From 2c282c34764f87d7dc00d3bdf6a80064f5191742 Mon Sep 17 00:00:00 2001 From: veejask-41 Date: Tue, 11 Aug 2026 18:11:01 +0530 Subject: [PATCH 1/3] Restructure next into a job-oriented nav, moving 56 pages with redirects and repointed links --- en/docs/ai-gateway/next/README.md | 4 +- .../configure-aws-bedrock-provider.md | 6 +- .../llm-templates.md | 6 +- .../secure-the-management-api.md} | 6 +- .../aws-bedrock-guardrail.md | 6 +- .../azure-content-safety.md | 6 +- .../content-length.md | 6 +- .../execution-order.md | 12 +- .../json-schema.md | 6 +- .../overview.md | 8 +- .../pii-masking-regex.md | 6 +- .../prompt-decorator.md | 6 +- .../prompt-template.md | 6 +- .../guardrails => control-content}/regex.md | 6 +- .../semantic-prompt-guard.md | 6 +- .../sentence-count.md | 6 +- .../guardrails => control-content}/url.md | 6 +- .../word-count.md | 6 +- .../model-round-robin.md | 8 +- .../model-weighted-round-robin.md | 8 +- .../semantic-caching.md | 6 +- .../timeouts.md | 6 +- .../multi-provider-routing.md | 14 +- .../{ => expose-llms}/streaming-responses.md | 12 +- ...-start-guide.md => create-an-mcp-proxy.md} | 23 +- .../mcp-proxy/{policies => }/mcp-acl-list.md | 6 +- .../{policies => }/mcp-authentication.md | 6 +- .../{policies => }/mcp-authorization.md | 6 +- .../mcp-proxy/{policies => }/mcp-rewrite.md | 6 +- .../analytics-header-filter.md | 6 +- .../logging.md | 6 +- .../moesif-analytics.md | 6 +- .../tracing.md | 6 +- en/docs/ai-gateway/next/overview.md | 20 +- en/docs/ai-gateway/next/quick-start-guide.md | 12 +- .../management-api}/certificate-management.md | 6 +- .../llm-provider-management.md | 6 +- .../llm-provider-template-management.md | 6 +- .../management-api}/llm-proxy-management.md | 6 +- .../management-api}/mcp-proxy-management.md | 6 +- .../management-api}/overview.md | 20 +- .../management-api}/schemas.md | 6 +- .../management-api}/secrets-management.md | 6 +- .../configuration.md | 8 +- .../database-setup.md | 6 +- .../immutable-gateway.md | 10 +- .../kubernetes/gateway-operator.md | 6 +- .../kubernetes/kubernetes-standalone.md | 6 +- .../kubernetes/overview.md | 6 +- .../ai-workload-tuning.md | 14 +- .../control-plane-connection.md | 6 +- .../database-configuration.md | 8 +- .../deploy-and-verify.md | 8 +- .../production-deployment/overview.md | 8 +- .../resources-and-scaling.md | 8 +- .../security-hardening.md | 6 +- .../ai-gateway-runtime-with-four-cpus.md | 16 +- .../ai-gateway-runtime-with-two-cpus.md | 16 +- .../sizing-and-performance}/overview.md | 8 +- .../ai-workspace/1.0.0/policies/overview.md | 2 +- .../ai-workspace/next/policies/overview.md | 2 +- .../next/sync-gateway-created-artifacts.md | 2 +- en/docs/llms.txt | 74 +++--- en/docs/next/index.md | 4 +- en/mkdocs.yml | 218 ++++++++++++------ 65 files changed, 416 insertions(+), 359 deletions(-) rename en/docs/ai-gateway/next/{llm-proxy => connect-llm-providers}/configure-aws-bedrock-provider.md (98%) rename en/docs/ai-gateway/next/{llm-proxy => connect-llm-providers}/llm-templates.md (98%) rename en/docs/ai-gateway/next/{gateway-controller-management-api/authentication.md => control-access/secure-the-management-api.md} (94%) rename en/docs/ai-gateway/next/{llm-proxy/guardrails => control-content}/aws-bedrock-guardrail.md (98%) rename en/docs/ai-gateway/next/{llm-proxy/guardrails => control-content}/azure-content-safety.md (98%) rename en/docs/ai-gateway/next/{llm-proxy/guardrails => control-content}/content-length.md (97%) rename en/docs/ai-gateway/next/{llm-proxy/guardrails => control-content}/execution-order.md (86%) rename en/docs/ai-gateway/next/{llm-proxy/guardrails => control-content}/json-schema.md (97%) rename en/docs/ai-gateway/next/{llm-proxy/guardrails => control-content}/overview.md (88%) rename en/docs/ai-gateway/next/{llm-proxy/guardrails => control-content}/pii-masking-regex.md (97%) rename en/docs/ai-gateway/next/{llm-proxy/prompt-management => control-content}/prompt-decorator.md (97%) rename en/docs/ai-gateway/next/{llm-proxy/prompt-management => control-content}/prompt-template.md (97%) rename en/docs/ai-gateway/next/{llm-proxy/guardrails => control-content}/regex.md (97%) rename en/docs/ai-gateway/next/{llm-proxy/guardrails => control-content}/semantic-prompt-guard.md (98%) rename en/docs/ai-gateway/next/{llm-proxy/guardrails => control-content}/sentence-count.md (97%) rename en/docs/ai-gateway/next/{llm-proxy/guardrails => control-content}/url.md (97%) rename en/docs/ai-gateway/next/{llm-proxy/guardrails => control-content}/word-count.md (97%) rename en/docs/ai-gateway/next/{llm-proxy/load-balancing => control-cost-and-traffic}/model-round-robin.md (96%) rename en/docs/ai-gateway/next/{llm-proxy/load-balancing => control-cost-and-traffic}/model-weighted-round-robin.md (96%) rename en/docs/ai-gateway/next/{llm-proxy => control-cost-and-traffic}/semantic-caching.md (98%) rename en/docs/ai-gateway/next/{resiliency => control-cost-and-traffic}/timeouts.md (98%) rename en/docs/ai-gateway/next/{llm-proxy => expose-llms}/multi-provider-routing.md (98%) rename en/docs/ai-gateway/next/{ => expose-llms}/streaming-responses.md (91%) rename en/docs/ai-gateway/next/mcp-proxy/{quick-start-guide.md => create-an-mcp-proxy.md} (90%) rename en/docs/ai-gateway/next/mcp-proxy/{policies => }/mcp-acl-list.md (98%) rename en/docs/ai-gateway/next/mcp-proxy/{policies => }/mcp-authentication.md (98%) rename en/docs/ai-gateway/next/mcp-proxy/{policies => }/mcp-authorization.md (99%) rename en/docs/ai-gateway/next/mcp-proxy/{policies => }/mcp-rewrite.md (98%) rename en/docs/ai-gateway/next/{analytics => monitor-traffic}/analytics-header-filter.md (96%) rename en/docs/ai-gateway/next/{observability => monitor-traffic}/logging.md (98%) rename en/docs/ai-gateway/next/{analytics => monitor-traffic}/moesif-analytics.md (97%) rename en/docs/ai-gateway/next/{observability => monitor-traffic}/tracing.md (99%) rename en/docs/ai-gateway/next/{gateway-controller-management-api => reference/management-api}/certificate-management.md (96%) rename en/docs/ai-gateway/next/{gateway-controller-management-api => reference/management-api}/llm-provider-management.md (99%) rename en/docs/ai-gateway/next/{gateway-controller-management-api => reference/management-api}/llm-provider-template-management.md (98%) rename en/docs/ai-gateway/next/{gateway-controller-management-api => reference/management-api}/llm-proxy-management.md (99%) rename en/docs/ai-gateway/next/{gateway-controller-management-api => reference/management-api}/mcp-proxy-management.md (98%) rename en/docs/ai-gateway/next/{gateway-controller-management-api => reference/management-api}/overview.md (84%) rename en/docs/ai-gateway/next/{gateway-controller-management-api => reference/management-api}/schemas.md (99%) rename en/docs/ai-gateway/next/{gateway-controller-management-api => reference/management-api}/secrets-management.md (97%) rename en/docs/ai-gateway/next/{setup => run-the-gateway}/configuration.md (96%) rename en/docs/ai-gateway/next/{setup => run-the-gateway}/database-setup.md (98%) rename en/docs/ai-gateway/next/{deployment/deployment-modes => run-the-gateway}/immutable-gateway.md (93%) rename en/docs/ai-gateway/next/{deployment/deployment-modes => run-the-gateway}/kubernetes/gateway-operator.md (98%) rename en/docs/ai-gateway/next/{deployment/deployment-modes => run-the-gateway}/kubernetes/kubernetes-standalone.md (96%) rename en/docs/ai-gateway/next/{deployment/deployment-modes => run-the-gateway}/kubernetes/overview.md (94%) rename en/docs/ai-gateway/next/{deployment => run-the-gateway}/production-deployment/ai-workload-tuning.md (86%) rename en/docs/ai-gateway/next/{deployment => run-the-gateway}/production-deployment/control-plane-connection.md (96%) rename en/docs/ai-gateway/next/{deployment => run-the-gateway}/production-deployment/database-configuration.md (94%) rename en/docs/ai-gateway/next/{deployment => run-the-gateway}/production-deployment/deploy-and-verify.md (96%) rename en/docs/ai-gateway/next/{deployment => run-the-gateway}/production-deployment/overview.md (96%) rename en/docs/ai-gateway/next/{deployment => run-the-gateway}/production-deployment/resources-and-scaling.md (94%) rename en/docs/ai-gateway/next/{deployment => run-the-gateway}/production-deployment/security-hardening.md (97%) rename en/docs/ai-gateway/next/{performance => run-the-gateway/sizing-and-performance}/ai-gateway-runtime-with-four-cpus.md (81%) rename en/docs/ai-gateway/next/{performance => run-the-gateway/sizing-and-performance}/ai-gateway-runtime-with-two-cpus.md (80%) rename en/docs/ai-gateway/next/{performance => run-the-gateway/sizing-and-performance}/overview.md (92%) diff --git a/en/docs/ai-gateway/next/README.md b/en/docs/ai-gateway/next/README.md index bc1a1e06d..6d9340df1 100644 --- a/en/docs/ai-gateway/next/README.md +++ b/en/docs/ai-gateway/next/README.md @@ -19,7 +19,7 @@ A gateway for managing and securing AI traffic, including Large Language Model ( ## Quick Start - [LLM Quick Start Guide](quick-start-guide.md) — Set up the gateway and route traffic to LLM providers like OpenAI -- [MCP Quick Start Guide](mcp-proxy/quick-start-guide.md) — Set up the gateway and route traffic to MCP servers +- [MCP Quick Start Guide](mcp-proxy/create-an-mcp-proxy.md) — Set up the gateway and route traffic to MCP servers ## Key Concepts @@ -49,7 +49,7 @@ An LLM Provider represents a connection to an AI backend service such as OpenAI, Once configured, the LLM Provider allows traffic to flow through the gateway to the AI backend. -To connect the gateway to AWS Bedrock, see [Configure an AWS Bedrock LLM Provider](llm-proxy/configure-aws-bedrock-provider.md). The guide covers both Bedrock bearer API keys and AWS Signature Version 4 (SigV4) authentication. +To connect the gateway to AWS Bedrock, see [Configure an AWS Bedrock LLM Provider](connect-llm-providers/configure-aws-bedrock-provider.md). The guide covers both Bedrock bearer API keys and AWS Signature Version 4 (SigV4) authentication. ### LLM Proxy diff --git a/en/docs/ai-gateway/next/llm-proxy/configure-aws-bedrock-provider.md b/en/docs/ai-gateway/next/connect-llm-providers/configure-aws-bedrock-provider.md similarity index 98% rename from en/docs/ai-gateway/next/llm-proxy/configure-aws-bedrock-provider.md rename to en/docs/ai-gateway/next/connect-llm-providers/configure-aws-bedrock-provider.md index 109a39f7a..7a65fa908 100644 --- a/en/docs/ai-gateway/next/llm-proxy/configure-aws-bedrock-provider.md +++ b/en/docs/ai-gateway/next/connect-llm-providers/configure-aws-bedrock-provider.md @@ -1,15 +1,15 @@ --- title: "Configure an AWS Bedrock Large Language Model provider" description: "Connect API Platform AI Gateway to AWS Bedrock using a bearer API key or AWS Signature Version 4 authentication, then invoke a model through the gateway." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/configure-aws-bedrock-provider/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/configure-aws-bedrock-provider.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/connect-llm-providers/configure-aws-bedrock-provider/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/connect-llm-providers/configure-aws-bedrock-provider.md tags: - ai-gateway - llm - aws-bedrock - authentication author: WSO2 API Platform Documentation Team -last_updated: 2026-08-04 +last_updated: 2026-08-11 content_type: "guide" --- diff --git a/en/docs/ai-gateway/next/llm-proxy/llm-templates.md b/en/docs/ai-gateway/next/connect-llm-providers/llm-templates.md similarity index 98% rename from en/docs/ai-gateway/next/llm-proxy/llm-templates.md rename to en/docs/ai-gateway/next/connect-llm-providers/llm-templates.md index 2177d7a88..2e7f01f4b 100644 --- a/en/docs/ai-gateway/next/llm-proxy/llm-templates.md +++ b/en/docs/ai-gateway/next/connect-llm-providers/llm-templates.md @@ -1,14 +1,14 @@ --- title: "LLM Provider Templates" description: "Reference for LLM Provider Templates in API Platform AI Gateway, covering built-in templates for OpenAI, Anthropic, Gemini, and more." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/llm-templates/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/llm-templates.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/connect-llm-providers/llm-templates/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/connect-llm-providers/llm-templates.md tags: - ai-gateway - llm - reference author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/gateway-controller-management-api/authentication.md b/en/docs/ai-gateway/next/control-access/secure-the-management-api.md similarity index 94% rename from en/docs/ai-gateway/next/gateway-controller-management-api/authentication.md rename to en/docs/ai-gateway/next/control-access/secure-the-management-api.md index 46c49c5ae..6c597bc9d 100644 --- a/en/docs/ai-gateway/next/gateway-controller-management-api/authentication.md +++ b/en/docs/ai-gateway/next/control-access/secure-the-management-api.md @@ -1,14 +1,14 @@ --- title: "Secure the management API" description: "Configure Basic Auth or JWT/IDP authentication and role-based authorization for the AI Gateway Controller REST API." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/gateway-controller-management-api/authentication/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/gateway-controller-management-api/authentication.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/control-access/secure-the-management-api/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/control-access/secure-the-management-api.md tags: - ai-gateway - security - authentication author: WSO2 API Platform Documentation Team -last_updated: 2026-08-10 +last_updated: 2026-08-11 content_type: "how-to" --- diff --git a/en/docs/ai-gateway/next/llm-proxy/guardrails/aws-bedrock-guardrail.md b/en/docs/ai-gateway/next/control-content/aws-bedrock-guardrail.md similarity index 98% rename from en/docs/ai-gateway/next/llm-proxy/guardrails/aws-bedrock-guardrail.md rename to en/docs/ai-gateway/next/control-content/aws-bedrock-guardrail.md index 12f1e458d..bb44d68c5 100644 --- a/en/docs/ai-gateway/next/llm-proxy/guardrails/aws-bedrock-guardrail.md +++ b/en/docs/ai-gateway/next/control-content/aws-bedrock-guardrail.md @@ -1,14 +1,14 @@ --- title: "AWS Bedrock Guardrail" description: "Validate LLM request and response content against AWS Bedrock Guardrails for content filtering, topic detection, and PII masking." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/aws-bedrock-guardrail/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/aws-bedrock-guardrail.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/aws-bedrock-guardrail/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/aws-bedrock-guardrail.md tags: - ai-gateway - guardrails - aws author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/llm-proxy/guardrails/azure-content-safety.md b/en/docs/ai-gateway/next/control-content/azure-content-safety.md similarity index 98% rename from en/docs/ai-gateway/next/llm-proxy/guardrails/azure-content-safety.md rename to en/docs/ai-gateway/next/control-content/azure-content-safety.md index 2982b0c36..afcad2f8a 100644 --- a/en/docs/ai-gateway/next/llm-proxy/guardrails/azure-content-safety.md +++ b/en/docs/ai-gateway/next/control-content/azure-content-safety.md @@ -1,14 +1,14 @@ --- title: "Azure Content Safety" description: "Validate LLM request and response content against Azure Content Safety API, detecting hate speech, sexual content, and violence." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/azure-content-safety/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/azure-content-safety.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/azure-content-safety/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/azure-content-safety.md tags: - ai-gateway - guardrails - azure author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/llm-proxy/guardrails/content-length.md b/en/docs/ai-gateway/next/control-content/content-length.md similarity index 97% rename from en/docs/ai-gateway/next/llm-proxy/guardrails/content-length.md rename to en/docs/ai-gateway/next/control-content/content-length.md index 75d75f0cf..91848f58b 100644 --- a/en/docs/ai-gateway/next/llm-proxy/guardrails/content-length.md +++ b/en/docs/ai-gateway/next/control-content/content-length.md @@ -1,14 +1,14 @@ --- title: "Content Length Guardrail" description: "Enforce minimum and maximum byte length limits on LLM request and response payloads using the Content Length guardrail." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/content-length/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/content-length.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/content-length/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/content-length.md tags: - ai-gateway - guardrails - policies author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/llm-proxy/guardrails/execution-order.md b/en/docs/ai-gateway/next/control-content/execution-order.md similarity index 86% rename from en/docs/ai-gateway/next/llm-proxy/guardrails/execution-order.md rename to en/docs/ai-gateway/next/control-content/execution-order.md index 4698a15b1..6cb890bee 100644 --- a/en/docs/ai-gateway/next/llm-proxy/guardrails/execution-order.md +++ b/en/docs/ai-gateway/next/control-content/execution-order.md @@ -1,8 +1,8 @@ --- title: "Guardrail execution order" description: "How guardrails execute across phases in the AI Gateway dual-hop model: the LLM Proxy chain runs before the LLM Provider chain on request, and in reverse on response." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/execution-order/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/execution-order.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/execution-order/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/execution-order.md tags: - ai-gateway - guardrails @@ -18,7 +18,7 @@ content_type: "concept" The AI Gateway routes every request through two policy chains in sequence: the **LLM Proxy chain** and the **LLM Provider chain**. Each chain runs the same four execution phases, but the order in which the two chains execute differs between the request and response paths. -This document covers the dual-hop execution model. For foundational concepts — within-chain policy ordering, streaming mode, and short-circuit behavior — see [Policy execution order](../../../../../api-gateway/next/policies/policy-execution-order.md). The same rules apply to each chain individually. +This document covers the dual-hop execution model. For foundational concepts — within-chain policy ordering, streaming mode, and short-circuit behavior — see [Policy execution order](../../../api-gateway/next/policies/policy-execution-order.md). The same rules apply to each chain individually. ## The two chains @@ -80,7 +80,7 @@ Client The following diagram shows how requests pass through the LLM Proxy chain and LLM Provider chain in sequence, and how responses return through both chains in reverse order: -![Dual-hop guardrail execution diagram showing request flowing through LLM Proxy chain then LLM Provider chain in forward order across request phases, and response flowing in reverse order through LLM Provider chain then LLM Proxy chain back to the client](../../../../assets/img/api-gateway/gateway-policy-execution-order-llm-provider-proxy.png) +![Dual-hop guardrail execution diagram showing request flowing through LLM Proxy chain then LLM Provider chain in forward order across request phases, and response flowing in reverse order through LLM Provider chain then LLM Proxy chain back to the client](../../../assets/img/api-gateway/gateway-policy-execution-order-llm-provider-proxy.png) This mirrors the request wrapping at the chain level: the LLM Proxy wraps the LLM Provider on the way in, so on the way back the inner chain (Provider) unwinds first, then the outer chain (Proxy). @@ -99,10 +99,10 @@ When an LLM returns a streaming response (such as SSE from a chat completion end The following diagram shows how streaming body chunks flow through the policy chain at each hop: -![Streaming policy chain execution order diagram showing request body chunks flowing through the policy chain via OnRequestBodyChunk in forward order, and response chunks flowing in reverse order via OnResponseBodyChunk](../../../../assets/img/api-gateway/gateway-policy-execution-order-streaming.png) +![Streaming policy chain execution order diagram showing request body chunks flowing through the policy chain via OnRequestBodyChunk in forward order, and response chunks flowing in reverse order via OnResponseBodyChunk](../../../assets/img/api-gateway/gateway-policy-execution-order-streaming.png) ## Related topics - [Guardrails overview](overview.md) -- [Policy execution order](../../../../../api-gateway/next/policies/policy-execution-order.md) — within-chain ordering, streaming, and short-circuit rules that apply to each chain individually +- [Policy execution order](../../../api-gateway/next/policies/policy-execution-order.md) — within-chain ordering, streaming, and short-circuit rules that apply to each chain individually diff --git a/en/docs/ai-gateway/next/llm-proxy/guardrails/json-schema.md b/en/docs/ai-gateway/next/control-content/json-schema.md similarity index 97% rename from en/docs/ai-gateway/next/llm-proxy/guardrails/json-schema.md rename to en/docs/ai-gateway/next/control-content/json-schema.md index 6a3a7b41e..2aafc3a42 100644 --- a/en/docs/ai-gateway/next/llm-proxy/guardrails/json-schema.md +++ b/en/docs/ai-gateway/next/control-content/json-schema.md @@ -1,14 +1,14 @@ --- title: "JSON Schema Guardrail" description: "Validate LLM request and response body content against a JSON Schema definition to enforce structured data formats." