diff --git a/fern/docs.yml b/fern/docs.yml index d70957c..55e968d 100644 --- a/fern/docs.yml +++ b/fern/docs.yml @@ -12,7 +12,8 @@ tabs: display-name: Home icon: home deployment: - display-name: Deployment & Administration + display-name: Administration & Governance + slug: admin icon: server development: display-name: Development and Integration @@ -58,36 +59,39 @@ navigation: path: ./docs/pages/deployment/overview.mdx - section: Installation contents: - - section: On-Premises - contents: - - page: Kubernetes - path: ./docs/pages/deployment/kubernetes.mdx - - page: Zero Dependency Binary - path: ./docs/pages/deployment/binary.mdx - section: Cloud contents: - - page: AWS - path: ./docs/pages/deployment/aws.mdx - - page: Azure - path: ./docs/pages/deployment/azure.mdx - page: GCP path: ./docs/pages/deployment/gcp.mdx + - page: Azure + path: ./docs/pages/deployment/azure.mdx + - page: AWS + path: ./docs/pages/deployment/aws.mdx - section: Air Gapped contents: - page: Air Gapped path: ./docs/pages/deployment/air-gapped.mdx + - section: On-Premises + contents: + - page: Kubernetes + path: ./docs/pages/deployment/kubernetes.mdx + - page: Zero Dependency Binary + path: ./docs/pages/deployment/binary.mdx - section: Administration contents: - - page: Admin Panel + - page: Admin Console path: ./docs/pages/deployment/admin-panel.mdx - - page: Clusters + - page: Create an AI System + path: ./docs/pages/deployment/custom_system.mdx + - page: AI System Management path: ./docs/pages/deployment/cluster-management.mdx - - page: Models + + - page: Model Management path: ./docs/pages/deployment/model-management.mdx - page: API Keys path: ./docs/pages/deployment/api-keys.mdx - - page: Security & Monitoring - path: ./docs/pages/deployment/security-monitoring.mdx + - page: Monitoring + path: ./docs/pages/deployment/monitoring.mdx - tab: development layout: - section: Getting Started diff --git a/fern/docs/pages/agent-forge/building-agents.mdx b/fern/docs/pages/agent-forge/building-agents.mdx index c5adf64..77c47c2 100644 --- a/fern/docs/pages/agent-forge/building-agents.mdx +++ b/fern/docs/pages/agent-forge/building-agents.mdx @@ -198,7 +198,7 @@ When explaining code vulnerabilities, provide: - ✅ When using MCP tool calls -**MCP requires "Non-streaming (with MCP capabilities)" mode**: If you plan to connect your agent to external tools via [MCP Integration](/agent-forge/using-agent-forge/mcp), make sure you choose the right mode. MCP tool calls execute in real-time and stream results back as they arrive. +**MCP requires "Non-streaming (with MCP capabilities)" mode**: If you plan to connect your agent to external tools via [MCP Integration](/agent-forge/using-agent-forge/mcp-integration), make sure you choose the right mode. MCP tool calls execute in real-time and stream results back as they arrive. ## Generation Settings (Advanced Settings) @@ -448,6 +448,6 @@ After creation, thoroughly test your agent: Now that you can build agents: -1. **[Configure MCP](/agent-forge/using-agent-forge/mcp)** - Connect your agent to external tools and live data sources +1. **[Configure MCP](/agent-forge/using-agent-forge/mcp-integration)** - Connect your agent to external tools and live data sources 2. **[Create Knowledge Bases](/agent-forge/using-agent-forge/knowledge-base)** - Add organizational knowledge to your agents 3. **[Share with Team](/agent-forge/using-agent-forge/chatting-with-agents)** - Enable organization sharing and collaborate \ No newline at end of file diff --git a/fern/docs/pages/agent-forge/mcp.mdx b/fern/docs/pages/agent-forge/mcp.mdx index bf65e0f..6644cb5 100644 --- a/fern/docs/pages/agent-forge/mcp.mdx +++ b/fern/docs/pages/agent-forge/mcp.mdx @@ -21,7 +21,7 @@ Agent Forge supports MCP at two levels: | Level | Configured By | Available To | |-------|--------------|--------------| -| **Organization-level** | Admin via Unified CX (coming soon!) | All agents in the organization | +| **Organization-level** | Admin via Admin Console (coming soon!) | All agents in the organization | | **Agent-level** | Agent Builder and above | That specific agent only | This layered approach lets administrators centrally manage shared infrastructure while allowing individual agent builders to extend with specialized tools. diff --git a/fern/docs/pages/agent-forge/overview.mdx b/fern/docs/pages/agent-forge/overview.mdx index 4cdc12b..441eb5e 100644 --- a/fern/docs/pages/agent-forge/overview.mdx +++ b/fern/docs/pages/agent-forge/overview.mdx @@ -125,5 +125,5 @@ Ready to get started? Continue with: - [Getting Started](/agent-forge/getting-started/getting-started) - Account setup and first login - [Chatting with Agents](/agent-forge/using-agent-forge/chatting-with-agents) - Learn the chat interface - [Building Agents](/agent-forge/using-agent-forge/building-agents) - Create your first agent -- [MCP Integration](/agent-forge/using-agent-forge/mcp) - Connect agents to external tools and data sources +- [MCP Integration](/agent-forge/using-agent-forge/mcp-integration) - Connect agents to external tools and data sources - [Knowledge Base](/agent-forge/using-agent-forge/knowledge-base) - Add RAG-based knowledge base to agents \ No newline at end of file diff --git a/fern/docs/pages/deployment/admin-panel.mdx b/fern/docs/pages/deployment/admin-panel.mdx index 2a82036..3378622 100644 --- a/fern/docs/pages/deployment/admin-panel.mdx +++ b/fern/docs/pages/deployment/admin-panel.mdx @@ -1,120 +1,131 @@ -# Admin Panel +--- +title: Admin Console +subtitle: Central control plane for managing your sovereign AI systems +description: Overview of the Admin Console — manage systems, models, API keys, governance policies, and monitor activity across your infrastructure +--- + +The Prediction Guard Admin Console is your central control plane for managing your sovereign AI systems. From here, you can create and manage multiple systems, deploy any open model, manage API keys, configure MCP servers, apply governance policies, and monitor all activity across your infrastructure. + +## Accessing the Admin Console + +Once deployed, access the Admin Console at your deployment's URL (e.g. [admin.predictionguard.com](https://admin.predictionguard.com)) and log in with your admin credentials. + +## Navigation + +The Admin Console sidebar is organized into three groups: + +**Systems** +- **Manage** — Create, view, and manage all your AI systems + +**Security** +- **Analyze** — Analyze AI interactions for security and compliance signals +- **Monitor** — Real-time monitoring of system usage and performance +- **Govern** — Configure and apply AI governance policies +- **Audit** — Review audit logs and compliance reports + +**Settings** +- **Users** — Manage user accounts and access +- **Organizations** — Manage organizational settings and structure + +## Systems: Manage + +The Systems page is your starting point — a unified view of all AI systems in your Prediction Guard deployment. + +![Systems Page](./ux-screenshots/01-systems.png) + +Each system card shows: +- **Status**: Health state (Healthy, Never Connected, Degraded) +- **API Keys**: Number of active API keys +- **Models**: Number of deployed models +- **MCP Servers**: Number of connected MCP servers +- **Location**: Deployment environment (e.g. `kubernetes`, `staging`) +- **Last Update**: Time of last heartbeat from the system + +Click **Manage** on any system card to open its management dashboard, where you can configure API keys, models, MCP servers, and advanced settings. Click **Create System** to add a new system. + +## Security: Analyze + +The Analyze section gives you visibility into the safety and composition of all AI models across your systems. It has two tabs: **Scans** and **BOMs**. + +### Scans + +![Analyze - Scans](./ux-screenshots/analyze-page-scans.png) -The Prediction Guard admin panel is your central command center for managing your entire Prediction Guard platform. From here, you can create and manage multiple clusters, deploy any open model, configure security settings, and monitor all activity across your infrastructure. +The Scans tab shows safety and security scores for every AI model in your deployment. At a glance you can see: -## Accessing the Admin Panel +- **Models Scanned**: Total number of models that have been analyzed +- **Avg. General Safety Score**: Average safety score across all scanned models (0–100) +- **Avg. Prompt Injection Refusal Rate**: How reliably models resist prompt injection attempts on average -Once your Prediction Guard instance is deployed, you can access the admin panel at: +The model table breaks this down per model, showing **Provider**, **Type**, **General Safety Score**, **Prompt Injection Refusal Rate**, and **Last Scan** date. Use this to compare models, identify weaker performers, and make informed decisions about which models to deploy in sensitive environments. -``` -https://admin.predictionguard.com -``` +### BOMs (Bill of Materials) -The admin panel is centrally managed by Prediction Guard, providing you with access to manage your clusters and deployments. +![Analyze - BOMs](./ux-screenshots/analyze-page-bom.png) -### Initial Setup +The BOMs tab provides a Bill of Materials for each AI system — a full inventory of everything running in that system: -1. **Login** with your admin credentials -2. **Configure basic settings** (organization name, timezone, etc.) -3. **Set up your first API key** for testing -4. **Deploy your first model** from the model library +- **Private Models**: Models you have deployed from your own repositories +- **Managed Models**: Models managed and maintained by Prediction Guard +- **External Models**: Third-party models connected to your system +- **MCP Servers**: Connected Model Context Protocol servers -## Key Features +See [Model Management](/admin/administration/model-management) for a full guide to deploying all three model types. -### Dashboard -![Admin Panel Dashboard](./admin-panel-dashboard.png) +Each system has an **Export BOM** button to download a full inventory report — useful for compliance audits, vendor assessments, and internal governance reviews. -The dashboard provides a comprehensive overview of your Prediction Guard platform: -- **Multi-cluster overview** with health status across all clusters -- **Real-time usage statistics** and performance metrics -- **Security alerts** and system notifications -- **Quick actions** for common administrative tasks -- **Resource utilization** across your infrastructure +## Security: Monitor -### Model Management -- **Browse available models** from Hugging Face -- **Deploy custom models** from your own repositories -- **Configure model settings** (temperature, max tokens, etc.) -- **Monitor model performance** and usage +The Monitor section provides real-time observability into your AI systems — tracking request volumes, latency, model performance, and resource utilization. Use this to detect anomalies, track usage trends, and ensure your systems are operating within expected parameters. -### API Key Management -- **Create and manage** API keys -- **Set permissions** and rate limits -- **Track usage** per API key -- **Revoke access** when needed +## Security: Govern -### System Configuration -- **Security settings** and policies -- **Resource allocation** and limits -- **Backup and recovery** options -- **Update management** and versioning +The Govern section is where you configure and apply AI governance policies system-wide. Policies set here are enforced across all agents and models within your systems without requiring per-agent configuration. -## Platform Workflow +### Governance Baselines -### After Deployment -Once you've deployed your Prediction Guard cluster, the admin panel becomes your central management hub: +![Govern - Standards](./ux-screenshots/govern-page-standards.png) -1. **Cluster Management**: Monitor and manage your deployed clusters -2. **Model Deployment**: Deploy models from Hugging Face or upload custom models -3. **API Key Management**: Create and manage API keys for application access -4. **Security Configuration**: Set up security policies and monitoring -5. **Monitoring**: Track usage, performance, and security across your platform +Prediction Guard ships with four pre-built governance baselines you can apply with a single click: -### Integration with Deployment Process -The admin panel integrates seamlessly with your deployment: +| Baseline | Description | +|----------|-------------| +| **NIST AI RMF** | The NIST AI Risk Management Framework. Sets recommended thresholds for PII protection, prompt injection detection, toxicity filtering, and factuality checks aligned with NIST's trustworthy AI principles. | +| **NIST 600-1** | The Generative AI Profile of the AI RMF, focused on risks specific to large language models. Tunes factuality, toxicity, and PII policies to stricter thresholds recommended for generative AI deployments. | +| **OWASP** | Based on the OWASP Top 10 for LLM Applications. Directly addresses prompt injection, sensitive data exposure, and toxic or harmful outputs. | +| **OMB M-26-04** | The Office of Management and Budget Memorandum M-26-04, which