diff --git a/aigw/changelog/enterprise.mdx b/aigw/changelog/enterprise.mdx index 5ee101b8..a45b2b82 100644 --- a/aigw/changelog/enterprise.mdx +++ b/aigw/changelog/enterprise.mdx @@ -2465,7 +2465,7 @@ Added new condition keys for fine-grained budget and rate limit policies: ### Workspace Budget Limits - You can now enforce budget and rate limits at the workspace level -- [Documentation Link](/aigw/product/administration/enforce-workspace-budget-limts-and-rate-limits) +- [Documentation Link](/aigw/product/administration/enforce-workspace-budget-and-rate-limits) ### Circuit Breaker - Introduced circuit breakers which can be added per-strategy in configurations @@ -2938,7 +2938,7 @@ We are redacting this release and will be releasing a patch with out Workspace B --- ### Enforce Organisation And Workspace Guardrails - It is now possible to enforce guardrails at organisation and workspace levels, which will be applied to all requests. -- Documentation: [Workspace-Level Guardrails](/aigw/product/administration/enforce-workspace-level-guardials), [Organisation-Level Guardrails](/aigw/product/administration/enforce-orgnization-level-guardrails) +- Documentation: [Workspace-Level Guardrails](/aigw/product/administration/enforce-workspace-level-guardrails), [Organisation-Level Guardrails](/aigw/product/administration/enforce-organisation-level-guardrails) ### Unified Finetuning APIs for Fireworks - Extended the existing unified finetuning APIs to support Fireworks provider. diff --git a/aigw/guides/use-cases/librechat-web-search.mdx b/aigw/guides/use-cases/librechat-web-search.mdx index cc64e671..6cff3bdc 100644 --- a/aigw/guides/use-cases/librechat-web-search.mdx +++ b/aigw/guides/use-cases/librechat-web-search.mdx @@ -51,7 +51,9 @@ Before starting, ensure you have: ## Setup Guide -### Step 1: Enable Exa Plugin in AI Gateway First, activate the Exa plugin in your Strata Cloud Manager account: +### Step 1: Enable Exa Plugin in AI Gateway + +First, activate the Exa plugin in your Strata Cloud Manager account: 1. Log into your [Strata Cloud Manager](https://stratacloudmanager.paloaltonetworks.com/) 2. Navigate to `Settings` → `Plugins` in the sidebar @@ -246,7 +248,5 @@ Use semantic caching for frequently asked current events questions to reduce API - **Set up access controls** with user-specific API keys ## Support - -Need help? Contact us: - Email: support@portkey.ai - Documentation diff --git a/aigw/help-center/you-do-not-have-enough-permissions.mdx b/aigw/help-center/you-do-not-have-enough-permissions.mdx index 2cd36b2f..9f59c439 100644 --- a/aigw/help-center/you-do-not-have-enough-permissions.mdx +++ b/aigw/help-center/you-do-not-have-enough-permissions.mdx @@ -278,10 +278,6 @@ The Admin API covers integrations, providers, users, workspaces, API key managem Edit the API key and add the required scopes. When in doubt, use **Select All** to grant all permissions. - -**Plan restriction:** Some Admin API endpoints (like programmatic API key creation) require Enterprise plans. If scopes are correct but requests still fail, verify your plan includes Admin API access. - - --- ## Logs, feedback, analytics, and audit logs @@ -384,7 +380,6 @@ If none of the above scenarios match, work through these checks: - **Wrong key type** — Using Admin key for completions, or Service key for Playground - - **Plan restriction** — Some Admin API endpoints require Enterprise plans - **Stale session** — Log out and back in, or clear browser cache - **Multiple User API keys** — All User keys need the required scopes diff --git a/aigw/integrations/agents.mdx b/aigw/integrations/agents.mdx index e2fb609d..a77afaf4 100644 --- a/aigw/integrations/agents.mdx +++ b/aigw/integrations/agents.mdx @@ -125,6 +125,6 @@ Use the AI Gateway as a centralized hub to store, version, and experiment with y Improve your Agent runs by capturing qualitative & quantitative user feedback on your requests, and then using that feedback to make your prompts AND LLMs themselves better. -### 8\. [Security & Compliance](/aigw/product/enterprise-offering/security-portkey) +### 8\. [Security & Compliance](/aigw/product/enterprise-offering/security) Set budget limits on provider API keys and implement fine-grained user roles and permissions for both the app and the AI Gateway APIs. diff --git a/aigw/integrations/agents/bring-your-own-agents.mdx b/aigw/integrations/agents/bring-your-own-agents.mdx index 3ea265c4..ea72b0a6 100644 --- a/aigw/integrations/agents/bring-your-own-agents.mdx +++ b/aigw/integrations/agents/bring-your-own-agents.mdx @@ -143,7 +143,7 @@ Agent runs are time-consuming and expensive due to their complex pipelines. Cach } ``` -### 7.[ Security & Compliance](/aigw/product/enterprise-offering/security-portkey) +### 7.[ Security & Compliance](/aigw/product/enterprise-offering/security) Set budget limits on provider API keys and implement fine-grained user roles and permissions for both the app and the AI Gateway APIs. diff --git a/aigw/integrations/agents/control-flow.mdx b/aigw/integrations/agents/control-flow.mdx index 838c958d..5ba9fbb5 100644 --- a/aigw/integrations/agents/control-flow.mdx +++ b/aigw/integrations/agents/control-flow.mdx @@ -139,7 +139,7 @@ Agent runs are time-consuming and expensive due to their complex pipelines. Cach } ``` -### 7\. [Security & Compliance](/aigw/product/enterprise-offering/security-portkey) +### 7\. [Security & Compliance](/aigw/product/enterprise-offering/security) Set budget limits on provider API keys and implement fine-grained user roles and permissions for both the app and the AI Gateway APIs. diff --git a/aigw/integrations/agents/crewai.mdx b/aigw/integrations/agents/crewai.mdx index a0bb5ec1..6f63aa05 100644 --- a/aigw/integrations/agents/crewai.mdx +++ b/aigw/integrations/agents/crewai.mdx @@ -491,7 +491,4 @@ Here's a basic configuration to route requests to OpenAI, specifically using GPT

Official CrewAI documentation

 - -

Get personalized guidance on implementing this integration

- diff --git a/aigw/integrations/agents/langchain-agents.mdx b/aigw/integrations/agents/langchain-agents.mdx index e2591e44..a5c01219 100644 --- a/aigw/integrations/agents/langchain-agents.mdx +++ b/aigw/integrations/agents/langchain-agents.mdx @@ -169,7 +169,7 @@ Agent runs are time-consuming and expensive due to their complex pipelines. Cach } ``` -### 9\. [Security & Compliance](/aigw/product/enterprise-offering/security-portkey) +### 9\. [Security & Compliance](/aigw/product/enterprise-offering/security) Set budget limits on provider API keys and implement fine-grained user roles and permissions for both the app and the AI Gateway APIs. diff --git a/aigw/integrations/agents/langgraph.mdx b/aigw/integrations/agents/langgraph.mdx index e48945fe..0fe6425c 100644 --- a/aigw/integrations/agents/langgraph.mdx +++ b/aigw/integrations/agents/langgraph.mdx @@ -742,11 +742,7 @@ Here's a basic configuration to route requests to OpenAI, specifically using GPT

Official LangGraph documentation

- +

Official AI Gateway documentation

 - - -

Get personalized guidance on implementing this integration

- diff --git a/aigw/integrations/agents/livekit.mdx b/aigw/integrations/agents/livekit.mdx index 684eb7b7..b4a10673 100644 --- a/aigw/integrations/agents/livekit.mdx +++ b/aigw/integrations/agents/livekit.mdx @@ -112,7 +112,7 @@ Build a simple voice assistant with Python in less than 10 minutes. ```bash DEEPGRAM_API_KEY= - OPENAI_API_KEY= + OPENAI_API_KEY= CARTESIA_API_KEY= LIVEKIT_API_KEY= LIVEKIT_API_SECRET= diff --git a/aigw/integrations/agents/llama-agents.mdx b/aigw/integrations/agents/llama-agents.mdx index 4054dcf6..61c3b98e 100644 --- a/aigw/integrations/agents/llama-agents.mdx +++ b/aigw/integrations/agents/llama-agents.mdx @@ -159,7 +159,7 @@ Choose between `simple` and `semantic` caching: } ``` -### 8\. [Security & Compliance](/aigw/product/enterprise-offering/security-portkey) +### 8\. [Security & Compliance](/aigw/product/enterprise-offering/security) Set budget limits on provider API keys and implement fine-grained user roles and permissions for both the app and the AI Gateway APIs. diff --git a/aigw/integrations/agents/mastra-agents.mdx b/aigw/integrations/agents/mastra-agents.mdx index abd3b21b..7c86ffbb 100644 --- a/aigw/integrations/agents/mastra-agents.mdx +++ b/aigw/integrations/agents/mastra-agents.mdx @@ -689,8 +689,4 @@ For detailed key management instructions, see our [API Keys documentation](/api-

Example implementations for various use cases

 - - -

Get personalized guidance on implementing this integration

- diff --git a/aigw/integrations/agents/openai-agents-ts.mdx b/aigw/integrations/agents/openai-agents-ts.mdx index ee8b6987..88fa102b 100644 --- a/aigw/integrations/agents/openai-agents-ts.mdx +++ b/aigw/integrations/agents/openai-agents-ts.mdx @@ -774,8 +774,4 @@ Monitor usage in Strata Cloud Manager:

Example implementations for various use cases

 - - -

Get personalized guidance on implementing this integration

- diff --git a/aigw/integrations/agents/openai-agents.mdx b/aigw/integrations/agents/openai-agents.mdx index fa790d66..5f1e197c 100644 --- a/aigw/integrations/agents/openai-agents.mdx +++ b/aigw/integrations/agents/openai-agents.mdx @@ -928,8 +928,4 @@ Monitor usage in Strata Cloud Manager:

Example implementations for various use cases

 - - -

Get personalized guidance on implementing this integration

- diff --git a/aigw/integrations/agents/openai-swarm.mdx b/aigw/integrations/agents/openai-swarm.mdx index f54d379d..5a929a67 100644 --- a/aigw/integrations/agents/openai-swarm.mdx +++ b/aigw/integrations/agents/openai-swarm.mdx @@ -143,7 +143,7 @@ Logs are essential for understanding agent behavior, diagnosing issues, and impr Access a dedicated section to view records of agent executions, including parameters, outcomes, function calls, and errors. Filter logs based on multiple parameters such as trace ID, model, tokens used, and metadata. -## 6. [Security & Compliance - Enterprise-Ready Controls](/aigw/product/enterprise-offering/security-portkey) +## 6. [Security & Compliance - Enterprise-Ready Controls](/aigw/product/enterprise-offering/security) When deploying agents in production, security is crucial. The AI Gateway provides enterprise-grade security features: diff --git a/aigw/integrations/agents/phidata.mdx b/aigw/integrations/agents/phidata.mdx index afe40a83..ac25c2f4 100644 --- a/aigw/integrations/agents/phidata.mdx +++ b/aigw/integrations/agents/phidata.mdx @@ -148,7 +148,7 @@ Agent runs are time-consuming and expensive due to their complex pipelines. Cach } ``` -### 7\. [Security & Compliance](/aigw/product/enterprise-offering/security-portkey) +### 7\. [Security & Compliance](/aigw/product/enterprise-offering/security) Set budget limits on provider API keys and implement fine-grained user roles and permissions for both the app and the AI Gateway APIs. diff --git a/aigw/integrations/agents/pydantic-ai.mdx b/aigw/integrations/agents/pydantic-ai.mdx index abc251e2..7835a900 100644 --- a/aigw/integrations/agents/pydantic-ai.mdx +++ b/aigw/integrations/agents/pydantic-ai.mdx @@ -1043,11 +1043,7 @@ Here's a basic configuration to route requests to OpenAI, specifically using GPT