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/json-schema/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/json-schema.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/json-schema/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/json-schema.md tags: - ai-gateway - guardrails - policies author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/llm-proxy/guardrails/overview.md b/en/docs/ai-gateway/next/control-content/overview.md similarity index 88% rename from en/docs/ai-gateway/next/llm-proxy/guardrails/overview.md rename to en/docs/ai-gateway/next/control-content/overview.md index c28259c64..a71e33737 100644 --- a/en/docs/ai-gateway/next/llm-proxy/guardrails/overview.md +++ b/en/docs/ai-gateway/next/control-content/overview.md @@ -1,14 +1,14 @@ --- title: "Guardrails overview" description: "Overview of AI Gateway guardrails: LLM-aware policies for content filtering, safety, and compliance that run in the LLM Proxy request and response pipeline." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/overview/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/overview.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/overview/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/overview.md tags: - ai-gateway - guardrails - llm-proxy author: WSO2 API Platform Documentation Team -last_updated: 2026-08-10 +last_updated: 2026-08-11 content_type: "concept" --- @@ -16,7 +16,7 @@ content_type: "concept" Guardrails are policies that run in the LLM Proxy's request and response pipeline to validate, filter, or transform content before it reaches an LLM or is returned to the client. -Guardrails use the same underlying policy engine as [API Gateway policies](../../../../../api-gateway/next/policies/overview.md). Each guardrail declares which execution phases it participates in, and the engine calls the appropriate hook for each phase. +Guardrails use the same underlying policy engine as [API Gateway policies](../../../api-gateway/next/policies/overview.md). Each guardrail declares which execution phases it participates in, and the engine calls the appropriate hook for each phase. ## What guardrails do diff --git a/en/docs/ai-gateway/next/llm-proxy/guardrails/pii-masking-regex.md b/en/docs/ai-gateway/next/control-content/pii-masking-regex.md similarity index 97% rename from en/docs/ai-gateway/next/llm-proxy/guardrails/pii-masking-regex.md rename to en/docs/ai-gateway/next/control-content/pii-masking-regex.md index b6144a164..73ecb019c 100644 --- a/en/docs/ai-gateway/next/llm-proxy/guardrails/pii-masking-regex.md +++ b/en/docs/ai-gateway/next/control-content/pii-masking-regex.md @@ -1,14 +1,14 @@ --- title: "PII Masking Regex Guardrail" description: "Mask or redact personally identifiable information from LLM request and response bodies using configurable regex patterns." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/pii-masking-regex/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/pii-masking-regex.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/pii-masking-regex/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/pii-masking-regex.md tags: - ai-gateway - guardrails - security author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/llm-proxy/prompt-management/prompt-decorator.md b/en/docs/ai-gateway/next/control-content/prompt-decorator.md similarity index 97% rename from en/docs/ai-gateway/next/llm-proxy/prompt-management/prompt-decorator.md rename to en/docs/ai-gateway/next/control-content/prompt-decorator.md index 344f8ca69..dadd6b6e9 100644 --- a/en/docs/ai-gateway/next/llm-proxy/prompt-management/prompt-decorator.md +++ b/en/docs/ai-gateway/next/control-content/prompt-decorator.md @@ -1,14 +1,14 @@ --- title: "Prompt Decorator" description: "Prepend or append custom content to LLM prompts, injecting system messages or standard instructions before requests reach the model." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/prompt-management/prompt-decorator/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/prompt-management/prompt-decorator.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/prompt-decorator/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/prompt-decorator.md tags: - ai-gateway - llm - prompt-management author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/llm-proxy/prompt-management/prompt-template.md b/en/docs/ai-gateway/next/control-content/prompt-template.md similarity index 97% rename from en/docs/ai-gateway/next/llm-proxy/prompt-management/prompt-template.md rename to en/docs/ai-gateway/next/control-content/prompt-template.md index f9df7da7a..5ca35d033 100644 --- a/en/docs/ai-gateway/next/llm-proxy/prompt-management/prompt-template.md +++ b/en/docs/ai-gateway/next/control-content/prompt-template.md @@ -1,14 +1,14 @@ --- title: "Prompt Template" description: "Replace 'template://' URI patterns in LLM request payloads with predefined, parameterized prompt templates." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/prompt-management/prompt-template/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/prompt-management/prompt-template.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/prompt-template/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/prompt-template.md tags: - ai-gateway - llm - prompt-management author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/llm-proxy/guardrails/regex.md b/en/docs/ai-gateway/next/control-content/regex.md similarity index 97% rename from en/docs/ai-gateway/next/llm-proxy/guardrails/regex.md rename to en/docs/ai-gateway/next/control-content/regex.md index f7f682dc6..cb9cdde85 100644 --- a/en/docs/ai-gateway/next/llm-proxy/guardrails/regex.md +++ b/en/docs/ai-gateway/next/control-content/regex.md @@ -1,14 +1,14 @@ --- title: "Regex Guardrail" description: "Validate LLM request and response content against regular expression patterns to enforce formats or detect prohibited content." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/regex/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/regex.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/regex/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/regex.md tags: - ai-gateway - guardrails - policies author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/llm-proxy/guardrails/semantic-prompt-guard.md b/en/docs/ai-gateway/next/control-content/semantic-prompt-guard.md similarity index 98% rename from en/docs/ai-gateway/next/llm-proxy/guardrails/semantic-prompt-guard.md rename to en/docs/ai-gateway/next/control-content/semantic-prompt-guard.md index 6b63d7daf..ef2b36352 100644 --- a/en/docs/ai-gateway/next/llm-proxy/guardrails/semantic-prompt-guard.md +++ b/en/docs/ai-gateway/next/control-content/semantic-prompt-guard.md @@ -1,14 +1,14 @@ --- title: "Semantic Prompt Guardrail" description: "Block semantically similar prompts using embedding-based similarity matching against configured allow and deny phrase lists." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/semantic-prompt-guard/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/semantic-prompt-guard.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/semantic-prompt-guard/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/semantic-prompt-guard.md tags: - ai-gateway - guardrails - llm author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/llm-proxy/guardrails/sentence-count.md b/en/docs/ai-gateway/next/control-content/sentence-count.md similarity index 97% rename from en/docs/ai-gateway/next/llm-proxy/guardrails/sentence-count.md rename to en/docs/ai-gateway/next/control-content/sentence-count.md index c534aab5a..f5e3d68f1 100644 --- a/en/docs/ai-gateway/next/llm-proxy/guardrails/sentence-count.md +++ b/en/docs/ai-gateway/next/control-content/sentence-count.md @@ -1,14 +1,14 @@ --- title: "Sentence Count Guardrail" description: "Enforce minimum and maximum sentence count limits on LLM request and response content using the Sentence Count guardrail." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/sentence-count/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/sentence-count.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/sentence-count/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/sentence-count.md tags: - ai-gateway - guardrails - policies author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/llm-proxy/guardrails/url.md b/en/docs/ai-gateway/next/control-content/url.md similarity index 97% rename from en/docs/ai-gateway/next/llm-proxy/guardrails/url.md rename to en/docs/ai-gateway/next/control-content/url.md index a9b000e7a..c1e97f46f 100644 --- a/en/docs/ai-gateway/next/llm-proxy/guardrails/url.md +++ b/en/docs/ai-gateway/next/control-content/url.md @@ -1,14 +1,14 @@ --- title: "URL Guardrail" description: "Validate URLs found in LLM request and response content by checking reachability through DNS resolution or HTTP HEAD requests." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/url/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/url.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/url/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/url.md tags: - ai-gateway - guardrails - policies author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/llm-proxy/guardrails/word-count.md b/en/docs/ai-gateway/next/control-content/word-count.md similarity index 97% rename from en/docs/ai-gateway/next/llm-proxy/guardrails/word-count.md rename to en/docs/ai-gateway/next/control-content/word-count.md index ee9070463..fa1f75128 100644 --- a/en/docs/ai-gateway/next/llm-proxy/guardrails/word-count.md +++ b/en/docs/ai-gateway/next/control-content/word-count.md @@ -1,14 +1,14 @@ --- title: "Word Count Guardrail" description: "Enforce minimum and maximum word count limits on LLM request and response content using the Word Count guardrail." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/word-count/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/word-count.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/word-count/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/control-content/word-count.md tags: - ai-gateway - guardrails - policies author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/llm-proxy/load-balancing/model-round-robin.md b/en/docs/ai-gateway/next/control-cost-and-traffic/model-round-robin.md similarity index 96% rename from en/docs/ai-gateway/next/llm-proxy/load-balancing/model-round-robin.md rename to en/docs/ai-gateway/next/control-cost-and-traffic/model-round-robin.md index a3d55ed6d..9d01743d7 100644 --- a/en/docs/ai-gateway/next/llm-proxy/load-balancing/model-round-robin.md +++ b/en/docs/ai-gateway/next/control-cost-and-traffic/model-round-robin.md @@ -1,14 +1,14 @@ --- title: "Model Round Robin" description: "Distribute LLM requests evenly across multiple AI models in a cyclic round-robin pattern with automatic failure suspension." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/load-balancing/model-round-robin/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/load-balancing/model-round-robin.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/control-cost-and-traffic/model-round-robin/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/control-cost-and-traffic/model-round-robin.md tags: - ai-gateway - llm - load-balancing author: WSO2 API Platform Documentation Team -last_updated: 2026-07-30 +last_updated: 2026-08-11 content_type: "reference" --- @@ -85,7 +85,7 @@ operationPolicies: suspendDuration: 60 ``` -The entry without `provider` uses the proxy's primary provider. The other entries route to providers declared under `spec.additionalProviders`. See [Multi-Provider Routing for LLM Proxies](../multi-provider-routing.md) for provider, authentication, transformer, and alias configuration. +The entry without `provider` uses the proxy's primary provider. The other entries route to providers declared under `spec.additionalProviders`. See [Multi-Provider Routing for LLM Proxies](../expose-llms/multi-provider-routing.md) for provider, authentication, transformer, and alias configuration. ### Example 1: Basic Round Robin with Payload-based Model diff --git a/en/docs/ai-gateway/next/llm-proxy/load-balancing/model-weighted-round-robin.md b/en/docs/ai-gateway/next/control-cost-and-traffic/model-weighted-round-robin.md similarity index 96% rename from en/docs/ai-gateway/next/llm-proxy/load-balancing/model-weighted-round-robin.md rename to en/docs/ai-gateway/next/control-cost-and-traffic/model-weighted-round-robin.md index 39b6f391c..be6963a3b 100644 --- a/en/docs/ai-gateway/next/llm-proxy/load-balancing/model-weighted-round-robin.md +++ b/en/docs/ai-gateway/next/control-cost-and-traffic/model-weighted-round-robin.md @@ -1,14 +1,14 @@ --- title: "Model Weighted Round Robin" description: "Distribute LLM requests across AI models by assigned weights, giving higher-capacity or lower-cost models proportionally more traffic." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/load-balancing/model-weighted-round-robin/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/load-balancing/model-weighted-round-robin.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/control-cost-and-traffic/model-weighted-round-robin/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/control-cost-and-traffic/model-weighted-round-robin.md tags: - ai-gateway - llm - load-balancing author: WSO2 API Platform Documentation Team -last_updated: 2026-07-30 +last_updated: 2026-08-11 content_type: "reference" --- @@ -103,7 +103,7 @@ operationPolicies: suspendDuration: 60 ``` -The entry without `provider` uses the proxy's primary provider. The other entries route to providers declared under `spec.additionalProviders`. See [Multi-Provider Routing for LLM Proxies](../multi-provider-routing.md) for provider, authentication, transformer, and alias configuration. +The entry without `provider` uses the proxy's primary provider. The other entries route to providers declared under `spec.additionalProviders`. See [Multi-Provider Routing for LLM Proxies](../expose-llms/multi-provider-routing.md) for provider, authentication, transformer, and alias configuration. ### Example 1: Basic Weighted Round Robin with Payload-based Model diff --git a/en/docs/ai-gateway/next/llm-proxy/semantic-caching.md b/en/docs/ai-gateway/next/control-cost-and-traffic/semantic-caching.md similarity index 98% rename from en/docs/ai-gateway/next/llm-proxy/semantic-caching.md rename to en/docs/ai-gateway/next/control-cost-and-traffic/semantic-caching.md index 1c4018527..63370bbd9 100644 --- a/en/docs/ai-gateway/next/llm-proxy/semantic-caching.md +++ b/en/docs/ai-gateway/next/control-cost-and-traffic/semantic-caching.md @@ -1,14 +1,14 @@ --- title: "Semantic Caching" description: "Cache LLM responses using vector similarity search so semantically similar queries are served from cache, reducing cost and latency." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/semantic-caching/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/semantic-caching.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/control-cost-and-traffic/semantic-caching/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/control-cost-and-traffic/semantic-caching.md tags: - ai-gateway - llm - caching author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/resiliency/timeouts.md b/en/docs/ai-gateway/next/control-cost-and-traffic/timeouts.md similarity index 98% rename from en/docs/ai-gateway/next/resiliency/timeouts.md rename to en/docs/ai-gateway/next/control-cost-and-traffic/timeouts.md index 25750345f..71339872d 100644 --- a/en/docs/ai-gateway/next/resiliency/timeouts.md +++ b/en/docs/ai-gateway/next/control-cost-and-traffic/timeouts.md @@ -1,15 +1,15 @@ --- title: "Configure Gateway Timeouts" description: "Configure gateway-level and API-level timeouts (connect, route, idle, and HTTP connection manager) in the API Platform AI Gateway to protect against slow or unreachable backends and slow clients." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/resiliency/timeouts/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/resiliency/timeouts.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/control-cost-and-traffic/timeouts/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/control-cost-and-traffic/timeouts.md tags: - ai-gateway - configuration - networking - resiliency author: WSO2 API Platform Documentation Team -last_updated: 2026-06-30 +last_updated: 2026-08-11 content_type: "how-to" --- diff --git a/en/docs/ai-gateway/next/llm-proxy/multi-provider-routing.md b/en/docs/ai-gateway/next/expose-llms/multi-provider-routing.md similarity index 98% rename from en/docs/ai-gateway/next/llm-proxy/multi-provider-routing.md rename to en/docs/ai-gateway/next/expose-llms/multi-provider-routing.md index 7381f67f4..af1101a41 100644 --- a/en/docs/ai-gateway/next/llm-proxy/multi-provider-routing.md +++ b/en/docs/ai-gateway/next/expose-llms/multi-provider-routing.md @@ -1,14 +1,14 @@ --- title: "Multi-Provider Routing for LLM Proxies" description: "Route OpenAI-compatible LLM proxy requests to multiple providers using header-based selection and provider-specific transformers." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/multi-provider-routing/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/multi-provider-routing.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/expose-llms/multi-provider-routing/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/expose-llms/multi-provider-routing.md tags: - ai-gateway - llm - routing author: WSO2 API Platform Documentation Team -last_updated: 2026-08-05 +last_updated: 2026-08-11 content_type: "guide" --- @@ -85,7 +85,7 @@ operationPolicies: The policy rewrites the model at the location defined by the provider template. It can rewrite a model in the request payload, a header, a query parameter, or a path parameter. -See [Model Round Robin](load-balancing/model-round-robin.md) for its complete configuration. +See [Model Round Robin](../control-cost-and-traffic/model-round-robin.md) for its complete configuration. ### Model weighted round robin @@ -110,7 +110,7 @@ operationPolicies: This example produces the repeating sequence `gpt-4o`, `gpt-4o`, `claude-sonnet-4-5-20250929` while both targets are available. It provides proportional deterministic distribution, not random or performance-based load balancing. -See [Model Weighted Round Robin](load-balancing/model-weighted-round-robin.md) for its complete configuration. +See [Model Weighted Round Robin](../control-cost-and-traffic/model-weighted-round-robin.md) for its complete configuration. ## Configure Providers @@ -984,7 +984,7 @@ For a larger configuration containing OpenAI, Anthropic, Azure OpenAI, Mistral, For automatic traffic distribution across models and providers, see: -- [Model Round Robin](load-balancing/model-round-robin.md) -- [Model Weighted Round Robin](load-balancing/model-weighted-round-robin.md) +- [Model Round Robin](../control-cost-and-traffic/model-round-robin.md) +- [Model Weighted Round Robin](../control-cost-and-traffic/model-weighted-round-robin.md) AWS Bedrock usage can also be evaluated by the [LLM Cost policy](../../../ai-workspace/next/policies/overview.md#llm-cost). diff --git a/en/docs/ai-gateway/next/streaming-responses.md b/en/docs/ai-gateway/next/expose-llms/streaming-responses.md similarity index 91% rename from en/docs/ai-gateway/next/streaming-responses.md rename to en/docs/ai-gateway/next/expose-llms/streaming-responses.md index 8c4f42aa4..79b5b0748 100644 --- a/en/docs/ai-gateway/next/streaming-responses.md +++ b/en/docs/ai-gateway/next/expose-llms/streaming-responses.md @@ -1,15 +1,15 @@ --- title: "Real-Time AI Streaming" description: "Stream responses through API Platform AI Gateway chunk by chunk across LLM providers, LLM proxies, and MCP proxies, and understand how policies, analytics, and token usage behave." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/streaming-responses/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/streaming-responses.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/expose-llms/streaming-responses/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/expose-llms/streaming-responses.md tags: - ai-gateway - llm - mcp - streaming author: WSO2 API Platform Documentation Team -last_updated: 2026-08-10 +last_updated: 2026-08-11 content_type: "concept" --- @@ -98,6 +98,6 @@ If a streamed response carries no `usage` block, the gateway has no token counts ## Related documentation -- [Quick Start Guide](quick-start-guide.md) — deploy a provider and a proxy, then send your first request -- [MCP Proxy Quick Start Guide](mcp-proxy/quick-start-guide.md) — deploy an MCP proxy -- [Sentence Count Guardrail](llm-proxy/guardrails/sentence-count.md) — a guardrail that gates a stream until it can evaluate the content +- [Quick Start Guide](../quick-start-guide.md) — deploy a provider and a proxy, then send your first request +- [MCP Proxy Quick Start Guide](../mcp-proxy/create-an-mcp-proxy.md) — deploy an MCP proxy +- [Sentence Count Guardrail](../control-content/sentence-count.md) — a guardrail that gates a stream until it can evaluate the content diff --git a/en/docs/ai-gateway/next/mcp-proxy/quick-start-guide.md b/en/docs/ai-gateway/next/mcp-proxy/create-an-mcp-proxy.md similarity index 90% rename from en/docs/ai-gateway/next/mcp-proxy/quick-start-guide.md rename to en/docs/ai-gateway/next/mcp-proxy/create-an-mcp-proxy.md index 5cbf4bb0f..6ca5b1744 100644 --- a/en/docs/ai-gateway/next/mcp-proxy/quick-start-guide.md +++ b/en/docs/ai-gateway/next/mcp-proxy/create-an-mcp-proxy.md @@ -1,31 +1,20 @@ --- -title: "MCP Proxy Quick Start Guide" +title: "Create an MCP proxy" description: "Run API Platform AI Gateway with Docker Compose, configure an MCP proxy, and route your first MCP traffic through the gateway." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/quick-start-guide/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/quick-start-guide.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/create-an-mcp-proxy/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/create-an-mcp-proxy.md tags: - ai-gateway - mcp - quickstart author: WSO2 API Platform Documentation Team -last_updated: 2026-08-05 +last_updated: 2026-08-11 content_type: "quickstart" --- -## Quick Start +# Create an MCP proxy -!!! info "Watch the video walkthrough" - [Check out this quick start on YouTube](https://youtu.be/xt6RIax__dU?rel=0) or watch below. - - +## Quick Start ### Using Docker Compose (Recommended) diff --git a/en/docs/ai-gateway/next/mcp-proxy/policies/mcp-acl-list.md b/en/docs/ai-gateway/next/mcp-proxy/mcp-acl-list.md similarity index 98% rename from en/docs/ai-gateway/next/mcp-proxy/policies/mcp-acl-list.md rename to en/docs/ai-gateway/next/mcp-proxy/mcp-acl-list.md index 0e3a2fcad..5f8457ee6 100644 --- a/en/docs/ai-gateway/next/mcp-proxy/policies/mcp-acl-list.md +++ b/en/docs/ai-gateway/next/mcp-proxy/mcp-acl-list.md @@ -1,14 +1,14 @@ --- title: "MCP ACL List" description: "Control access to MCP tools, resources, and prompts using allow or deny mode with exceptions in API Platform AI Gateway." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/policies/mcp-acl-list/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/policies/mcp-acl-list.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/mcp-acl-list/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/mcp-acl-list.md tags: - ai-gateway - mcp - policies author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/mcp-proxy/policies/mcp-authentication.md b/en/docs/ai-gateway/next/mcp-proxy/mcp-authentication.md similarity index 98% rename from en/docs/ai-gateway/next/mcp-proxy/policies/mcp-authentication.md rename to en/docs/ai-gateway/next/mcp-proxy/mcp-authentication.md index 2b97837f8..0df312553 100644 --- a/en/docs/ai-gateway/next/mcp-proxy/policies/mcp-authentication.md +++ b/en/docs/ai-gateway/next/mcp-proxy/mcp-authentication.md @@ -1,14 +1,14 @@ --- title: "MCP Authentication" description: "Secure MCP server traffic by validating JWT access tokens and serving OAuth protected resource metadata in AI Gateway." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/policies/mcp-authentication/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/policies/mcp-authentication.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/mcp-authentication/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/mcp-authentication.md tags: - ai-gateway - mcp - security author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/mcp-proxy/policies/mcp-authorization.md b/en/docs/ai-gateway/next/mcp-proxy/mcp-authorization.md similarity index 99% rename from en/docs/ai-gateway/next/mcp-proxy/policies/mcp-authorization.md rename to en/docs/ai-gateway/next/mcp-proxy/mcp-authorization.md index 4c977ce6e..e197af590 100644 --- a/en/docs/ai-gateway/next/mcp-proxy/policies/mcp-authorization.md +++ b/en/docs/ai-gateway/next/mcp-proxy/mcp-authorization.md @@ -1,14 +1,14 @@ --- title: "MCP Authorization" description: "Define fine-grained access control rules for MCP tools, resources, and prompts based on JWT claims and scopes." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/policies/mcp-authorization/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/policies/mcp-authorization.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/mcp-authorization/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/mcp-authorization.md tags: - ai-gateway - mcp - security author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/mcp-proxy/policies/mcp-rewrite.md b/en/docs/ai-gateway/next/mcp-proxy/mcp-rewrite.md similarity index 98% rename from en/docs/ai-gateway/next/mcp-proxy/policies/mcp-rewrite.md rename to en/docs/ai-gateway/next/mcp-proxy/mcp-rewrite.md index f06278d56..f948d9f9d 100644 --- a/en/docs/ai-gateway/next/mcp-proxy/policies/mcp-rewrite.md +++ b/en/docs/ai-gateway/next/mcp-proxy/mcp-rewrite.md @@ -1,14 +1,14 @@ --- title: "MCP Rewrite" description: "Expose user-facing names for MCP tools, resources, and prompts while mapping them to different backend capability names." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/policies/mcp-rewrite/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/policies/mcp-rewrite.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/mcp-rewrite/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/mcp-rewrite.md tags: - ai-gateway - mcp - policies author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/analytics/analytics-header-filter.md b/en/docs/ai-gateway/next/monitor-traffic/analytics-header-filter.md similarity index 96% rename from en/docs/ai-gateway/next/analytics/analytics-header-filter.md rename to en/docs/ai-gateway/next/monitor-traffic/analytics-header-filter.md index 91d619a6c..411ab3058 100644 --- a/en/docs/ai-gateway/next/analytics/analytics-header-filter.md +++ b/en/docs/ai-gateway/next/monitor-traffic/analytics-header-filter.md @@ -1,14 +1,14 @@ --- title: "Analytics Header Filter" description: "Control which request and response headers are sent to analytics backends using allow or deny mode in API Platform AI Gateway." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/analytics/analytics-header-filter/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/analytics/analytics-header-filter.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/monitor-traffic/analytics-header-filter/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/monitor-traffic/analytics-header-filter.md tags: - ai-gateway - analytics - policies author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/observability/logging.md b/en/docs/ai-gateway/next/monitor-traffic/logging.md similarity index 98% rename from en/docs/ai-gateway/next/observability/logging.md rename to en/docs/ai-gateway/next/monitor-traffic/logging.md index 8565c1a76..29cf95a35 100644 --- a/en/docs/ai-gateway/next/observability/logging.md +++ b/en/docs/ai-gateway/next/monitor-traffic/logging.md @@ -1,14 +1,14 @@ --- title: "Gateway Logging" description: "Configure centralized log collection for API Platform AI Gateway using Fluent Bit, OpenSearch, and alternative logging stacks." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/observability/logging/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/observability/logging.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/monitor-traffic/logging/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/monitor-traffic/logging.md tags: - ai-gateway - observability - devops author: WSO2 API Platform Documentation Team -last_updated: 2026-06-16 +last_updated: 2026-08-11 content_type: "how-to" --- diff --git a/en/docs/ai-gateway/next/analytics/moesif-analytics.md b/en/docs/ai-gateway/next/monitor-traffic/moesif-analytics.md similarity index 97% rename from en/docs/ai-gateway/next/analytics/moesif-analytics.md rename to en/docs/ai-gateway/next/monitor-traffic/moesif-analytics.md index bff1d93c9..a6f949a3e 100644 --- a/en/docs/ai-gateway/next/analytics/moesif-analytics.md +++ b/en/docs/ai-gateway/next/monitor-traffic/moesif-analytics.md @@ -1,14 +1,14 @@ --- title: "Moesif Analytics" description: "Configure Moesif in API Platform AI Gateway to capture and publish API request and response data." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/analytics/moesif-analytics/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/analytics/moesif-analytics.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/monitor-traffic/moesif-analytics/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/monitor-traffic/moesif-analytics.md tags: - ai-gateway - analytics - observability author: WSO2 API Platform Documentation Team -last_updated: 2026-06-16 +last_updated: 2026-08-11 content_type: "how-to" --- diff --git a/en/docs/ai-gateway/next/observability/tracing.md b/en/docs/ai-gateway/next/monitor-traffic/tracing.md similarity index 99% rename from en/docs/ai-gateway/next/observability/tracing.md rename to en/docs/ai-gateway/next/monitor-traffic/tracing.md index 9353ff60a..863ac0dc3 100644 --- a/en/docs/ai-gateway/next/observability/tracing.md +++ b/en/docs/ai-gateway/next/monitor-traffic/tracing.md @@ -1,14 +1,14 @@ --- title: "Gateway Tracing" description: "Configure distributed tracing for API Platform AI Gateway using OpenTelemetry and Jaeger, with support for cloud-native tracing backends." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/observability/tracing/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/observability/tracing.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/monitor-traffic/tracing/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/monitor-traffic/tracing.md tags: - ai-gateway - observability - devops author: WSO2 API Platform Documentation Team -last_updated: 2026-06-16 +last_updated: 2026-08-11 content_type: "how-to" --- diff --git a/en/docs/ai-gateway/next/overview.md b/en/docs/ai-gateway/next/overview.md index 7f72dcf7f..889b9f4a2 100644 --- a/en/docs/ai-gateway/next/overview.md +++ b/en/docs/ai-gateway/next/overview.md @@ -19,7 +19,7 @@ A gateway for managing and securing AI traffic, including Large Language Model ( ## Quick Start - [Quick Start Guide](quick-start-guide.md)—Set up the gateway, verify the controller admin health endpoint, and route traffic to LLM providers like OpenAI -- [MCP Quick Start Guide](mcp-proxy/quick-start-guide.md)—Set up the gateway, verify the controller admin health endpoint, and route traffic to MCP servers +- [MCP Quick Start Guide](mcp-proxy/create-an-mcp-proxy.md)—Set up the gateway, verify the controller admin health endpoint, and route traffic to MCP servers ## Key Concepts @@ -49,14 +49,14 @@ An LLM Provider represents a connection to an AI backend service such as OpenAI, Once configured, the LLM Provider allows traffic to flow through the gateway to the AI backend. -To connect the gateway to AWS Bedrock, see [Configure an AWS Bedrock LLM Provider](llm-proxy/configure-aws-bedrock-provider.md). The guide covers both Bedrock bearer API keys and AWS Signature Version 4 (SigV4) authentication. +To connect the gateway to AWS Bedrock, see [Configure an AWS Bedrock LLM Provider](connect-llm-providers/configure-aws-bedrock-provider.md). The guide covers both Bedrock bearer API keys and AWS Signature Version 4 (SigV4) authentication. ### LLM Proxy An LLM Proxy allows developers to create custom API endpoints that consume an LLM Provider, while inheriting administrator-enforced access control, budgeting and organization-wide policies defined at the provider level. Each proxy gets its own URL context (e.g., `/assistant`) and can have its own policies applied. This enables: - Multiple AI applications to share a single LLM Provider -- A single OpenAI-compatible endpoint to route requests to multiple LLM providers. See [Multi-Provider Routing for LLM Proxies](./llm-proxy/multi-provider-routing.md). +- A single OpenAI-compatible endpoint to route requests to multiple LLM providers. See [Multi-Provider Routing for LLM Proxies](./expose-llms/multi-provider-routing.md). - Per-application policies such as prompt management and guardrails - Separation between platform administration and application development @@ -70,7 +70,7 @@ An MCP Proxy routes Model Context Protocol traffic to MCP servers. MCP is a prot ### Streaming -When an upstream service streams its response, the gateway relays it to the client chunk by chunk instead of buffering the whole response. This holds for LLM providers and LLM proxies, and needs no configuration. On MCP proxies, request bodies stream, but response bodies stay buffered. See [Real-time AI streaming](./streaming-responses.md). +When an upstream service streams its response, the gateway relays it to the client chunk by chunk instead of buffering the whole response. This holds for LLM providers and LLM proxies, and needs no configuration. On MCP proxies, request bodies stream, but response bodies stay buffered. See [Real-time AI streaming](./expose-llms/streaming-responses.md). ## Default Ports @@ -119,11 +119,11 @@ The following table lists the AI Gateway documentation sections and what each on | Section | Description | |---------|-------------| | [LLM](quick-start-guide.md) | LLM provider configuration, guardrails, prompt management, and semantic caching | -| [MCP](mcp-proxy/quick-start-guide.md) | MCP proxy setup and policies | -| [Real-time AI streaming](streaming-responses.md) | Streamed responses across providers and proxies, and how policies and analytics behave | -| [Observability](observability/logging.md) | Logging and tracing configuration | -| [Analytics](analytics/moesif-analytics.md) | Analytics integrations (Moesif) | +| [MCP](mcp-proxy/create-an-mcp-proxy.md) | MCP proxy setup and policies | +| [Real-time AI streaming](expose-llms/streaming-responses.md) | Streamed responses across providers and proxies, and how policies and analytics behave | +| [Observability](monitor-traffic/logging.md) | Logging and tracing configuration | +| [Analytics](monitor-traffic/moesif-analytics.md) | Analytics integrations (Moesif) | | [Policies and Guardrails](https://github.com/wso2/gateway-controllers/blob/main/docs/README.md) | Gateway policies and guardrails for AI traffic control | -| [Gateway Controller Management API](./gateway-controller-management-api/overview.md) | REST API reference for managing LLM providers, LLM proxies, MCP proxies, certificates, and secrets | -| [Production deployment](./deployment/production-deployment/overview.md) | High-availability Kubernetes deployment with Helm, an external database, replicated workloads, and AI workload tuning | +| [Gateway Controller Management API](./reference/management-api/overview.md) | REST API reference for managing LLM providers, LLM proxies, MCP proxies, certificates, and secrets | +| [Production deployment](./run-the-gateway/production-deployment/overview.md) | High-availability Kubernetes deployment with Helm, an external database, replicated workloads, and AI workload tuning | | [AI Workspace](../../ai-workspace/next/overview.md) | The control plane for governing LLM providers, proxies, and policies across every gateway you run | diff --git a/en/docs/ai-gateway/next/quick-start-guide.md b/en/docs/ai-gateway/next/quick-start-guide.md index acd2f553d..4aa556743 100644 --- a/en/docs/ai-gateway/next/quick-start-guide.md +++ b/en/docs/ai-gateway/next/quick-start-guide.md @@ -126,7 +126,7 @@ The commands below use version `1.2.0`. Substitute the API Platform AI Gateway r Stop the conflicting service if you don't need it. If you need to keep it running, change the host-side value of the relevant `ports:` mapping in `docker-compose.yaml`. Then use the remapped host port in the verification and test commands on this page. !!! tip "Customizing configuration" - The setup script (`setup.sh`, or `setup.ps1` on Windows) writes `api-platform.env`, which is loaded into the containers via Docker Compose `env_file`. To change the storage backend, connect to a control plane, or tune other settings, edit that file (or the `config.toml` interpolation tokens directly). See [Gateway Configuration and Environment Interpolation](./setup/configuration.md). + The setup script (`setup.sh`, or `setup.ps1` on Windows) writes `api-platform.env`, which is loaded into the containers via Docker Compose `env_file`. To change the storage backend, connect to a control plane, or tune other settings, edit that file (or the `config.toml` interpolation tokens directly). See [Gateway Configuration and Environment Interpolation](./run-the-gateway/configuration.md). ## Deploy an OpenAI LLM provider configuration @@ -350,9 +350,9 @@ This stops the containers and removes the `controller-data` volume. The next sta ## Next steps -- Route to more than one provider, with failover: [Multi-provider routing](./llm-proxy/multi-provider-routing.md) -- Add guardrails to a proxy, such as [PII masking](./llm-proxy/guardrails/pii-masking-regex.md) or a [JSON schema guardrail](./llm-proxy/guardrails/json-schema.md) -- Expose an MCP server through the gateway: [MCP proxy quick start guide](./mcp-proxy/quick-start-guide.md) +- Route to more than one provider, with failover: [Multi-provider routing](./expose-llms/multi-provider-routing.md) +- Add guardrails to a proxy, such as [PII masking](./control-content/pii-masking-regex.md) or a [JSON schema guardrail](./control-content/json-schema.md) +- Expose an MCP server through the gateway: [MCP proxy quick start guide](./mcp-proxy/create-an-mcp-proxy.md) - Govern AI traffic across all your gateways from the control plane: [AI Workspace overview](../../ai-workspace/next/overview.md) -- Take this gateway to production on Kubernetes: [Production deployment overview](./deployment/production-deployment/overview.md) -- Register a production gateway with the control plane: [Connect to AI Workspace](./deployment/production-deployment/control-plane-connection.md) +- Take this gateway to production on Kubernetes: [Production deployment overview](./run-the-gateway/production-deployment/overview.md) +- Register a production gateway with the control plane: [Connect to AI Workspace](./run-the-gateway/production-deployment/control-plane-connection.md) diff --git a/en/docs/ai-gateway/next/gateway-controller-management-api/certificate-management.md b/en/docs/ai-gateway/next/reference/management-api/certificate-management.md similarity index 96% rename from en/docs/ai-gateway/next/gateway-controller-management-api/certificate-management.md rename to en/docs/ai-gateway/next/reference/management-api/certificate-management.md index 6b84f691c..1e20ecfdd 100644 --- a/en/docs/ai-gateway/next/gateway-controller-management-api/certificate-management.md +++ b/en/docs/ai-gateway/next/reference/management-api/certificate-management.md @@ -1,15 +1,15 @@ --- title: "Management API: Certificate Management" description: "REST API reference for managing custom TLS certificates in API Platform Gateway: list, upload, delete, and reload certificates dynamically." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/gateway-controller-management-api/certificate-management/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/gateway-controller-management-api/certificate-management.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/reference/management-api/certificate-management/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/reference/management-api/certificate-management.md tags: - ai-gateway - management-api - certificates - tls author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/gateway-controller-management-api/llm-provider-management.md b/en/docs/ai-gateway/next/reference/management-api/llm-provider-management.md similarity index 99% rename from en/docs/ai-gateway/next/gateway-controller-management-api/llm-provider-management.md rename to en/docs/ai-gateway/next/reference/management-api/llm-provider-management.md index 00b124e2f..f8d45f769 100644 --- a/en/docs/ai-gateway/next/gateway-controller-management-api/llm-provider-management.md +++ b/en/docs/ai-gateway/next/reference/management-api/llm-provider-management.md @@ -1,14 +1,14 @@ --- title: "Management API: LLM Provider Management" description: "REST API reference for creating, listing, updating, and deleting LLM provider configurations and API keys in API Platform Gateway." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/gateway-controller-management-api/llm-provider-management/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/gateway-controller-management-api/llm-provider-management.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/reference/management-api/llm-provider-management/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/reference/management-api/llm-provider-management.md tags: - ai-gateway - management-api - llm author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/gateway-controller-management-api/llm-provider-template-management.md b/en/docs/ai-gateway/next/reference/management-api/llm-provider-template-management.md similarity index 98% rename from en/docs/ai-gateway/next/gateway-controller-management-api/llm-provider-template-management.md rename to en/docs/ai-gateway/next/reference/management-api/llm-provider-template-management.md index 521e29d26..355a71b6a 100644 --- a/en/docs/ai-gateway/next/gateway-controller-management-api/llm-provider-template-management.md +++ b/en/docs/ai-gateway/next/reference/management-api/llm-provider-template-management.md @@ -1,14 +1,14 @@ --- title: "Management API: LLM Provider Template Management" description: "REST API reference for creating, listing, updating, and deleting LLM provider templates in API Platform Gateway." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/gateway-controller-management-api/llm-provider-template-management/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/gateway-controller-management-api/llm-provider-template-management.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/reference/management-api/llm-provider-template-management/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/reference/management-api/llm-provider-template-management.md tags: - ai-gateway - management-api - llm author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/gateway-controller-management-api/llm-proxy-management.md b/en/docs/ai-gateway/next/reference/management-api/llm-proxy-management.md similarity index 99% rename from en/docs/ai-gateway/next/gateway-controller-management-api/llm-proxy-management.md rename to en/docs/ai-gateway/next/reference/management-api/llm-proxy-management.md index d524139f8..8014bce86 100644 --- a/en/docs/ai-gateway/next/gateway-controller-management-api/llm-proxy-management.md +++ b/en/docs/ai-gateway/next/reference/management-api/llm-proxy-management.md @@ -1,14 +1,14 @@ --- title: "Management API: LLM Proxy Management" description: "REST API reference for creating, listing, updating, and deleting LLM proxy configurations and API keys in API Platform Gateway." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/gateway-controller-management-api/llm-proxy-management/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/gateway-controller-management-api/llm-proxy-management.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/reference/management-api/llm-proxy-management/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/reference/management-api/llm-proxy-management.md tags: - ai-gateway - management-api - llm author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/gateway-controller-management-api/mcp-proxy-management.md b/en/docs/ai-gateway/next/reference/management-api/mcp-proxy-management.md similarity index 98% rename from en/docs/ai-gateway/next/gateway-controller-management-api/mcp-proxy-management.md rename to en/docs/ai-gateway/next/reference/management-api/mcp-proxy-management.md index 966968f95..9ee6524e6 100644 --- a/en/docs/ai-gateway/next/gateway-controller-management-api/mcp-proxy-management.md +++ b/en/docs/ai-gateway/next/reference/management-api/mcp-proxy-management.md @@ -1,14 +1,14 @@ --- title: "Management API: MCP Proxy Management" description: "REST API reference for creating, listing, updating, and deleting MCP proxy configurations in API Platform Gateway." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/gateway-controller-management-api/mcp-proxy-management/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/gateway-controller-management-api/mcp-proxy-management.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/reference/management-api/mcp-proxy-management/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/reference/management-api/mcp-proxy-management.md tags: - ai-gateway - management-api - mcp author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/gateway-controller-management-api/overview.md b/en/docs/ai-gateway/next/reference/management-api/overview.md similarity index 84% rename from en/docs/ai-gateway/next/gateway-controller-management-api/overview.md rename to en/docs/ai-gateway/next/reference/management-api/overview.md index 97e18f539..f816f0c8b 100644 --- a/en/docs/ai-gateway/next/gateway-controller-management-api/overview.md +++ b/en/docs/ai-gateway/next/reference/management-api/overview.md @@ -1,13 +1,13 @@ --- title: "AI Gateway Controller Management API" description: "Overview of the AI Gateway Controller REST API for managing LLM providers, LLM proxies, MCP proxies, certificates, and secrets." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/gateway-controller-management-api/overview/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/gateway-controller-management-api/overview.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/reference/management-api/overview/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/reference/management-api/overview.md tags: - ai-gateway - management-api author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "overview" --- @@ -21,14 +21,14 @@ Base URLs: ## Table of Contents -### [Authentication](authentication.md) +### [Authentication](../../control-access/secure-the-management-api.md) -- [Overview](authentication.md#overview) -- [How It Works](authentication.md#how-it-works) -- [Configuration](authentication.md#configuration) -- [Role Mapping Semantics](authentication.md#role-mapping-semantics) -- [Troubleshooting (What you’ll observe)](authentication.md#troubleshooting-what-youll-observe) -- [Testing](authentication.md#testing) +- [Overview](../../control-access/secure-the-management-api.md#overview) +- [How It Works](../../control-access/secure-the-management-api.md#how-it-works) +- [Configuration](../../control-access/secure-the-management-api.md#configuration) +- [Role Mapping Semantics](../../control-access/secure-the-management-api.md#role-mapping-semantics) +- [Troubleshooting (What you’ll observe)](../../control-access/secure-the-management-api.md#troubleshooting-what-youll-observe) +- [Testing](../../control-access/secure-the-management-api.md#testing) ### [MCP Proxy Management](mcp-proxy-management.md) diff --git a/en/docs/ai-gateway/next/gateway-controller-management-api/schemas.md b/en/docs/ai-gateway/next/reference/management-api/schemas.md similarity index 99% rename from en/docs/ai-gateway/next/gateway-controller-management-api/schemas.md rename to en/docs/ai-gateway/next/reference/management-api/schemas.md index dd7e60496..b2aa50798 100644 --- a/en/docs/ai-gateway/next/gateway-controller-management-api/schemas.md +++ b/en/docs/ai-gateway/next/reference/management-api/schemas.md @@ -1,13 +1,13 @@ --- title: "Management API Schemas" description: "JSON schema definitions for all API Platform Gateway Controller management API request and response objects." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/gateway-controller-management-api/schemas/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/gateway-controller-management-api/schemas.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/reference/management-api/schemas/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/reference/management-api/schemas.md tags: - ai-gateway - management-api author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/gateway-controller-management-api/secrets-management.md b/en/docs/ai-gateway/next/reference/management-api/secrets-management.md similarity index 97% rename from en/docs/ai-gateway/next/gateway-controller-management-api/secrets-management.md rename to en/docs/ai-gateway/next/reference/management-api/secrets-management.md index 0eb703065..5c2d4d9f8 100644 --- a/en/docs/ai-gateway/next/gateway-controller-management-api/secrets-management.md +++ b/en/docs/ai-gateway/next/reference/management-api/secrets-management.md @@ -1,14 +1,14 @@ --- title: "Management API: Secrets Management" description: "REST API reference for creating, listing, retrieving, updating, and deleting secrets in API Platform Gateway." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/gateway-controller-management-api/secrets-management/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/gateway-controller-management-api/secrets-management.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/reference/management-api/secrets-management/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/reference/management-api/secrets-management.md tags: - ai-gateway - management-api - security author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "reference" --- diff --git a/en/docs/ai-gateway/next/setup/configuration.md b/en/docs/ai-gateway/next/run-the-gateway/configuration.md similarity index 96% rename from en/docs/ai-gateway/next/setup/configuration.md rename to en/docs/ai-gateway/next/run-the-gateway/configuration.md index d74c0d490..de6df61c0 100644 --- a/en/docs/ai-gateway/next/setup/configuration.md +++ b/en/docs/ai-gateway/next/run-the-gateway/configuration.md @@ -1,14 +1,14 @@ --- title: "Gateway Configuration and Environment Interpolation" description: "How the API Platform Gateway loads its config.toml, injects environment values through interpolation tokens, and bootstraps required keys and certificates with the setup script." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/setup/configuration/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/setup/configuration.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/configuration/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/configuration.md tags: - api-gateway - configuration - interpolation author: WSO2 API Platform Documentation Team -last_updated: 2026-07-22 +last_updated: 2026-08-11 content_type: "reference" --- @@ -92,7 +92,7 @@ APIP_GW_CONTROLLER_CONTROLPLANE_HOST=your-control-plane-host:9443 APIP_GW_CONTROLLER_CONTROLPLANE_TOKEN= ``` -For Kubernetes/Helm deployments, the chart renders `config.toml` into a ConfigMap and injects the runtime secrets (control plane token, database password) as interpolation tokens backed by Kubernetes Secrets — see [Security Hardening](../deployment/production-deployment/security-hardening.md) and [Database Configuration](../deployment/production-deployment/database-configuration.md). +For Kubernetes/Helm deployments, the chart renders `config.toml` into a ConfigMap and injects the runtime secrets (control plane token, database password) as interpolation tokens backed by Kubernetes Secrets — see [Security Hardening](./production-deployment/security-hardening.md) and [Database Configuration](./production-deployment/database-configuration.md). ## No development / demo mode diff --git a/en/docs/ai-gateway/next/setup/database-setup.md b/en/docs/ai-gateway/next/run-the-gateway/database-setup.md similarity index 98% rename from en/docs/ai-gateway/next/setup/database-setup.md rename to en/docs/ai-gateway/next/run-the-gateway/database-setup.md index c8266dec3..35edca014 100644 --- a/en/docs/ai-gateway/next/setup/database-setup.md +++ b/en/docs/ai-gateway/next/run-the-gateway/database-setup.md @@ -1,8 +1,8 @@ --- title: "Setting Up the Database" description: "Create the database and apply the Gateway Controller schema for PostgreSQL or SQL Server before starting the API Platform AI Gateway." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/setup/database-setup/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/setup/database-setup.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/database-setup/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/database-setup.md tags: - ai-gateway - configuration @@ -10,7 +10,7 @@ tags: - sqlserver - devops author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "how-to" --- diff --git a/en/docs/ai-gateway/next/deployment/deployment-modes/immutable-gateway.md b/en/docs/ai-gateway/next/run-the-gateway/immutable-gateway.md similarity index 93% rename from en/docs/ai-gateway/next/deployment/deployment-modes/immutable-gateway.md rename to en/docs/ai-gateway/next/run-the-gateway/immutable-gateway.md index adddeacfd..5f02265c5 100644 --- a/en/docs/ai-gateway/next/deployment/deployment-modes/immutable-gateway.md +++ b/en/docs/ai-gateway/next/run-the-gateway/immutable-gateway.md @@ -1,14 +1,14 @@ --- title: "Immutable Gateway" description: "Run API Platform AI Gateway in immutable mode, loading LLM and MCP configurations from files at startup for GitOps workflows." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/deployment/deployment-modes/immutable-gateway/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/deployment/deployment-modes/immutable-gateway.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/immutable-gateway/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/immutable-gateway.md tags: - ai-gateway - deployment - gitops author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "how-to" --- @@ -62,7 +62,7 @@ By default, the gateway controller loads artifacts from `/etc/api-platform-gatew ``` {% endraw %} - Then set `APIP_GW_IMMUTABLE_GATEWAY_ENABLED=true`. See [Gateway Configuration and Environment Interpolation](../../setup/configuration.md). + Then set `APIP_GW_IMMUTABLE_GATEWAY_ENABLED=true`. See [Gateway Configuration and Environment Interpolation](./configuration.md). ## Artifact format @@ -79,7 +79,7 @@ Artifact files support Go template expressions for injecting dynamic values. Tem | `{{ env "KEY" | redact }}` | Yes | Sensitive env vars (tokens, API keys) | {% endraw %} -Use `| redact` for sensitive values to hide them from config dumps. A `| default "value"` pipe is available for fallback values. See [Gateway Artifact Templating](../../../../api-gateway/1.1.0/setup/artifact-templating.md) for the full function reference. +Use `| redact` for sensitive values to hide them from config dumps. A `| default "value"` pipe is available for fallback values. See [Gateway Artifact Templating](../../../api-gateway/1.1.0/setup/artifact-templating.md) for the full function reference. ### Sample: Reading List API diff --git a/en/docs/ai-gateway/next/deployment/deployment-modes/kubernetes/gateway-operator.md b/en/docs/ai-gateway/next/run-the-gateway/kubernetes/gateway-operator.md similarity index 98% rename from en/docs/ai-gateway/next/deployment/deployment-modes/kubernetes/gateway-operator.md rename to en/docs/ai-gateway/next/run-the-gateway/kubernetes/gateway-operator.md index 26adee308..69c087215 100644 --- a/en/docs/ai-gateway/next/deployment/deployment-modes/kubernetes/gateway-operator.md +++ b/en/docs/ai-gateway/next/run-the-gateway/kubernetes/gateway-operator.md @@ -1,14 +1,14 @@ --- title: "Kubernetes Operator for API Platform Gateway" description: "Deploy API Platform AI Gateway on Kubernetes using the Gateway Operator with platform CRDs or the Kubernetes Gateway API." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/deployment/deployment-modes/kubernetes/gateway-operator/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/deployment/deployment-modes/kubernetes/gateway-operator.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/kubernetes/gateway-operator/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/kubernetes/gateway-operator.md tags: - ai-gateway - kubernetes - deployment author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "how-to" --- diff --git a/en/docs/ai-gateway/next/deployment/deployment-modes/kubernetes/kubernetes-standalone.md b/en/docs/ai-gateway/next/run-the-gateway/kubernetes/kubernetes-standalone.md similarity index 96% rename from en/docs/ai-gateway/next/deployment/deployment-modes/kubernetes/kubernetes-standalone.md rename to en/docs/ai-gateway/next/run-the-gateway/kubernetes/kubernetes-standalone.md index 6b517e668..542145bea 100644 --- a/en/docs/ai-gateway/next/deployment/deployment-modes/kubernetes/kubernetes-standalone.md +++ b/en/docs/ai-gateway/next/run-the-gateway/kubernetes/kubernetes-standalone.md @@ -1,14 +1,14 @@ --- title: "Kubernetes Standalone Mode" description: "Install and manage API Platform AI Gateway on Kubernetes using the standalone Helm chart without the Gateway Operator." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/deployment/deployment-modes/kubernetes/kubernetes-standalone/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/deployment/deployment-modes/kubernetes/kubernetes-standalone.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/kubernetes/kubernetes-standalone/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/kubernetes/kubernetes-standalone.md tags: - ai-gateway - kubernetes - deployment author: WSO2 API Platform Documentation Team -last_updated: 2026-08-07 +last_updated: 2026-08-11 content_type: "how-to" --- diff --git a/en/docs/ai-gateway/next/deployment/deployment-modes/kubernetes/overview.md b/en/docs/ai-gateway/next/run-the-gateway/kubernetes/overview.md similarity index 94% rename from en/docs/ai-gateway/next/deployment/deployment-modes/kubernetes/overview.md rename to en/docs/ai-gateway/next/run-the-gateway/kubernetes/overview.md index f72471cc6..f89936a94 100644 --- a/en/docs/ai-gateway/next/deployment/deployment-modes/kubernetes/overview.md +++ b/en/docs/ai-gateway/next/run-the-gateway/kubernetes/overview.md @@ -1,14 +1,14 @@ --- title: "AI Gateway Kubernetes Deployment Modes" description: "Choose between standalone and operator-managed Kubernetes deployment modes for API Platform AI Gateway." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/deployment/deployment-modes/kubernetes/overview/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/deployment/deployment-modes/kubernetes/overview.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/kubernetes/overview/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/kubernetes/overview.md tags: - ai-gateway - kubernetes - deployment author: WSO2 API Platform Documentation Team -last_updated: 2026-06-19 +last_updated: 2026-08-11 content_type: "overview" --- diff --git a/en/docs/ai-gateway/next/deployment/production-deployment/ai-workload-tuning.md b/en/docs/ai-gateway/next/run-the-gateway/production-deployment/ai-workload-tuning.md similarity index 86% rename from en/docs/ai-gateway/next/deployment/production-deployment/ai-workload-tuning.md rename to en/docs/ai-gateway/next/run-the-gateway/production-deployment/ai-workload-tuning.md index 6929d27f7..d7afe47da 100644 --- a/en/docs/ai-gateway/next/deployment/production-deployment/ai-workload-tuning.md +++ b/en/docs/ai-gateway/next/run-the-gateway/production-deployment/ai-workload-tuning.md @@ -1,8 +1,8 @@ --- title: "Tune the Gateway for AI Traffic" description: "Tune API Platform AI Gateway for LLM and MCP traffic: streaming timeouts, body buffers, guardrail limits, cost pricing data, and semantic cache backing." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/deployment/production-deployment/ai-workload-tuning/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/deployment/production-deployment/ai-workload-tuning.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/production-deployment/ai-workload-tuning/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/production-deployment/ai-workload-tuning.md tags: - ai-gateway - production @@ -10,7 +10,7 @@ tags: - streaming - guardrails author: WSO2 API Platform Documentation Team -last_updated: 2026-08-09 +last_updated: 2026-08-11 content_type: "how-to" --- @@ -40,7 +40,7 @@ gateway: The two idle timeouts are what keep a streaming response alive. `route_idle_timeout_ms` bounds the gap between chunks arriving from the provider, and `stream_idle_timeout` bounds the same gap on the client side. Set both longer than the longest pause you expect between tokens, not longer than the response as a whole. -Individual proxies can override the route timeouts through their `resilience` block, which is useful when one model is much slower than the rest. For the full precedence order between the `resilience` block and these defaults, see [Timeouts](../../resiliency/timeouts.md). +Individual proxies can override the route timeouts through their `resilience` block, which is useful when one model is much slower than the rest. For the full precedence order between the `resilience` block and these defaults, see [Timeouts](../../control-cost-and-traffic/timeouts.md). !!! note Raise the matching timeouts on whatever sits in front of the gateway as well. An ingress controller or load balancer with a 60-second read timeout cuts the response off regardless of what the gateway allows. @@ -81,7 +81,7 @@ gateway: timeout: 30s ``` -- `python_executor.timeout` bounds a single policy execution. Guardrails that call an external service spend most of that budget on the network call. [Azure Content Safety](../../llm-proxy/guardrails/azure-content-safety.md), [AWS Bedrock guardrails](../../llm-proxy/guardrails/aws-bedrock-guardrail.md), and a [semantic prompt guardrail](../../llm-proxy/guardrails/semantic-prompt-guard.md) that generates embeddings all behave this way. Raise the timeout when the guardrail service is slow or distant. Keep it below `route_timeout_ms`, so the route timeout stays the outer bound. +- `python_executor.timeout` bounds a single policy execution. Guardrails that call an external service spend most of that budget on the network call. [Azure Content Safety](../../control-content/azure-content-safety.md), [AWS Bedrock guardrails](../../control-content/aws-bedrock-guardrail.md), and a [semantic prompt guardrail](../../control-content/semantic-prompt-guard.md) that generates embeddings all behave this way. Raise the timeout when the guardrail service is slow or distant. Keep it below `route_timeout_ms`, so the route timeout stays the outer bound. - `route_cache_action: RETAIN` keeps the route cache warm across requests. Leave it at `RETAIN`. Guardrails that reach an external service add that service's latency and its failure modes to every request. Deploy the guardrail service in the same region as the gateway, and check what your chosen guardrail does when the service is unreachable before you rely on it in production. @@ -129,7 +129,7 @@ Cost figures are only as accurate as this file. Treat it as data to review on a ## Provision infrastructure for semantic caching -[Semantic caching](../../llm-proxy/semantic-caching.md) depends on two external services that the gateway chart doesn't deploy, so provision both before you enable the policy: +[Semantic caching](../../control-cost-and-traffic/semantic-caching.md) depends on two external services that the gateway chart doesn't deploy, so provision both before you enable the policy: - **A vector database** — Redis or Milvus — that stores the cached responses and their embeddings. Size it for your retention window, place it in the same region as the gateway, and secure it: it holds prompt and completion content in full. - **An embedding provider** — OpenAI, Mistral, or Azure OpenAI — called on every request that reaches the policy. Its latency is added to every cache miss, and its API key is stored as a gateway secret, encrypted with the key from [Security hardening](./security-hardening.md). @@ -154,7 +154,7 @@ gateway: ``` !!! warning "Prompts and completions are sensitive" - Debug-level logging can record request and response bodies, which on an AI Gateway means user prompts and model completions. Before you enable debug-level logging in production, confirm that your log retention and access controls suit that content. If you forward traffic data to an external analytics service, control what leaves the gateway with the [analytics header filter](../../analytics/analytics-header-filter.md). For where the logs go and how to read them, see [Gateway logging](../../observability/logging.md). + Debug-level logging can record request and response bodies, which on an AI Gateway means user prompts and model completions. Before you enable debug-level logging in production, confirm that your log retention and access controls suit that content. If you forward traffic data to an external analytics service, control what leaves the gateway with the [analytics header filter](../../monitor-traffic/analytics-header-filter.md). For where the logs go and how to read them, see [Gateway logging](../../monitor-traffic/logging.md). --- diff --git a/en/docs/ai-gateway/next/deployment/production-deployment/control-plane-connection.md b/en/docs/ai-gateway/next/run-the-gateway/production-deployment/control-plane-connection.md similarity index 96% rename from en/docs/ai-gateway/next/deployment/production-deployment/control-plane-connection.md rename to en/docs/ai-gateway/next/run-the-gateway/production-deployment/control-plane-connection.md index 7e9304170..d91700247 100644 --- a/en/docs/ai-gateway/next/deployment/production-deployment/control-plane-connection.md +++ b/en/docs/ai-gateway/next/run-the-gateway/production-deployment/control-plane-connection.md @@ -1,15 +1,15 @@ --- title: "Connect to AI Workspace" description: "Register a production AI Gateway with AI Workspace: the registration token as a Kubernetes Secret, the control plane address, TLS trust, and sync behavior." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/deployment/production-deployment/control-plane-connection/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/deployment/production-deployment/control-plane-connection.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/production-deployment/control-plane-connection/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/production-deployment/control-plane-connection.md tags: - ai-gateway - production - ai-workspace - control-plane author: WSO2 API Platform Documentation Team -last_updated: 2026-08-09 +last_updated: 2026-08-11 content_type: "how-to" --- diff --git a/en/docs/ai-gateway/next/deployment/production-deployment/database-configuration.md b/en/docs/ai-gateway/next/run-the-gateway/production-deployment/database-configuration.md similarity index 94% rename from en/docs/ai-gateway/next/deployment/production-deployment/database-configuration.md rename to en/docs/ai-gateway/next/run-the-gateway/production-deployment/database-configuration.md index cfb4c2ba6..ee504dc32 100644 --- a/en/docs/ai-gateway/next/deployment/production-deployment/database-configuration.md +++ b/en/docs/ai-gateway/next/run-the-gateway/production-deployment/database-configuration.md @@ -1,8 +1,8 @@ --- title: "Database Configuration" description: "Point AI Gateway controller replicas at a shared PostgreSQL or SQL Server database, inject the password from a Secret, and tune the connection pool." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/deployment/production-deployment/database-configuration/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/deployment/production-deployment/database-configuration.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/production-deployment/database-configuration/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/production-deployment/database-configuration.md tags: - ai-gateway - production @@ -10,7 +10,7 @@ tags: - sqlserver - high-availability author: WSO2 API Platform Documentation Team -last_updated: 2026-08-09 +last_updated: 2026-08-11 content_type: "how-to" --- @@ -20,7 +20,7 @@ An external database is what makes controller high availability possible. It rep ## Before you begin -Create the database, the gateway account, and the schema first. That procedure, including where the schema scripts live and how to restrict runtime privileges, is covered in [Setting up the database](../../setup/database-setup.md). The Helm chart has no bootstrap job, so run the schema scripts from a CI job, a bastion host, or a temporary pod with network access to the database. +Create the database, the gateway account, and the schema first. That procedure, including where the schema scripts live and how to restrict runtime privileges, is covered in [Setting up the database](../database-setup.md). The Helm chart has no bootstrap job, so run the schema scripts from a CI job, a bastion host, or a temporary pod with network access to the database. Come back here once the schema exists. This page covers only the chart configuration. diff --git a/en/docs/ai-gateway/next/deployment/production-deployment/deploy-and-verify.md b/en/docs/ai-gateway/next/run-the-gateway/production-deployment/deploy-and-verify.md similarity index 96% rename from en/docs/ai-gateway/next/deployment/production-deployment/deploy-and-verify.md rename to en/docs/ai-gateway/next/run-the-gateway/production-deployment/deploy-and-verify.md index 5dfb378b2..42b9bae37 100644 --- a/en/docs/ai-gateway/next/deployment/production-deployment/deploy-and-verify.md +++ b/en/docs/ai-gateway/next/run-the-gateway/production-deployment/deploy-and-verify.md @@ -1,15 +1,15 @@ --- title: "Deploy and Verify" description: "Install the API Platform AI Gateway Helm chart, confirm the controller and runtime are healthy, route a live LLM request, and run upgrades and rollbacks." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/deployment/production-deployment/deploy-and-verify/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/deployment/production-deployment/deploy-and-verify.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/production-deployment/deploy-and-verify/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/production-deployment/deploy-and-verify.md tags: - ai-gateway - production - helm - kubernetes author: WSO2 API Platform Documentation Team -last_updated: 2026-08-09 +last_updated: 2026-08-11 content_type: "how-to" --- @@ -198,7 +198,7 @@ curl -N -X POST "https://ai-gateway.example.com/assistant/chat/completions" \ Chunks should arrive progressively. If the whole response arrives at once, one layer in the path is holding it until the response completes. Check these in order: - The ingress controller or reverse proxy in front of the gateway. Response buffering there hides the stream from the client. -- A gateway policy that needs the complete body before it can run. See [Real-time AI streaming](../../streaming-responses.md). +- A gateway policy that needs the complete body before it can run. See [Real-time AI streaming](../../expose-llms/streaming-responses.md). - The provider or the model. Not every model streams every request. If the response cuts off partway, revisit the timeouts in [Tune the gateway for AI traffic](./ai-workload-tuning.md#raise-the-timeouts-for-long-completions). diff --git a/en/docs/ai-gateway/next/deployment/production-deployment/overview.md b/en/docs/ai-gateway/next/run-the-gateway/production-deployment/overview.md similarity index 96% rename from en/docs/ai-gateway/next/deployment/production-deployment/overview.md rename to en/docs/ai-gateway/next/run-the-gateway/production-deployment/overview.md index 38ce9519d..e2ec611f6 100644 --- a/en/docs/ai-gateway/next/deployment/production-deployment/overview.md +++ b/en/docs/ai-gateway/next/run-the-gateway/production-deployment/overview.md @@ -1,8 +1,8 @@ --- title: "Production Deployment Overview" description: "Plan a high-availability production deployment of API Platform AI Gateway on Kubernetes with Helm, an external database, and replicated workloads." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/deployment/production-deployment/overview/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/deployment/production-deployment/overview.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/production-deployment/overview/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/production-deployment/overview.md tags: - ai-gateway - production @@ -10,7 +10,7 @@ tags: - kubernetes - high-availability author: WSO2 API Platform Documentation Team -last_updated: 2026-08-09 +last_updated: 2026-08-11 content_type: "concept" --- @@ -23,7 +23,7 @@ This section is for platform engineers and site reliability engineers who run AP - Replicated workloads. - The AI-specific tuning that large language model (LLM) and Model Context Protocol (MCP) traffic needs. -For a single-host evaluation, follow the [quick start guide](../../quick-start-guide.md) instead. For the other ways to run the gateway, see [Immutable Gateway](../deployment-modes/immutable-gateway.md) and [Kubernetes deployment modes](../deployment-modes/kubernetes/overview.md). +For a single-host evaluation, follow the [quick start guide](../../quick-start-guide.md) instead. For the other ways to run the gateway, see [Immutable Gateway](../immutable-gateway.md) and [Kubernetes deployment modes](../kubernetes/overview.md). !!! info "Version-pinned instructions" Every command and configuration key on these pages is taken from the `ai-gateway/v1.2.0` release tag and Helm chart `1.2.0`. Chart fields change between releases, so follow the pages for the AI Gateway version you deploy. diff --git a/en/docs/ai-gateway/next/deployment/production-deployment/resources-and-scaling.md b/en/docs/ai-gateway/next/run-the-gateway/production-deployment/resources-and-scaling.md similarity index 94% rename from en/docs/ai-gateway/next/deployment/production-deployment/resources-and-scaling.md rename to en/docs/ai-gateway/next/run-the-gateway/production-deployment/resources-and-scaling.md index 87bf9b5a1..cfdd5863d 100644 --- a/en/docs/ai-gateway/next/deployment/production-deployment/resources-and-scaling.md +++ b/en/docs/ai-gateway/next/run-the-gateway/production-deployment/resources-and-scaling.md @@ -1,15 +1,15 @@ --- title: "Resources and Scaling" description: "Size CPU and memory for the AI Gateway controller and runtime, spread replicas with anti-affinity, and configure autoscaling and pod disruption budgets." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/deployment/production-deployment/resources-and-scaling/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/deployment/production-deployment/resources-and-scaling.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/production-deployment/resources-and-scaling/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/production-deployment/resources-and-scaling.md tags: - ai-gateway - production - kubernetes - scaling author: WSO2 API Platform Documentation Team -last_updated: 2026-08-09 +last_updated: 2026-08-11 content_type: "how-to" --- @@ -19,7 +19,7 @@ content_type: "how-to" Set requests and limits on both components in production. Without them, a traffic spike on the gateway can starve other workloads on the node. -The allocations below match the ones used in the [AI Gateway performance tests](../../performance/overview.md), so the published throughput and latency figures describe what these settings deliver. +The allocations below match the ones used in the [AI Gateway performance tests](../sizing-and-performance/overview.md), so the published throughput and latency figures describe what these settings deliver. **Gateway Controller:** diff --git a/en/docs/ai-gateway/next/deployment/production-deployment/security-hardening.md b/en/docs/ai-gateway/next/run-the-gateway/production-deployment/security-hardening.md similarity index 97% rename from en/docs/ai-gateway/next/deployment/production-deployment/security-hardening.md rename to en/docs/ai-gateway/next/run-the-gateway/production-deployment/security-hardening.md index ced5bae94..ee1e80a72 100644 --- a/en/docs/ai-gateway/next/deployment/production-deployment/security-hardening.md +++ b/en/docs/ai-gateway/next/run-the-gateway/production-deployment/security-hardening.md @@ -1,8 +1,8 @@ --- title: "Security Hardening" description: "Harden API Platform AI Gateway before production: AES-256 at-rest encryption keys, TLS for the listener and upstreams, and management API authentication." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/deployment/production-deployment/security-hardening/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/deployment/production-deployment/security-hardening.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/production-deployment/security-hardening/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/production-deployment/security-hardening.md tags: - ai-gateway - production @@ -10,7 +10,7 @@ tags: - encryption - tls author: WSO2 API Platform Documentation Team -last_updated: 2026-08-09 +last_updated: 2026-08-11 content_type: "how-to" --- diff --git a/en/docs/ai-gateway/next/performance/ai-gateway-runtime-with-four-cpus.md b/en/docs/ai-gateway/next/run-the-gateway/sizing-and-performance/ai-gateway-runtime-with-four-cpus.md similarity index 81% rename from en/docs/ai-gateway/next/performance/ai-gateway-runtime-with-four-cpus.md rename to en/docs/ai-gateway/next/run-the-gateway/sizing-and-performance/ai-gateway-runtime-with-four-cpus.md index 724677e52..4b818019e 100644 --- a/en/docs/ai-gateway/next/performance/ai-gateway-runtime-with-four-cpus.md +++ b/en/docs/ai-gateway/next/run-the-gateway/sizing-and-performance/ai-gateway-runtime-with-four-cpus.md @@ -1,15 +1,15 @@ --- title: "AI Gateway Runtime with Four CPUs - Performance Results" description: "View API Platform AI Gateway performance benchmark results with a four-CPU gateway runtime, including throughput, average response time, and percentile response times for Auth No Guardrails, PII Masking, and Advanced Guardrails scenarios." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/performance/ai-gateway-runtime-with-four-cpus/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/performance/ai-gateway-runtime-with-four-cpus.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/sizing-and-performance/ai-gateway-runtime-with-four-cpus/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/sizing-and-performance/ai-gateway-runtime-with-four-cpus.md tags: - ai-gateway - performance - benchmarks - gateway-runtime author: WSO2 API Platform Documentation Team -last_updated: 2026-07-15 +last_updated: 2026-08-11 content_type: "reference" --- @@ -26,7 +26,7 @@ The table below displays the resource allocations for the AI Gateway components The graph below shows how AI Gateway throughput changes as concurrent users increase for AI API Auth No Guardrails, AI API PII Masking, and AI API Advanced Guardrails. -![Line chart of AI Gateway throughput in requests per second versus concurrent users at 100, 500, 800, and 1000 users, comparing AI API Auth No Guardrails, AI API PII Masking, and AI API Advanced Guardrails on a four-CPU gateway runtime](../../../assets/img/ai-gateway/performance/four-core-Throughput-vs-Concurrent-Users.svg){ width="900" } +![Line chart of AI Gateway throughput in requests per second versus concurrent users at 100, 500, 800, and 1000 users, comparing AI API Auth No Guardrails, AI API PII Masking, and AI API Advanced Guardrails on a four-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/four-core-Throughput-vs-Concurrent-Users.svg){ width="900" } **Key observations:** @@ -38,7 +38,7 @@ The graph below shows how AI Gateway throughput changes as concurrent users incr The graph below shows how average response time changes for the same AI API scenarios as concurrent users increase. The backend delay was configured to 10 ms for these tests. -![Line chart of average response time in milliseconds versus concurrent users at 100, 500, 800, and 1000 users, comparing AI API Auth No Guardrails, AI API PII Masking, and AI API Advanced Guardrails on a four-CPU gateway runtime](../../../assets/img/ai-gateway/performance/four-core-Average-Response-Time-vs-Concurrent-Users.svg){ width="900" } +![Line chart of average response time in milliseconds versus concurrent users at 100, 500, 800, and 1000 users, comparing AI API Auth No Guardrails, AI API PII Masking, and AI API Advanced Guardrails on a four-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/four-core-Average-Response-Time-vs-Concurrent-Users.svg){ width="900" } **Key observations:** @@ -49,7 +49,7 @@ The graph below shows how average response time changes for the same AI API scen The graphs below show the 90th, 95th, and 99th percentile response times at 10 ms backend delay. Percentile values indicate the response time below which that percentage of requests completed, for example, the 99th percentile is the response time exceeded by only 1% of requests. -![Line chart of 90th, 95th, and 99th percentile response times in milliseconds versus concurrent users for AI API Auth No Guardrails on a four-CPU gateway runtime](../../../assets/img/ai-gateway/performance/4-core-Percentile-Response-Times-aiapi.svg){ width="900" } +![Line chart of 90th, 95th, and 99th percentile response times in milliseconds versus concurrent users for AI API Auth No Guardrails on a four-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/4-core-Percentile-Response-Times-aiapi.svg){ width="900" } **Key observations:** @@ -57,7 +57,7 @@ The graphs below show the 90th, 95th, and 99th percentile response times at 10 m - The four-CPU configuration yields lower percentile values at high concurrency than the two-CPU configuration. - Percentile growth mainly reflects load on the gateway and the fixed backend delay, without content-level guardrail processing. -![Line chart of 90th, 95th, and 99th percentile response times in milliseconds versus concurrent users for AI API PII Masking on a four-CPU gateway runtime](../../../assets/img/ai-gateway/performance/4-core-Percentile-Response-Times-pii-masking.svg){ width="900" } +![Line chart of 90th, 95th, and 99th percentile response times in milliseconds versus concurrent users for AI API PII Masking on a four-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/4-core-Percentile-Response-Times-pii-masking.svg){ width="900" } **Key observations:** @@ -65,7 +65,7 @@ The graphs below show the 90th, 95th, and 99th percentile response times at 10 m - Compared with Auth No Guardrails, percentile values are higher at each concurrency level due to request and response masking. - Compared with the two-CPU PII Masking results, the four-CPU configuration keeps percentiles lower under similar concurrency. -![Line chart of 90th, 95th, and 99th percentile response times in milliseconds versus concurrent users for AI API Advanced Guardrails on a four-CPU gateway runtime](../../../assets/img/ai-gateway/performance/4-core-Percentile-Response-Times-advanced.svg){ width="900" } +![Line chart of 90th, 95th, and 99th percentile response times in milliseconds versus concurrent users for AI API Advanced Guardrails on a four-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/4-core-Percentile-Response-Times-advanced.svg){ width="900" } **Key observations:** diff --git a/en/docs/ai-gateway/next/performance/ai-gateway-runtime-with-two-cpus.md b/en/docs/ai-gateway/next/run-the-gateway/sizing-and-performance/ai-gateway-runtime-with-two-cpus.md similarity index 80% rename from en/docs/ai-gateway/next/performance/ai-gateway-runtime-with-two-cpus.md rename to en/docs/ai-gateway/next/run-the-gateway/sizing-and-performance/ai-gateway-runtime-with-two-cpus.md index 34da46d2b..edebc7b67 100644 --- a/en/docs/ai-gateway/next/performance/ai-gateway-runtime-with-two-cpus.md +++ b/en/docs/ai-gateway/next/run-the-gateway/sizing-and-performance/ai-gateway-runtime-with-two-cpus.md @@ -1,15 +1,15 @@ --- title: "AI Gateway Runtime with Two CPUs - Performance Results" description: "View API Platform AI Gateway performance benchmark results with a two-CPU gateway runtime, including throughput, average response time, and percentile response times for Auth No Guardrails, PII Masking, and Advanced Guardrails scenarios." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/performance/ai-gateway-runtime-with-two-cpus/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/performance/ai-gateway-runtime-with-two-cpus.