sets federal requirements for responsible AI use. Enforces PII protections, prompt injection defenses, and factuality/toxicity policies at federally recommended thresholds. | -- **Cluster Status**: View health and status of all deployed clusters -- **Resource Monitoring**: Track CPU, GPU, and memory usage across clusters -- **Model Management**: Deploy and configure models on your clusters -- **API Access**: Create keys for applications to access your deployed models -- **Security Management**: Configure and monitor security across your platform +Click **Apply Configuration** on any baseline to apply it as your system-wide governance policy. -## Quick Start Guide +### Custom Governance Configuration -### 1. Deploy Your First Model +![Govern - Custom Configuration](./ux-screenshots/govern-page-custom-config.png) -1. Navigate to **Models** → **Browse Library** -2. Search for a model (e.g., "llama-2-7b-chat") -3. Click **Deploy** and configure settings -4. Wait for deployment to complete -5. Test the model via API +Below the baselines, the **Governance Configuration** section lets you fine-tune individual policies. Each policy can be independently enabled or disabled, and configured with specific actions: -### 2. Create an API Key +| Policy | Purpose | Available Actions | +|--------|---------|-------------------| +| **PII Policy** | Prevent unauthorized disclosure, storage, or processing of PII within your AI systems | Block, Log Events | +| **Prompt Injection Policy** | Prevent jailbreaking or manipulation of AI instructions to bypass safety filters or access restricted data | Block, Log Events | +| **Toxicity Policy** | Ensure AI outputs remain professional, inclusive, and free from harmful or discriminatory content | Block, Log Events | +| **Factuality Policy** | Mitigate hallucinations and ensure AI-generated information is verifiable | Block | -1. Go to **API Keys** → **Create New** -2. Set a name and description -3. Configure permissions and rate limits -4. Copy the generated key securely -5. Test with a simple API call + +Applying a governance baseline will pre-configure these toggles to the recommended settings for that standard. You can then adjust individual policies from the custom configuration below. + -### 3. Configure Security +## Security: Audit -1. Review **Security** → **Policies** -2. Enable input/output filtering as needed -3. Set up PII detection rules -4. Configure injection prevention -5. Test security features +The Audit section provides a tamper-evident log of all significant actions and interactions across your Admin Console — including system changes, model deployments, API key activity, and user actions. Use this for compliance reporting, incident investigation, and access reviews. -## Best Practices +## Settings: Users -### Security -- **Use strong passwords** for admin accounts -- **Enable two-factor authentication** if available -- **Regularly rotate API keys** -- **Monitor access logs** for suspicious activity +Manage user accounts that have access to the Admin Console. From here you can invite new administrators, update roles, and revoke access. -### Model Management -- **Start with smaller models** for testing -- **Monitor resource usage** during deployment -- **Keep models updated** for security patches -- **Document model configurations** for team members +## Settings: Organizations -### Monitoring -- **Set up alerts** for system health -- **Monitor API usage** and performance -- **Track model inference** metrics -- **Review logs** regularly for issues +Configure organizational settings including your organization's name, structure, and any organization-wide defaults that apply across all systems. --- -**Complete documentation coming soon** - Detailed guides for each admin panel feature are being developed. +**Need help?** Contact our support team or join our Discord community for assistance. diff --git a/fern/docs/pages/deployment/air-gapped.mdx b/fern/docs/pages/deployment/air-gapped.mdx index 8a789c8..7c6c5f8 100644 --- a/fern/docs/pages/deployment/air-gapped.mdx +++ b/fern/docs/pages/deployment/air-gapped.mdx @@ -1,6 +1,8 @@ -# Air Gapped Deployment - -Deploy Prediction Guard in completely isolated environments with no external internet access. +--- +title: Air Gapped Deployment +subtitle: Deploy Prediction Guard in completely isolated environments with no external internet access +description: Step-by-step guide to deploying Prediction Guard in an air-gapped environment using offline installation packages +--- ## Prerequisites @@ -10,13 +12,13 @@ Deploy Prediction Guard in completely isolated environments with no external int - **Docker** pre-installed or installation package - **No internet access** required after initial setup -## Create Your Cluster in the Prediction Guard Admin +## Create Your System in the Admin Console 1. Navigate and login to admin.predictionguard.com -2. View the *Clusters* page and click on **+ Create Cluster** in the top-right. -3. Provide a Cluster Name -4. Enable **Air-Gapped Cluster** option -5. Click **Create Cluster.** +2. View the *Systems* page and click on **+ Create System** in the top-right. +3. Provide a System Name +4. Enable **Air-Gapped System** option +5. Click **Create System.** ## Installation Instructions @@ -32,22 +34,21 @@ tar xvzf prediction-guard-air-gapped.tgz sudo ./prediction-guard-air-gapped install --license license.yaml ``` -Provide a password for the local admin console. This is rarely used, but can be helpful for updating certain fields for offline clusters. The installer will run through a series of pre-flight checks to ensure compatibility. If any of the pre-flight checks fail, a message will be displayed regarding which checks are failing. Either attempt to address and resolve the issue (some are related to available disk space, performance, etc.) or reach out to your Prediction Guard account representative for assistance. Once the installer has completed, proceed to step 4. +Provide a password for the local admin console. This is rarely used, but can be helpful for updating certain fields for offline systems. The installer will run through a series of pre-flight checks to ensure compatibility. If any of the pre-flight checks fail, a message will be displayed regarding which checks are failing. Either attempt to address and resolve the issue (some are related to available disk space, performance, etc.) or reach out to your Prediction Guard account representative for assistance. Once the installer has completed, proceed to step 4. -4. Shell into the cluster to run the bootstrap command: +4. Shell into the system to run the bootstrap command: ```bash sudo ./prediction-guard-air-gapped shell ``` -5. Retrieve the bootstrap command from [admin.predictionguard.com](https://admin.predictionguard.com) by navigating to Clusters, then clicking the **Deploy** button in the row of the cluster you wish to deploy. Click the **Copy** button above the deploy command and proceed to step 6. +5. Retrieve the bootstrap command from [admin.predictionguard.com](https://admin.predictionguard.com) by navigating to Systems, then clicking the **Deploy** button in the row of the system you wish to deploy. Click the **Copy** button above the deploy command and proceed to step 6. -6. Paste the bootstrap command into the terminal where you are shelled into the cluster. This will install your authentication token and begin the initial bootstrapping of Prediction Guard services. After a few minutes, feel free to check the installation by checking the running services: +6. Paste the bootstrap command into the terminal where you are shelled into the system. This will install your authentication token and begin the initial bootstrapping of Prediction Guard services. After a few minutes, feel free to check the installation by checking the running services: ```bash docker ps | grep predictionguard ``` -You should see running services, including `pg-inside` indicating that the cluster has been successfully installed. The cluster should also show as **Healthy** in the Prediction Guard admin. - -7. Deploy any desired AI models from the Models page in the Prediction Guard admin. Pay attention to any settings around number of AI accelerators, CPU and memory allocation to the model and ensure it fits within your air-gapped environment. +You should see running services, including `pg-inside` indicating that the system has been successfully installed. The system should also show as **Healthy** in the Admin Console. +7. Deploy any desired AI models from the Models page in the Admin Console. Only **Private Models** can be deployed in air-gapped environments — Managed Models and External Models require internet access and are not available. diff --git a/fern/docs/pages/deployment/api-keys.mdx b/fern/docs/pages/deployment/api-keys.mdx index 2c1cfd2..f9ec3be 100644 --- a/fern/docs/pages/deployment/api-keys.mdx +++ b/fern/docs/pages/deployment/api-keys.mdx @@ -30,7 +30,7 @@ Manage API keys for secure access to your Prediction Guard platform. - **Key Type**: Evaluation, Ultimate, or Enterprise - **Expiration**: Set expiration date or make it permanent - **Organization**: Automatically assigned to your organization -- **Cluster**: Automatically assigned to your cluster +- **System**: Automatically assigned to your system ### Rate Limits - **Requests Per Second**: Maximum API calls per second diff --git a/fern/docs/pages/deployment/aws.mdx b/fern/docs/pages/deployment/aws.mdx index 13c8a80..e215f56 100644 --- a/fern/docs/pages/deployment/aws.mdx +++ b/fern/docs/pages/deployment/aws.mdx @@ -1,91 +1,102 @@ -# AWS Deployment - -Deploy Prediction Guard on Amazon Web Services (AWS) using our managed Kubernetes deployment. +--- +title: AWS Deployment +subtitle: Deploy Prediction Guard on Amazon Web Services using a managed Kubernetes deployment +description: Step-by-step guide to deploying Prediction Guard on AWS with EKS, including cluster setup, system installation, and ingress configuration +--- ## Prerequisites - **AWS Account** with appropriate permissions - **AWS CLI** configured with your credentials - **kubectl** configured for your EKS cluster -- **Access to admin panel** at admin.predictionguard.com +- **Access to Admin Console** at admin.predictionguard.com ## Deployment Process ### 1. Create EKS Cluster -First, create an Amazon EKS cluster in your AWS account: +Create an Amazon EKS cluster in your AWS account: ```bash -# Create EKS cluster -eksctl create cluster --name predictionguard-cluster --region us-west-2 --nodegroup-name workers --node-type t3.large --nodes 3 --nodes-min 1 --nodes-max 5 +# Set your cluster name that reflects the AI system on the Admin Console +export CLUSTER_NAME= + +eksctl create cluster \ + --name $CLUSTER_NAME \ + --region us-west-2 \ + --nodegroup-name workers \ + --node-type t3.large \ + --nodes 3 \ + --nodes-min 1 \ + --nodes-max 5 ``` ### 2. Configure kubectl ```bash # Update kubeconfig -aws eks update-kubeconfig --region us-west-2 --name predictionguard-cluster +aws eks update-kubeconfig --region us-west-2 --name $CLUSTER_NAME # Verify connection kubectl get nodes ``` -### 3. Access Admin Panel +### 3. Set AWS-Specific Configuration +- **Node Groups**: Configure your EKS node groups +- **Storage Classes**: Use EBS CSI driver for persistent volumes +- **Load Balancer**: Configure ALB or NLB for ingress +- **VPC**: Specify your VPC and subnet configuration -Navigate to [admin.predictionguard.com](https://admin.predictionguard.com) and log in with your credentials. +### 4. Create an AI System in the Admin Console -### 4. Create Cluster in Admin Panel +If you have not already created your AI system in the Admin Console, follow the [Quick Start](/admin/getting-started/quick-start) or the [Custom System](/admin/administration/create-an-ai-system) guide to create your system and generate the installation command. -1. Click **"Create Cluster"** from the dashboard -2. Select **"Advanced"** mode for full configuration -3. Configure your cluster settings: +### 5. Get the Deployment Command -#### General Settings -- **Cluster Name**: Choose a unique name (e.g., `aws-production-cluster`) -- **Air-Gapped Cluster**: Leave disabled for cloud deployment -- **Image Registry**: Use AWS ECR or your preferred registry -- **Hugging Face API Token**: Provide your token for model access -- **Enable Ingress**: Enable for external API access +Navigate to your system in the Admin Console and click the **Deploy** button in the top-right corner of the system management page. -#### AWS-Specific Configuration -- **Node Groups**: Configure your EKS node groups -- **Storage Classes**: Use EBS CSI driver for persistent volumes -- **Load Balancer**: Configure ALB or NLB for ingress -- **VPC**: Specify your VPC and subnet configuration +![System Management - Deploy Button](./ux-screenshots/03-quicksystem-deploy.png) + +This opens the **Deploy Command** modal. Select **kubectl** as the deployment method, then click **Copy** to copy the generated installation command. +![Deploy Command Modal](./ux-screenshots/04-deploy-kubectl.png) -### 5. Copy the Install command -Copy the Kubernetes installation command from your Prediction Guard Admin portal using the Deploy button on the Clusters page. +### 6. Execute the Installation on Your Cluster -### 6. Execute the install -Paste and run the command on a machine that can connect to your Kubernetes cluster API via `kubectl`.This will install your authentication token and begin the initial bootstrapping of Prediction Guard services. After a few minutes, feel free to check the installation by checking the running pods in the `predictionguard` namespace: +Paste and run the copied command on a machine with `kubectl` access to your EKS cluster. The command authenticates with your Prediction Guard instance and bootstraps all services into the `predictionguard` namespace. + +![Running the Installation Command](./ux-screenshots/05-deploy-system-cli.png) + +After a few minutes, verify the installation: ```bash kubectl get pods -n predictionguard ``` -You should see running pods in the namespace, including `pg-inside` indicating that the cluster has been successfully installed. The cluster should also show as **Healthy** in the Prediction Guard admin. +You should see running pods including `pg-inside`, indicating the system has been successfully installed. The system will also show as **Healthy** in the Admin Console. -### 7. Deploy any desired AI models -Select desired models from the Models page in the Prediction Guard admin. Pay attention to any settings around number of AI accelerators, CPU and memory allocation to the model and ensure it fits within your Kubernetes cluster resources. +![System Healthy in Admin Console](./ux-screenshots/06-system-deployed-healthy.png) ## Configuring Ingress and Reverse Proxy -Prediction Guard comes preconfigured for NGINX and a default Ingress which can be enabled on the cluster within the **Edit** section of the Clusters page. Here you can configure the desired domain names and have NGINX deploy into the `predictionguard` namespace with preconfigured settings for the Prediction Guard API. Then, simply ensure that your DNS entry is routable to the ingress IP on your Kubernetes cluster or load balancer in AWS. +Prediction Guard comes preconfigured for NGINX and a default Ingress which can be enabled on the system within the **Edit** section of the Systems page. Here you can configure the desired domain names and have NGINX deploy into the `predictionguard` namespace with preconfigured settings for the Prediction Guard API. Then, simply ensure that your DNS entry is routable to the ingress IP on your Kubernetes cluster or load balancer in AWS. ## Post-Deployment -### Access Your Cluster +Once deployed, your system is fully manageable from the Admin Console dashboard. + +![Admin Console Dashboard](./ux-screenshots/06-system-deployed-manage-screen.png) -Once deployed, your cluster will be accessible through: +From here you can: -- **Admin Panel**: Monitor and manage from admin.predictionguard.com -- **API Endpoints**: Access your deployed models via the configured endpoints -- **Kubernetes Dashboard**: Use kubectl to manage cluster resources +- **API Keys**: Manage API keys for secure access to your system endpoints +- **Models**: Deploy [private, managed, or external models](/admin/administration/model-management) and their configurations +- **MCP Servers**: Configure Model Context Protocol servers and their connections +- **Advanced Settings**: Configure system settings, resource limits, networking, and cluster-specific options ### AWS Integration -Your deployment will automatically integrate with: +Your deployment automatically integrates with: - **EBS**: Persistent storage for models and data - **ALB/NLB**: Load balancing for high availability diff --git a/fern/docs/pages/deployment/azure.mdx b/fern/docs/pages/deployment/azure.mdx index 5858b63..ac16dea 100644 --- a/fern/docs/pages/deployment/azure.mdx +++ b/fern/docs/pages/deployment/azure.mdx @@ -1,92 +1,106 @@ -# Azure Deployment - -Deploy Prediction Guard on Microsoft Azure using our managed Kubernetes deployment. +--- +title: Azure Deployment +subtitle: Deploy Prediction Guard on Microsoft Azure using a managed Kubernetes deployment +description: Step-by-step guide to deploying Prediction Guard on Azure with AKS, including cluster setup, system installation, and ingress configuration +--- ## Prerequisites - **Azure subscription** with appropriate permissions - **Azure CLI** installed and configured - **kubectl** configured for your AKS cluster -- **Access to admin panel** at admin.predictionguard.com +- **Access to Admin Console** at admin.predictionguard.com ## Deployment Process ### 1. Create AKS Cluster -First, create an Azure Kubernetes Service cluster: +Create an Azure Kubernetes Service cluster: ```bash -# Create resource group -az group create --name predictionguard-rg --location eastus +# Set your cluster name that reflects the AI system on the Admin Console +export CLUSTER_NAME= + +# Set your resource group (use an existing one or create a new one) +export RESOURCE_GROUP= +az group create --name $RESOURCE_GROUP --location eastus # Create AKS cluster -az aks create --resource-group predictionguard-rg --name predictionguard-cluster --node-count 3 --node-vm-size Standard_D2s_v3 --enable-addons monitoring --generate-ssh-keys +az aks create \ + --resource-group $RESOURCE_GROUP \ + --name $CLUSTER_NAME \ + --node-count 3 \ + --node-vm-size Standard_D2s_v3 \ + --enable-addons monitoring \ + --generate-ssh-keys ``` ### 2. Configure kubectl ```bash # Get credentials -az aks get-credentials --resource-group predictionguard-rg --name predictionguard-cluster +az aks get-credentials --resource-group $RESOURCE_GROUP --name $CLUSTER_NAME # Verify connection kubectl get nodes ``` -### 3. Access Admin Panel +### 3. Set Azure-Specific Configuration +- **Node Pools**: Configure your AKS node pools +- **Storage Classes**: Use Azure Disk CSI driver for persistent volumes +- **Load Balancer**: Configure Azure Load Balancer for ingress +- **Virtual Network**: Specify your VNet and subnet configuration -Navigate to [admin.predictionguard.com](https://admin.predictionguard.com) and log in with your credentials. +### 4. Create an AI System in the Admin Console -### 4. Create Cluster in Admin Panel +If you have not already created your AI system in the Admin Console, follow the [Quick Start](/admin/getting-started/quick-start) or the [Custom System](/admin/administration/create-an-ai-system) guide to create your system and generate the installation command. -1. Click **"Create Cluster"** from the dashboard -2. Select **"Advanced"** mode for full configuration -3. Configure your cluster settings: +### 5. Get the Deployment Command -#### General Settings -- **Cluster Name**: Choose a unique name (e.g., `azure-production-cluster`) -- **Air-Gapped Cluster**: Leave disabled for cloud deployment -- **Image Registry**: Use Azure Container Registry or your preferred registry -- **Hugging Face API Token**: Provide your token for model access -- **Enable Ingress**: Enable for external API access +Navigate to your system in the Admin Console and click the **Deploy** button in the top-right corner of the system management page. -#### Azure-Specific Configuration -- **Node Pools**: Configure your AKS node pools -- **Storage Classes**: Use Azure Disk CSI driver for persistent volumes -- **Load Balancer**: Configure Azure Load Balancer for ingress -- **Virtual Network**: Specify your VNet and subnet configuration +![System Management - Deploy Button](./ux-screenshots/03-quicksystem-deploy.png) + +This opens the **Deploy Command** modal. Select **kubectl** as the deployment method, then click **Copy** to copy the generated installation command. -### 5. Copy the Install command -Copy the Kubernetes installation command from your Prediction Guard Admin portal using the Deploy button on the Clusters page. +![Deploy Command Modal](./ux-screenshots/04-deploy-kubectl.png) -### 6. Execute the install -Paste and run the command on a machine that can connect to your Kubernetes cluster API via `kubectl`.This will install your authentication token and begin the initial bootstrapping of Prediction Guard services. After a few minutes, feel free to check the installation by checking the running pods in the `predictionguard` namespace: +### 6. Execute the Installation on Your Cluster + +Paste and run the copied command on a machine with `kubectl` access to your AKS cluster. The command authenticates with your Prediction Guard instance and bootstraps all services into the `predictionguard` namespace. + +![Running the Installation Command](./ux-screenshots/05-deploy-system-cli.png) + +After a few minutes, verify the installation: ```bash kubectl get pods -n predictionguard ``` -You should see running pods in the namespace, including `pg-inside` indicating that the cluster has been successfully installed. The cluster should also show as **Healthy** in the Prediction Guard admin. +You should see running pods including `pg-inside`, indicating the system has been successfully installed. The system will also show as **Healthy** in the Admin Console. -### 7. Deploy any desired AI models from the Models page in the Prediction Guard admin. Pay attention to any settings around number of AI accelerators, CPU and memory allocation to the model and ensure it fits within your Kubernetes cluster resources. +![System Healthy in Admin Console](./ux-screenshots/06-system-deployed-healthy.png) ## Configuring Ingress and Reverse Proxy -Prediction Guard comes preconfigured for NGINX and a default Ingress which can be enabled on the cluster within the **Edit** section of the Clusters page. Here you can configure the desired domain names and have NGINX deploy into the `predictionguard` namespace with preconfigured settings for the Prediction Guard API. Then, simply ensure that your DNS entry is routable to the ingress IP on your Kubernetes cluster or load balancer in Azure. +Prediction Guard comes preconfigured for NGINX and a default Ingress which can be enabled on the system within the **Edit** section of the Systems page. Here you can configure the desired domain names and have NGINX deploy into the `predictionguard` namespace with preconfigured settings for the Prediction Guard API. Then, simply ensure that your DNS entry is routable to the ingress IP on your Kubernetes cluster or load balancer in Azure. ## Post-Deployment -### Access Your Cluster +Once deployed, your system is fully manageable from the Admin Console dashboard. + +![Admin Console Dashboard](./ux-screenshots/06-system-deployed-manage-screen.png) -Once deployed, your cluster will be accessible through: +From here you can: -- **Admin Panel**: Monitor and manage from admin.predictionguard.com -- **API Endpoints**: Access your deployed models via the configured endpoints -- **Kubernetes Dashboard**: Use kubectl to manage cluster resources +- **API Keys**: Manage API keys for secure access to your system endpoints +- **Models**: Deploy [private, managed, or external models](/admin/administration/model-management) and their configurations +- **MCP Servers**: Configure Model Context Protocol servers and their connections +- **Advanced Settings**: Configure system settings, resource limits, networking, and cluster-specific options ### Azure Integration -Your deployment will automatically integrate with: +Your deployment automatically integrates with: - **Azure Disk**: Persistent storage for models and data - **Azure Load Balancer**: Load balancing for high availability diff --git a/fern/docs/pages/deployment/binary.mdx b/fern/docs/pages/deployment/binary.mdx index 9d4fe98..b81f8b2 100644 --- a/fern/docs/pages/deployment/binary.mdx +++ b/fern/docs/pages/deployment/binary.mdx @@ -1,7 +1,7 @@ --- title: Zero Dependency Binary description: Deploy and manage your own Prediction Guard platform -slug: deployment-administration/installation/on-premises/binary +slug: admin/installation/on-premises/binary --- # Zero Dependency Binary @@ -10,7 +10,7 @@ Deploy Prediction Guard using a single-binary installer on a single-node system. ## Minimum Requirements -These are the minimum recommended specifications for a Prediction Guard single-node cluster. Please keep in mind that actual hardware requirements may vary based on the models you choose to deploy. +These are the minimum recommended specifications for a Prediction Guard single-node system. Please keep in mind that actual hardware requirements may vary based on the models you choose to deploy. - 32-cores CPU - 256 GB RAM @@ -18,13 +18,13 @@ These are the minimum recommended specifications for a Prediction Guard single-n - 1 NVIDIA GPU of a supported type: (L4, L40S, A10, A100, H100/200, B100/200) with installed drivers on host - Ubuntu or Debian Linux (LTS or newer) -## Create Your Cluster in the Prediction Guard Admin +## Create Your System in the Admin Console 1. Navigate and login to admin.predictionguard.com -2. View the *Clusters* page and click on **+ Create Cluster** in the top-right. -3. Provide a Cluster Name -4. If you intend to use any models that are restricted by an API token on HuggingFace, be sure to ensure your HuggingFace API key. -5. Click **Create Cluster.