Official PydanticAI documentation

 - +

Official AI Gateway documentation

 - - -

Get personalized guidance on implementing this integration

- diff --git a/aigw/integrations/agents/strands.mdx b/aigw/integrations/agents/strands.mdx index 4bfdf17d..64247fb7 100644 --- a/aigw/integrations/agents/strands.mdx +++ b/aigw/integrations/agents/strands.mdx @@ -379,10 +379,6 @@ All of this works automatically with your existing Strands agents—no code chan - - -

Get personalized guidance on implementing this integration

- ### Troubleshooting diff --git a/aigw/integrations/cloud/azure.mdx b/aigw/integrations/cloud/azure.mdx index 23d80a5a..eba7a9b1 100644 --- a/aigw/integrations/cloud/azure.mdx +++ b/aigw/integrations/cloud/azure.mdx @@ -193,7 +193,3 @@ flowchart LR - [Azure AI Foundry integration](/aigw/integrations/llms/azure-foundry) - [Azure Content Safety guardrails](/product/guardrails/azure-guardrails) - [Azure Private Cloud deployment guide](/product/enterprise-offering/private-cloud-deployments/azure) - - -Need something bespoke? Reach out to our team for a tailored architecture review. - diff --git a/aigw/integrations/guardrails/acuvity.mdx b/aigw/integrations/guardrails/acuvity.mdx index 82a0d28b..da5ee3ea 100644 --- a/aigw/integrations/guardrails/acuvity.mdx +++ b/aigw/integrations/guardrails/acuvity.mdx @@ -223,10 +223,6 @@ When using raw guardrails, you must provide valid credentials for the Acuvity se -## Get Support - -If you face any issues with the Acuvity integration, reach out to [support@portkey.ai](mailto:support@portkey.ai). - ## Learn More - [Acuvity Website](https://acuvity.ai/) diff --git a/aigw/integrations/guardrails/akto.mdx b/aigw/integrations/guardrails/akto.mdx index eca60772..6fc1b20e 100644 --- a/aigw/integrations/guardrails/akto.mdx +++ b/aigw/integrations/guardrails/akto.mdx @@ -92,7 +92,3 @@ client = OpenAI( For more, refer to the [Config documentation](/aigw/product/ai-gateway/configs). Your requests are now guarded by Akto's security scanning, and you can see the verdict and any actions taken directly in your AI Gateway logs! - -## Get Support - -If you face any issues with the Akto integration, reach out to [support@portkey.ai](mailto:support@portkey.ai) for assistance. diff --git a/aigw/integrations/guardrails/aporia.mdx b/aigw/integrations/guardrails/aporia.mdx index b1896ead..d583dc35 100644 --- a/aigw/integrations/guardrails/aporia.mdx +++ b/aigw/integrations/guardrails/aporia.mdx @@ -40,7 +40,3 @@ Your Aporia Guardrail is now ready to be added to any AI Gateway request you'd l Your requests are now guarded by your Aporia policies and you can see the Verdict and any action you take directly on AI Gateway logs! More detailed logs for your requests will also be available on your Aporia dashboard. --- - -## Get Support - -If you face any issues with the Aporia integration, reach out to [support@portkey.ai](mailto:support@portkey.ai). diff --git a/aigw/integrations/guardrails/azure-guardrails.mdx b/aigw/integrations/guardrails/azure-guardrails.mdx index 9ecd2ae0..62de85b6 100644 --- a/aigw/integrations/guardrails/azure-guardrails.mdx +++ b/aigw/integrations/guardrails/azure-guardrails.mdx @@ -251,7 +251,3 @@ To completely block requests that violate your policies: - You can customize denial messages to provide guidance to users --- - -## Need Support? - -If you encounter any issues with Azure Guardrails, reach out to [support@portkey.ai](mailto:support@portkey.ai). diff --git a/aigw/integrations/guardrails/bedrock-guardrails.mdx b/aigw/integrations/guardrails/bedrock-guardrails.mdx index 35035256..7dca8b88 100644 --- a/aigw/integrations/guardrails/bedrock-guardrails.mdx +++ b/aigw/integrations/guardrails/bedrock-guardrails.mdx @@ -214,7 +214,3 @@ You can define AWS Bedrock guardrails directly in your code for more programmati When using raw guardrails, you must provide valid credentials for AWS Bedrock directly in your config. Make sure to handle these credentials securely and consider using environment variables or secrets management. - -## Get Support - -If you face any issues with the AWS Bedrock Guardrails integration, reach out to [support@portkey.ai](mailto:support@portkey.ai). diff --git a/aigw/integrations/guardrails/crowdstrike-aidr.mdx b/aigw/integrations/guardrails/crowdstrike-aidr.mdx index 2f8e65b2..85888c61 100644 --- a/aigw/integrations/guardrails/crowdstrike-aidr.mdx +++ b/aigw/integrations/guardrails/crowdstrike-aidr.mdx @@ -94,7 +94,3 @@ client = OpenAI( For more, refer to the [Config documentation](/aigw/product/ai-gateway/configs). Your requests are now guarded by CrowdStrike AIDR and you can see the Verdict and any action you take directly on AI Gateway logs! - -## Get Support - -If you face any issues with the CrowdStrike AIDR integration, reach out to [support@portkey.ai](mailto:support@portkey.ai). diff --git a/aigw/integrations/guardrails/f5-guardrails.mdx b/aigw/integrations/guardrails/f5-guardrails.mdx index a26934ec..11462379 100644 --- a/aigw/integrations/guardrails/f5-guardrails.mdx +++ b/aigw/integrations/guardrails/f5-guardrails.mdx @@ -96,7 +96,3 @@ client = OpenAI( For more, refer to the [Config documentation](/aigw/product/ai-gateway/configs). Your requests are now guarded by F5 Guardrails, and you can see the verdict and any actions taken directly in your AI Gateway logs! - -## Get Support - -If you face any issues with the F5 Guardrails integration, reach out to [support@portkey.ai](mailto:support@portkey.ai) for assistance. diff --git a/aigw/integrations/guardrails/headroom.mdx b/aigw/integrations/guardrails/headroom.mdx index 86d009a1..dbb83b91 100644 --- a/aigw/integrations/guardrails/headroom.mdx +++ b/aigw/integrations/guardrails/headroom.mdx @@ -126,7 +126,3 @@ Headroom compresses requests with a `messages` array: - **Messages** (Anthropic-style) Requests without a `messages` array pass through untouched. Compression also fails open — if the proxy is unreachable, slow, or errors, the original request is sent to the provider and the failure is recorded in `hook_results`. - -## Get Support - -If you face any issues with the Headroom integration, reach out to [support@portkey.ai](mailto:support@portkey.ai) for assistance. diff --git a/aigw/integrations/guardrails/javelin.mdx b/aigw/integrations/guardrails/javelin.mdx index e946208a..a6aefa1d 100644 --- a/aigw/integrations/guardrails/javelin.mdx +++ b/aigw/integrations/guardrails/javelin.mdx @@ -334,7 +334,3 @@ Ensure content compliance with language policies: - **Confidence Scoring**: Configurable confidence thresholds for accurate detection - **Language Allowlisting**: Restrict content to specific languages - **Cultural Compliance**: Maintain cultural and regional content standards - -## Get Support - -If you face any issues with the Javelin integration, please reach out to Javelin support through their [Get in Touch page](https://www.getjavelin.com/get-in-touch). diff --git a/aigw/integrations/guardrails/lasso.mdx b/aigw/integrations/guardrails/lasso.mdx index ff3d784f..43cf1386 100644 --- a/aigw/integrations/guardrails/lasso.mdx +++ b/aigw/integrations/guardrails/lasso.mdx @@ -131,7 +131,3 @@ Lasso works across multiple request types: If you are running a self-hosted Lasso deployment, you can configure a custom `apiEndpoint` in your Lasso credentials to point to your own instance instead of the default Lasso cloud. Learn more about Lasso Security's features [here](https://www.lasso.security). - -## Get Support - -If you face any issues with the Lasso Security integration, reach out to [support@portkey.ai](mailto:support@portkey.ai) for assistance. diff --git a/aigw/integrations/guardrails/mistral.mdx b/aigw/integrations/guardrails/mistral.mdx index c0b392cb..b8742ba7 100644 --- a/aigw/integrations/guardrails/mistral.mdx +++ b/aigw/integrations/guardrails/mistral.mdx @@ -119,10 +119,6 @@ Mistral's moderation service can detect content across 9 key policy categories: Mistral's moderation service is natively multilingual, with support for Arabic, Chinese, English, French, German, Italian, Japanese, Korean, Portuguese, Russian, and Spanish. -## Get Support - -If you face any issues with the Mistral integration, reach out to [support@portkey.ai](mailto:support@portkey.ai) for assistance. - ## Learn More - [Mistral AI Website](https://mistral.ai/) diff --git a/aigw/integrations/guardrails/model-rules.mdx b/aigw/integrations/guardrails/model-rules.mdx index ea6b382a..8381287f 100644 --- a/aigw/integrations/guardrails/model-rules.mdx +++ b/aigw/integrations/guardrails/model-rules.mdx @@ -134,7 +134,3 @@ curl https://aigw.portkey.ai/v1/chat/completions \ ``` In this example, the guardrail resolves the allowed model list from the `customer_tier: enterprise` metadata (which allows `*`), so the request for `claude-3-7-sonnet` is permitted. - -## Get support - -If you face any issues with Model Rules, reach out to [support@portkey.ai](mailto:support@portkey.ai) for assistance. diff --git a/aigw/integrations/guardrails/palo-alto-panw-prisma.mdx b/aigw/integrations/guardrails/palo-alto-panw-prisma.mdx index 36645037..975cd500 100644 --- a/aigw/integrations/guardrails/palo-alto-panw-prisma.mdx +++ b/aigw/integrations/guardrails/palo-alto-panw-prisma.mdx @@ -167,8 +167,6 @@ Prisma AIRS provides multi-layered protection against various AI-specific threat 4. **Policy Updates**: Keep your Prisma AIRS security policies updated based on emerging threats ## Get Support - -If you face any issues with the Prisma AIRS integration, reach out to: - Palo Alto Networks support through your enterprise account ## Learn More diff --git a/aigw/integrations/guardrails/pangea.mdx b/aigw/integrations/guardrails/pangea.mdx index b748e750..d9158788 100644 --- a/aigw/integrations/guardrails/pangea.mdx +++ b/aigw/integrations/guardrails/pangea.mdx @@ -181,10 +181,6 @@ When using raw guardrails, you must provide valid credentials for the Pangea ser -## Get Support - -If you face any issues with the Pangea integration, reach out to [support@portkey.ai](mailto:support@portkey.ai). - ## Learn More - [Pangea Documentation](https://pangea.cloud/docs/) diff --git a/aigw/integrations/guardrails/patronus-ai.mdx b/aigw/integrations/guardrails/patronus-ai.mdx index c0821bb0..8d93aec6 100644 --- a/aigw/integrations/guardrails/patronus-ai.mdx +++ b/aigw/integrations/guardrails/patronus-ai.mdx @@ -12,7 +12,9 @@ description: "Patronus excels in industry-specific guardrails for RAG workflows. ## Using Patronus with the AI Gateway -### 1\. Add Patronus API Key to AI Gateway Grab your Patronus API [key from here](https://app.patronus.ai/). +### 1\. Add Patronus API Key to AI Gateway + +Grab your Patronus API [key from here](https://app.patronus.ai/). On the `Integrations` page, click on the edit button for the Patronus and add your API key. @@ -51,7 +53,3 @@ Patronus integration on the AI Gateway currently only