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/sizing-and-performance/ai-gateway-runtime-with-two-cpus/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/sizing-and-performance/ai-gateway-runtime-with-two-cpus.md tags: - ai-gateway - performance - benchmarks - gateway-runtime author: WSO2 API Platform Documentation Team -last_updated: 2026-07-15 +last_updated: 2026-08-11 content_type: "reference" --- @@ -26,7 +26,7 @@ The table below displays the resource allocations for the AI Gateway components The graph below shows how AI Gateway throughput changes as concurrent users increase for AI API Auth No Guardrails, AI API PII Masking, and AI API Advanced Guardrails. -![Line chart of AI Gateway throughput in requests per second versus concurrent users at 100, 500, and 1000 users, comparing AI API Auth No Guardrails, AI API PII Masking, and AI API Advanced Guardrails on a two-CPU gateway runtime](../../../assets/img/ai-gateway/performance/two-core-throughput-vs-concurrent-users.svg){ width="900" } +![Line chart of AI Gateway throughput in requests per second versus concurrent users at 100, 500, and 1000 users, comparing AI API Auth No Guardrails, AI API PII Masking, and AI API Advanced Guardrails on a two-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/two-core-throughput-vs-concurrent-users.svg){ width="900" } **Key observations:** @@ -37,7 +37,7 @@ The graph below shows how AI Gateway throughput changes as concurrent users incr The graph below shows how average response time changes for the same AI API scenarios as concurrent users increase. The backend delay was configured to 10 ms for these tests. -![Line chart of average response time in milliseconds versus concurrent users at 100, 500, and 1000 users, comparing AI API Auth No Guardrails, AI API PII Masking, and AI API Advanced Guardrails on a two-CPU gateway runtime](../../../assets/img/ai-gateway/performance/two-core-average-response-time-vs-concurrent-users.svg){ width="900" } +![Line chart of average response time in milliseconds versus concurrent users at 100, 500, and 1000 users, comparing AI API Auth No Guardrails, AI API PII Masking, and AI API Advanced Guardrails on a two-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/two-core-average-response-time-vs-concurrent-users.svg){ width="900" } **Key observations:** @@ -48,7 +48,7 @@ The graph below shows how average response time changes for the same AI API scen The graphs below show the 90th, 95th, and 99th percentile response times at 10 ms backend delay. Percentile values indicate the response time below which that percentage of requests completed, for example, the 99th percentile is the response time exceeded by only 1% of requests. -![Line chart of 90th, 95th, and 99th percentile response times in milliseconds versus concurrent users for AI API Auth No Guardrails on a two-CPU gateway runtime](../../../assets/img/ai-gateway/performance/2-core-Percentile-Response-Times-ai-api.svg){ width="900" } +![Line chart of 90th, 95th, and 99th percentile response times in milliseconds versus concurrent users for AI API Auth No Guardrails on a two-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/2-core-Percentile-Response-Times-ai-api.svg){ width="900" } **Key observations:** @@ -56,14 +56,14 @@ The graphs below show the 90th, 95th, and 99th percentile response times at 10 m - Higher concurrency widens the spread between lower and upper percentiles. - Because this scenario uses API key authentication without content guardrails, percentile growth mainly reflects gateway load and the backend delay. -![Line chart of 90th, 95th, and 99th percentile response times in milliseconds versus concurrent users for AI API PII Masking on a two-CPU gateway runtime](../../../assets/img/ai-gateway/performance/2-core-Percentile-Response-AI-api-pii-masking.svg){ width="900" } +![Line chart of 90th, 95th, and 99th percentile response times in milliseconds versus concurrent users for AI API PII Masking on a two-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/2-core-Percentile-Response-AI-api-pii-masking.svg){ width="900" } **Key observations:** - Percentile trends follow the same upward pattern as concurrent users increase across the test range. - Compared with Auth No Guardrails, percentile values sit higher at each concurrency level because of message inspection and masking. -![Line chart of 90th, 95th, and 99th percentile response times in milliseconds versus concurrent users for AI API Advanced Guardrails on a two-CPU gateway runtime](../../../assets/img/ai-gateway/performance/2-core-Percentile-Response-Times-ai-api-advanced.svg){ width="900" } +![Line chart of 90th, 95th, and 99th percentile response times in milliseconds versus concurrent users for AI API Advanced Guardrails on a two-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/2-core-Percentile-Response-Times-ai-api-advanced.svg){ width="900" } **Key observations:** diff --git a/en/docs/ai-gateway/next/performance/overview.md b/en/docs/ai-gateway/next/run-the-gateway/sizing-and-performance/overview.md similarity index 92% rename from en/docs/ai-gateway/next/performance/overview.md rename to en/docs/ai-gateway/next/run-the-gateway/sizing-and-performance/overview.md index 481ee0c6d..9ff0616b3 100644 --- a/en/docs/ai-gateway/next/performance/overview.md +++ b/en/docs/ai-gateway/next/run-the-gateway/sizing-and-performance/overview.md @@ -1,15 +1,15 @@ --- title: "API Platform AI Gateway Performance" description: "Review WSO2 API Platform AI Gateway performance test methodology, deployment architecture, metrics, and benchmark results for two-CPU and four-CPU gateway runtime configurations." -canonical_url: https://wso2.com/api-platform/docs/ai-gateway/performance/overview/ -md_url: https://wso2.com/api-platform/docs/ai-gateway/performance/overview.md +canonical_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/sizing-and-performance/overview/ +md_url: https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/sizing-and-performance/overview.md tags: - ai-gateway - performance - benchmarks - guardrails author: WSO2 API Platform Documentation Team -last_updated: 2026-07-15 +last_updated: 2026-08-11 content_type: "overview" --- @@ -34,7 +34,7 @@ The following key metrics were used to evaluate AI Gateway performance: The diagram below shows the deployment architecture used for the performance tests documented here. -![Performance test deployment architecture showing Apache JMeter client and servers, Netty HTTP backend, and WSO2 API Platform AI Gateway on separate EC2 instances connected in a test topology](../../../assets/img/ai-gateway/performance/deployment-used-for-test.png){ width="900" } +![Performance test deployment architecture showing Apache JMeter client and servers, Netty HTTP backend, and WSO2 API Platform AI Gateway on separate EC2 instances connected in a test topology](../../../../assets/img/ai-gateway/performance/deployment-used-for-test.png){ width="900" } | Component | EC2 Instance Type | vCPU | Memory (GiB) | | ---------------------------- | ----------------- | :--: | :----------: | diff --git a/en/docs/ai-workspace/1.0.0/policies/overview.md b/en/docs/ai-workspace/1.0.0/policies/overview.md index 1da4d913c..aace0b5d7 100644 --- a/en/docs/ai-workspace/1.0.0/policies/overview.md +++ b/en/docs/ai-workspace/1.0.0/policies/overview.md @@ -88,7 +88,7 @@ These policies shape how requests are routed and composed: ### Provider transformation policies -These policies translate an OpenAI Chat Completions request into another provider's API shape, and translate the response back. Pair them with the [LLM header router](https://wso2.com/api-platform/policy-hub/policies/llm-header-router) to route one endpoint across several providers. Use one on its own to point a single OpenAI-shaped endpoint at a different provider. For an end-to-end example configured on the gateway, see [Multi-provider routing](../../../ai-gateway/next/llm-proxy/multi-provider-routing.md). +These policies translate an OpenAI Chat Completions request into another provider's API shape, and translate the response back. Pair them with the [LLM header router](https://wso2.com/api-platform/policy-hub/policies/llm-header-router) to route one endpoint across several providers. Use one on its own to point a single OpenAI-shaped endpoint at a different provider. For an end-to-end example configured on the gateway, see [Multi-provider routing](../../../ai-gateway/next/expose-llms/multi-provider-routing.md). | Policy | Target provider | |--------|-----------------| diff --git a/en/docs/ai-workspace/next/policies/overview.md b/en/docs/ai-workspace/next/policies/overview.md index ea71300de..6df4f6567 100644 --- a/en/docs/ai-workspace/next/policies/overview.md +++ b/en/docs/ai-workspace/next/policies/overview.md @@ -88,7 +88,7 @@ These policies shape how requests are routed and composed: ### Provider transformation policies -These policies translate an OpenAI Chat Completions request into another provider's API shape, and translate the response back. Pair them with the [LLM header router](https://wso2.com/api-platform/policy-hub/policies/llm-header-router) to route one endpoint across several providers, or use one on its own to point a single OpenAI-shaped endpoint at a different provider. For an end-to-end example configured on the gateway, see [Multi-provider routing](../../../ai-gateway/next/llm-proxy/multi-provider-routing.md). +These policies translate an OpenAI Chat Completions request into another provider's API shape, and translate the response back. Pair them with the [LLM header router](https://wso2.com/api-platform/policy-hub/policies/llm-header-router) to route one endpoint across several providers, or use one on its own to point a single OpenAI-shaped endpoint at a different provider. For an end-to-end example configured on the gateway, see [Multi-provider routing](../../../ai-gateway/next/expose-llms/multi-provider-routing.md). | Policy | Target provider | |--------|-----------------| diff --git a/en/docs/ai-workspace/next/sync-gateway-created-artifacts.md b/en/docs/ai-workspace/next/sync-gateway-created-artifacts.md index f3d942a29..bb2f3948b 100644 --- a/en/docs/ai-workspace/next/sync-gateway-created-artifacts.md +++ b/en/docs/ai-workspace/next/sync-gateway-created-artifacts.md @@ -306,7 +306,7 @@ You can create artifacts on a gateway while it's disconnected, and they reconcil ## Immutable gateways -Some gateways run in **immutable** mode, where artifacts are loaded from on-disk configuration at startup rather than created through the management API (see [Immutable Gateway](../../ai-gateway/next/deployment/deployment-modes/immutable-gateway.md)). +Some gateways run in **immutable** mode, where artifacts are loaded from on-disk configuration at startup rather than created through the management API (see [Immutable Gateway](../../ai-gateway/next/run-the-gateway/immutable-gateway.md)). The sync behaves exactly the same for these gateways: artifacts loaded from files are synced up to AI Workspace just like ones created through the management API, with the same read-only copies and the same automatic reconciliation — no extra configuration. An immutable, file-driven gateway is still fully visible in AI Workspace. diff --git a/en/docs/llms.txt b/en/docs/llms.txt index 1af47f9de..e3f705034 100644 --- a/en/docs/llms.txt +++ b/en/docs/llms.txt @@ -310,43 +310,43 @@ - [AI Gateway Overview](https://wso2.com/api-platform/docs/ai-gateway/overview.md): Overview of the standalone AI Gateway: LLM proxy, MCP proxy, deployment, and observability - [AI Gateway Quick Start](https://wso2.com/api-platform/docs/ai-gateway/quick-start-guide.md): Deploy the standalone AI Gateway and route your first LLM request -- [LLM Provider Templates](https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/llm-templates.md): Provider templates for OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, Gemini, and Azure AI Foundry -- [Semantic Caching](https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/semantic-caching.md): Cache LLM responses by semantic similarity in the standalone gateway -- [Model Round Robin](https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/load-balancing/model-round-robin.md): Distribute LLM traffic evenly across multiple providers or model endpoints -- [Model Weighted Round Robin](https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/load-balancing/model-weighted-round-robin.md): Distribute LLM traffic across providers with configurable traffic weights -- [Prompt Decorator](https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/prompt-management/prompt-decorator.md): Prepend or append system-level instructions to every LLM request at the gateway level -- [Prompt Template](https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/prompt-management/prompt-template.md): Replace 'template://' URI references in LLM request payloads with predefined, parameterized prompt templates -- [AWS Bedrock Guardrail](https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/aws-bedrock-guardrail.md): AWS Bedrock Guardrail for enterprise-grade content filtering, topic detection, and PII protection -- [Azure Content Safety](https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/azure-content-safety.md): Azure Content Safety integration for detecting hate speech, sexual content, violence, and self-harm -- [Content Length Guardrail](https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/content-length.md): Enforce byte-length limits on LLM inputs and outputs -- [JSON Schema Guardrail](https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/json-schema.md): Validate LLM request and response body content against a JSON schema definition to enforce structured data formats -- [PII Masking Regex Guardrail](https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/pii-masking-regex.md): Mask personally identifiable information using configurable regex patterns -- [Regex Guardrail](https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/regex.md): Block or allow content matching a regular expression pattern -- [Semantic Prompt Guard](https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/semantic-prompt-guard.md): Block semantically similar prompts using embedding-based similarity matching against allow/deny phrase lists -- [Sentence Count Guardrail](https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/sentence-count.md): Enforce min/max sentence count on LLM inputs and outputs -- [URL Guardrail](https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/url.md): Validate and block URLs in LLM prompts or completions -- [Word Count Guardrail](https://wso2.com/api-platform/docs/ai-gateway/llm-proxy/guardrails/word-count.md): Enforce min/max word count on LLM inputs and outputs -- [MCP Proxy Quick Start](https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/quick-start-guide.md): Set up a standalone MCP proxy and invoke it through an MCP client -- [MCP Access Control List](https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/policies/mcp-acl-list.md): Control access to MCP tools, resources, and prompts using allow or deny mode with exceptions -- [MCP Authentication](https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/policies/mcp-authentication.md): Enforce authentication on inbound MCP traffic -- [MCP Authorization](https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/policies/mcp-authorization.md): Define fine-grained access control rules for MCP tools, resources, and prompts based on JWT claims and scopes -- [MCP Rewrite](https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/policies/mcp-rewrite.md): Expose user-facing names for MCP tools, resources, and prompts while mapping them to different backend capability names -- [AI Gateway Immutable Deployment](https://wso2.com/api-platform/docs/ai-gateway/deployment/deployment-modes/immutable-gateway.md): Run the standalone AI Gateway in immutable mode, loading all configuration from files at startup -- [AI Gateway Kubernetes Overview](https://wso2.com/api-platform/docs/ai-gateway/deployment/deployment-modes/kubernetes/overview.md): Overview of Kubernetes deployment for the standalone AI Gateway -- [AI Gateway Kubernetes Standalone](https://wso2.com/api-platform/docs/ai-gateway/deployment/deployment-modes/kubernetes/kubernetes-standalone.md): Deploy the standalone AI Gateway on Kubernetes without an operator -- [AI Gateway Kubernetes Operator](https://wso2.com/api-platform/docs/ai-gateway/deployment/deployment-modes/kubernetes/gateway-operator.md): Deploy the standalone AI Gateway using the Kubernetes operator -- [AI Gateway Production Deployment Overview](https://wso2.com/api-platform/docs/ai-gateway/deployment/production-deployment/overview.md): Plan a high-availability production deployment of the standalone AI Gateway on Kubernetes with Helm, an external database, and replicated controller and runtime workloads -- [AI Gateway Security Hardening](https://wso2.com/api-platform/docs/ai-gateway/deployment/production-deployment/security-hardening.md): Harden the AI Gateway for production with AES-256 at-rest encryption keys, TLS for the listener and upstreams, and authentication on the management API -- [AI Gateway Database Configuration](https://wso2.com/api-platform/docs/ai-gateway/deployment/production-deployment/database-configuration.md): Point AI Gateway controller replicas at a shared PostgreSQL or SQL Server database, inject the password from a Secret, and tune the connection pool and EventHub -- [AI Gateway Resources and Scaling](https://wso2.com/api-platform/docs/ai-gateway/deployment/production-deployment/resources-and-scaling.md): Size CPU and memory for the AI Gateway controller and runtime, spread replicas with anti-affinity, and configure the Horizontal Pod Autoscaler and Pod Disruption Budget -- [Tune the AI Gateway for AI Traffic](https://wso2.com/api-platform/docs/ai-gateway/deployment/production-deployment/ai-workload-tuning.md): Production tuning for LLM and MCP workloads: streaming timeouts, large body buffers, guardrail execution limits, token cost pricing data, and semantic cache infrastructure -- [AI Gateway Deploy and Verify](https://wso2.com/api-platform/docs/ai-gateway/deployment/production-deployment/deploy-and-verify.md): Install the AI Gateway Helm chart, confirm the controller and runtime are healthy, route a live LLM request, and run upgrades and rollbacks -- [Connect an AI Gateway to AI Workspace](https://wso2.com/api-platform/docs/ai-gateway/deployment/production-deployment/control-plane-connection.md): Register a production AI Gateway with AI Workspace: the registration token as a Kubernetes Secret, the control plane address, TLS trust, and sync behavior -- [AI Gateway Logging](https://wso2.com/api-platform/docs/ai-gateway/observability/logging.md): Configure structured logging for the standalone AI Gateway -- [AI Gateway Tracing](https://wso2.com/api-platform/docs/ai-gateway/observability/tracing.md): Configure distributed tracing for the standalone AI Gateway -- [AI Gateway Moesif Analytics](https://wso2.com/api-platform/docs/ai-gateway/analytics/moesif-analytics.md): Integrate the standalone AI Gateway with Moesif for LLM usage analytics and cost tracking -- [AI Gateway Analytics Header Filter](https://wso2.com/api-platform/docs/ai-gateway/analytics/analytics-header-filter.md): Control which request and response headers are sent to analytics backends using allow or deny mode -- [AI Gateway Controller Authentication](https://wso2.com/api-platform/docs/ai-gateway/ai-gateway-rest-api/authentication.md): Configure Basic Auth or JWT/IDP authentication and role-based authorization for the AI Gateway Controller REST API +- [LLM Provider Templates](https://wso2.com/api-platform/docs/ai-gateway/connect-llm-providers/llm-templates.md): Provider templates for OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, Gemini, and Azure AI Foundry +- [Semantic Caching](https://wso2.com/api-platform/docs/ai-gateway/control-cost-and-traffic/semantic-caching.md): Cache LLM responses by semantic similarity in the standalone gateway +- [Model Round Robin](https://wso2.com/api-platform/docs/ai-gateway/control-cost-and-traffic/model-round-robin.md): Distribute LLM traffic evenly across multiple providers or model endpoints +- [Model Weighted Round Robin](https://wso2.com/api-platform/docs/ai-gateway/control-cost-and-traffic/model-weighted-round-robin.md): Distribute LLM traffic across providers with configurable traffic weights +- [Prompt Decorator](https://wso2.com/api-platform/docs/ai-gateway/control-content/prompt-decorator.md): Prepend or append system-level instructions to every LLM request at the gateway level +- [Prompt Template](https://wso2.com/api-platform/docs/ai-gateway/control-content/prompt-template.md): Replace 'template://' URI references in LLM request payloads with predefined, parameterized prompt templates +- [AWS Bedrock Guardrail](https://wso2.com/api-platform/docs/ai-gateway/control-content/aws-bedrock-guardrail.md): AWS Bedrock Guardrail for enterprise-grade content filtering, topic detection, and PII protection +- [Azure Content Safety](https://wso2.com/api-platform/docs/ai-gateway/control-content/azure-content-safety.md): Azure Content Safety integration for detecting hate speech, sexual content, violence, and self-harm +- [Content Length Guardrail](https://wso2.com/api-platform/docs/ai-gateway/control-content/content-length.md): Enforce byte-length limits on LLM inputs and outputs +- [JSON Schema Guardrail](https://wso2.com/api-platform/docs/ai-gateway/control-content/json-schema.md): Validate LLM request and response body content against a JSON schema definition to enforce structured data formats +- [PII Masking Regex Guardrail](https://wso2.com/api-platform/docs/ai-gateway/control-content/pii-masking-regex.md): Mask personally identifiable information using configurable regex patterns +- [Regex Guardrail](https://wso2.com/api-platform/docs/ai-gateway/control-content/regex.md): Block or allow content matching a regular expression pattern +- [Semantic Prompt Guard](https://wso2.com/api-platform/docs/ai-gateway/control-content/semantic-prompt-guard.md): Block semantically similar prompts using embedding-based similarity matching against allow/deny phrase lists +- [Sentence Count Guardrail](https://wso2.com/api-platform/docs/ai-gateway/control-content/sentence-count.md): Enforce min/max sentence count on LLM inputs and outputs +- [URL Guardrail](https://wso2.com/api-platform/docs/ai-gateway/control-content/url.md): Validate and block URLs in LLM prompts or completions +- [Word Count Guardrail](https://wso2.com/api-platform/docs/ai-gateway/control-content/word-count.md): Enforce min/max word count on LLM inputs and outputs +- [MCP Proxy Quick Start](https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/create-an-mcp-proxy.md): Set up a standalone MCP proxy and invoke it through an MCP client +- [MCP Access Control List](https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/mcp-acl-list.md): Control access to MCP tools, resources, and prompts using allow or deny mode with exceptions +- [MCP Authentication](https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/mcp-authentication.md): Enforce