** +2. View the *Systems* page and click on **+ Create System** in the top-right. +3. Provide a System Name +4. If you intend to use any models that are restricted by an API token on HuggingFace, be sure to provide your HuggingFace API key. +5. Click **Create System.** ## Installation Instructions @@ -34,42 +34,42 @@ These are the minimum recommended specifications for a Prediction Guard single-n curl -f "https://storage.googleapis.com/temp_public_pg/prediction-guard-platform.tgz?alt=media" ``` -1. Untar the installation file: +2. Untar the installation file: ```bash tar xvzf prediction-guard-platform.tgz ``` -1. Run the installer, which will run pre-flight checks to ensure compatible environment: +3. Run the installer, which will run pre-flight checks to ensure compatible environment: ```bash sudo ./prediction-guard-platform install --license license.yaml ``` -Provide a password for the local admin console. This is rarely used, but can be helpful for updating certain fields for offline clusters. +Provide a password for the local admin console. This is rarely used, but can be helpful for updating certain fields for offline systems. The installer will run through a series of pre-flight checks to ensure compatibility. If any of the pre-flight checks fail, a message will be displayed regarding which checks are failing. Either attempt to address and resolve the issue (some are related to available disk space, performance, etc.) or reach out to your Prediction Guard account representative for assistance. Once the installer has completed, proceed to step 4. -1. Shell into the cluster to run the bootstrap command: +4. Shell into the system to run the bootstrap command: ```bash sudo ./prediction-guard-platform shell ``` -1. Retrieve the bootstrap command from [admin.predictionguard.com](http://admin.predictionguard.com) by navigating to Clusters, then clicking the **Deploy** button in the row of the cluster you wish to deploy. Click the **Copy** button above the deploy command and proceed to step 6. +5. Retrieve the bootstrap command from [admin.predictionguard.com](http://admin.predictionguard.com) by navigating to Systems, then clicking the **Deploy** button in the row of the system you wish to deploy. Click the **Copy** button above the deploy command and proceed to step 6. -2. Paste the bootstrap command into the terminal where you are shelled into the cluster. This will install your authentication token and begin the initial bootstrapping of Prediction Guard services. After a few minutes, feel free to check the installation by checking the running pods in the `predictionguard` namespace: +6. Paste the bootstrap command into the terminal where you are shelled into the system. This will install your authentication token and begin the initial bootstrapping of Prediction Guard services. After a few minutes, feel free to check the installation by checking the running pods in the `predictionguard` namespace: ```bash kubectl get pods -n predictionguard ``` -You should see running pods in the namespace, including `pg-inside` indicating that the cluster has been successfully installed. The cluster should also show as **Healthy** in the Prediction Guard admin. +You should see running pods in the namespace, including `pg-inside` indicating that the system has been successfully installed. The system should also show as **Healthy** in the Admin Console. -1. Deploy any desired AI models from the Models page in the Prediction Guard admin. Pay attention to any settings around number of AI accelerators, CPU and memory allocation to the model and ensure it fits within your VM/machine. +7. Deploy any desired AI models from the Models page in the Admin Console. Pay attention to any settings around number of AI accelerators, CPU and memory allocation to the model and ensure it fits within your VM/machine. ## Configuring Ingress and Reverse Proxy -Prediction Guard comes preconfigured for NGINX and a default Ingress which can be enabled on the cluster within the **Edit** section of the Clusters page. Here you can configure the desired domain names and have NGINX deploy into the `predictionguard` namespace with preconfigured settings for the Prediction Guard API. Then, simply ensure that your DNS entry is routable to the ingress IP on your VM/machine. \ No newline at end of file +Prediction Guard comes preconfigured for NGINX and a default Ingress which can be enabled on the system within the **Edit** section of the Systems page. Here you can configure the desired domain names and have NGINX deploy into the `predictionguard` namespace with preconfigured settings for the Prediction Guard API. Then, simply ensure that your DNS entry is routable to the ingress IP on your VM/machine. diff --git a/fern/docs/pages/deployment/cluster-management.mdx b/fern/docs/pages/deployment/cluster-management.mdx index 0d963e5..824f6ab 100644 --- a/fern/docs/pages/deployment/cluster-management.mdx +++ b/fern/docs/pages/deployment/cluster-management.mdx @@ -1,74 +1,58 @@ -# Cluster Management +--- +title: System Management +subtitle: Create and manage sovereign AI systems in the Admin Console +description: Guide to creating, deploying, and managing AI systems in the Prediction Guard Admin Console +--- -Create and manage multiple clusters in your Prediction Guard platform to organize your infrastructure based on teams, environments, or use cases. +The **Systems** page is your central view of all AI systems in your Prediction Guard deployment. From here you can create new systems, monitor their health, and manage their configuration. -## Creating a New Cluster +![Systems Page](./ux-screenshots/01-systems.png) -![Create Cluster Page](./create-cluster-admin.png) +Each system card displays: +- **Status**: Health state (Healthy, Never Connected, Degraded) +- **API Keys**: Number of active API keys +- **Models**: Number of deployed models +- **MCP Servers**: Number of connected MCP servers +- **Location**: Deployment environment (e.g. `kubernetes`, `staging`) +- **Last Update / Created**: Timestamps for the system -### General Settings +## Creating a System -When creating a new cluster, configure these basic settings: +Click **Create System** in the top-right corner. You'll be prompted to choose a configuration mode: -- **Cluster Name**: A descriptive name for your cluster (required) -- **Air-Gapped Cluster**: Enable for offline deployments -- **Image Registry**: Docker registry for container images -- **Hugging Face API Token**: Token for accessing Hugging Face models -- **Enable Ingress**: Enable external API access +![Create System - Choose Mode](./ux-screenshots/02-CreateSystem-QuickStart.png) -### Core Components +| Mode | Best For | +|------|---------| +| **Quick Start** | Standard deployments — simplified setup with sensible defaults | +| **Custom** | Full infrastructure control, air-gapped environments, or advanced configuration | -#### Namespace Configuration -- **Create Namespaces**: Automatically create required namespaces -- **Custom Namespaces**: Use existing namespaces if disabled +For Quick Start, provide a **System Name** and optionally configure a **Public API Endpoint** for external access. See the [Quick Start guide](/admin/getting-started/quick-start) for the full walkthrough. -#### Inside Component -- **Use Default Inside Image**: Use standard Prediction Guard image -- **Custom Image**: Configure custom container image -- **Service Account**: Enable automatic service account creation -- **Service Account Name**: Name for the service account +For Custom configuration, see the [Create an AI System](/admin/administration/create-an-ai-system) guide. -### Advanced Configuration +## Managing a System -The cluster creation interface includes additional configuration sections: +Click **Manage** on any system card to open its management dashboard. -- **Redis**: Cache and session storage configuration -- **API v2 Auth**: Authentication service settings -- **API v2 LLM**: Language model API configuration -- **Nginx**: Web server and load balancer settings -- **Pre-Processing**: Input processing pipeline -- **Post-Processing**: Output processing pipeline -- **Document Processing**: Document handling capabilities -- **Audio Processing**: Audio model support -- **OpenTelemetry**: Monitoring and observability -- **Cert Manager**: SSL certificate management -- **Advanced Scheduling**: Kubernetes scheduling options +![System Management Dashboard](./ux-screenshots/06-system-deployed-manage-screen.png) -## Managing Existing Clusters +From the dashboard you can: -### Cluster Overview -- **Health Status**: Monitor cluster health and performance -- **Resource Usage**: Track CPU, memory, and GPU utilization -- **Model Status**: View deployed models and their status -- **Activity Logs**: Review recent cluster activity +- **API Keys**: Create and manage API keys for secure access to your system's endpoints +- **Models**: Deploy private, managed, or external models — see [Model Management](/admin/administration/model-management) +- **MCP Servers**: Configure Model Context Protocol servers and connections +- **Advanced Settings**: Update system settings, resource limits, networking, and cluster-specific options -### Basic Operations -- **View Clusters**: See all your clusters and their status -- **Edit Configuration**: Modify cluster settings -- **Scale Resources**: Adjust resource allocation -- **Deploy Models**: Add models to the cluster -- **Monitor Usage**: Track performance and costs +To update a system's configuration, click **Edit** from the system management page. To get the deployment command for a system, click **Deploy**. -## Best Practices +## Deploying a System -### Cluster Organization -- **Naming Convention**: Use descriptive names for easy identification -- **Environment Separation**: Keep development and production separate -- **Resource Planning**: Plan resources based on expected workloads -- **Documentation**: Document cluster purposes and configurations +Once created, a system needs to be deployed to your infrastructure. Click the **Deploy** button on the system management page to get the installation command, then follow the guide for your environment: -### Security -- **Access Control**: Implement proper access controls -- **Network Security**: Use secure network configurations -- **Regular Updates**: Keep clusters updated with latest versions -- **Monitoring**: Set up comprehensive monitoring and alerting +- [GCP](/admin/installation/cloud/gcp) +- [Azure](/admin/installation/cloud/azure) +- [AWS](/admin/installation/cloud/aws) +- [Air Gapped](/admin/installation/air-gapped/air-gapped) +- [Kubernetes](/admin/installation/on-premises/kubernetes) +- [Zero Dependency Binary](/admin/installation/on-premises/binary) diff --git a/fern/docs/pages/deployment/custom_system.mdx b/fern/docs/pages/deployment/custom_system.mdx new file mode 100644 index 0000000..4112c64 --- /dev/null +++ b/fern/docs/pages/deployment/custom_system.mdx @@ -0,0 +1,59 @@ +--- +title: Create an AI System +subtitle: Build your sovereign AI system with custom configurations +description: Create and configure your own sovereign AI system in the Admin Console admin console with custom settings for your specific use case and environment. +--- + +# Create Custom AI System in Admin Console + +1. Click **"Create System"** from the dashboard +2. Select **"Custom"** mode for full configuration +3. Select **"Air-Gapped"** for isolated environment with no external network access or **"Normal"** for standard deployment with external network access. + + +## General Settings + +![General Settings](./ux-screenshots/custom_system_general_settings.png) +- **System Name**: Choose a unique name (e.g., `pg-system-v3`) +- **Namespace Configuration**: Enable automated Kubernetes namespaces creation. +- **Pull Secret Configuration**: "Enable Pull Secret" to use image pull secret for accessing private container registries. "Use Default Prediction Guard Credentials" to automatically create Kubernetes secret with the specified name. +- **OpenTelemetry (Otel) Config**: Enter your OTEL Collector Endpoint to enable distributed tracing and observability for your AI system. +- **Advanced Scheduling**: Configure Kubernetes scheduling constraints for all system components, including node selectors, tolerations and affinity rules. + +## Core Components + +![Core Components](./ux-screenshots/custom_system_core_components.png) +- **Core Service Component**: Enable a centralized core service that orchestrates all system operations. +- **Redis Component**: Leave blank for default Redis deployment or provide custom Redis connection details. +- **Authentication Service**: Default of 1 replica +- **API Component**: Default of 1 replica + +## Ingress + +![Ingress](./ux-screenshots/custom_system_ingress.png) +- **Public API Endpoint**: Enable for external API access. Add TLS hosts and TLS secret name +- **Nginx Component**: Enable for reverse proxy and load balancing + +## Data Processing + +![Data Processing](./ux-screenshots/custom_system_data_processing.png) +Use