works on model outputs and Your requests are now guarded by your Patronus evaluators and you can see the Verdict and any action you take directly on AI Gateway logs! More detailed logs for your requests will also be available on your Patronus dashboard. --- - -## Get Support - -If you face any issues with the Patronus integration, reach out to [support@portkey.ai](mailto:support@portkey.ai). diff --git a/aigw/integrations/guardrails/pillar.mdx b/aigw/integrations/guardrails/pillar.mdx index b4e5bb4d..c3b96c91 100644 --- a/aigw/integrations/guardrails/pillar.mdx +++ b/aigw/integrations/guardrails/pillar.mdx @@ -38,7 +38,3 @@ Your Pillar Guardrail is now ready to be added to any AI Gateway request you'd l Your requests are now guarded by your Pillar checks and you can see the Verdict and any action you take directly on AI Gateway logs! More detailed logs for your requests will also be available on your Pillar dashboard. --- - -## Get Support - -If you face any issues with the Pillar integration, reach out to [support@portkey.ai](mailto:support@portkey.ai). diff --git a/aigw/integrations/guardrails/prompt-security.mdx b/aigw/integrations/guardrails/prompt-security.mdx index 1bd0539e..deee7efa 100644 --- a/aigw/integrations/guardrails/prompt-security.mdx +++ b/aigw/integrations/guardrails/prompt-security.mdx @@ -99,7 +99,3 @@ client = OpenAI( For more, refer to the [Config documentation](/aigw/product/ai-gateway/configs). Your requests are now guarded by Prompt Security's protection mechanisms, and you can see the verdict and any actions taken directly in your AI Gateway logs! - -## Get Support - -If you face any issues with the Prompt Security integration, reach out to [support@portkey.ai](mailto:support@portkey.ai) for assistance. diff --git a/aigw/integrations/guardrails/qualifire.mdx b/aigw/integrations/guardrails/qualifire.mdx index 0230f5b4..e3595371 100644 --- a/aigw/integrations/guardrails/qualifire.mdx +++ b/aigw/integrations/guardrails/qualifire.mdx @@ -176,6 +176,4 @@ Qualifire's guardrails are particularly useful for: ## Get Support -If you face any issues with the Qualifire integration, reach out to [support@portkey.ai](mailto:support@portkey.ai) for assistance. - For Qualifire-specific support, visit their [documentation](https://docs.qualifire.ai) or contact their support team. diff --git a/aigw/integrations/guardrails/request-parameters-check.mdx b/aigw/integrations/guardrails/request-parameters-check.mdx index baa7181c..02488e4d 100644 --- a/aigw/integrations/guardrails/request-parameters-check.mdx +++ b/aigw/integrations/guardrails/request-parameters-check.mdx @@ -400,7 +400,3 @@ When the guardrail denies a request, the failure payload in `hook_results` conta | Yes | Yes | Entries must be in the allow list **and** not in the block list | --- - -## Get Support - -If you face any issues with the Request Parameters Check guardrail, reach out to [support@portkey.ai](mailto:support@portkey.ai) for assistance. diff --git a/aigw/integrations/guardrails/tavily.mdx b/aigw/integrations/guardrails/tavily.mdx index 6dcbee3e..7b2b0f79 100644 --- a/aigw/integrations/guardrails/tavily.mdx +++ b/aigw/integrations/guardrails/tavily.mdx @@ -89,7 +89,3 @@ curl https://aigw.portkey.ai/v1/chat/completions \ For more, refer to the [Config documentation](/aigw/product/ai-gateway/configs). - -## Get Support - -If you face any issues with the Tavily integration, reach out to [support@portkey.ai](mailto:support@portkey.ai) for assistance. diff --git a/aigw/integrations/guardrails/zscaler.mdx b/aigw/integrations/guardrails/zscaler.mdx index 228ad436..988d8ce2 100644 --- a/aigw/integrations/guardrails/zscaler.mdx +++ b/aigw/integrations/guardrails/zscaler.mdx @@ -89,7 +89,3 @@ client = OpenAI( For more, refer to the [Config documentation](/aigw/product/ai-gateway/configs). Your requests are now guarded by Zscaler AI Guard, and you can see the verdict and any actions taken directly in your AI Gateway logs! - -## Get Support - -If you face any issues with the Zscaler AI Guard integration, reach out to [support@portkey.ai](mailto:support@portkey.ai) for assistance. diff --git a/aigw/integrations/libraries/dspy.mdx b/aigw/integrations/libraries/dspy.mdx index fa2bf680..3a456131 100644 --- a/aigw/integrations/libraries/dspy.mdx +++ b/aigw/integrations/libraries/dspy.mdx @@ -135,7 +135,9 @@ While the basic setup is simple, you can still access advanced AI Gateway featur These features are configured at the provider level in Strata Cloud Manager, keeping your DSPy code clean and simple. -## Advanced Example: RAG with DSPy and AI Gateway Here's a complete example showing how to build a RAG system with DSPy and the AI Gateway: +## Advanced Example: RAG with DSPy and AI Gateway + +Here's a complete example showing how to build a RAG system with DSPy and the AI Gateway: ```python import dspy diff --git a/aigw/integrations/libraries/openai-agent-builder-python.mdx b/aigw/integrations/libraries/openai-agent-builder-python.mdx index 242e00fd..5b9bc2c5 100644 --- a/aigw/integrations/libraries/openai-agent-builder-python.mdx +++ b/aigw/integrations/libraries/openai-agent-builder-python.mdx @@ -255,7 +255,4 @@ client = AsyncOpenAI( Official documentation - - Get implementation guidance - diff --git a/aigw/integrations/libraries/openai-agent-builder.mdx b/aigw/integrations/libraries/openai-agent-builder.mdx index fc645793..d7dfba74 100644 --- a/aigw/integrations/libraries/openai-agent-builder.mdx +++ b/aigw/integrations/libraries/openai-agent-builder.mdx @@ -251,7 +251,4 @@ const client = new OpenAI({ Official documentation - - Get implementation guidance - diff --git a/aigw/integrations/libraries/openai-compatible.mdx b/aigw/integrations/libraries/openai-compatible.mdx index c12f5716..d9443447 100644 --- a/aigw/integrations/libraries/openai-compatible.mdx +++ b/aigw/integrations/libraries/openai-compatible.mdx @@ -67,7 +67,7 @@ https://aigw.portkey.ai/v1 **API Key** ``` -Your Portkey API Key (from step 2) +Your Gateway API Key (from step 2) ``` **Model** (if configurable) diff --git a/aigw/integrations/libraries/openwebui.mdx b/aigw/integrations/libraries/openwebui.mdx index cf108bbd..4243618a 100644 --- a/aigw/integrations/libraries/openwebui.mdx +++ b/aigw/integrations/libraries/openwebui.mdx @@ -118,7 +118,7 @@ class Pipe: class Valves(BaseModel): PORTKEY_API_KEY: str = Field( default="", - description="Your Portkey API key (required).", + description="Your Gateway API key (required).", ) PORTKEY_API_BASE_URL: str = Field( default="https://aigw.portkey.ai/v1", @@ -260,7 +260,9 @@ class Pipe: -#### What You'll See in AI Gateway User emails appear directly in the **User column** of your logs—no need to click into individual entries. +#### What You'll See in AI Gateway + +User emails appear directly in the **User column** of your logs—no need to click into individual entries. **Captured metadata:** User email, name, role, chat ID, user ID. Filter logs by user, attribute costs to departments, maintain audit trails—all without individual API keys per user. @@ -272,7 +274,7 @@ class Pipe: ```text Without Manifold Pipe Open WebUI (User A, User B, User C...) ↓ -Shared Portkey API Key +Shared Gateway API Key ↓ Portkey Logs: All requests appear anonymous diff --git a/aigw/integrations/libraries/vercel.mdx b/aigw/integrations/libraries/vercel.mdx index c0e64d73..b471eb0c 100644 --- a/aigw/integrations/libraries/vercel.mdx +++ b/aigw/integrations/libraries/vercel.mdx @@ -608,7 +608,4 @@ const { text } = await generateText({ Complete API documentation - - Reach out to our team - diff --git a/aigw/integrations/llms/azure-openai/azure-openai.mdx b/aigw/integrations/llms/azure-openai/azure-openai.mdx index 0f88f44f..c01f31ec 100644 --- a/aigw/integrations/llms/azure-openai/azure-openai.mdx +++ b/aigw/integrations/llms/azure-openai/azure-openai.mdx @@ -206,8 +206,6 @@ curl https://{YOUR_RESOURCE_NAME}.openai.azure.com/openai/deployments/{YOUR_DEPL If you have configured fine-grained access for Azure OpenAI and need to use `JSON web token (JWT)` in the `Authorization` header instead of the regular `API Key`, you can use the `forwardHeaders` parameter to do this. -For further questions on custom Azure deployments or fine-grained access tokens, reach out to us on support@portkey.ai - ## Next Steps You'll find more information in the relevant sections: diff --git a/aigw/integrations/llms/claude-platform-aws/setup-assumed-role.mdx b/aigw/integrations/llms/claude-platform-aws/setup-assumed-role.mdx index 9dec7fa0..c600a59b 100644 --- a/aigw/integrations/llms/claude-platform-aws/setup-assumed-role.mdx +++ b/aigw/integrations/llms/claude-platform-aws/setup-assumed-role.mdx @@ -3,8 +3,8 @@ title: "Setup Assumed Role for Claude Platform on AWS" description: "Configure AWS IAM assumed role authentication for Claude Platform on AWS on Prisma AIRS AI Gateway" --- - - On the Enterprise plan? See the Helm documentation for assumed role setup in self-hosted deployments. + + See the Helm documentation for assumed role setup in self-hosted deployments. ## Enable Outbound Web Identity Federation diff --git a/aigw/integrations/llms/vertex-ai.mdx b/aigw/integrations/llms/vertex-ai.mdx index 8b45be2f..5efd37f6 100644 --- a/aigw/integrations/llms/vertex-ai.mdx +++ b/aigw/integrations/llms/vertex-ai.mdx @@ -2124,8 +2124,6 @@ main(); -For further questions on custom Vertex AI deployments or fine-grained access tokens, reach out to us on support@portkey.ai - ### How to Find Your Google Vertex Project Details To obtain your **Vertex Project ID and Region,** [navigate to Google Vertex Dashboard]( https://console.cloud.google.com/vertex-ai). diff --git a/aigw/integrations/mcp-clients/cursor.mdx b/aigw/integrations/mcp-clients/cursor.mdx index 2ce0d9f6..d5be1881 100644 --- a/aigw/integrations/mcp-clients/cursor.mdx +++ b/aigw/integrations/mcp-clients/cursor.mdx @@ -155,4 +155,4 @@ The AI Gateway handles all authentication flows automatically: Need help? We're here for you: - 📧 Email: support@portkey.ai -- 📚 Documentation: [Prisma AIRS AI Gateway docs](/aigw/introduction/what-is-portkey) +- 📚 Documentation: [Prisma AIRS AI Gateway docs](/aigw/introduction/welcome) diff --git a/aigw/integrations/plugins/exa.mdx b/aigw/integrations/plugins/exa.mdx index e7ad383a..c5229c30 100644 --- a/aigw/integrations/plugins/exa.mdx +++ b/aigw/integrations/plugins/exa.mdx @@ -132,10 +132,6 @@ All Exa-enhanced requests are logged in Strata Cloud Manager. You can review: -## Get Support - -If you face any issues with the Exa integration, reach out to [support@portkey.ai](mailto:support@portkey.ai). - ## Learn More - [Exa API Documentation](https://exa.ai/docs) diff --git a/aigw/integrations/tracing-providers/arize.mdx b/aigw/integrations/tracing-providers/arize.mdx index 971609c7..a4463e66 100644 --- a/aigw/integrations/tracing-providers/arize.mdx +++ b/aigw/integrations/tracing-providers/arize.mdx @@ -213,7 +213,7 @@ Block harmful, toxic, or inappropriate content in real-time based on custom poli Fine-grained RBAC with team management, user permissions, and audit logs. - + Enterprise-grade security with SOC2 Type II certification and GDPR compliance. @@ -221,7 +221,7 @@ Enterprise-grade security with SOC2 Type II certification and GDPR compliance. Complete audit trail of all API usage, configuration changes, and user actions. - + Zero data retention options and deployment in your own VPC for maximum privacy. @@ -265,5 +265,3 @@ Configure fallbacks, load balancing, and more Use the AI Gateway's native observability features - -**Need help?