authentication on inbound MCP traffic +- [MCP Authorization](https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/mcp-authorization.md): Define fine-grained access control rules for MCP tools, resources, and prompts based on JWT claims and scopes +- [MCP Rewrite](https://wso2.com/api-platform/docs/ai-gateway/mcp-proxy/mcp-rewrite.md): Expose user-facing names for MCP tools, resources, and prompts while mapping them to different backend capability names +- [AI Gateway Immutable Deployment](https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/immutable-gateway.md): Run the standalone AI Gateway in immutable mode, loading all configuration from files at startup +- [AI Gateway Kubernetes Overview](https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/kubernetes/overview.md): Overview of Kubernetes deployment for the standalone AI Gateway +- [AI Gateway Kubernetes Standalone](https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/kubernetes/kubernetes-standalone.md): Deploy the standalone AI Gateway on Kubernetes without an operator +- [AI Gateway Kubernetes Operator](https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/kubernetes/gateway-operator.md): Deploy the standalone AI Gateway using the Kubernetes operator +- [AI Gateway Production Deployment Overview](https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/production-deployment/overview.md): Plan a high-availability production deployment of the standalone AI Gateway on Kubernetes with Helm, an external database, and replicated controller and runtime workloads +- [AI Gateway Security Hardening](https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/production-deployment/security-hardening.md): Harden the AI Gateway for production with AES-256 at-rest encryption keys, TLS for the listener and upstreams, and authentication on the management API +- [AI Gateway Database Configuration](https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/production-deployment/database-configuration.md): Point AI Gateway controller replicas at a shared PostgreSQL or SQL Server database, inject the password from a Secret, and tune the connection pool and EventHub +- [AI Gateway Resources and Scaling](https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/production-deployment/resources-and-scaling.md): Size CPU and memory for the AI Gateway controller and runtime, spread replicas with anti-affinity, and configure the Horizontal Pod Autoscaler and Pod Disruption Budget +- [Tune the AI Gateway for AI Traffic](https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/production-deployment/ai-workload-tuning.md): Production tuning for LLM and MCP workloads: streaming timeouts, large body buffers, guardrail execution limits, token cost pricing data, and semantic cache infrastructure +- [AI Gateway Deploy and Verify](https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/production-deployment/deploy-and-verify.md): Install the AI Gateway Helm chart, confirm the controller and runtime are healthy, route a live LLM request, and run upgrades and rollbacks +- [Connect an AI Gateway to AI Workspace](https://wso2.com/api-platform/docs/ai-gateway/run-the-gateway/production-deployment/control-plane-connection.md): Register a production AI Gateway with AI Workspace: the registration token as a Kubernetes Secret, the control plane address, TLS trust, and sync behavior +- [AI Gateway Logging](https://wso2.com/api-platform/docs/ai-gateway/monitor-traffic/logging.md): Configure structured logging for the standalone AI Gateway +- [AI Gateway Tracing](https://wso2.com/api-platform/docs/ai-gateway/monitor-traffic/tracing.md): Configure distributed tracing for the standalone AI Gateway +- [AI Gateway Moesif Analytics](https://wso2.com/api-platform/docs/ai-gateway/monitor-traffic/moesif-analytics.md): Integrate the standalone AI Gateway with Moesif for LLM usage analytics and cost tracking +- [AI Gateway Analytics Header Filter](https://wso2.com/api-platform/docs/ai-gateway/monitor-traffic/analytics-header-filter.md): Control which request and response headers are sent to analytics backends using allow or deny mode +- [AI Gateway Controller Authentication](https://wso2.com/api-platform/docs/ai-gateway/control-access/secure-the-management-api.md): Configure Basic Auth or JWT/IDP authentication and role-based authorization for the AI Gateway Controller REST API ## Policy Hub diff --git a/en/docs/next/index.md b/en/docs/next/index.md index 34d15dba7..d54bdbb7b 100644 --- a/en/docs/next/index.md +++ b/en/docs/next/index.md @@ -159,8 +159,8 @@ The following is a complete view of all components and where to find their docum | Run everything on my own infrastructure with a UI | [API Manager](../api-manager/overview.md) | | Run a lightweight API gateway with no UI | [API Gateway](../api-gateway/next/overview.md) | | Govern LLM traffic (rate limits, guardrails, cost control) | [AI Gateway Quick Start Guide](../ai-gateway/next/quick-start-guide.md) | -| Expose my APIs as MCP tools for AI agents | [AI Gateway MCP Proxy](../ai-gateway/next/mcp-proxy/quick-start-guide.md) | -| Govern MCP traffic (inbound + outbound) | [AI Gateway MCP Proxy](../ai-gateway/next/mcp-proxy/quick-start-guide.md) | +| Expose my APIs as MCP tools for AI agents | [AI Gateway MCP Proxy](../ai-gateway/next/mcp-proxy/create-an-mcp-proxy.md) | +| Govern MCP traffic (inbound + outbound) | [AI Gateway MCP Proxy](../ai-gateway/next/mcp-proxy/create-an-mcp-proxy.md) | | Manage LLM providers and AI policies at the organizational level | [AI Workspace](../ai-workspace/next/overview.md) | | Set up an API Portal & MCP Hub for API discovery | [API Portal](api-portal/overview.md) | | Monitor traffic and monetize my APIs | [Analytics](../analytics/overview.md) and [Monetization](../monetization/overview.md) | diff --git a/en/mkdocs.yml b/en/mkdocs.yml index ea1d711db..936b54a5a 100644 --- a/en/mkdocs.yml +++ b/en/mkdocs.yml @@ -615,77 +615,89 @@ nav: - "next": - Overview: ai-gateway/next/overview.md - Quick Start Guide: ai-gateway/next/quick-start-guide.md - - Setup: - - Configuration & Interpolation: ai-gateway/next/setup/configuration.md - - Setting Up the Database: ai-gateway/next/setup/database-setup.md - - LLM Proxy: - - LLM Provider Templates: ai-gateway/next/llm-proxy/llm-templates.md - - Multi-Provider Routing: ai-gateway/next/llm-proxy/multi-provider-routing.md - - Guardrails: - - Overview: ai-gateway/next/llm-proxy/guardrails/overview.md - - Guardrail execution order: ai-gateway/next/llm-proxy/guardrails/execution-order.md - - AWS Bedrock Guardrail: ai-gateway/next/llm-proxy/guardrails/aws-bedrock-guardrail.md - - Azure Content Safety: ai-gateway/next/llm-proxy/guardrails/azure-content-safety.md - - Content Length Guardrail: ai-gateway/next/llm-proxy/guardrails/content-length.md - - JSON Schema Guardrail: ai-gateway/next/llm-proxy/guardrails/json-schema.md - - PII Masking Regex Guardrail: ai-gateway/next/llm-proxy/guardrails/pii-masking-regex.md - - Regex Guardrail: ai-gateway/next/llm-proxy/guardrails/regex.md - - Semantic Prompt Guardrail: ai-gateway/next/llm-proxy/guardrails/semantic-prompt-guard.md - - Sentence Count Guardrail: ai-gateway/next/llm-proxy/guardrails/sentence-count.md - - URL Guardrail: ai-gateway/next/llm-proxy/guardrails/url.md - - Word Count Guardrail: ai-gateway/next/llm-proxy/guardrails/word-count.md - - Load Balancing: - - Model Round Robin: ai-gateway/next/llm-proxy/load-balancing/model-round-robin.md - - Model Weighted Round Robin: ai-gateway/next/llm-proxy/load-balancing/model-weighted-round-robin.md - - Prompt Management: - - Prompt Decorator: ai-gateway/next/llm-proxy/prompt-management/prompt-decorator.md - - Prompt Template: ai-gateway/next/llm-proxy/prompt-management/prompt-template.md - - Semantic Caching: ai-gateway/next/llm-proxy/semantic-caching.md - - MCP Proxy: - - Quick Start Guide: ai-gateway/next/mcp-proxy/quick-start-guide.md - - Policies: - - MCP Access Control List: ai-gateway/next/mcp-proxy/policies/mcp-acl-list.md - - MCP Authentication: ai-gateway/next/mcp-proxy/policies/mcp-authentication.md - - MCP Authorization: ai-gateway/next/mcp-proxy/policies/mcp-authorization.md - - MCP Rewrite: ai-gateway/next/mcp-proxy/policies/mcp-rewrite.md - - Real-Time AI Streaming: ai-gateway/next/streaming-responses.md - - Deployment: - - Deployment Modes: - - Immutable Gateway: ai-gateway/next/deployment/deployment-modes/immutable-gateway.md + - Run the Gateway: - Kubernetes: - - Overview: ai-gateway/next/deployment/deployment-modes/kubernetes/overview.md - - Standalone Mode: ai-gateway/next/deployment/deployment-modes/kubernetes/kubernetes-standalone.md - - Kubernetes Operator Mode: ai-gateway/next/deployment/deployment-modes/kubernetes/gateway-operator.md - - Production Deployment: - - Overview: ai-gateway/next/deployment/production-deployment/overview.md - - Security Hardening: ai-gateway/next/deployment/production-deployment/security-hardening.md - - Database Configuration: ai-gateway/next/deployment/production-deployment/database-configuration.md - - Resources & Scaling: ai-gateway/next/deployment/production-deployment/resources-and-scaling.md - - Tune for AI Traffic: ai-gateway/next/deployment/production-deployment/ai-workload-tuning.md - - Deploy & Verify: ai-gateway/next/deployment/production-deployment/deploy-and-verify.md - - Connect to AI Workspace: ai-gateway/next/deployment/production-deployment/control-plane-connection.md - - Resiliency: - - Timeouts: ai-gateway/next/resiliency/timeouts.md - - Observability: - - Logging: ai-gateway/next/observability/logging.md - - Tracing: ai-gateway/next/observability/tracing.md - - Analytics: - - Moesif Analytics: ai-gateway/next/analytics/moesif-analytics.md - - Analytics Header Filter: ai-gateway/next/analytics/analytics-header-filter.md - - Performance: - - Overview: ai-gateway/next/performance/overview.md - - AI Gateway runtime with two CPUs: ai-gateway/next/performance/ai-gateway-runtime-with-two-cpus.md - - AI Gateway runtime with four CPUs: ai-gateway/next/performance/ai-gateway-runtime-with-four-cpus.md - - Management API: - - Overview: ai-gateway/next/gateway-controller-management-api/overview.md - - Secure the Management API: ai-gateway/next/gateway-controller-management-api/authentication.md - - LLM Provider Template Management: ai-gateway/next/gateway-controller-management-api/llm-provider-template-management.md - - LLM Provider Management: ai-gateway/next/gateway-controller-management-api/llm-provider-management.md - - LLM Proxy Management: ai-gateway/next/gateway-controller-management-api/llm-proxy-management.md - - MCP Proxy Management: ai-gateway/next/gateway-controller-management-api/mcp-proxy-management.md - - Certificate Management: ai-gateway/next/gateway-controller-management-api/certificate-management.md - - Secrets Management: ai-gateway/next/gateway-controller-management-api/secrets-management.md - - Schemas: ai-gateway/next/gateway-controller-management-api/schemas.md + - Overview: ai-gateway/next/run-the-gateway/kubernetes/overview.md + - Standalone Mode: ai-gateway/next/run-the-gateway/kubernetes/kubernetes-standalone.md + - Kubernetes Operator Mode: ai-gateway/next/run-the-gateway/kubernetes/gateway-operator.md + - Immutable Gateway: ai-gateway/next/run-the-gateway/immutable-gateway.md + - Configuration & Interpolation: ai-gateway/next/run-the-gateway/configuration.md + - Database: ai-gateway/next/run-the-gateway/database-setup.md + - Production Deployment: + - Overview: ai-gateway/next/run-the-gateway/production-deployment/overview.md + - Security Hardening: ai-gateway/next/run-the-gateway/production-deployment/security-hardening.md + - Database Configuration: ai-gateway/next/run-the-gateway/production-deployment/database-configuration.md + - Resources & Scaling: ai-gateway/next/run-the-gateway/production-deployment/resources-and-scaling.md + - Tune for AI Traffic: ai-gateway/next/run-the-gateway/production-deployment/ai-workload-tuning.md + - Deploy & Verify: ai-gateway/next/run-the-gateway/production-deployment/deploy-and-verify.md + - Connect to AI Workspace: ai-gateway/next/run-the-gateway/production-deployment/control-plane-connection.md + - Sizing & Performance: + - Overview: ai-gateway/next/run-the-gateway/sizing-and-performance/overview.md + - AI Gateway runtime with two CPUs: ai-gateway/next/run-the-gateway/sizing-and-performance/ai-gateway-runtime-with-two-cpus.md + - AI Gateway runtime with four CPUs: ai-gateway/next/run-the-gateway/sizing-and-performance/ai-gateway-runtime-with-four-cpus.md + - Connect LLM Providers: + - Provider Templates: ai-gateway/next/connect-llm-providers/llm-templates.md + - Configure an AWS Bedrock LLM Provider: ai-gateway/next/connect-llm-providers/configure-aws-bedrock-provider.md + - Expose LLMs to Applications: + - Route Across Multiple Providers: ai-gateway/next/expose-llms/multi-provider-routing.md + - Stream Responses: ai-gateway/next/expose-llms/streaming-responses.md + - MCP Proxy: + - Create an MCP Proxy: ai-gateway/next/mcp-proxy/create-an-mcp-proxy.md + - Rewrite Tool Definitions: ai-gateway/next/mcp-proxy/mcp-rewrite.md + - MCP Authentication: ai-gateway/next/mcp-proxy/mcp-authentication.md + - MCP Authorization: ai-gateway/next/mcp-proxy/mcp-authorization.md + - MCP Access Control Lists: ai-gateway/next/mcp-proxy/mcp-acl-list.md + - Control Access: + - Secure the Management API: ai-gateway/next/control-access/secure-the-management-api.md + - Control Content: + - Guardrails Overview: ai-gateway/next/control-content/overview.md + - Guardrail execution order: ai-gateway/next/control-content/execution-order.md + - Regex Guardrail: ai-gateway/next/control-content/regex.md + - JSON Schema Guardrail: ai-gateway/next/control-content/json-schema.md + - Word Count Guardrail: ai-gateway/next/control-content/word-count.md + - Sentence Count Guardrail: ai-gateway/next/control-content/sentence-count.md + - Content Length Guardrail: ai-gateway/next/control-content/content-length.md + - URL Guardrail: ai-gateway/next/control-content/url.md + - PII Masking Regex Guardrail: ai-gateway/next/control-content/pii-masking-regex.md + - Semantic Prompt Guardrail: ai-gateway/next/control-content/semantic-prompt-guard.md + - Azure Content Safety: ai-gateway/next/control-content/azure-content-safety.md + - AWS Bedrock Guardrail: ai-gateway/next/control-content/aws-bedrock-guardrail.md + - Prompt Decorator: ai-gateway/next/control-content/prompt-decorator.md + - Prompt Template: ai-gateway/next/control-content/prompt-template.md + - Control Cost & Traffic: + - Model Round Robin: ai-gateway/next/control-cost-and-traffic/model-round-robin.md + - Model Weighted Round Robin: ai-gateway/next/control-cost-and-traffic/model-weighted-round-robin.md + - Semantic Caching: ai-gateway/next/control-cost-and-traffic/semantic-caching.md + - Timeouts: ai-gateway/next/control-cost-and-traffic/timeouts.md + - Monitor Traffic: + - Logging: ai-gateway/next/monitor-traffic/logging.md + - Tracing: ai-gateway/next/monitor-traffic/tracing.md + - Moesif Analytics: ai-gateway/next/monitor-traffic/moesif-analytics.md + - Analytics Header Filter: ai-gateway/next/monitor-traffic/analytics-header-filter.md + - Extend the Gateway: + - Customizing Gateway Policies: tools/cli/customizing-gateway-policies.md + - Guides: + - Set up a Governed Multi-Model LLM Proxy with Cost Controls and Failover: guides/ai-and-mcp/set-up-a-governed-multi-model-llm-proxy-with-cost-controls-and-failover.md + - Enforce Token-Based Rate Limiting on an LLM Proxy: guides/ai-and-mcp/enforce-token-based-rate-limiting-on-an-llm-proxy.md + - Enforce a Consistent AI Persona with the Prompt Decorator Policy: guides/ai-and-mcp/using-prompt-decorator-policy.md + - Build an AI App with Claude Code that Calls Governed Backend APIs: guides/ai-and-mcp/build-ai-app-with-claude-code.md + - Build an AI Agent That Uses Aggregated MCP Tools from Multiple APIs: guides/ai-and-mcp/build-ai-agent-with-multiple-mcp-servers.md + - Convert a REST API into an MCP Tool and Use It in Claude Desktop: guides/ai-and-mcp/convert-rest-api-to-mcp-server.md + - Find and Connect to an Enterprise MCP Server from the MCP Hub: guides/ai-and-mcp/find-and-connect-to-an-enterprise-mcp-server-from-the-mcp-hub.md + - Configure AI Coding Assistants: + - Configure Claude Code with AI Gateway: guides/ai-and-mcp/ai-coding-assistants/claude-code-configuration-with-ai-gateway.md + - Configure Google Gemini CLI with AI Gateway: guides/ai-and-mcp/ai-coding-assistants/gemini-cli-configuration-with-ai-gateway.md + - Configure OpenAI Codex CLI with AI Gateway: guides/ai-and-mcp/ai-coding-assistants/codex-configuration-with-ai-gateway.md + - Reference: + - Management REST API: + - Overview: ai-gateway/next/reference/management-api/overview.md + - LLM Provider Template Management: ai-gateway/next/reference/management-api/llm-provider-template-management.md + - LLM Provider Management: ai-gateway/next/reference/management-api/llm-provider-management.md + - LLM Proxy Management: ai-gateway/next/reference/management-api/llm-proxy-management.md + - MCP Proxy Management: ai-gateway/next/reference/management-api/mcp-proxy-management.md + - Certificate Management: ai-gateway/next/reference/management-api/certificate-management.md + - Secrets Management: ai-gateway/next/reference/management-api/secrets-management.md + - Schemas: ai-gateway/next/reference/management-api/schemas.md - About this release: ai-gateway/next/about-this-release.md - "1.2.0": - Overview: ai-gateway/1.2.0/overview.md @@ -1237,7 +1249,6 @@ nav: - Set up a Governed Multi-Model LLM Proxy with Cost Controls and Failover: guides/ai-and-mcp/set-up-a-governed-multi-model-llm-proxy-with-cost-controls-and-failover.md - Enforce Token-Based Rate Limiting on an LLM Proxy: guides/ai-and-mcp/enforce-token-based-rate-limiting-on-an-llm-proxy.md - Enforce a Consistent AI Persona with the Prompt Decorator Policy: guides/ai-and-mcp/using-prompt-decorator-policy.md - - Configure an AWS Bedrock LLM Provider: ai-gateway/next/llm-proxy/configure-aws-bedrock-provider.md - AI Coding Assistants: - Configure Claude Code with AI Gateway: guides/ai-and-mcp/ai-coding-assistants/claude-code-configuration-with-ai-gateway.md - Configure Google Gemini CLI with AI Gateway: guides/ai-and-mcp/ai-coding-assistants/gemini-cli-configuration-with-ai-gateway.md @@ -1341,10 +1352,10 @@ plugins: ai-gateway/1.2.0/deployment-modes/kubernetes/gateway-operator.md: ai-gateway/1.2.0/deployment/deployment-modes/kubernetes/gateway-operator.md ai-gateway/1.2.0/deployment-modes/kubernetes/kubernetes-standalone.md: ai-gateway/1.2.0/deployment/deployment-modes/kubernetes/kubernetes-standalone.md ai-gateway/1.2.0/deployment-modes/kubernetes/overview.md: ai-gateway/1.2.0/deployment/deployment-modes/kubernetes/overview.md - ai-gateway/next/deployment-modes/immutable-gateway.md: ai-gateway/next/deployment/deployment-modes/immutable-gateway.md - ai-gateway/next/deployment-modes/kubernetes/gateway-operator.md: ai-gateway/next/deployment/deployment-modes/kubernetes/gateway-operator.md - ai-gateway/next/deployment-modes/kubernetes/kubernetes-standalone.md: ai-gateway/next/deployment/deployment-modes/kubernetes/kubernetes-standalone.md - ai-gateway/next/deployment-modes/kubernetes/overview.md: ai-gateway/next/deployment/deployment-modes/kubernetes/overview.md + ai-gateway/next/deployment-modes/immutable-gateway.md: ai-gateway/next/run-the-gateway/immutable-gateway.md + ai-gateway/next/deployment-modes/kubernetes/gateway-operator.md: ai-gateway/next/run-the-gateway/kubernetes/gateway-operator.md + ai-gateway/next/deployment-modes/kubernetes/kubernetes-standalone.md: ai-gateway/next/run-the-gateway/kubernetes/kubernetes-standalone.md + ai-gateway/next/deployment-modes/kubernetes/overview.md: ai-gateway/next/run-the-gateway/kubernetes/overview.md # AI/API Gateway versioning restructuring (per-product Cloud/Self-Hosted variants) ai-gateway/ai-gateway-rest-api/authentication.md: ai-gateway/1.1.0/ai-gateway-rest-api/authentication.md ai-gateway/analytics/analytics-header-filter.md: ai-gateway/1.1.0/analytics/analytics-header-filter.md @@ -1430,6 +1441,63 @@ plugins: api-gateway/setup/upstream-timeouts.md: api-gateway/1.1.0/setup/upstream-timeouts.md # AI Gateway revamp phase 0: the two quick starts merged into one canonical page ai-gateway/next/llm-proxy/quick-start-guide.md: ai-gateway/next/quick-start-guide.md + # AI Gateway revamp phase 1: job-oriented nav + ai-gateway/next/setup/configuration.md: ai-gateway/next/run-the-gateway/configuration.md + ai-gateway/next/setup/database-setup.md: ai-gateway/next/run-the-gateway/database-setup.md + ai-gateway/next/deployment/deployment-modes/immutable-gateway.md: ai-gateway/next/run-the-gateway/immutable-gateway.md + ai-gateway/next/deployment/deployment-modes/kubernetes/overview.md: ai-gateway/next/run-the-gateway/kubernetes/overview.md + ai-gateway/next/deployment/deployment-modes/kubernetes/kubernetes-standalone.md: ai-gateway/next/run-the-gateway/kubernetes/kubernetes-standalone.md + ai-gateway/next/deployment/deployment-modes/kubernetes/gateway-operator.md: ai-gateway/next/run-the-gateway/kubernetes/gateway-operator.md + ai-gateway/next/deployment/production-deployment/overview.md: ai-gateway/next/run-the-gateway/production-deployment/overview.md + ai-gateway/next/deployment/production-deployment/security-hardening.md: ai-gateway/next/run-the-gateway/production-deployment/security-hardening.md + ai-gateway/next/deployment/production-deployment/database-configuration.md: ai-gateway/next/run-the-gateway/production-deployment/database-configuration.md + ai-gateway/next/deployment/production-deployment/resources-and-scaling.md: ai-gateway/next/run-the-gateway/production-deployment/resources-and-scaling.md + ai-gateway/next/deployment/production-deployment/ai-workload-tuning.md: ai-gateway/next/run-the-gateway/production-deployment/ai-workload-tuning.md + ai-gateway/next/deployment/production-deployment/deploy-and-verify.md: ai-gateway/next/run-the-gateway/production-deployment/deploy-and-verify.md + ai-gateway/next/deployment/production-deployment/control-plane-connection.md: ai-gateway/next/run-the-gateway/production-deployment/control-plane-connection.md + ai-gateway/next/performance/overview.md: ai-gateway/next/run-the-gateway/sizing-and-performance/overview.md + ai-gateway/next/performance/ai-gateway-runtime-with-two-cpus.md: ai-gateway/next/run-the-gateway/sizing-and-performance/ai-gateway-runtime-with-two-cpus.md + ai-gateway/next/performance/ai-gateway-runtime-with-four-cpus.md: ai-gateway/next/run-the-gateway/sizing-and-performance/ai-gateway-runtime-with-four-cpus.md + ai-gateway/next/llm-proxy/llm-templates.md: ai-gateway/next/connect-llm-providers/llm-templates.md + ai-gateway/next/llm-proxy/configure-aws-bedrock-provider.md: ai-gateway/next/connect-llm-providers/configure-aws-bedrock-provider.md + ai-gateway/next/llm-proxy/multi-provider-routing.md: ai-gateway/next/expose-llms/multi-provider-routing.md + ai-gateway/next/streaming-responses.md: ai-gateway/next/expose-llms/streaming-responses.md + ai-gateway/next/mcp-proxy/quick-start-guide.md: ai-gateway/next/mcp-proxy/create-an-mcp-proxy.md + ai-gateway/next/mcp-proxy/policies/mcp-rewrite.md: ai-gateway/next/mcp-proxy/mcp-rewrite.md + ai-gateway/next/mcp-proxy/policies/mcp-authentication.md: ai-gateway/next/mcp-proxy/mcp-authentication.md + ai-gateway/next/mcp-proxy/policies/mcp-authorization.md: ai-gateway/next/mcp-proxy/mcp-authorization.md + ai-gateway/next/mcp-proxy/policies/mcp-acl-list.md: ai-gateway/next/mcp-proxy/mcp-acl-list.md + ai-gateway/next/gateway-controller-management-api/authentication.md: ai-gateway/next/control-access/secure-the-management-api.md + ai-gateway/next/llm-proxy/guardrails/overview.md: ai-gateway/next/control-content/overview.md + ai-gateway/next/llm-proxy/guardrails/execution-order.md: ai-gateway/next/control-content/execution-order.md + ai-gateway/next/llm-proxy/guardrails/regex.md: ai-gateway/next/control-content/regex.md + ai-gateway/next/llm-proxy/guardrails/json-schema.md: ai-gateway/next/control-content/json-schema.md + ai-gateway/next/llm-proxy/guardrails/word-count.md: ai-gateway/next/control-content/word-count.md + ai-gateway/next/llm-proxy/guardrails/sentence-count.md: ai-gateway/next/control-content/sentence-count.md + ai-gateway/next/llm-proxy/guardrails/content-length.md: ai-gateway/next/control-content/content-length.md + ai-gateway/next/llm-proxy/guardrails/url.md: ai-gateway/next/control-content/url.md + ai-gateway/next/llm-proxy/guardrails/pii-masking-regex.md: ai-gateway/next/control-content/pii-masking-regex.md + ai-gateway/next/llm-proxy/guardrails/semantic-prompt-guard.md: ai-gateway/next/control-content/semantic-prompt-guard.md + ai-gateway/next/llm-proxy/guardrails/azure-content-safety.md: ai-gateway/next/control-content/azure-content-safety.md + ai-gateway/next/llm-proxy/guardrails/aws-bedrock-guardrail.md: ai-gateway/next/control-content/aws-bedrock-guardrail.md + ai-gateway/next/llm-proxy/prompt-management/prompt-decorator.md: ai-gateway/next/control-content/prompt-decorator.md + ai-gateway/next/llm-proxy/prompt-management/prompt-template.md: ai-gateway/next/control-content/prompt-template.md + ai-gateway/next/llm-proxy/load-balancing/model-round-robin.md: ai-gateway/next/control-cost-and-traffic/model-round-robin.md + ai-gateway/next/llm-proxy/load-balancing/model-weighted-round-robin.md: ai-gateway/next/control-cost-and-traffic/model-weighted-round-robin.md + ai-gateway/next/llm-proxy/semantic-caching.md: ai-gateway/next/control-cost-and-traffic/semantic-caching.md + ai-gateway/next/resiliency/timeouts.md: ai-gateway/next/control-cost-and-traffic/timeouts.md + ai-gateway/next/observability/logging.md: ai-gateway/next/monitor-traffic/logging.md + ai-gateway/next/observability/tracing.md: ai-gateway/next/monitor-traffic/tracing.md + ai-gateway/next/analytics/moesif-analytics.md: ai-gateway/next/monitor-traffic/moesif-analytics.md + ai-gateway/next/analytics/analytics-header-filter.md: ai-gateway/next/monitor-traffic/analytics-header-filter.md + ai-gateway/next/gateway-controller-management-api/overview.md: ai-gateway/next/reference/management-api/overview.md + ai-gateway/next/gateway-controller-management-api/llm-provider-template-management.md: ai-gateway/next/reference/management-api/llm-provider-template-management.md + ai-gateway/next/gateway-controller-management-api/llm-provider-management.md: ai-gateway/next/reference/management-api/llm-provider-management.md + ai-gateway/next/gateway-controller-management-api/llm-proxy-management.md: ai-gateway/next/reference/management-api/llm-proxy-management.md + ai-gateway/next/gateway-controller-management-api/mcp-proxy-management.md: ai-gateway/next/reference/management-api/mcp-proxy-management.md + ai-gateway/next/gateway-controller-management-api/certificate-management.md: ai-gateway/next/reference/management-api/certificate-management.md + ai-gateway/next/gateway-controller-management-api/secrets-management.md: ai-gateway/next/reference/management-api/secrets-management.md + ai-gateway/next/gateway-controller-management-api/schemas.md: ai-gateway/next/reference/management-api/schemas.md # AI Workspace self-hosted docs moved from next/ai-workspace to the # versioned ai-workspace/ layout; 1.0.0 is the latest release. next/ai-workspace/index.md: ai-workspace/1.0.0/overview.md From ad788809d0246b660073f2ab23dd6ba1047a30a2 Mon Sep 17 00:00:00 2001 From: veejask-41 Date: Tue, 11 Aug 2026 19:36:49 +0530 Subject: [PATCH 2/3] Address code rabbit change reqeusts --- .../ai-gateway/next/control-content/execution-order.md | 4 ++-- .../ai-gateway/next/mcp-proxy/create-an-mcp-proxy.md | 6 +++--- .../next/run-the-gateway/immutable-gateway.md | 2 +- .../ai-gateway-runtime-with-four-cpus.md | 10 +++++----- .../ai-gateway-runtime-with-two-cpus.md | 10 +++++----- .../run-the-gateway/sizing-and-performance/overview.md | 2 +- 6 files changed, 17 insertions(+), 17 deletions(-) diff --git a/en/docs/ai-gateway/next/control-content/execution-order.md b/en/docs/ai-gateway/next/control-content/execution-order.md index 6cb890bee..d3bd0d2e6 100644 --- a/en/docs/ai-gateway/next/control-content/execution-order.md +++ b/en/docs/ai-gateway/next/control-content/execution-order.md @@ -80,7 +80,7 @@ Client The following diagram shows how requests pass through the LLM Proxy chain and LLM Provider chain in sequence, and how responses return through both chains in reverse order: -![Dual-hop guardrail execution diagram showing request flowing through LLM Proxy chain then LLM Provider chain in forward order across request phases, and response flowing in reverse order through LLM Provider chain then LLM Proxy chain back to the client](../../../assets/img/api-gateway/gateway-policy-execution-order-llm-provider-proxy.png) +![Diagram of dual-hop guardrail execution: a request traverses the LLM Proxy chain then the LLM Provider chain, and the response returns in reverse order](../../../assets/img/api-gateway/gateway-policy-execution-order-llm-provider-proxy.png) This mirrors the request wrapping at the chain level: the LLM Proxy wraps the LLM Provider on the way in, so on the way back the inner chain (Provider) unwinds first, then the outer chain (Proxy). @@ -99,7 +99,7 @@ When an LLM returns a streaming response (such as SSE from a chat completion end The following diagram shows how streaming body chunks flow through the policy chain at each hop: -![Streaming policy chain execution order diagram showing request body chunks flowing through the policy chain via OnRequestBodyChunk in forward order, and response chunks flowing in reverse order via OnResponseBodyChunk](../../../assets/img/api-gateway/gateway-policy-execution-order-streaming.png) +![Diagram of streaming policy chain execution order, with request body chunks flowing forward through the chain and response chunks flowing in reverse](../../../assets/img/api-gateway/gateway-policy-execution-order-streaming.png) ## Related topics diff --git a/en/docs/ai-gateway/next/mcp-proxy/create-an-mcp-proxy.md b/en/docs/ai-gateway/next/mcp-proxy/create-an-mcp-proxy.md index 6ca5b1744..9c7ef8781 100644 --- a/en/docs/ai-gateway/next/mcp-proxy/create-an-mcp-proxy.md +++ b/en/docs/ai-gateway/next/mcp-proxy/create-an-mcp-proxy.md @@ -14,9 +14,9 @@ content_type: "quickstart" # Create an MCP proxy -## Quick Start +## Quick start -### Using Docker Compose (Recommended) +### Using Docker Compose (recommended) ### Prerequisites @@ -145,7 +145,7 @@ http://localhost:8080/everything/mcp The gateway syncs the artifacts you deploy on it up to [AI Workspace](../../../ai-workspace/next/overview.md), the control plane for AI traffic across your organization. The `everything-mcp-v1.0` proxy you deployed above appears there without being re-declared, in the `default` project named in its `project-id` annotation. See [Manage Gateway-deployed AI artifacts in AI Workspace](../../../ai-workspace/next/sync-gateway-created-artifacts.md). -## Stopping the Gateway +## Stopping the gateway Stop and remove the MCP backend first. diff --git a/en/docs/ai-gateway/next/run-the-gateway/immutable-gateway.md b/en/docs/ai-gateway/next/run-the-gateway/immutable-gateway.md index 5f02265c5..bc7e8d3de 100644 --- a/en/docs/ai-gateway/next/run-the-gateway/immutable-gateway.md +++ b/en/docs/ai-gateway/next/run-the-gateway/immutable-gateway.md @@ -79,7 +79,7 @@ Artifact files support Go template expressions for injecting dynamic values. Tem | `{{ env "KEY" | redact }}` | Yes | Sensitive env vars (tokens, API keys) | {% endraw %} -Use `| redact` for sensitive values to hide them from config dumps. A `| default "value"` pipe is available for fallback values. See [Gateway Artifact Templating](../../../api-gateway/1.1.0/setup/artifact-templating.md) for the full function reference. +Use `| redact` for sensitive values to hide them from config dumps. A `| default "value"` pipe is available for fallback values. See [Gateway Artifact Templating](../../../api-gateway/next/setup/artifact-templating.md) for the full function reference. ### Sample: Reading List API diff --git a/en/docs/ai-gateway/next/run-the-gateway/sizing-and-performance/ai-gateway-runtime-with-four-cpus.md b/en/docs/ai-gateway/next/run-the-gateway/sizing-and-performance/ai-gateway-runtime-with-four-cpus.md index 4b818019e..7cab6a9b4 100644 --- a/en/docs/ai-gateway/next/run-the-gateway/sizing-and-performance/ai-gateway-runtime-with-four-cpus.md +++ b/en/docs/ai-gateway/next/run-the-gateway/sizing-and-performance/ai-gateway-runtime-with-four-cpus.md @@ -26,7 +26,7 @@ The table below displays the resource allocations for the AI Gateway components The graph below shows how AI Gateway throughput changes as concurrent users increase for AI API Auth No Guardrails, AI API PII Masking, and AI API Advanced Guardrails. -![Line chart of AI Gateway throughput in requests per second versus concurrent users at 100, 500, 800, and 1000 users, comparing AI API Auth No Guardrails, AI API PII Masking, and AI API Advanced Guardrails on a four-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/four-core-Throughput-vs-Concurrent-Users.svg){ width="900" } +![Line chart of AI Gateway throughput in requests per second versus concurrent users on a four-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/four-core-Throughput-vs-Concurrent-Users.svg){ width="900" } **Key observations:** @@ -38,7 +38,7 @@ The graph below shows how AI Gateway throughput changes as concurrent users incr The graph below shows how average response time changes for the same AI API scenarios as concurrent users increase. The backend delay was configured to 10 ms for these tests. -![Line chart of average response time in milliseconds versus concurrent users at 100, 500, 800, and 1000 users, comparing AI API Auth No Guardrails, AI API PII Masking, and AI API Advanced Guardrails on a four-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/four-core-Average-Response-Time-vs-Concurrent-Users.svg){ width="900" } +![Line chart of average response time in milliseconds versus concurrent users on a four-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/four-core-Average-Response-Time-vs-Concurrent-Users.svg){ width="900" } **Key observations:** @@ -49,7 +49,7 @@ The graph below shows how average response time changes for the same AI API scen The graphs below show the 90th, 95th, and 99th percentile response times at 10 ms backend delay. Percentile values indicate the response time below which that percentage of requests completed, for example, the 99th percentile is the response time exceeded by only 1% of requests. -![Line chart of 90th, 95th, and 99th percentile response times in milliseconds versus concurrent users for AI API Auth No Guardrails on a four-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/4-core-Percentile-Response-Times-aiapi.svg){ width="900" } +![Line chart of 90th, 95th, and 99th percentile response times for AI API Auth No Guardrails on a four-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/4-core-Percentile-Response-Times-aiapi.svg){ width="900" } **Key observations:** @@ -57,7 +57,7 @@ The graphs below show the 90th, 95th, and 99th percentile response times at 10 m - The four-CPU configuration yields lower percentile values at high concurrency than the two-CPU configuration. - Percentile growth mainly reflects load on the gateway and the fixed backend delay, without content-level guardrail processing. -![Line chart of 90th, 95th, and 99th percentile response times in milliseconds versus concurrent users for AI API PII Masking on a four-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/4-core-Percentile-Response-Times-pii-masking.svg){ width="900" } +![Line chart of 90th, 95th, and 99th percentile response times for AI API PII Masking on a four-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/4-core-Percentile-Response-Times-pii-masking.svg){ width="900" } **Key observations:** @@ -65,7 +65,7 @@ The graphs below show the 90th, 95th, and 99th percentile response times at 10 m - Compared with Auth No Guardrails, percentile values are higher at each concurrency level due to request and response masking. - Compared with the two-CPU PII Masking results, the four-CPU configuration keeps percentiles lower under similar concurrency. -![Line chart of 90th, 95th, and 99th percentile response times in milliseconds versus concurrent users for AI API Advanced Guardrails on a four-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/4-core-Percentile-Response-Times-advanced.svg){ width="900" } +![Line chart of 90th, 95th, and 99th percentile response times for AI API Advanced Guardrails on a four-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/4-core-Percentile-Response-Times-advanced.svg){ width="900" } **Key observations:** diff --git a/en/docs/ai-gateway/next/run-the-gateway/sizing-and-performance/ai-gateway-runtime-with-two-cpus.md b/en/docs/ai-gateway/next/run-the-gateway/sizing-and-performance/ai-gateway-runtime-with-two-cpus.md index edebc7b67..d10556394 100644 --- a/en/docs/ai-gateway/next/run-the-gateway/sizing-and-performance/ai-gateway-runtime-with-two-cpus.md +++ b/en/docs/ai-gateway/next/run-the-gateway/sizing-and-performance/ai-gateway-runtime-with-two-cpus.md @@ -26,7 +26,7 @@ The table below displays the resource allocations for the AI Gateway components The graph below shows how AI Gateway throughput changes as concurrent users increase for AI API Auth No Guardrails, AI API PII Masking, and AI API Advanced Guardrails. -![Line chart of AI Gateway throughput in requests per second versus concurrent users at 100, 500, and 1000 users, comparing AI API Auth No Guardrails, AI API PII Masking, and AI API Advanced Guardrails on a two-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/two-core-throughput-vs-concurrent-users.svg){ width="900" } +![Line chart of AI Gateway throughput in requests per second versus concurrent users on a two-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/two-core-throughput-vs-concurrent-users.svg){ width="900" } **Key observations:** @@ -37,7 +37,7 @@ The graph below shows how AI Gateway throughput changes as concurrent users incr The graph below shows how average response time changes for the same AI API scenarios as concurrent users increase. The backend delay was configured to 10 ms for these tests. -![Line chart of average response time in milliseconds versus concurrent users at 100, 500, and 1000 users, comparing AI API Auth No Guardrails, AI API PII Masking, and AI API Advanced Guardrails on a two-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/two-core-average-response-time-vs-concurrent-users.svg){ width="900" } +![Line chart of average response time in milliseconds versus concurrent users on a two-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/two-core-average-response-time-vs-concurrent-users.svg){ width="900" } **Key observations:** @@ -48,7 +48,7 @@ The graph below shows how average response time changes for the same AI API scen The graphs below show the 90th, 95th, and 99th percentile response times at 10 ms backend delay. Percentile values indicate the response time below which that percentage of requests completed, for example, the 99th percentile is the response time exceeded by only 1% of requests. -![Line chart of 90th, 95th, and 99th percentile response times in milliseconds versus concurrent users for AI API Auth No Guardrails on a two-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/2-core-Percentile-Response-Times-ai-api.svg){ width="900" } +![Line chart of 90th, 95th, and 99th percentile response times for AI API Auth No Guardrails on a two-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/2-core-Percentile-Response-Times-ai-api.svg){ width="900" } **Key observations:** @@ -56,14 +56,14 @@ The graphs below show the 90th, 95th, and 99th percentile response times at 10 m - Higher concurrency widens the spread between lower and upper percentiles. - Because this scenario uses API key authentication without content guardrails, percentile growth mainly reflects gateway load and the backend delay. -![Line chart of 90th, 95th, and 99th percentile response times in milliseconds versus concurrent users for AI API PII Masking on a two-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/2-core-Percentile-Response-AI-api-pii-masking.svg){ width="900" } +![Line chart of 90th, 95th, and 99th percentile response times for AI API PII Masking on a two-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/2-core-Percentile-Response-AI-api-pii-masking.svg){ width="900" } **Key observations:** - Percentile trends follow the same upward pattern as concurrent users increase across the test range. - Compared with Auth No Guardrails, percentile values sit higher at each concurrency level because of message inspection and masking. -![Line chart of 90th, 95th, and 99th percentile response times in milliseconds versus concurrent users for AI API Advanced Guardrails on a two-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/2-core-Percentile-Response-Times-ai-api-advanced.svg){ width="900" } +![Line chart of 90th, 95th, and 99th percentile response times for AI API Advanced Guardrails on a two-CPU gateway runtime](../../../../assets/img/ai-gateway/performance/2-core-Percentile-Response-Times-ai-api-advanced.svg){ width="900" } **Key observations:** diff --git a/en/docs/ai-gateway/next/run-the-gateway/sizing-and-performance/overview.md b/en/docs/ai-gateway/next/run-the-gateway/sizing-and-performance/overview.md index 9ff0616b3..890bb1030 100644 --- a/en/docs/ai-gateway/next/run-the-gateway/sizing-and-performance/overview.md +++ b/en/docs/ai-gateway/next/run-the-gateway/sizing-and-performance/overview.md @@ -34,7 +34,7 @@ The following key metrics were used to evaluate AI Gateway performance: The diagram below shows the deployment architecture used for the performance tests documented here. -![Performance test deployment architecture showing Apache JMeter client and servers, Netty HTTP backend, and WSO2 API Platform AI Gateway on separate EC2 instances connected in a test topology](../../../../assets/img/ai-gateway/performance/deployment-used-for-test.png){ width="900" } +![Performance test topology with a JMeter client and servers, a Netty HTTP backend, and AI Gateway on separate EC2 instances](../../../../assets/img/ai-gateway/performance/deployment-used-for-test.png){ width="900" } | Component | EC2 Instance Type | vCPU | Memory (GiB) | | ---------------------------- | ----------------- | :--: | :----------: | From 6f8d27e846d118591be8052ee07a286c8485485b Mon Sep 17 00:00:00 2001 From: veejask-41 Date: Wed, 12 Aug 2026 12:17:26 +0530 Subject: [PATCH 3/3] Change Control Content nav section into Control Content (Guardrails) --- en/mkdocs.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/en/mkdocs.yml b/en/mkdocs.yml index 936b54a5a..7b0bc15e3 100644 --- a/en/mkdocs.yml +++ b/en/mkdocs.yml @@ -649,7 +649,7 @@ nav: - MCP Access Control Lists: ai-gateway/next/mcp-proxy/mcp-acl-list.md - Control Access: - Secure the Management API: ai-gateway/next/control-access/secure-the-management-api.md - - Control Content: + - Control Content (Guardrails): - Guardrails Overview: ai-gateway/next/control-content/overview.md - Guardrail execution order: ai-gateway/next/control-content/execution-order.md - Regex Guardrail: ai-gateway/next/control-content/regex.md