SDK documentation and API reference - - Add metadata to your Sagemaker requests diff --git a/aigw/integrations/llms/azure-foundry.mdx b/aigw/integrations/llms/azure-foundry.mdx index bbef8f6a0..007d5c942 100644 --- a/aigw/integrations/llms/azure-foundry.mdx +++ b/aigw/integrations/llms/azure-foundry.mdx @@ -607,10 +607,6 @@ The native `/v1/ocr` endpoint requires gateway version **2.18.0** or higher for - - Complete SDK documentation and API reference - - - - You'll find more information in the relevant sections: 1. [Add metadata to your requests](/aigw/product/observability/metadata) diff --git a/aigw/integrations/llms/bedrock/aws-bedrock.mdx b/aigw/integrations/llms/bedrock/aws-bedrock.mdx index 7c0c3cbc1..850c9e65c 100644 --- a/aigw/integrations/llms/bedrock/aws-bedrock.mdx +++ b/aigw/integrations/llms/bedrock/aws-bedrock.mdx @@ -581,10 +581,6 @@ Integration is identical to standard Bedrock. Only the endpoint changes — set ## Next Steps -The complete list of features supported in the SDK are available on the link below. - - - You'll find more information in the relevant sections: 1. [Add metadata to your requests](/aigw/product/observability/metadata) diff --git a/aigw/integrations/llms/gemini.mdx b/aigw/integrations/llms/gemini.mdx index 8b0e36e9b..b0535147c 100644 --- a/aigw/integrations/llms/gemini.mdx +++ b/aigw/integrations/llms/gemini.mdx @@ -1395,10 +1395,6 @@ You can edit generated images by continuing the conversation. Pass the image dat - -Complete SDK documentation and API reference - - Add metadata to your Gemini requests diff --git a/aigw/integrations/llms/oracle.mdx b/aigw/integrations/llms/oracle.mdx index 8dca3d2af..4de3e97fc 100644 --- a/aigw/integrations/llms/oracle.mdx +++ b/aigw/integrations/llms/oracle.mdx @@ -80,11 +80,6 @@ You can specify the API version using the `oracleApiVersion` parameter (defaults ## Next Steps -The complete list of features supported in the SDK are available on the link below. - - - - You'll find more information in the relevant sections: 1. [Add metadata to your requests](/aigw/product/observability/metadata) diff --git a/aigw/integrations/llms/vertex-ai.mdx b/aigw/integrations/llms/vertex-ai.mdx index 1c3d1bd06..8b45be2f2 100644 --- a/aigw/integrations/llms/vertex-ai.mdx +++ b/aigw/integrations/llms/vertex-ai.mdx @@ -2344,10 +2344,6 @@ environment: - -Complete SDK documentation and API reference - - Add metadata to your Vertex AI requests diff --git a/aigw/integrations/tracing-providers/honeyhive.mdx b/aigw/integrations/tracing-providers/honeyhive.mdx index fe05607a9..a3667d4d7 100644 --- a/aigw/integrations/tracing-providers/honeyhive.mdx +++ b/aigw/integrations/tracing-providers/honeyhive.mdx @@ -281,7 +281,6 @@ def call_openai(): - [HoneyHive Documentation](https://docs.honeyhive.ai) - [AI Gateway Guide](/aigw/product/ai-gateway) -- [AI Gateway Python SDK Reference](/api-reference/sdk) For enterprise support and custom features, contact our [enterprise team](https://www.paloaltonetworks.com/ai-security/ai-gateway#:~:text=See%20Prisma%20AIRS%20AI%20Gateway%20in%20Action diff --git a/aigw/integrations/tracing-providers/langfuse.mdx b/aigw/integrations/tracing-providers/langfuse.mdx index 6320b2373..67522f90b 100644 --- a/aigw/integrations/tracing-providers/langfuse.mdx +++ b/aigw/integrations/tracing-providers/langfuse.mdx @@ -226,7 +226,6 @@ client = OpenAI( - [Langfuse Documentation](https://langfuse.com/docs) - [AI Gateway Guide](/aigw/product/ai-gateway) -- [AI Gateway Python SDK Reference](/api-reference/sdk) For enterprise support and custom features, contact our [enterprise team](https://www.paloaltonetworks.com/ai-security/ai-gateway#:~:text=See%20Prisma%20AIRS%20AI%20Gateway%20in%20Action diff --git a/aigw/integrations/tracing-providers/langsmith.mdx b/aigw/integrations/tracing-providers/langsmith.mdx index dbbf5fdfa..d80f5b1a7 100644 --- a/aigw/integrations/tracing-providers/langsmith.mdx +++ b/aigw/integrations/tracing-providers/langsmith.mdx @@ -182,7 +182,6 @@ If you're already using LangSmith with OpenAI, migrating to use the AI Gateway i * [LangSmith Documentation](https://docs.smith.langchain.com/) * [AI Gateway Guide](/aigw/product/ai-gateway) -* [AI Gateway Python SDK Reference](/api-reference/sdk) For enterprise support and custom features, contact our [enterprise team](https://www.paloaltonetworks.com/ai-security/ai-gateway#:~:text=See%20Prisma%20AIRS%20AI%20Gateway%20in%20Action diff --git a/aigw/product/administration/enforce-workspace-budget-limts-and-rate-limits.mdx