** Reach out to [support@portkey.ai](mailto:support@portkey.ai) diff --git a/aigw/integrations/tracing-providers/logfire.mdx b/aigw/integrations/tracing-providers/logfire.mdx index 6c5de432..9ba6a7cf 100644 --- a/aigw/integrations/tracing-providers/logfire.mdx +++ b/aigw/integrations/tracing-providers/logfire.mdx @@ -42,7 +42,9 @@ Install the required packages for Logfire and AI Gateway integration: pip install logfire openai ``` -### Step 2: Basic Setup - Send Traces to AI Gateway First, let's configure Logfire to send traces to the AI Gateway's OpenTelemetry endpoint: +### Step 2: Basic Setup - Send Traces to AI Gateway + +First, let's configure Logfire to send traces to the AI Gateway's OpenTelemetry endpoint: ```python import os diff --git a/aigw/introduction/make-your-first-request.mdx b/aigw/introduction/simple-setup.mdx similarity index 55% rename from aigw/introduction/make-your-first-request.mdx rename to aigw/introduction/simple-setup.mdx index cd9dba2f..c06dd458 100644 --- a/aigw/introduction/make-your-first-request.mdx +++ b/aigw/introduction/simple-setup.mdx @@ -1,28 +1,29 @@ --- -title: "Setup Guide" -sidebarTitle: "Setup Guide" -description: "Set up Prisma AIRS AI Gateway in Strata Cloud Manager and make your first secured LLM request." +title: "Simple Setup" +sidebarTitle: "Simple Setup" +description: "Set up Prisma AIRS AI Gateway in Strata Cloud Manager and make your first LLM request." --- -This guide takes you from an empty gateway to a working, guardrailed request. It uses OpenAI as -the provider because it is the shortest path; every step works the same way for Anthropic, -Vertex AI, Bedrock, Azure OpenAI and the rest of the [supported -providers](/aigw/integrations/llms). +This guide takes you from an empty gateway to a working LLM request. It uses OpenAI as the +provider because it is the shortest path; every step works the same way for Anthropic, Vertex +AI, Bedrock, Azure OpenAI and the rest of the [supported providers](/aigw/integrations/llms). -**Before you start.** AI Gateway must be enabled on your Strata Cloud Manager tenant, and you -need a Prisma AIRS API key with at least one security profile configured. Both are set up in -Strata Cloud Manager outside the gateway. +**Before you start.** AI Gateway must be enabled on your Strata Cloud Manager tenant. + +This is the minimal path. To scan requests with Prisma AIRS, enable the plugin and attach a +guardrail — see the [Prisma AIRS guardrail +reference](/aigw/integrations/guardrails/palo-alto-panw-prisma) — then bind it to your key with +a [config](/aigw/product/ai-gateway/configs). + + ## Overview - - - @@ -30,14 +31,7 @@ Strata Cloud Manager outside the gateway. --- -## 1. Enable the Prisma AIRS plugin - -Go to **Admin Settings → Plugins** and enable the **Prisma AIRS** plugin. - -Open the plugin's credential editor, paste your **Prisma AIRS API key**, and click **Update**. -This key is what the gateway uses to call Prisma AIRS on every scanned request. - -## 2. Set up a workspace +## 1. Set up a workspace Workspaces are managed under **Workspace Control**. A workspace is the unit that owns integrations, configs and API keys, and it is the boundary your access scopes are evaluated @@ -52,7 +46,7 @@ Strata Cloud Manager tenant; workspaces divide it; users and machine identities workspace. -## 3. Add an LLM integration +## 2. Add an LLM integration Go to **Integrations → Add LLM Integration**. @@ -75,62 +69,13 @@ Go to **Integrations → Add LLM Integration**. The integration gets a **provider slug** — something like `@openai-prod`. You will use it in the `model` parameter of every request. -## 4. Create a Prisma AIRS guardrail - -Go to **Catalogs → Create Guardrail** and add the **PANW Prisma AIRS Guardrail** check. - -| Field | What to put in it | -| :--- | :--- | -| **Profile Name** or **Profile ID** | The Prisma AIRS security profile to scan against. Leave both empty to use the profile linked to your API key. | -| **Scan Scope** | Which messages get scanned: `last_message` (default), `last_user_message`, `user_messages`, or `all_messages`. | -| **Strip Scaffolding** | Removes known agent-harness wrappers — system reminders, MCP tool instructions — before scanning. Turn this on when the caller is an agentic client like Claude Code or Cursor. | - -Set the guardrail **actions** — what happens when Prisma AIRS returns a block verdict — and click -**Save**. - - -If you later modify a guardrail, click **Update** after **Save**. Saving alone does not publish -the change. - - -Note the **guardrail ID** on the saved guardrail. It looks like `pg-xxxxxx`, and you need it in -the next step. - - - Every parameter, the threats it detects, and the recommended settings for agentic clients. - - -## 5. Create a config - -Go to **Profiles & Policies → Config** and click **Create**. - -A config is the routing and policy object attached to a request. Attach the guardrail from step 4 -to it: - -```json -{ - "input_guardrails": ["pg-xxxxxx"], - "output_guardrails": ["pg-xxxxxx"] -} -``` - -`input_guardrails` scans the prompt before it reaches the provider; `output_guardrails` scans the -response on the way back. Use one or both. - -Configs can be scoped to specific workspaces. Save it and note the **config ID** — it looks like -`pc-xxxxxx`. - - - Routing, fallbacks, retries, caching and conditional routing all live in the config object. - - -## 6. Create an API key +## 3. Create an API key Go to **Security Keys → Create New**. -Assign the config from step 5 to the key. Any request made with this key gets that config — -including the guardrail — without the caller having to pass anything extra. You can also attach -default metadata here, which then shows up on every log line. +Create the key inside the workspace from step 1. You can attach default metadata here, which +then shows up on every log line, and a [config](/aigw/product/ai-gateway/configs) if you have +one — any request made with the key then picks it up without the caller passing anything extra. Copy the key. It is shown once. @@ -138,7 +83,7 @@ Copy the key. It is shown once. Scopes, metadata enforcement, expiry and rotation. -## 7. Make your first request +## 4. Make your first request The gateway speaks the OpenAI API. Point your existing client at `https://aigw.portkey.ai/v1`, authenticate with your gateway API key, and prefix the model with @@ -195,28 +140,21 @@ console.log(completion.choices[0].message.content); Three things to note: - **`Authorization` carries the gateway key**, not the provider key. The gateway holds the OpenAI - credential from step 3 and attaches it upstream. + credential from step 2 and attaches it upstream. - **The provider slug lives in `model`.** `@openai-prod/gpt-4o` means "the `gpt-4o` model, via the `@openai-prod` integration". You do not need a provider header. -- **The guardrail is already applied**, because it is attached to the config, which is attached to - the API key. - -### Confirm the guardrail fires - -Send something your security profile should block. Depending on the actions you set in step 4, -you will get either a hard denial or a `200` response carrying the guardrail verdict — the "soft -deny" behaviour, which is the right choice for long-running agent sessions that a fatal error -would terminate. +- **Policy rides on the key.** Anything attached to the config on your API key — guardrails, + fallbacks, retries, caching — applies without the caller opting in. To scope a config to a single request rather than to the whole API key, pass `-H "x-portkey-config: pc-xxxxxx"`. The header overrides the key's default. -## 8. Check the logs +## 5. Check the logs Go to **Observability → Logs**. Your request is there with the model, provider, token counts, -cost, latency and the guardrail verdict. +cost and latency. If a guardrail is attached to the key, its verdict shows here too. To correlate a set of calls, pass a trace ID on the request: @@ -226,8 +164,8 @@ To correlate a set of calls, pass a trace ID on the request: Requests sharing a trace ID are grouped as one session in the log view. -On the Prisma AIRS side, go to **AI Runtime → AI Sessions** and paste the same trace ID to see -the scan results for that session. +Once Prisma AIRS scanning is enabled, the same trace ID resolves on the Prisma AIRS side under +**AI Runtime → AI Sessions**, where you can see the scan results for that session. ## Next steps diff --git a/aigw/introduction/what-is-portkey.mdx b/aigw/introduction/welcome.mdx similarity index 100% rename from aigw/introduction/what-is-portkey.mdx rename to aigw/introduction/welcome.mdx diff --git a/aigw/product/administration/configure-guardrail-access-permissions.mdx b/aigw/product/administration/configure-guardrail-access-permissions.mdx index e7cc8763..db7a9c6a 100644 --- a/aigw/product/administration/configure-guardrail-access-permissions.mdx +++ b/aigw/product/administration/configure-guardrail-access-permissions.mdx @@ -53,6 +53,6 @@ To configure workspace-level overrides: Configure who can view and manage prompts within workspaces - + Learn how to enforce organisation-level request guardrails across all workspaces diff --git a/aigw/product/administration/configure-model-access-permissioning-for-ai-integratinon.mdx b/aigw/product/administration/configure-model-access-permissioning-for-ai-integrations.mdx similarity index 100% rename from aigw/product/administration/configure-model-access-permissioning-for-ai-integratinon.mdx rename to aigw/product/administration/configure-model-access-permissioning-for-ai-integrations.mdx diff --git a/aigw/product/administration/configuring-request-logging.mdx b/aigw/product/administration/configuring-request-logging.mdx index 4c869719..f4180c38 100644 --- a/aigw/product/administration/configuring-request-logging.mdx +++ b/aigw/product/administration/configuring-request-logging.mdx @@ -75,7 +75,3 @@ When different logging settings exist at multiple levels: 1. **Workspace settings** (highest priority) - if workspace-level control is enabled 2. **Organisation settings** (applies when workspace control is disabled) - -## Support - -For questions about configuring request logging or assistance with