Default for all resources for standard deployment. +- **Pre-Processing**: Enable for pre-processing tools like PII anonymization and Prompt Injection Detection. +- **Post-Processing**: Enable for post-processing tools like factuality check and toxicity filtering. +- **Document Processing**: Enable for document processing for extraction and analysis of text from various file formats (PDFs, images, Word documents) +- **Audio Processing**: Enable for audio processing for transcription and analysis of audio files. Also supports audio diarization. + +## Operations + +![Operations](./ux-screenshots/custom_system_operations.png) +- **Cert Manager**: Enter your Cert Manager configurations to automate the provisioning and renewal of SSL/TLS certificates for your system. It integrates with certificate authorities like Let's Encrypt to ensure secure HTTPS connections without manual certificate management. + + +If you enabled a **Public API Endpoint** with TLS hosts in the Ingress section, make sure your DNS records for those hostnames point to the NGINX ingress IP address on your cluster. Without this, external traffic will not route correctly to your AI system. To do this, you can run `kubectl get service ingress-nginx-controller -n predictionguard` to get the external IP address of the NGINX ingress controller and then update your DNS records accordingly. + + +## Review + +![Review](./ux-screenshots/custom_system_review.png) + +Review your configurations and click **"Create System"** to register your system and generate the deployment command. You can then use this command to deploy your system in your environment. \ No newline at end of file diff --git a/fern/docs/pages/deployment/gcp.mdx b/fern/docs/pages/deployment/gcp.mdx index c920fb9..d367f7b 100644 --- a/fern/docs/pages/deployment/gcp.mdx +++ b/fern/docs/pages/deployment/gcp.mdx @@ -1,13 +1,15 @@ -# GCP Deployment - -Deploy Prediction Guard on Google Cloud Platform using our managed Kubernetes deployment. +--- +title: GCP Deployment +subtitle: Deploy Prediction Guard on Google Cloud Platform using a managed Kubernetes deployment +description: Step-by-step guide to deploying Prediction Guard on GCP with GKE, including cluster setup, system installation, and ingress configuration +--- ## Prerequisites - **Google Cloud Project** with billing enabled - **gcloud CLI** installed and configured - **kubectl** configured for your GKE cluster -- **Access to admin panel** at admin.predictionguard.com +- **Access to Admin Console** Admin Console ## Deployment Process @@ -20,8 +22,11 @@ First, create a Google Kubernetes Engine cluster: export PROJECT_ID=your-project-id gcloud config set project $PROJECT_ID +# Set your cluster name that reflects the AI system on the Admin Console +export CLUSTER_NAME= + # Create GKE cluster -gcloud container clusters create predictionguard-cluster \ +gcloud container clusters create $CLUSTER_NAME \ --zone us-central1-a \ --num-nodes 3 \ --machine-type e2-standard-2 \ @@ -34,69 +39,71 @@ gcloud container clusters create predictionguard-cluster \ ```bash # Get credentials -gcloud container clusters get-credentials predictionguard-cluster --zone us-central1-a +gcloud container clusters get-credentials $CLUSTER_NAME --zone us-central1-a # Verify connection kubectl get nodes ``` -### 3. Access Admin Panel +### 3. Set GCP-Specific Configuration +- **Node Pools**: Configure your GKE node pools +- **Storage Classes**: Use Google Persistent Disk CSI driver for persistent volumes +- **Load Balancer**: Configure Google Cloud Load Balancer for ingress +- **VPC**: Specify your VPC and subnet configuration -Navigate to [admin.predictionguard.com](https://admin.predictionguard.com) and log in with your credentials. +### 4. Create an AI System in the Admin Console -### 4. Create Cluster in Admin Panel +If you have not already created your AI system in the Admin Console, follow the [Quick Start](/admin/getting-started/quick-start) or the [Custom System](/admin/administration/create-an-ai-system) guide to create your system and generate the installation command. -1. Click **"Create Cluster"** from the dashboard -2. Select **"Advanced"** mode for full configuration -3. Configure your cluster settings: +### 5. Get the Deployment Command -#### General Settings -- **Cluster Name**: Choose a unique name (e.g., `gcp-production-cluster`) -- **Air-Gapped Cluster**: Leave disabled for cloud deployment -- **Image Registry**: Use Google Container Registry or your preferred registry -- **Hugging Face API Token**: Provide your token for model access -- **Enable Ingress**: Enable for external API access +Navigate to your system in the Admin Console and click the **Deploy** button in the top-right corner of the system management page. -#### GCP-Specific Configuration -- **Node Pools**: Configure your GKE node pools -- **Storage Classes**: Use Google Persistent Disk CSI driver for persistent volumes -- **Load Balancer**: Configure Google Cloud Load Balancer for ingress -- **VPC**: Specify your VPC and subnet configuration +![System Management - Deploy Button](./ux-screenshots/03-quicksystem-deploy.png) + +This opens the **Deploy Command** modal. Select **kubectl** as the deployment method, then click **Copy** to copy the generated installation command. + +![Deploy Command Modal](./ux-screenshots/04-deploy-kubectl.png) +### 6. Execute the Installation on Your Cluster -### 5. Copy the Install command -Copy the Kubernetes installation command from your Prediction Guard Admin portal using the Deploy button on the Clusters page. +Paste and run the copied command on a machine that has `kubectl` access to your GKE cluster. The command authenticates with your Prediction Guard instance and bootstraps all services into the `predictionguard` namespace. -### 6. Execute the install -Paste and run the command on a machine that can connect to your Kubernetes cluster API via `kubectl`.This will install your authentication token and begin the initial bootstrapping of Prediction Guard services. After a few minutes, feel free to check the installation by checking the running pods in the `predictionguard` namespace: +![Running the Installation Command](./ux-screenshots/05-deploy-system-cli.png) + +After a few minutes, verify the installation by checking the running pods: ```bash kubectl get pods -n predictionguard ``` -You should see running pods in the namespace, including `pg-inside` indicating that the cluster has been successfully installed. The cluster should also show as **Healthy** in the Prediction Guard admin. +You should see running pods including `pg-inside`, indicating the system has been successfully installed. The system will also show as **Healthy** in the Admin Console. -### 7. Deploy any desired AI models -Select desired models from the Models page in the Prediction Guard admin. Pay attention to any settings around number of AI accelerators, CPU and memory allocation to the model and ensure it fits within your Kubernetes cluster resources. +![System Healthy in Admin Console](./ux-screenshots/06-system-deployed-healthy.png) ## Configuring Ingress and Reverse Proxy -Prediction Guard comes preconfigured for NGINX and a default Ingress which can be enabled on the cluster within the **Edit** section of the Clusters page. Here you can configure the desired domain names and have NGINX deploy into the `predictionguard` namespace with preconfigured settings for the Prediction Guard API. Then, simply ensure that your DNS entry is routable to the ingress IP on your Kubernetes cluster or load balancer in GCP. - +Prediction Guard comes preconfigured for NGINX and a default Ingress which can be enabled on the system within the **Edit** section of the Systems page. Here you can configure the desired domain names and have NGINX deploy into the `predictionguard` namespace with preconfigured settings for the Prediction Guard API. Then, simply ensure that your DNS entry is routable to the ingress IP on your Kubernetes cluster or load balancer in GCP. ## Post-Deployment -### Access Your Cluster +### Access Your AI System + +Once deployed, your AI system is accessible and manageable from the Admin Console. + +![System Management Dashboard](./ux-screenshots/06-system-deployed-manage-screen.png) -Once deployed, your cluster will be accessible through: +From here you can: -- **Admin Panel**: Monitor and manage from admin.predictionguard.com -- **API Endpoints**: Access your deployed models via the configured endpoints -- **Kubernetes Dashboard**: Use kubectl to manage cluster resources +- **API Keys**: Manage API keys for secure access to your system endpoints +- **Models**: Deploy private, managed, or external models and their configurations +- **MCP Servers**: Configure Model Context Protocol servers and their connections +- **Advanced Settings**: Configure system settings, resource limits, networking, and cluster-specific options +- **Kubernetes Dashboard**: Use `kubectl` to manage cluster resources directly ### GCP Integration -Your deployment will automatically integrate with: +Your deployment automatically integrates with: - **Google Persistent Disk**: Persistent storage for models and data - **Google Cloud Load Balancer**: Load balancing for high availability @@ -105,4 +112,4 @@ Your deployment will automatically integrate with: --- -**Need help?** Contact our support team for assistance with your GCP deployment. +**Need help?** Contact our support team for assistance with your GCP deployment. \ No newline at end of file diff --git a/fern/docs/pages/deployment/kubernetes.mdx b/fern/docs/pages/deployment/kubernetes.mdx index 61a848e..4c45b4a 100644 --- a/fern/docs/pages/deployment/kubernetes.mdx +++ b/fern/docs/pages/deployment/kubernetes.mdx @@ -1,40 +1,69 @@ -# Kubernetes - -Deploy Prediction Guard on a multi-node Kubernetes cluster. +--- +title: Kubernetes +subtitle: Deploy Prediction Guard on a multi-node Kubernetes cluster +description: Step-by-step guide to deploying Prediction Guard on a Kubernetes cluster, including system creation, installation, and ingress configuration +--- ## Minimum Requirements -These are the minimum recommended specifications for a Prediction Guard multi-node cluster. Please keep in mind that actual hardware requirements may vary based on the models you choose to deploy. +These are the minimum recommended specifications for a Prediction Guard multi-node cluster. Actual hardware requirements may vary based on the models you choose to deploy. -- 32-cores CPU per node +- 32-core CPU per node - 256 GB RAM per node -- Minimum of 100 GB of free disk space per node -- 1 NVIDIA GPU of a supported type: (L4, L40S, A10, A100, H100/200, B100/200) with installed drivers on each node +- Minimum 100 GB of free disk space per node +- 1 NVIDIA GPU of a supported type (L4, L40S, A10, A100, H100/200, B100/200) with installed drivers on each node - Ubuntu or Debian Linux (LTS or newer) - Kubernetes cluster (v1.24 or newer) -## Create Your Cluster in the Prediction Guard Admin +## Deployment Process + +### 1. Create Your AI System in the Admin Console + +If you have not already created your AI system in the Admin Console, follow the [Quick Start](/admin/getting-started/quick-start) or the [Custom System](/admin/administration/create-an-ai-system) guide to create your system and generate the installation command. + +### 2. Get the Deployment Command + +Navigate to your system in the Admin Console and click the **Deploy** button in the top-right corner of the system management page. + +![System Management - Deploy Button](./ux-screenshots/03-quicksystem-deploy.png) + +This opens the **Deploy Command** modal. Select **kubectl** as the deployment method, then click **Copy** to copy the generated installation command. + +![Deploy Command Modal](./ux-screenshots/04-deploy-kubectl.png) -1. Navigate and login to admin.predictionguard.com -2. View the *Clusters* page and click on **+ Create Cluster** in the top-right. -3. Provide a Cluster Name -4. If you intend to use any models that are restricted by an API token on HuggingFace, be sure to ensure your HuggingFace API key. -5. Click **Create Cluster.