b/aigw/product/administration/enforce-workspace-budget-limts-and-rate-limits.mdx index abffff758..3c6c76811 100644 --- a/aigw/product/administration/enforce-workspace-budget-limts-and-rate-limits.mdx +++ b/aigw/product/administration/enforce-workspace-budget-limts-and-rate-limits.mdx @@ -113,12 +113,6 @@ Use the Admin API to programmatically manage workspace budgets and rate limits. - Rate limits support request- or token-based throttling with units `rpm` (per minute), `rph` (per hour), or `rpd` (per day). -Learn more here: - - -AI Gateway Workspace API documentation - - ## Availability Workspace Budget Limits are available to AI Gateway Enterprise customers and select Pro users. To enable these features for your account, please contact [support@portkey.ai](mailto:support@portkey.ai). diff --git a/aigw/product/ai-gateway.mdx b/aigw/product/ai-gateway.mdx index 72778db1f..e15d3e9bf 100644 --- a/aigw/product/ai-gateway.mdx +++ b/aigw/product/ai-gateway.mdx @@ -68,7 +68,7 @@ description: The world's fastest AI Gateway with advanced routing & integrated G Route requests to privately hosted or local models using custom host URLs - + Call rerank, video, listen, and other provider paths through https://aigw.portkey.ai/v1/... with the same configs and logging as unified routes diff --git a/aigw/product/ai-gateway/cache-simple-and-semantic.mdx b/aigw/product/ai-gateway/cache-simple-and-semantic.mdx index 1889c3e03..917bccac7 100644 --- a/aigw/product/ai-gateway/cache-simple-and-semantic.mdx +++ b/aigw/product/ai-gateway/cache-simple-and-semantic.mdx @@ -21,7 +21,7 @@ Cache LLM responses to serve requests up to **20x faster** and cheaper. ## Enable Cache -Add `cache` to your [config object](/api-reference/config-object#cache-object-details): +Add `cache` to your [config object](/aigw/api-reference/inference-api/config-object#cache-object-details): @@ -162,7 +162,7 @@ To enable semantic caching on a self-hosted AI Gateway, configure the embedding - Set the cache mode to `semantic` in your [config object](/api-reference/config-object#cache-object-details) for each LLM request: + Set the cache mode to `semantic` in your [config object](/aigw/api-reference/inference-api/config-object#cache-object-details) for each LLM request: ```json { "cache": { "mode": "semantic" } } diff --git a/aigw/product/ai-gateway/messages-api.mdx b/aigw/product/ai-gateway/messages-api.mdx index f671cb344..7766f7133 100644 --- a/aigw/product/ai-gateway/messages-api.mdx +++ b/aigw/product/ai-gateway/messages-api.mdx @@ -849,7 +849,7 @@ curl https://aigw.portkey.ai/v1/messages \ ## API Reference -- [Messages](/api-reference/inference-api/anthropic-transform) — `POST /v1/messages` +- Messages — `POST /v1/messages` Anthropic specification - - AI Gateway Messages API reference - - + diff --git a/aigw/product/enterprise-offering/org-management/user-roles-and-permissions.mdx b/aigw/product/enterprise-offering/org-management/user-roles-and-permissions.mdx index bacf946f7..e147704d7 100644 --- a/aigw/product/enterprise-offering/org-management/user-roles-and-permissions.mdx +++ b/aigw/product/enterprise-offering/org-management/user-roles-and-permissions.mdx @@ -98,6 +98,6 @@ Organisation Owners and Admins can configure access permissions for various reso ## Related Topics - + diff --git a/aigw/product/enterprise-offering/org-management/workspaces.mdx b/aigw/product/enterprise-offering/org-management/workspaces.mdx index 9e85869fe..7b7bbe513 100644 --- a/aigw/product/enterprise-offering/org-management/workspaces.mdx +++ b/aigw/product/enterprise-offering/org-management/workspaces.mdx @@ -65,10 +65,6 @@ Once all resources have been removed, enter the workspace name in the confirmati Workspace deletion is permanent and cannot be undone -Alternatively you can also delete workspaces using the Admin API: - - - ### Related Topics diff --git a/aigw/product/observability/logs-export.mdx b/aigw/product/observability/logs-export.mdx index ef857e8ef..c961adb41 100644 --- a/aigw/product/observability/logs-export.mdx +++ b/aigw/product/observability/logs-export.mdx @@ -288,8 +288,6 @@ Here's a complete script that creates, starts, monitors, and downloads a log exp ### API reference -For detailed API specifications, see the [Log Exports API reference](/api-reference/admin-api/data-plane/logs/log-exports-beta/create-a-log-export). - | Endpoint | Description | |----------|-------------| | `POST /v1/logs/exports` | Create a new export job |