compliance requirements, contact [Palo Alto Networks support](mailto:support@portkey.ai). diff --git a/aigw/product/administration/enforce-budget-and-rate-limit.mdx b/aigw/product/administration/enforce-budget-and-rate-limit.mdx index e6bd8f92..06941fb0 100644 --- a/aigw/product/administration/enforce-budget-and-rate-limit.mdx +++ b/aigw/product/administration/enforce-budget-and-rate-limit.mdx @@ -3,12 +3,8 @@ title: "Enforce Budget Limits and Rate Limits for Your API Keys" description: "Configure budget and rate limits on API keys to effectively manage AI spending and usage across your organisation" --- - -Available on **Enterprise** plan and select **Pro** customers. - - -Looking to set limits for an entire workspace instead of individual API keys? See [Enforce Workspace Budget and Rate Limits](/aigw/product/administration/enforce-workspace-budget-limts-and-rate-limits). +Looking to set limits for an entire workspace instead of individual API keys? See [Enforce Workspace Budget and Rate Limits](/aigw/product/administration/enforce-workspace-budget-and-rate-limits). ## Overview @@ -101,8 +97,3 @@ When limits are reached or thresholds are crossed, the AI Gateway automatically You can add additional recipients such as finance team members, department heads, or project managers who need visibility into AI usage. -## Availability - -These features are available to AI Gateway Enterprise customers and select Pro users. To enable these features for your account, please contact [support@portkey.ai](mailto:support@portkey.ai). - -To learn more about the AI Gateway Enterprise plan, [schedule a consultation](https://www.paloaltonetworks.com/ai-security/ai-gateway#:~:text=See%20Prisma%20AIRS%20AI%20Gateway%20in%20Action). diff --git a/aigw/product/administration/enforce-default-config.mdx b/aigw/product/administration/enforce-default-config.mdx index d6ba9af3..69c0a2f9 100644 --- a/aigw/product/administration/enforce-default-config.mdx +++ b/aigw/product/administration/enforce-default-config.mdx @@ -186,7 +186,3 @@ Control AI spending by: - Routing to cost-effective models by default - Implementing caching for frequently used prompts - Applying rate limits to prevent unexpected usage spikes - -## Support - -For questions about configuring default settings for API keys or troubleshooting issues, contact [Palo Alto Networks support](mailto:support@portkey.ai). diff --git a/aigw/product/administration/enforce-orgnization-level-guardrails.mdx b/aigw/product/administration/enforce-organisation-level-guardrails.mdx similarity index 94% rename from aigw/product/administration/enforce-orgnization-level-guardrails.mdx rename to aigw/product/administration/enforce-organisation-level-guardrails.mdx index 66a01d1e..9ee9e6c8 100644 --- a/aigw/product/administration/enforce-orgnization-level-guardrails.mdx +++ b/aigw/product/administration/enforce-organisation-level-guardrails.mdx @@ -53,7 +53,4 @@ Use `/workspace-exclusions/output-guardrails` for output guardrails, and set `ex Best Practices - Clearly communicate guardrail requirements to all developers in your organisation. - Maintain internal documentation on your guardrail policies to ensure consistency. - - -## Support -For questions about configuring metadata schemas or troubleshooting issues, contact [Palo Alto Networks support](mailto:support@portkey.ai). + \ No newline at end of file diff --git a/aigw/product/administration/enforce-saved-only-config.mdx b/aigw/product/administration/enforce-saved-only-config.mdx index a227dffb..7d14d64f 100644 --- a/aigw/product/administration/enforce-saved-only-config.mdx +++ b/aigw/product/administration/enforce-saved-only-config.mdx @@ -158,7 +158,3 @@ Because every request references a named, saved resource, logs and analytics att Full reference for the `x-portkey-*` request headers. - -## Support - -For questions about saved-only mode or other data-plane security settings, contact [Palo Alto Networks support](mailto:support@portkey.ai). diff --git a/aigw/product/administration/enforce-workspace-budget-limts-and-rate-limits.mdx b/aigw/product/administration/enforce-workspace-budget-and-rate-limits.mdx similarity index 98% rename from aigw/product/administration/enforce-workspace-budget-limts-and-rate-limits.mdx rename to aigw/product/administration/enforce-workspace-budget-and-rate-limits.mdx index 3c6c7681..a83162fb 100644 --- a/aigw/product/administration/enforce-workspace-budget-limts-and-rate-limits.mdx +++ b/aigw/product/administration/enforce-workspace-budget-and-rate-limits.mdx @@ -3,10 +3,6 @@ title: "Enforce Workspace Budget and Rate Limits" description: "Configure budget and rate limits at the workspace level to effectively manage AI spending and resource allocation" --- - -Available on **Enterprise** plan and select **Pro** customers. - - ## Overview Workspace Budget Limits provide granular financial and usage control at the workspace level, allowing organisation admins/owners and workspace admins to allocate resources effectively across teams and projects. This feature complements API key-level budget controls, creating a comprehensive governance framework for AI spending across your organisation. diff --git a/aigw/product/administration/enforce-workspace-level-guardials.mdx b/aigw/product/administration/enforce-workspace-level-guardrails.mdx similarity index 91% rename from aigw/product/administration/enforce-workspace-level-guardials.mdx rename to aigw/product/administration/enforce-workspace-level-guardrails.mdx index deadd4d0..3af32754 100644 --- a/aigw/product/administration/enforce-workspace-level-guardials.mdx +++ b/aigw/product/administration/enforce-workspace-level-guardrails.mdx @@ -31,7 +31,4 @@ Once configured, these guardrails will be enforced on all API requests within th **Best Practices** - Clearly communicate guardrail requirements to all members in your workspace. - Maintain internal documentation on your workspace guardrail policies to ensure consistency. - - -## Support -For questions about configuring workspace-level guardrails or troubleshooting issues, contact [Palo Alto Networks support](mailto:support@portkey.ai). + \ No newline at end of file diff --git a/aigw/product/administration/enforcing-request-metadata.mdx b/aigw/product/administration/enforcing-request-metadata.mdx index 5531ec1d..4570ecd6 100644 --- a/aigw/product/administration/enforcing-request-metadata.mdx +++ b/aigw/product/administration/enforcing-request-metadata.mdx @@ -122,7 +122,9 @@ The metadata schema follows [JSON Schema draft-07](https://json-schema.org/draft -## Using this Metadata in AI Gateway Metadata validation on the schema is enforced on API Key/Workspace creation time. +## Using this Metadata in AI Gateway + +Metadata validation on the schema is enforced on API Key/Workspace creation time. ### When Creating API Keys When creating a new API key (either Service or User type), you must provide metadata that conforms to the defined schema: @@ -163,7 +165,4 @@ When the same key appears at multiple levels, the **precedence order** is: Best Practices - Organisation owners should clearly communicate metadata requirements to all developers - Maintain internal documentation of your metadata schema - - -## Support -For questions about configuring metadata schemas or troubleshooting issues, contact [Palo Alto Networks support](mailto:support@portkey.ai). + \ No newline at end of file diff --git a/aigw/product/ai-gateway/batches.mdx b/aigw/product/ai-gateway/batches.mdx index e3b4c9d4..33bb26a1 100644 --- a/aigw/product/ai-gateway/batches.mdx +++ b/aigw/product/ai-gateway/batches.mdx @@ -3,10 +3,6 @@ title: "Unified Batch Inference" description: "Run large‑scale inference jobs through one consistent endpoint" --- - - **Enterprise Feature**
Batch inference is available on **Enterprise** hybrid and self-hosted plans only. Contact Prisma AIRS AI Gateway team to enable it for your Organisation. - - AI Gateway lets you send a single request that fan‑outs to hundreds—or millions—of completions. Choose the mode that best fits cost, latency, and provider support. ## Choose Your Batching Mode diff --git a/aigw/product/ai-gateway/cache-simple-and-semantic.mdx b/aigw/product/ai-gateway/cache-simple-and-semantic.mdx index 917bccac..9342674b 100644 --- a/aigw/product/ai-gateway/cache-simple-and-semantic.mdx +++ b/aigw/product/ai-gateway/cache-simple-and-semantic.mdx @@ -4,12 +4,7 @@ description: Speed up requests and reduce costs by caching LLM responses. --- - **Simple** caching is available for all plans. -
- **Semantic** caching requires a vector database and is only available on - select Enterprise plans. [Contact - us](/aigw/support/contact-us) to learn more about enabling - this feature. + **Semantic** caching requires a vector database. Cache LLM responses to serve requests up to **20x faster** and cheaper. diff --git a/aigw/product/ai-gateway/grpc.mdx b/aigw/product/ai-gateway/grpc.mdx index 6cf4bc2e..038a66e7 100644 --- a/aigw/product/ai-gateway/grpc.mdx +++ b/aigw/product/ai-gateway/grpc.mdx @@ -3,10 +3,6 @@ title: "gRPC (Beta)" description: "Use gRPC as an alternative transport protocol for lower latency and efficient binary serialization" --- - - **Enterprise Feature**
gRPC support is available on **Enterprise** self-hosted plans only. Contact the [Prisma AIRS AI Gateway team](/support/contact-us) to enable it for your gateway deployment. - - gRPC support is currently in **beta**. The API surface may change based on feedback. diff --git a/aigw/product/ai-gateway/virtual-keys/bedrock-amazon-assumed-role.mdx b/aigw/product/ai-gateway/virtual-keys/bedrock-amazon-assumed-role.mdx index 22ce04a5..9df880e2 100644 --- a/aigw/product/ai-gateway/virtual-keys/bedrock-amazon-assumed-role.mdx +++ b/aigw/product/ai-gateway/virtual-keys/bedrock-amazon-assumed-role.mdx @@ -6,8 +6,8 @@ description: "How to create a new integration for Bedrock using Amazon Assumed R Available on all plans. - - On the Enterprise plan and need to connect to Bedrock using an AWS assumed role? Check out the documentation here. + + Connecting to Bedrock using an AWS assumed role? Check out the documentation here. ## Select AWS Assumed Role Authentication diff --git a/aigw/product/ai-gateway/virtual-keys/budget-limits.mdx b/aigw/product/ai-gateway/virtual-keys/budget-limits.mdx index 1fd4e4e6..6b4540eb 100644 --- a/aigw/product/ai-gateway/virtual-keys/budget-limits.mdx +++ b/aigw/product/ai-gateway/virtual-keys/budget-limits.mdx @@ -5,18 +5,12 @@ description: "Budget Limits lets you set cost limits on providers/integrations" Budget Limits lets you set cost or token limits on providers/integrations - -Available on **Enterprise** plan and select **Pro** customers. - - -To apply budgets and rate limits at the workspace level (across keys), see [Enforce Workspace Budget and Rate Limits](/aigw/product/administration/enforce-workspace-budget-limts-and-rate-limits). +To