** +### 3. Execute the Installation on Your Cluster -## Installation Instructions +Paste and run the copied command on a machine with `kubectl` access to your cluster. The command authenticates with your Prediction Guard instance and bootstraps all services into the `predictionguard` namespace. -1. Copy the Kubernetes installation command from your Prediction Guard Admin portal using the Deploy button on the Clusters page. +![Running the Installation Command](./ux-screenshots/05-deploy-system-cli.png) -2. Paste and run the command on a machine that can connect to your Kubernetes cluster API via `kubectl`.This will install your authentication token and begin the initial bootstrapping of Prediction Guard services. After a few minutes, feel free to check the installation by checking the running pods in the `predictionguard` namespace: +After a few minutes, verify the installation: ```bash kubectl get pods -n predictionguard ``` -You should see running pods in the namespace, including `pg-inside` indicating that the cluster has been successfully installed. The cluster should also show as **Healthy** in the Prediction Guard admin. +You should see running pods including `pg-inside`, indicating the system has been successfully installed. The system will also show as **Healthy** in the Admin Console. -3. Deploy any desired AI models from the Models page in the Prediction Guard admin. Pay attention to any settings around number of AI accelerators, CPU and memory allocation to the model and ensure it fits within your Kubernetes cluster resources. +![System Healthy in Admin Console](./ux-screenshots/06-system-deployed-healthy.png) ## Configuring Ingress and Reverse Proxy -Prediction Guard comes preconfigured for NGINX and a default Ingress which can be enabled on the cluster within the **Edit** section of the Clusters page. Here you can configure the desired domain names and have NGINX deploy into the `predictionguard` namespace with preconfigured settings for the Prediction Guard API. Then, simply ensure that your DNS entry is routable to the ingress IP on your Kubernetes cluster. \ No newline at end of file +Prediction Guard comes preconfigured for NGINX and a default Ingress which can be enabled on the system within the **Edit** section of the Systems page. Here you can configure the desired domain names and have NGINX deploy into the `predictionguard` namespace with preconfigured settings for the Prediction Guard API. Then, simply ensure that your DNS entry is routable to the ingress IP on your Kubernetes cluster. + +## Post-Deployment + +Once deployed, your system is fully manageable from the Admin Console dashboard. + +![Admin Console Dashboard](./ux-screenshots/06-system-deployed-manage-screen.png) + +From here you can: + +- **API Keys**: Manage API keys for secure access to your system endpoints +- **Models**: Deploy [private, managed, or external models](/admin/administration/model-management) and their configurations +- **MCP Servers**: Configure Model Context Protocol servers and their connections +- **Advanced Settings**: Configure system settings, resource limits, networking, and cluster-specific options + +--- + +**Need help?** Contact our support team for assistance with your Kubernetes deployment. diff --git a/fern/docs/pages/deployment/model-management.mdx b/fern/docs/pages/deployment/model-management.mdx index 4e6f96f..808cc5a 100644 --- a/fern/docs/pages/deployment/model-management.mdx +++ b/fern/docs/pages/deployment/model-management.mdx @@ -1,61 +1,94 @@ -# Model Management +--- +title: Model Management +subtitle: Deploy and manage private, managed, and external models in your Prediction Guard system +description: Guide to deploying private models, enabling managed models, and connecting external models from providers like OpenAI, Anthropic, and Google — all inheriting your system's governance policies and safeguards +--- -Deploy and configure models in your Prediction Guard platform. +Prediction Guard supports three types of models, all accessible through the **Models** section of your system's management dashboard. Regardless of type, every model inherits your AI system's governance policies, safeguards, and integrations automatically. -## Model Deployment +| Type | Hosted By | Setup Required | License | +|------|-----------|---------------|---------| +| **Private** | Your own infrastructure | Yes | Included | +| **Managed** | Prediction Guard (SOC 2) | No | Managed Models license required | +| **External** | Third-party provider (OpenAI, Anthropic, etc.) | No | Included | -![Deploy New Model Page](./deploy-model-admin.png) +## Private Models -### Deploy from Hugging Face +Private models run within your own infrastructure — behind your firewall or within your VPC. You have full control over deployment and data residency. -1. **Browse the model library** in the admin panel -2. **Search for models** by name or type -3. **Click Deploy** and configure settings -4. **Monitor deployment** progress -5. **Test the model** via API +All models in the Prediction Guard catalog are **curated, scanned, and tested** before being made available. This means every model you deploy has been evaluated for safety, security vulnerabilities, and performance characteristics — so you're not pulling arbitrary weights from a public registry. -### Upload Custom Models +![Private Models](./ux-screenshots/08-models-private-models-1.png) -1. **Upload model files** to your platform -2. **Configure model settings** (name, description, capabilities) -3. **Set resource requirements** (CPU, GPU, memory) -4. **Deploy and test** the model -5. **Make available** to API users +Click **Add Private Model** to open the model catalog. -## Model Configuration +![Select a Model](./ux-screenshots/08-models-private-models-select-models-2.png) + +Browse the catalog and select a model. The catalog is organized by type (Chat Models, Embedding Models, etc.) and each entry includes a description of the model's intended use. Then configure the model across two tabs: ### General Settings -- **Select from Catalog**: Choose from available model catalog -- **Model Name**: Display name for the model -- **Description**: Model description and capabilities -- **Container Image URL**: Custom container image (optional) -- **Replicas**: Number of model instances to run -- **Enable Model**: Toggle model availability -- **Runtime Class Name**: Kubernetes runtime class + +![Configure Model - General Settings](./ux-screenshots/08-models-private-models-configure-gen-settings.png) + +- **Model Name**: Identifier for this model deployment +- **Replicas**: Number of instances to run +- **Runtime Class Name**: Kubernetes runtime class (optional) +- **Model Image**: Use the default Prediction Guard image or provide a custom registry, repository, and tag ### Model Parameters -- **Model CPU (millicores)**: CPU allocation for the model server -- **Model Memory (GB)**: RAM allocation for the model -- **Accelerator Cards**: Number of GPUs to allocate -- **Card Type**: GPU type (NVIDIA, etc.) -- **Hugepages (GB)**: Memory optimization settings -- **Max Input Tokens**: Maximum input context length -- **Max Total Tokens**: Maximum total tokens per request -- **Min Input Tokens**: Minimum input tokens required -- **Max Client Batches**: Maximum concurrent client batches -- **Aliases**: Model aliases (one per line) - -### Model Capabilities -- **Streaming**: Enable streaming responses -- **Tool Use**: Enable tool/function calling capabilities -- **Image Input**: Enable image processing capabilities -- **Image Formats**: Supported image formats (PNG, JPEG, etc.) -- **Capabilities**: Model capabilities (embedding, chat, etc.) - -### Advanced Configuration -- **Container Execution**: Define container command and arguments -- **Environment Variables**: Set environment variables (YAML) -- **K8s Resource Limits**: Configure Kubernetes resource limits (YAML) -- **K8s Scheduling**: Control pod placement with selectors and affinity -- **K8s Storage**: Configure and mount storage volumes -- **K8s Health Probes**: Configure liveness and readiness probes + +![Configure Model - Parameters](./ux-screenshots/08-models-private-models-configure-model-params-makesureyournodeissizedtothis.png) + + +Make sure your node is sized appropriately for the model you've selected before setting these values. + + +- **Model CPU (millicores)** — Allowed range: 2000–16000 +- **Model Memory (GB)** — Allowed range: 16–64 +- **Accelerator Cards** — Number of GPUs (1–8) +- **Card Type** — GPU type (e.g. NVIDIA) +- **Hugepages (GB)** — Memory optimization (0–64) +- **Max Client Batches** — Max concurrent client batches (10–10000) +- **Min / Max Input Tokens** — Token range for inputs (1–2000) +- **Max Total Tokens** — Maximum total tokens per request +- **Aliases** — Alternative names for this model (one per line) +- **Capabilities** — e.g. `completion`, `chat_completion`, `responses` +- **Streaming / Tool Use / Reasoning** — Toggle supported capabilities +- **Image Input** — Enable and specify accepted image formats + +Click **Create Private Model** to deploy. + +## Managed Models + +Managed Models are hosted by Prediction Guard in secure, SOC 2 compliant managed cloud infrastructure. No infrastructure setup or configuration is required on your end. + +![Managed Models](./ux-screenshots/add-managed-models.png) + + +Managed Models require an additional **Managed Models license**. Contact your Prediction Guard account team to enable this. + + +Click **Add Managed Model** to select from the available managed model catalog. Once added, the model card shows: + +- **Model Settings**: Streaming, Tools, and Reasoning capabilities +- **Capabilities**: Supported API capabilities (e.g. `COMPLETION`, `CHAT_COMPLETION`, `TOKENIZE`, `DETOKENIZE`, `RESPONSES`, `EMBEDDING`) + +Managed models are immediately available via your system's API endpoint with no deployment wait time. + +## External Models + +External Models connect your Prediction Guard system to models hosted by third-party providers — such as OpenAI, Anthropic, Google, AWS, Azure, and GCP — through their native APIs. No infrastructure setup is required. + +![External Models](./ux-screenshots/add-external-models.png) + +Click **Add External Model** to configure a connection. Each external model card displays: + +- **Provider**: The external provider (e.g. `openai`, `anthropic`, `google`) +- **Model Settings**: Streaming, Tools, and Reasoning capabilities +- **API URL**: The provider's API endpoint being used + + +External models fully inherit your AI system's governance policies, prompt injection protection, PII safeguards, toxicity filtering, and MCP integrations — giving you centralized control over third-party models without any additional configuration. + + +Use **Configure** on any external model card to update credentials or settings. diff --git a/fern/docs/pages/deployment/monitoring.mdx b/fern/docs/pages/deployment/monitoring.mdx new file mode 100644 index 0000000..d98d086 --- /dev/null +++ b/fern/docs/pages/deployment/monitoring.mdx @@ -0,0 +1,7 @@ +--- +title: Monitoring +subtitle: Real-time observability into your sovereign AI systems +description: Track and observe your sovereign AI systems with external monitoring tools. +--- + +Comprehensive documentation coming soon. Please contact [support@predictionguard.com](mailto:support@predictionguard.com). \ No newline at end of file diff --git a/fern/docs/pages/deployment/overview.mdx b/fern/docs/pages/deployment/overview.mdx index 973250d..328b538 100644 --- a/fern/docs/pages/deployment/overview.mdx +++ b/fern/docs/pages/deployment/overview.mdx @@ -1,14 +1,22 @@ --- title: Quick Start -subtitle: Reliable, future-proof AI predictions -description: Deploy and manage your own Prediction Guard platform +subtitle: Compose your sovereign AI systems without compromising security via Prediction Guard's Admin Console +description: Build and govern sovereign AI systems across any infrastructure without compromising security, using Prediction Guard's Admin Console. --- -Deploy and manage your own Prediction Guard clusters with full control over your AI infrastructure. Choose from multiple deployment options to fit your security, compliance, and infrastructure requirements. +**Manage** and control your AI security by composing sovereign AI Systems that contain internal and external models, MCP servers, and connections to applications. -## Deployment Options +**Govern**, monitor and audit your AI systems by applying AI governance policies that aligns to NIST, OWASP and OMB out of the box. -Prediction Guard supports flexible deployment across different environments: +**Deploy** AI agents that automatically inherit your system-wide governance and integrate directly with your sovereign AI systems. + + +An **AI System** is an abstraction that consolidates your AI models, MCP servers, tool connections, and agent integrations into a single unit. Prediction Guard's control plane, which is self-hosted in your infrastructure, applies your sovereign configuration of access, auditing, governance, and monitoring to each AI system. + + +## AI System Deployment Options + +Prediction Guard supports flexible AI System deployment across different environments: - **On-Premises**: Deploy in your own data center with Kubernetes or single-node binary - **Cloud**: Deploy on AWS, Azure, or Google Cloud with managed Kubernetes @@ -18,25 +26,39 @@ Prediction Guard supports flexible deployment across different environments: Your deployed Prediction Guard platform provides: -- **Model Management**: Deploy any open model from Hugging Face or your own repositories -- **Cluster Management**: Create and manage multiple clusters across environments +- **Model Management**: Deploy [private models](/admin/administration/model-management#private-models), connect to Prediction Guard's [managed models](/admin/administration/model-management#managed-models), or integrate [external models](/admin/administration/model-management#external-models) such as Azure Foundry, AWS Bedrock, Google Vertex, OpenAI, Anthropic and more +- **System Management**: Create and manage multiple systems across environments - **Security & Compliance**: Built-in security scanning, audit logs, and compliance features - **API Management**: Create and manage API keys with granular permissions +- **Integrations**: Connect your AI systems to applications, knowledge bases and MCP servers that will be inherited by the agents that you deploy +- **Governance**: Apply AI governance policies across your systems that aligns with NIST, OWASP and OMB standards - **Monitoring**: Real-time monitoring and alerting for your AI infrastructure ## Getting Started - -### Create your cluster in the admin panel -Start by creating your cluster in the Prediction Guard admin panel: +### Create your first sovereign AI system in the Admin Console + +Start by creating your system in the Admin Console: + +1. **Navigate to your Admin Console (e.g. [admin.predictionguard.com](https://admin.predictionguard.com))** and log in + +2. **Go to Systems → Manage** and click **"Create System"** in the top-right corner + +![Systems Page](./ux-screenshots/01-systems.png) -1. **Navigate to [admin.predictionguard.com](https://admin.predictionguard.com)** and log in -2. **Click "Create Cluster"** from the dashboard -3. **Choose your deployment type** (On-Premises, Cloud, or Air-Gapped) -4. **Configure cluster settings** (name, resources, security) -5. **Click "Create Cluster"** to generate your cluster configuration +3. **Select "Quick Start"** for a simplified setup with sensible defaults + +![Select Quick Start](./ux-screenshots/02-CreateSystem-QuickStart.png) + +4. **Fill in your system details:** + - **System Name**: A unique name for your system (e.g. `production`, `staging`) + - **Public API Endpoint**: Enable this if you need access from outside your Kubernetes deployment, and add your TLS hostname(s) + +![System Name and Public API Endpoint](./ux-screenshots/03-quicksystem-pg1.png) + +5. **Click "Create System"** to create your AI system with default settings ### Choose your deployment method @@ -44,53 +66,48 @@ Prediction Guard can be deployed anywhere that fits your needs. Choose the deplo #### On-Premises Deploy in your own data center: -- [Kubernetes Cluster](/deployment-administration/installation/on-premises/kubernetes) - Full Kubernetes deployment -- [Zero Dependency Binary](/deployment-administration/installation/on-premises/binary) - Single node binary installation +- [Kubernetes Cluster](/admin/installation/on-premises/kubernetes) - Full Kubernetes deployment +- [Zero Dependency Binary](/admin/installation/on-premises/binary) - Single node binary installation #### Cloud Deployment Deploy on major cloud providers: -- [AWS Deployment](/deployment-administration/installation/cloud/aws) - Amazon Web Services -- [Azure Deployment](/deployment-administration/installation/cloud/azure) - Microsoft Azure -- [GCP Deployment](/deployment-administration/installation/cloud/gcp) - Google Cloud Platform +- [AWS Deployment](/admin/installation/cloud/aws) - Amazon Web Services +- [Azure Deployment](/admin/installation/cloud/azure) - Microsoft Azure +- [GCP Deployment](/admin/installation/cloud/gcp) - Google Cloud Platform #### Air Gapped -Deploy in isolated environments: -- [Air Gapped Deployment](/deployment-administration/installation/air-gapped/air-gapped) - Offline deployment guide +Deploy in isolated environments. Note that air-gapped deployment requires **Custom** configuration instead of Quick Start during system creation: +- [Air Gapped Deployment](/admin/installation/air-gapped/air-gapped) - Offline deployment guide -### Deploy your Prediction Guard cluster +### Deploy your AI system -Follow the specific deployment guide for your chosen environment. The deployment process will: +Follow the specific deployment guide for your chosen environment. When ready, click the **Deploy** button on your system in the Admin Console to get the installation command. -1. **Download the installation package** for your environment -2. **Run the installer** with pre-flight checks and configuration -3. **Bootstrap your cluster** using the command from the admin panel -4. **Verify the deployment** is working correctly +![Deploy Command](./ux-screenshots/04-deploy-kubectl.png) -### Access your Prediction Guard admin panel +The deployment process will: -Once deployed, access your Prediction Guard admin panel (your dashboard) to manage your cluster and deploy models. +1. **Generate an installation command** scoped to your system from the Admin Console +2. **Run the command** on a machine with `kubectl` access to your cluster +3. **Bootstrap your system** — Prediction Guard services will start up in the `predictionguard` namespace -### Deploy your first model +![Healthy AI System](./ux-screenshots/06-system-deployed-healthy.png) +4. **Verify the deployment** — your system will show as **Healthy** in the Admin Console once complete -From the admin panel dashboard, deploy your first model: +### Connect an AI model to your system -1. **Navigate to Models** in the admin panel -2. **Browse available models** from Hugging Face or upload your own -3. **Configure model settings** (hardware requirements, parameters) -4. **Deploy the model** to your cluster and verify it's running -5. **Test the model** via API calls +Once your system is healthy, connect AI models to start building: -### Create API keys and start building +1. **External or Managed Models** — Connect to [external models](/admin/administration/model-management#external-models) (e.g. Azure Foundry, AWS Bedrock, Google Vertex, OpenAI, Anthropic, and more) or Prediction Guard's [managed models](/admin/administration/model-management#managed-models) (if available) with no additional infrastructure required. +2. **Private Models** — If you need models running on your own infrastructure, deploy and connect them as [private models](/admin/administration/model-management#private-models). -Set up access for your applications: + -1. **Create API keys** with appropriate permissions -2. **Configure rate limits** and usage quotas -3. **Test API access** with your deployed models -4. **Start building** secure, compliant AI applications +## Next Steps - +Once your system is deployed and healthy, you can configure it further: - - Need help with deployment? Contact our support team or join our Discord community for assistance. - +- **Deploy models** — Add private, managed, or external models to your system. See the [Model Management](/admin/administration/model-management) guide for details on all three model types. +- **Set up governance** — Apply AI governance policies aligned with NIST, OWASP, and OMB standards. See the [Governance](/admin/administration/admin-console#security-govern) section of the Admin Console guide. +- **Create API keys** — Set up API keys with appropriate permissions for your applications. See the [API Keys](/admin/administration/api-keys) guide. +- **Explore the Admin Console** — Manage systems, monitor activity, and review audit logs. See the full [Admin Console](/admin/administration/admin-console) overview. \ No newline at end of file diff --git a/fern/docs/pages/deployment/security-monitoring.mdx b/fern/docs/pages/deployment/security-monitoring.mdx deleted file mode 100644 index e0e983b..0000000 --- a/fern/docs/pages/deployment/security-monitoring.mdx +++ /dev/null @@ -1,58 +0,0 @@ -# Security & Monitoring - -Track admin panel changes and integrate Prediction Guard's built-in security features with your monitoring dashboards. - -## Audit Logs - -### Admin Panel Activity Tracking - -Prediction Guard tracks all changes made in the admin panel: - -- **User Actions**: Login attempts, configuration changes, model deployments -- **API Usage**: All API calls, requests, and responses -- **System Events**: Cluster changes, resource allocation, security events -- **Model Activity**: Model deployments, updates, and usage patterns - -### Log Information -- **Timestamp**: When the action occurred -- **User Identity**: Who performed the action -- **Action Details**: What was changed -- **Resource Information**: Which resources were affected -- **Outcome**: Success or failure status - -## Built-in Security Features - -### Prediction Guard Guardrails - -Prediction Guard includes built-in security scanning and protection: - -- **PII Detection**: Automatically detects and removes personally identifiable information -- **Prompt Injection Protection**: Prevents malicious prompt injection attacks -- **Toxicity Checks**: Identifies and filters harmful or toxic content -- **Bias Detection**: Monitors for potential bias in model outputs -- **Content Moderation**: Filters inappropriate or harmful content - -### Security Alerts - -- **Real-time Monitoring**: Immediate alerts for security events -- **Policy Violations**: Alerts when security policies are breached -- **Unusual Activity**: Detection of suspicious patterns -- **Failed Authentication**: Multiple failed login attempts - -## Dashboard Integration - -### OpenTelemetry Integration - -Connect Prediction Guard to your existing monitoring stack: - -- **Metrics Export**: Send metrics to Prometheus, Grafana, or other tools -- **Log Aggregation**: Forward logs to ELK stack or similar -- **Custom Dashboards**: Create dashboards in your preferred tool -- **Alert Integration**: Connect to your existing alerting systems - -### Monitoring Setup - -1. **Configure OpenTelemetry** in your cluster settings -2. **Set up metrics collection** for your monitoring stack -3. **Create dashboards** to visualize Prediction Guard metrics -4. **Configure alerts** for security events and performance issues diff --git a/fern/docs/pages/deployment/ux-screenshots/01-create-system.png b/fern/docs/pages/deployment/ux-screenshots/01-create-system.png new file mode 100644 index 0000000..f4d1c25 Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/01-create-system.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/01-systems.png b/fern/docs/pages/deployment/ux-screenshots/01-systems.png new file mode 100644 index 0000000..a8b0c5b Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/01-systems.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/02-CreateSystem-QuickStart.png b/fern/docs/pages/deployment/ux-screenshots/02-CreateSystem-QuickStart.png new file mode 100644 index 0000000..f32b9c3 Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/02-CreateSystem-QuickStart.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/03-quicksystem-deploy.png b/fern/docs/pages/deployment/ux-screenshots/03-quicksystem-deploy.png new file mode 100644 index 0000000..83f232f Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/03-quicksystem-deploy.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/03-quicksystem-pg1.png b/fern/docs/pages/deployment/ux-screenshots/03-quicksystem-pg1.png new file mode 100644 index 0000000..0670ff6 Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/03-quicksystem-pg1.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/04-deploy-kubectl.png b/fern/docs/pages/deployment/ux-screenshots/04-deploy-kubectl.png new file mode 100644 index 0000000..7103231 Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/04-deploy-kubectl.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/05-deploy-system-cli.png b/fern/docs/pages/deployment/ux-screenshots/05-deploy-system-cli.png new file mode 100644 index 0000000..639a5ce Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/05-deploy-system-cli.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/06-system-deployed-healthy.png b/fern/docs/pages/deployment/ux-screenshots/06-system-deployed-healthy.png new file mode 100644 index 0000000..42d2566 Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/06-system-deployed-healthy.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/06-system-deployed-manage-screen.png b/fern/docs/pages/deployment/ux-screenshots/06-system-deployed-manage-screen.png new file mode 100644 index 0000000..84687a4 Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/06-system-deployed-manage-screen.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/07-api-keys-01.png b/fern/docs/pages/deployment/ux-screenshots/07-api-keys-01.png new file mode 100644 index 0000000..a83741b Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/07-api-keys-01.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/07-api-keys-02.png b/fern/docs/pages/deployment/ux-screenshots/07-api-keys-02.png new file mode 100644 index 0000000..6cedd21 Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/07-api-keys-02.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/07-api-keys.png b/fern/docs/pages/deployment/ux-screenshots/07-api-keys.png new file mode 100644 index 0000000..d6e6c3a Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/07-api-keys.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/08-models-private-models-1.png b/fern/docs/pages/deployment/ux-screenshots/08-models-private-models-1.png new file mode 100644 index 0000000..ff4096e Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/08-models-private-models-1.