apply budgets and rate limits at the workspace level (across keys), see [Enforce Workspace Budget and Rate Limits](/aigw/product/administration/enforce-workspace-budget-and-rate-limits). **Budget Limits on Providers** provide a simple way to manage your spending on AI providers (and LLMs) - giving you confidence and control over your application's costs. -Budget Limit is currently only available to **Prisma AIRS AI Gateway** [**Enterprise Plan**](/aigw/product/enterprise-offering) customers. Email us at `support@portkey.ai` if you would like to enable it for your org. - ## Setting Budget Limits on Providers When creating a new integration on the AI Gateway, you can set limits in two ways: @@ -77,10 +71,3 @@ For token-based budgets, the AI Gateway tracks both input and output tokens acro It's important to note that budget limits cannot be applied retrospectively. The spend counter starts from zero only after you've set a budget limit for a key. -## Availability - -Budget Limits is currently available **exclusively to AI Gateway Enterprise** customers and select Pro users. If you're interested in enabling this feature for your account, please reach out to us at [support@portkey.ai](mailto:support@portkey.ai). - -## Enterprise Plan - -To discuss AI Gateway Enterprise plan details and pricing, [you can schedule a quick call here](https://www.paloaltonetworks.com/ai-security/ai-gateway#:~:text=See%20Prisma%20AIRS%20AI%20Gateway%20in%20Action). diff --git a/aigw/product/ai-gateway/virtual-keys/rate-limits.mdx b/aigw/product/ai-gateway/virtual-keys/rate-limits.mdx index 7b3e5b21..9ec7e483 100644 --- a/aigw/product/ai-gateway/virtual-keys/rate-limits.mdx +++ b/aigw/product/ai-gateway/virtual-keys/rate-limits.mdx @@ -5,14 +5,8 @@ description: "Set Rate Limts to your Integrations/Providers" Rate Limits lets you set request or token consumption limits on providers/integrations - -Available on **Enterprise** plan and select **Pro** customers. - - **Rate Limits provide a powerful way to control the frequency of API requests or token consumption for your requests - giving you confidence and control over your application's usage patterns and performance. -Rate Limit is currently only available to **Prisma AIRS AI Gateway** [**Enterprise Plan**](/aigw/product/enterprise-offering) customers and select Pro users. Email us at `support@portkey.ai` if you would like to enable it for your org. - ## Setting Rate Limits on Providers When creating a new provider on the AI Gateway, you can set rate limits in two ways: @@ -64,10 +58,3 @@ You can track your request and token usage for any specific provider by navigati * **Security**: Mitigate potential abuse or DoS attacks * **Provider Compliance**: Stay within the rate limits imposed by underlying AI providers -## Availability - -Rate Limits is currently available **exclusively to AI Gateway Enterprise** customers and select Pro users. If you're interested in enabling this feature for your account, please reach out to us at [support@portkey.ai](mailto:support@portkey.ai). - -## Enterprise Plan - -To discuss AI Gateway Enterprise plan details and pricing, [you can schedule a quick call here](https://www.paloaltonetworks.com/ai-security/ai-gateway#:~:text=See%20Prisma%20AIRS%20AI%20Gateway%20in%20Action). diff --git a/aigw/product/enterprise-offering.mdx b/aigw/product/enterprise-offering.mdx index b48f0960..01631601 100644 --- a/aigw/product/enterprise-offering.mdx +++ b/aigw/product/enterprise-offering.mdx @@ -63,13 +63,3 @@ mode: "wide" -## Interested? Schedule a Call Below - - diff --git a/aigw/product/enterprise-offering/audit-logs.mdx b/aigw/product/enterprise-offering/audit-logs.mdx index 2d2bcd8f..f575de11 100644 --- a/aigw/product/enterprise-offering/audit-logs.mdx +++ b/aigw/product/enterprise-offering/audit-logs.mdx @@ -118,13 +118,4 @@ The AI Gateway's Audit Logs include enterprise-grade capabilities: Authentication and authorization with API keys - -## Support - -For questions about Audit Logs or assistance with interpreting specific entries, contact [Palo Alto Networks support](mailto:support@portkey.ai). - - - Ready to bring enterprise-grade governance to your AI infrastructure? Learn more about the AI Gateway's Audit Logs and other enterprise features in a personalized demo. - - --- diff --git a/aigw/product/enterprise-offering/budget-policies.mdx b/aigw/product/enterprise-offering/budget-policies.mdx index 45baa0e8..1aea5830 100644 --- a/aigw/product/enterprise-offering/budget-policies.mdx +++ b/aigw/product/enterprise-offering/budget-policies.mdx @@ -4,7 +4,7 @@ description: Create fine-grained controls over API usage and rate limits at the --- -Available on **Enterprise** Self Hosting plan only. +Available on self-hosted deployments. Requires **1.17.0** or higher version of the Gateway. diff --git a/aigw/product/enterprise-offering/org-management.mdx b/aigw/product/enterprise-offering/org-management.mdx index 592a5c24..bae93147 100644 --- a/aigw/product/enterprise-offering/org-management.mdx +++ b/aigw/product/enterprise-offering/org-management.mdx @@ -9,10 +9,6 @@ The account hierarchy in the AI Gateway is organized as follows: This hierarchy allows for efficient management of resources and access control across your organisation. At the top level, you have your Account, which can contain one or more Organisations. Each Organisation can have multiple Workspaces, providing a way to separate teams, projects, or departments within your company. - - **Workspaces** is currently a feature only enabled on the **Enterprise Plans**. If you're looking to add this feature to your organisation, please reach out to us via email on [support@portkey.ai](mailto:support@portkey.ai) - - Organisations contain User Invites & Users, Admin API Keys, and Workspaces. Workspaces, in turn, have their own Team structure (with Managers and Members), Workspace API Keys, and various features like Integrations, Model Catalog, Configs, Prompts, and more. This structure enables you to: diff --git a/aigw/product/enterprise-offering/org-management/api-key-rotation.mdx b/aigw/product/enterprise-offering/org-management/api-key-rotation.mdx index 2ff74d20..f8eac396 100644 --- a/aigw/product/enterprise-offering/org-management/api-key-rotation.mdx +++ b/aigw/product/enterprise-offering/org-management/api-key-rotation.mdx @@ -4,7 +4,7 @@ description: "Periodically replace API key secrets without downtime using manual --- -**Availability:** API key rotation is available on **all plans** (Free, Growth, and Enterprise) on Prisma AIRS AI Gateway Cloud. +**Availability:** API key rotation is available on Prisma AIRS AI Gateway Cloud. For self-hosted deployments: - **Airgapped:** Backend `v1.14.0+` diff --git a/aigw/product/enterprise-offering/org-management/api-keys-authn-and-authz.mdx b/aigw/product/enterprise-offering/org-management/api-keys-authn-and-authz.mdx index ed917e69..b2d39481 100644 --- a/aigw/product/enterprise-offering/org-management/api-keys-authn-and-authz.mdx +++ b/aigw/product/enterprise-offering/org-management/api-keys-authn-and-authz.mdx @@ -45,7 +45,7 @@ Admin API Keys should be carefully managed and their use should be limited to ne | `organisation_guardrails.update` | Modify organisation guardrails | | `organisation_guardrails.delete` | Remove organisation guardrails | | `organisation_guardrails.list` | List organisation guardrails | - | `organisation_exclusions.update` | Exempt workspaces from [organisation-level guardrails](/aigw/product/administration/enforce-orgnization-level-guardrails#excluding-workspaces) | + | `organisation_exclusions.update` | Exempt workspaces from [organisation-level guardrails](/aigw/product/administration/enforce-organisation-level-guardrails#excluding-workspaces) | | `organisation_exclusions.list` | List workspaces exempted from organisation-level guardrails | | `audit_logs.list` | Access system-wide audit logs | | `plugins.create` | Create plugins | diff --git a/aigw/product/enterprise-offering/org-management/gateway-urls.mdx b/aigw/product/enterprise-offering/org-management/gateway-urls.mdx index 9a49b32e..f8ef8772 100644 --- a/aigw/product/enterprise-offering/org-management/gateway-urls.mdx +++ b/aigw/product/enterprise-offering/org-management/gateway-urls.mdx @@ -3,10 +3,6 @@ title: "Gateway URLs" description: "Configure custom gateway endpoints for your organisation's AI gateway and MCP gateway deployments." --- - - Gateway URLs are available on the **Enterprise** plan only. - - The Gateway URLs settings let you point Prisma AIRS AI Gateway at your own self-hosted gateway deployments instead of the AI Gateway's cloud endpoints. Once configured, the dashboard uses your custom URLs when generating code snippets, running playground completions, and constructing MCP server endpoints. Both fields are set at the **organisation level** and apply across all workspaces within that organisation. diff --git a/aigw/product/enterprise-offering/org-management/jwt.mdx b/aigw/product/enterprise-offering/org-management/jwt.mdx index a1fe1c0a..9b539a5c 100644 --- a/aigw/product/enterprise-offering/org-management/jwt.mdx +++ b/aigw/product/enterprise-offering/org-management/jwt.mdx @@ -3,10 +3,6 @@ title: JWT Authentication description: Configure JWT-based authentication for your organisation in Prisma AIRS AI Gateway --- - - This feature is available only on the [Enterprise Plan](/aigw/product/enterprise-offering) of the AI Gateway. - - The AI Gateway supports JWT-based authentication in addition to API key authentication. Clients send a JWT in `x-portkey-api-key` or `Authorization: Bearer`; the token is validated against JWKS configured on the organisation. **AI Gateway Cloud** validates JWTs on the management plane. **[Hybrid](/aigw/self-hosting/hybrid-deployments/architecture) and [air-gapped](/self-hosting/airgapped/model-pricing) deployments** can optionally enable **gateway-local JWT authentication** so the AI Gateway validates tokens locally instead of delegating every request to the management plane. diff --git a/aigw/product/enterprise-offering/org-management/scim/azure-ad.mdx b/aigw/product/enterprise-offering/org-management/scim/azure-ad.mdx index 63c43d4f..62ac2c68 100644 --- a/aigw/product/enterprise-offering/org-management/scim/azure-ad.mdx +++ b/aigw/product/enterprise-offering/org-management/scim/azure-ad.mdx @@ -137,7 +137,3 @@ Then your groups should follow: `ws-{group}{role_separator}{admin,manager,member For detailed instructions, see the [SCIM Group Management](/aigw/product/enterprise-offering/org-management/scim/group-management#configuring-group-naming-format-optional) guide. --- - -### Support - -If you face any issues with the group provisioning, please reach out to us at [here](mailto:support@portkey.ai). diff --git a/aigw/product/enterprise-offering/org-management/scim/group-management.mdx b/aigw/product/enterprise-offering/org-management/scim/group-management.mdx index dd001297..df7bbd30 100644 --- a/aigw/product/enterprise-offering/org-management/scim/group-management.mdx +++ b/aigw/product/enterprise-offering/org-management/scim/group-management.mdx @@ -226,7 +226,3 @@ The flexible group management feature provides several advantages: - **User-based management** - Optionally manage group memberships via the `/Users` endpoint for providers that require it --- - -## Support - -If you encounter any issues with group management or need assistance with mapping groups to workspaces, please contact our support team at [support@portkey.ai](mailto:support@portkey.ai). diff --git a/aigw/product/enterprise-offering/org-management/scim/okta.mdx b/aigw/product/enterprise-offering/org-management/scim/okta.mdx index afb945cf..8c81639a 100644 --- a/aigw/product/enterprise-offering/org-management/scim/okta.mdx +++ b/aigw/product/enterprise-offering/org-management/scim/okta.mdx @@ -151,7 +151,3 @@ To push the groups to the AI Gateway, navigate to the `Push Groups` tab. If it i --- - -### Support - -If you encounter any issues with group provisioning, please reach out to us [here](mailto:support@portkey.ai). diff --git a/aigw/product/enterprise-offering/otel/complete-logs.mdx b/aigw/product/enterprise-offering/otel/complete-logs.mdx index 05df9ce3..b7d8808e 100644 --- a/aigw/product/enterprise-offering/otel/complete-logs.mdx +++ b/aigw/product/enterprise-offering/otel/complete-logs.mdx @@ -5,7 +5,7 @@ description: Export complete LLM request/response logs to OpenTelemetry endpoint --- - This is an experimental feature available for **Enterprise** and **Self-Hosted** deployments only. + This is an experimental feature available for **self-hosted** deployments only. ## Overview diff --git a/aigw/product/enterprise-offering/secret-references.mdx b/aigw/product/enterprise-offering/secret-references.mdx index cc3e39e5..106a36ba 100644 --- a/aigw/product/enterprise-offering/secret-references.mdx +++ b/aigw/product/enterprise-offering/secret-references.mdx @@ -7,7 +7,7 @@ Secret References let you point the AI Gateway to credentials stored in your ext This keeps sensitive material in infrastructure you already control and audit. -Available on **Enterprise** plans only. Requires: +Requires: - Gateway version **2.2.4** or higher - Backend version **1.12.0** or higher (for air-gapped deployments). diff --git a/aigw/product/enterprise-offering/security-portkey.mdx b/aigw/product/enterprise-offering/security.mdx similarity index 99% rename from aigw/product/enterprise-offering/security-portkey.mdx rename to aigw/product/enterprise-offering/security.mdx index da301107..680e8fce 100644 --- a/aigw/product/enterprise-offering/security-portkey.mdx +++ b/aigw/product/enterprise-offering/security.mdx @@ -10,7 +10,7 @@ At the AI Gateway, we understand the critical importance of security in today's ### Authentication -The AI Gateway ensures secure API access through token-based authentication mechanisms, supporting Single Sign-On (SSO) via OIDC on enterprise plans. +The AI Gateway ensures secure API access through token-based authentication mechanisms, supporting Single Sign-On (SSO) via OIDC. We also implement key encryption, which provide an added layer of security by securely storing provider API keys within a controlled and monitored environment. diff --git a/aigw/product/guardrails/list-of-guardrail-checks.mdx b/aigw/product/guardrails/list-of-guardrail-checks.mdx index 424fea21..0a5b59ac 100644 --- a/aigw/product/guardrails/list-of-guardrail-checks.mdx +++ b/aigw/product/guardrails/list-of-guardrail-checks.mdx @@ -177,9 +177,6 @@ Each Guardrail Check has a specific purpose, it's own parameters, supported hook Along with the partner Guardrails, there are also deterministic as well as LLM-based Guardrails supported natively by the AI Gateway. - - `BASIC` Guardrails are available on all AI Gateway plans. - - `PRO` Guardrails are available on AI Gateway Pro & Enterprise plans. - ### Understanding Supported Hooks * `input_guardrails`: Runs on the user's prompt *before* calling the model. diff --git a/aigw/product/mcp-gateway/advanced-configuration.mdx b/aigw/product/mcp-gateway/advanced-configuration.mdx index e24657a7..13f8a2e9 100644 --- a/aigw/product/mcp-gateway/advanced-configuration.mdx +++ b/aigw/product/mcp-gateway/advanced-configuration.mdx @@ -122,7 +122,7 @@ Supports three validation methods: **JWKS URI**, **inline JWKS keys**, and **tok ## External Auth Config -Enterprise only — available for self-hosted deployments. +Available for self-hosted deployments. Use an external identity provider (Okta, Auth0, Azure AD, Cognito) instead of the AI Gateway's built-in OAuth. Users authenticate with corporate credentials. diff --git a/aigw/product/mcp-gateway/authentication.mdx b/aigw/product/mcp-gateway/authentication.mdx index f7e2cb95..2cda4aa9 100644 --- a/aigw/product/mcp-gateway/authentication.mdx +++ b/aigw/product/mcp-gateway/authentication.mdx @@ -162,7 +162,7 @@ See [Forwarding Headers](/aigw/product/mcp-gateway/authentication/forwarding-hea Credentials never cross boundaries. ``` -Agent knows: Portkey API key +Agent knows: Gateway API key Portkey knows: MCP server OAuth tokens, API keys, user identity claims MCP Server knows: Its own credentials ``` diff --git a/aigw/product/mcp-gateway/authentication/custom-auth.mdx b/aigw/product/mcp-gateway/authentication/custom-auth.mdx index ec61cdc7..41b639e7 100644 --- a/aigw/product/mcp-gateway/authentication/custom-auth.mdx +++ b/aigw/product/mcp-gateway/authentication/custom-auth.mdx @@ -215,7 +215,7 @@ Headers configured in the MCP Registry are stored encrypted. They're never expos ### Credential Isolation ``` -Agent knows: Portkey API key only +Agent knows: Gateway API key only Portkey knows: MCP server auth headers MCP Server knows: Its own credentials ``` diff --git a/aigw/product/mcp-gateway/authentication/external-oauth.mdx b/aigw/product/mcp-gateway/authentication/external-oauth.mdx index 653e2875..07f581db 100644 --- a/aigw/product/mcp-gateway/authentication/external-oauth.mdx +++ b/aigw/product/mcp-gateway/authentication/external-oauth.mdx @@ -22,7 +22,7 @@ Common scenarios: ``` 1. The request authenticates to the Portkey gateway - (Portkey API key, or a JWT carrying Portkey org claims) + (Gateway API key, or a JWT carrying Portkey org claims) 2. User authenticates with your IdP and obtains a token (JWT or opaque) 3. User includes that token in the MCP request to Portkey 4. Portkey validates the token against your IdP (JWKS or introspection) diff --git a/aigw/product/model-catalog/connect-bedrock-with-amazon-assumed-role.mdx b/aigw/product/model-catalog/connect-bedrock-with-amazon-assumed-role.mdx index 5097e50c..67d60004 100644 --- a/aigw/product/model-catalog/connect-bedrock-with-amazon-assumed-role.mdx +++ b/aigw/product/model-catalog/connect-bedrock-with-amazon-assumed-role.mdx @@ -3,8 +3,8 @@ title: "Connect Bedrock with Amazon Assumed Role" description: "How to create an integrate Bedrock using Amazon Assumed Role Authentication on Prisma AIRS AI Gateway" --- - - On the Enterprise plan and need to connect to Bedrock using an AWS assumed role? Check out the documentation here. + + Connecting to Bedrock using an AWS assumed role? Check out the documentation here. ## Select AWS Assumed Role Authentication diff --git a/aigw/product/model-catalog/portkey-models.mdx b/aigw/product/model-catalog/gateway-models.mdx similarity index 100% rename from aigw/product/model-catalog/portkey-models.mdx rename to aigw/product/model-catalog/gateway-models.mdx diff --git a/aigw/product/model-catalog/pricing-adjustments.mdx b/aigw/product/model-catalog/pricing-adjustments.mdx index 63985c33..73f4dda9 100644 --- a/aigw/product/model-catalog/pricing-adjustments.mdx +++ b/aigw/product/model-catalog/pricing-adjustments.mdx @@ -79,7 +79,7 @@ For other token types — reasoning, audio/image/text variants, image generation } ``` -The multiplier keys mirror the pricing keys in [AI Gateway Models](/aigw/product/model-catalog/portkey-models) — the open-source pricing database backing the AI Gateway's cost tracking. Any key present in a model's `pay_as_you_go` (or in `additional_units`) can be adjusted here. +The multiplier keys mirror the pricing keys in [AI Gateway Models](/aigw/product/model-catalog/gateway-models) — the open-source pricing database backing the AI Gateway's cost tracking. Any key present in a model's `pay_as_you_go` (or in `additional_units`) can be adjusted here. @@ -94,7 +94,7 @@ The multiplier keys mirror the pricing keys in [AI Gateway Models](/aigw/product | `request_image_token` / `response_image_token` / `cache_*_image_input_token` | Image-modality breakdowns | | `prediction_accepted_token` / `prediction_rejected_token` | Predicted-output tokens | | `image.default` | Per-image generation pricing across all qualities and sizes | -| `additional_units.` | Per-unit charges such as `web_search`, `file_search`, `input_image`, `input_video_standard`. See [Additional Units Reference](/aigw/product/model-catalog/portkey-models#additional-units-reference). | +| `additional_units.` | Per-unit charges such as `web_search`, `file_search`, `input_image`, `input_video_standard`. See [Additional Units Reference](/aigw/product/model-catalog/gateway-models#additional-units-reference). | diff --git a/aigw/product/observability/logs-export.mdx b/aigw/product/observability/logs-export.mdx index c961adb4..fe38b3e8 100644 --- a/aigw/product/observability/logs-export.mdx +++ b/aigw/product/observability/logs-export.mdx @@ -3,10 +3,6 @@ title: "Logs Export" description: "Easily access your Prisma AIRS AI Gateway logs data for further analysis and reporting" --- - - Logs export feature is only available on the enterprise plan. For more info reach us at support@portkey.ai - - [Data Service](/aigw/changelog/data-service) must be enabled to use the Logs Export feature for Self Hosted Enterprise customers. @@ -300,8 +296,6 @@ Here's a complete script that creates, starts, monitors, and downloads a log exp ## Support -If you have any questions or need assistance with the logs export feature, reach out to the Palo Alto Networks team at [support@portkey.ai](mailto:support@portkey.ai). - diff --git a/aigw/product/observability/metadata.mdx b/aigw/product/observability/metadata.mdx index 543ec5eb..b4562a2f 100644 --- a/aigw/product/observability/metadata.mdx +++ b/aigw/product/observability/metadata.mdx @@ -112,7 +112,7 @@ You can also apply any metadata filters to the logs or analytics and filter data ## Automatic Metadata from Headers (Self-Hosted) -Available on **Enterprise** Self Hosting plan. Requires gateway **2.5.0** or higher. +Available on self-hosted deployments. Requires gateway **2.5.0** or higher. For self-hosted deployments, you can automatically inject request header values into metadata using the `HEADERS_TO_METADATA` environment variable. This is useful for enriching observability data with upstream context without requiring clients to set `x-portkey-metadata`. diff --git a/aigw/scripts/strip_ctas.py b/aigw/scripts/strip_ctas.py new file mode 100644 index 00000000..d2e7c9c6 --- /dev/null +++ b/aigw/scripts/strip_ctas.py @@ -0,0 +1,152 @@ +#!/usr/bin/env python3 +"""Phase 5 — strip sales CTAs and support "reach out" trailers from aigw/. + +Handles only the shapes that repeat verbatim across many pages. Anything it does +not recognise is left alone and reported, so it gets a hand edit instead of a +guess. Idempotent: running it twice changes nothing the second time. + +Deliberately line-based rather than a whole-file regex. A global blank-line +collapse reflows spacing the corpus already had, which is hundreds of files of +diff noise for no change in rendered output — so each removal instead consumes +its own adjacent blank line and nothing else is touched. +""" + +import re +import sys +from pathlib import Path + +ROOT = Path(__file__).resolve().parent.parent +REPO = ROOT.parent +TARGETS = [ROOT, REPO / "snippets" / "aigw"] + +# Standalone trailer paragraphs. Each is a whole line existing only to ask the +# reader to make contact; removing the line leaves the section coherent. +TRAILERS = [ + re.compile(p, re.IGNORECASE) + for p in [ + r"^If you (?:face|encounter|run into) any (?:issues|problems)[^\n]*" + r"(?:reach out|contact|email)", + r"^\*{0,2}Need help\?\*{0,2}[^\n]*(?:reach out|contact)", + r"^For (?:more help|further questions|questions about)[^\n]*" + r"(?:reach out|reach us|contact)", + r"^If you have any questions[^\n]*(?:reach out|contact)", + ] +] + +CARD_OPEN = re.compile(r"^\s*\s*$") +HEADING = re.compile(r"^#{2,4} ") +RULE = re.compile(r"^-{3,}\s*$") + +# Left for a hand edit: these need surrounding prose rewritten, not a line cut. +NEEDS_HAND_EDIT = re.compile( + r"Interested\? Schedule a Call" + r"|schedule a (?:quick call|consultation)" + r"|Reach out to our team" + r"|Book a call" + r"|cal\.link", + re.IGNORECASE, +) + + +def drop(lines, i): + """Delete line i plus one adjacent blank, so no blank run is created.""" + del lines[i] + if i < len(lines) and not lines[i].strip(): + del lines[i] + elif i > 0 and not lines[i - 1].strip(): + del lines[i - 1] + return i - 1 + return i + + +def strip_cards(lines): + i = 0 + while i < len(lines): + if CARD_OPEN.match(lines[i]): + j = i + while j < len(lines) and not CARD_CLOSE.match(lines[j]): + j += 1 + del lines[i:j + 1] + if i < len(lines) and not lines[i].strip(): + del lines[i] + elif i > 0 and not lines[i - 1].strip(): + del lines[i - 1] + i -= 1 + continue + i += 1 + return lines + + +def strip_trailers(lines): + i = 0 + while i < len(lines): + if any(t.match(lines[i]) for t in TRAILERS): + i = drop(lines, i) + continue + i += 1 + return lines + + +def empty_headings(lines): + """Indices of headings whose body is blank up to the next heading, a + horizontal rule, or EOF.""" + out = set() + for i, line in enumerate(lines): + if HEADING.match(line): + rest = [x for x in lines[i + 1:] if x.strip()] + if not rest or HEADING.match(rest[0]) or RULE.match(rest[0]): + out.add(line.strip()) + return out + + +def drop_new_orphans(before, after): + """Delete headings this run emptied. + + A "## Get Support" whose only content was the removed trailer is now a + heading with no body. Headings already empty beforehand are pre-existing + structure and are left alone. + """ + orphaned = empty_headings(after) - empty_headings(before) + if not orphaned: + return after + i = 0 + while i < len(after): + if after[i].strip() in orphaned: + i = drop(after, i) + continue + i += 1 + return after + + +def main() -> int: + changed, flagged = [], [] + + for target in TARGETS: + for path in sorted(target.rglob("*.mdx")): + if "_project" in path.parts: + continue + original = path.read_text() + before = original.split("\n") + lines = strip_trailers(strip_cards(list(before))) + if lines != before: + lines = drop_new_orphans(before, lines) + + text = "\n".join(lines) + if text != original: + path.write_text(text) + changed.append(path.relative_to(REPO)) + if NEEDS_HAND_EDIT.search(text): + flagged.append(path.relative_to(REPO)) + + print(f"rewritten: {len(changed)}") + for p in changed: + print(f" {p}") + print(f"\nneeds a hand edit: {len(flagged)}") + for p in flagged: + print(f" {p}") + return 0 + + +if __name__ == "__main__": + sys.exit(main()) diff --git a/aigw/self-hosting/hybrid-deployments/aws/eks.mdx b/aigw/self-hosting/hybrid-deployments/aws/eks.mdx index 9dca4eee..0ec8e4bf 100644 --- a/aigw/self-hosting/hybrid-deployments/aws/eks.mdx +++ b/aigw/self-hosting/hybrid-deployments/aws/eks.mdx @@ -337,9 +337,9 @@ To confirm that the deployment was successful, follow these steps: 2. Once port forwarding is active, open a new terminal window or tab and send a test request by running: ```sh - # Specify LLM provider and Portkey API keys + # Specify LLM provider and Gateway API keys OPENAI_API_KEY= # Replace with an actual API key - PORTKEY_API_KEY= # Replace with Portkey API key which can be created from Portkey website(https://stratacloudmanager.paloaltonetworks.com/). + PORTKEY_API_KEY= # Replace with Gateway API Key which can be created from Strata Cloud Manager(https://stratacloudmanager.paloaltonetworks.com/). # Configure and send the curl request curl 'http://localhost:9000/v1/chat/completions' \ diff --git a/aigw/self-hosting/hybrid-deployments/azure/aks.mdx b/aigw/self-hosting/hybrid-deployments/azure/aks.mdx index fdf189bd..a788d0a6 100644 --- a/aigw/self-hosting/hybrid-deployments/azure/aks.mdx +++ b/aigw/self-hosting/hybrid-deployments/azure/aks.mdx @@ -393,9 +393,9 @@ To confirm that the deployment was successful, follow these steps: 2. Once port forwarding is active, open a new terminal window or tab and send a test request by running: ```sh - # Specify LLM provider and Portkey API keys + # Specify LLM provider and Gateway API keys OPENAI_API_KEY= # Replace with an actual API key - PORTKEY_API_KEY= # Replace with Portkey API key which can be created from Portkey website(https://stratacloudmanager.paloaltonetworks.com/). + PORTKEY_API_KEY= # Replace with Gateway API Key which can be created from Strata Cloud Manager(https://stratacloudmanager.paloaltonetworks.com/). # Configure and send the curl request curl 'http://localhost:9000/v1/chat/completions' \ diff --git a/aigw/self-hosting/hybrid-deployments/gateway-registration.mdx b/aigw/self-hosting/hybrid-deployments/gateway-registration.mdx index 9e869ff6..8b814d45 100644 --- a/aigw/self-hosting/hybrid-deployments/gateway-registration.mdx +++ b/aigw/self-hosting/hybrid-deployments/gateway-registration.mdx @@ -35,10 +35,6 @@ Fill in the following fields: ## Step 2: Workspace Provisioning - - Workspace Provisioning is available on the **Hybrid Enterprise plan** only. - - Choose which workspaces in your organisation will have access to this gateway. ### Workspace Access Options diff --git a/aigw/self-hosting/hybrid-deployments/gcp.mdx b/aigw/self-hosting/hybrid-deployments/gcp.mdx index 74fd9423..00f79557 100644 --- a/aigw/self-hosting/hybrid-deployments/gcp.mdx +++ b/aigw/self-hosting/hybrid-deployments/gcp.mdx @@ -344,9 +344,9 @@ To confirm that the deployment was successful, follow these steps: 2. Once port forwarding is active, open a new terminal window or tab and send a test request by running: ```sh - # Specify LLM provider and Portkey API keys + # Specify LLM provider and Gateway API keys OPENAI_API_KEY= # Replace with an actual API key - PORTKEY_API_KEY= # Replace with Portkey API key which can be created from Portkey website(https://stratacloudmanager.paloaltonetworks.com/). + PORTKEY_API_KEY= # Replace with Gateway API Key which can be created from Strata Cloud Manager(https://stratacloudmanager.paloaltonetworks.com/). # Configure and send the curl request curl 'http://localhost:9000/v1/chat/completions' \ diff --git a/docs.json b/docs.json index 60dac558..a5ec78c8 100644 --- a/docs.json +++ b/docs.json @@ -9,10 +9,6 @@ "dark": "#0891B2" }, "favicon": "/favicon.png", - "banner": { - "content": "🚀 Introducing **[Agent Gateway](https://portkey.sh/agent-gateway)** — governance, observability, and control for your AI agents.   [Register for live webinar ↗](https://portkey.sh/agent-webinar)", - "dismissible": true - }, "navigation": { "versions": [ { @@ -1471,8 +1467,8 @@ { "group": "Introduction", "pages": [ - "aigw/introduction/what-is-portkey", - "aigw/introduction/make-your-first-request", + "aigw/introduction/welcome", + "aigw/introduction/simple-setup", "aigw/introduction/feature-overview" ] }, @@ -1561,7 +1557,7 @@ "group": "Model Catalog", "pages": [ "aigw/product/model-catalog", - "aigw/product/model-catalog/portkey-models", + "aigw/product/model-catalog/gateway-models", "aigw/product/model-catalog/integrations", "aigw/product/model-catalog/budget-limits", "aigw/product/model-catalog/rate-limits", @@ -1647,13 +1643,13 @@ "group": "Administration", "pages": [ "aigw/product/administration/enforcing-request-metadata", - "aigw/product/administration/enforce-orgnization-level-guardrails", - "aigw/product/administration/enforce-workspace-level-guardials", + "aigw/product/administration/enforce-organisation-level-guardrails", + "aigw/product/administration/enforce-workspace-level-guardrails", "aigw/product/administration/configuring-request-logging", "aigw/product/administration/enforce-default-config", "aigw/product/administration/enforce-saved-only-config", "aigw/product/administration/enforce-budget-and-rate-limit", - "aigw/product/administration/enforce-workspace-budget-limts-and-rate-limits", + "aigw/product/administration/enforce-workspace-budget-and-rate-limits", "aigw/product/administration/configure-logs-access-permissions-in-workspace", "aigw/product/administration/configure-analytics-access-permissions", "aigw/product/administration/configure-data-visibility-settings", @@ -1663,7 +1659,7 @@ "aigw/product/administration/configure-guardrail-access-permissions", "aigw/product/administration/configure-integration-access-permissions", "aigw/product/administration/configure-workspace-provisioning-for-your-ai-integrations", - "aigw/product/administration/configure-model-access-permissioning-for-ai-integratinon", + "aigw/product/administration/configure-model-access-permissioning-for-ai-integrations", "aigw/product/administration/enforce-rate-limits-on-your-ai-provider", "aigw/product/administration/enforce-budget-limits-on-your-ai-provider" ] @@ -1703,7 +1699,7 @@ }, "aigw/product/enterprise-offering/access-control-management", "aigw/product/enterprise-offering/budget-limits", - "aigw/product/enterprise-offering/security-portkey", + "aigw/product/enterprise-offering/security", { "group": "OpenTelemetry(OTel)", "pages": [