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/08-models-private-models-configure-gen-settings.png b/fern/docs/pages/deployment/ux-screenshots/08-models-private-models-configure-gen-settings.png new file mode 100644 index 0000000..e35f941 Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/08-models-private-models-configure-gen-settings.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/08-models-private-models-configure-model-params-makesureyournodeissizedtothis.png b/fern/docs/pages/deployment/ux-screenshots/08-models-private-models-configure-model-params-makesureyournodeissizedtothis.png new file mode 100644 index 0000000..143d590 Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/08-models-private-models-configure-model-params-makesureyournodeissizedtothis.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/08-models-private-models-select-models-2.png b/fern/docs/pages/deployment/ux-screenshots/08-models-private-models-select-models-2.png new file mode 100644 index 0000000..f50bd97 Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/08-models-private-models-select-models-2.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/08-models.png b/fern/docs/pages/deployment/ux-screenshots/08-models.png new file mode 100644 index 0000000..e5d10e5 Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/08-models.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/add-external-models.png b/fern/docs/pages/deployment/ux-screenshots/add-external-models.png new file mode 100644 index 0000000..c0c0b9a Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/add-external-models.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/add-managed-models.png b/fern/docs/pages/deployment/ux-screenshots/add-managed-models.png new file mode 100644 index 0000000..0d30de2 Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/add-managed-models.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/analyze-page-bom.png b/fern/docs/pages/deployment/ux-screenshots/analyze-page-bom.png new file mode 100644 index 0000000..8bd629f Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/analyze-page-bom.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/analyze-page-scans.png b/fern/docs/pages/deployment/ux-screenshots/analyze-page-scans.png new file mode 100644 index 0000000..b027ee3 Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/analyze-page-scans.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/custom_system_core_components.png b/fern/docs/pages/deployment/ux-screenshots/custom_system_core_components.png new file mode 100644 index 0000000..6ba97f6 Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/custom_system_core_components.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/custom_system_data_processing.png b/fern/docs/pages/deployment/ux-screenshots/custom_system_data_processing.png new file mode 100644 index 0000000..1d13fe7 Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/custom_system_data_processing.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/custom_system_general_settings.png b/fern/docs/pages/deployment/ux-screenshots/custom_system_general_settings.png new file mode 100644 index 0000000..643caa0 Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/custom_system_general_settings.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/custom_system_ingress.png b/fern/docs/pages/deployment/ux-screenshots/custom_system_ingress.png new file mode 100644 index 0000000..92f3fdf Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/custom_system_ingress.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/custom_system_operations.png b/fern/docs/pages/deployment/ux-screenshots/custom_system_operations.png new file mode 100644 index 0000000..f7fdc44 Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/custom_system_operations.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/custom_system_review.png b/fern/docs/pages/deployment/ux-screenshots/custom_system_review.png new file mode 100644 index 0000000..a91a4ad Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/custom_system_review.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/govern-page-custom-config.png b/fern/docs/pages/deployment/ux-screenshots/govern-page-custom-config.png new file mode 100644 index 0000000..3a80537 Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/govern-page-custom-config.png differ diff --git a/fern/docs/pages/deployment/ux-screenshots/govern-page-standards.png b/fern/docs/pages/deployment/ux-screenshots/govern-page-standards.png new file mode 100644 index 0000000..73aa96a Binary files /dev/null and b/fern/docs/pages/deployment/ux-screenshots/govern-page-standards.png differ diff --git a/fern/docs/pages/input/PII.mdx b/fern/docs/pages/input/PII.mdx index 003eed1..ccf82c5 100644 --- a/fern/docs/pages/input/PII.mdx +++ b/fern/docs/pages/input/PII.mdx @@ -70,7 +70,7 @@ print(json.dumps( )) ``` -The processed prompt will then be. +The processed prompt will then be: ```json copy { @@ -114,7 +114,7 @@ response = client.completions.create( print(json.dumps(response, sort_keys=True, indent=4, separators=(',', ': '))) ``` -In the response, you can see the PII has been replced and the LLM response is for +In the response, you can see the PII has been replaced and the LLM response is for the modified prompt. ```json copy diff --git a/fern/docs/pages/input/injection.mdx b/fern/docs/pages/input/injection.mdx index 7a98945..9f0c774 100644 --- a/fern/docs/pages/input/injection.mdx +++ b/fern/docs/pages/input/injection.mdx @@ -4,7 +4,7 @@ description: Controlled and compliant AI applications --- There are several types of prompt injection attacks, new attacks being discovered -at a rapid speed. As you integrate LLMs to regular workflow is is always good to +at a rapid speed. As you integrate LLMs to regular workflow, it is always good to be prepared against these injection attacks. With Prediction Guard, you have the ability to assess whether an incoming prompt @@ -60,11 +60,11 @@ We can now get an output with probability of injection. } ``` -Let's try this again with an inoccuous prompt. +Let's try this again with an innocuous prompt. ```python copy result = client.injection.check( - prompt="hello I had placed an order of running shoes. It was supposed to arrive yesterday. Could you please let me know when I will recieve it", + prompt="hello I had placed an order of running shoes. It was supposed to arrive yesterday. Could you please let me know when I will receive it", detect=True ) @@ -93,9 +93,9 @@ This will produce an output like the following. } ``` -Similar to the PII feature, the injection feature can be used with both the `\completions` and `\chat\completions` endpoints. +Similar to the PII feature, the injection feature can be used with both the `/completions` and `/chat/completions` endpoints. -How to detect Injections while using the \completions Endpoint: +How to detect Injections while using the `/completions` Endpoint: ```python copy import os @@ -132,7 +132,7 @@ this will produce the following ValueError: ValueError: Could not make prediction. prompt injection detected ``` -How to detect Injections while using the `\chat\completions`: +How to detect Injections while using the `/chat/completions` Endpoint: ```python copy import os diff --git a/fern/docs/pages/usingllms/accessing_llms.mdx b/fern/docs/pages/usingllms/accessing_llms.mdx index f235598..e313ed0 100644 --- a/fern/docs/pages/usingllms/accessing_llms.mdx +++ b/fern/docs/pages/usingllms/accessing_llms.mdx @@ -29,10 +29,10 @@ Further, it will illustrate how companies can access a wide range of models In order to "prompt" an LLM via Prediction Guard (and eventually engineer prompts), you can use any of the following SDKs: -[Python](/sdk-docs/software-development-kits/sd-ks), -[Go](/sdk-docs/software-development-kits/sd-ks), -[Rust](/sdk-docs/software-development-kits/sd-ks), -[JS](/sdk-docs/software-development-kits/sd-ks), and +[Python](/sdk-docs/software-development-kits/sdks), +[Go](/sdk-docs/software-development-kits/sdks), +[Rust](/sdk-docs/software-development-kits/sdks), +[JS](/sdk-docs/software-development-kits/sdks), and [HTTP](/api-reference). We will use Python to show an example: @@ -104,8 +104,8 @@ output which includes the completion. You can also try these examples using the other official SDKs: -[Python](/sdk-docs/software-development-kits/sd-ks), -[Go](/sdk-docs/software-development-kits/sd-ks), -[Rust](/sdk-docs/software-development-kits/sd-ks), -[JS](/sdk-docs/software-development-kits/sd-ks), +[Python](/sdk-docs/software-development-kits/sdks), +[Go](/sdk-docs/software-development-kits/sdks), +[Rust](/sdk-docs/software-development-kits/sdks), +[JS](/sdk-docs/software-development-kits/sdks), [HTTP](/api-reference) diff --git a/fern/docs/pages/usingllms/agents.mdx b/fern/docs/pages/usingllms/agents.mdx index a09582f..7156916 100644 --- a/fern/docs/pages/usingllms/agents.mdx +++ b/fern/docs/pages/usingllms/agents.mdx @@ -24,7 +24,7 @@ We will use Python to show an example: ## Dependencies and Imports You will need to install the Prediction Guard, LangChain and Google Search Results -dependencies in you Python environment. +dependencies in your Python environment. ```bash $ pip install predictionguard langchain google-search-results @@ -71,8 +71,8 @@ agent = initialize_agent(tools, PredictionGuard(model="{{TEXT_MODEL}}"), agent.run("How are Domino's gift cards delivered?") ``` -This will verbosely log the agents activities until it reaching a final answer -nd generates the response: +This will verbosely log the agent's activities until it reaches a final answer +and generates the response: ``` > Entering new AgentExecutor chain... @@ -91,8 +91,8 @@ Domino's gift cards can be delivered electronically or physically, and can be us You can also try these examples using the other official SDKs: -[Python](/sdk-docs/software-development-kits/sd-ks), -[Go](/sdk-docs/software-development-kits/sd-ks), -[Rust](/sdk-docs/software-development-kits/sd-ks), -[JS](/sdk-docs/software-development-kits/sd-ks), +[Python](/sdk-docs/software-development-kits/sdks), +[Go](/sdk-docs/software-development-kits/sdks), +[Rust](/sdk-docs/software-development-kits/sdks), +[JS](/sdk-docs/software-development-kits/sdks), [HTTP](/api-reference) diff --git a/fern/docs/pages/usingllms/basic_prompting.mdx b/fern/docs/pages/usingllms/basic_prompting.mdx index 6117526..e522b00 100644 --- a/fern/docs/pages/usingllms/basic_prompting.mdx +++ b/fern/docs/pages/usingllms/basic_prompting.mdx @@ -280,8 +280,8 @@ Wow, you've told me a lot of things. I thought you'd like this movie. You said L You can also try these examples using the other official SDKs: -[Python](/sdk-docs/software-development-kits/sd-ks), -[Go](/sdk-docs/software-development-kits/sd-ks), -[Rust](/sdk-docs/software-development-kits/sd-ks), -[JS](/sdk-docs/software-development-kits/sd-ks), +[Python](/sdk-docs/software-development-kits/sdks), +[Go](/sdk-docs/software-development-kits/sdks), +[Rust](/sdk-docs/software-development-kits/sdks), +[JS](/sdk-docs/software-development-kits/sdks), [HTTP](/api-reference) diff --git a/fern/docs/pages/usingllms/chaining_retrieval.mdx b/fern/docs/pages/usingllms/chaining_retrieval.mdx index 9528b5b..bec5714 100644 --- a/fern/docs/pages/usingllms/chaining_retrieval.mdx +++ b/fern/docs/pages/usingllms/chaining_retrieval.mdx @@ -29,7 +29,7 @@ We will use Python to show an example: ## Dependencies and Imports You will need to install Prediction Guard, LangChain, LanceDB and a few more -dependencies in you Python environment. +dependencies in your Python environment. ```bash copy $ pip install langchain predictionguard lancedb html2text sentence-transformers @@ -77,7 +77,7 @@ possible, and complicated instructions don't do that. template = """### Instruction: Decide if the following input message is an informational question, a general chat message, or a request for code generation. If the message is an informational question, answer it based on the informational context provided below. -If the message is a general chat message, respond in a kind and friendly manner based on the coversation context provided below. +If the message is a general chat message, respond in a kind and friendly manner based on the conversation context provided below. If the message is a request for code generation, respond with a code snippet. ### Input: @@ -88,7 +88,7 @@ Informational Context: The Greater Los Angeles and San Francisco Bay areas in Ca Conversational Context: Human - "Hello, how are you?" AI - "I'm good, what can I help you with?" -Human - "What is the captital of California?" +Human - "What is the capital of California?" AI - "Sacramento" Human - "Thanks!" AI - "You are welcome!" @@ -118,7 +118,7 @@ The population of LA is approximately 3.9 million people. Rather than try to handle everything in one call to the LLM, let's decompose our logic into multiple calls that are each simple. We will also add in some non-LLM -logic The chain of processing is: +logic. The chain of processing is: - Prompt 1 - Determine if the message is a request for code generation. - Prompt 2 - Q&A prompt to answer based on informational context @@ -282,7 +282,7 @@ info_context = "The Greater Los Angeles and San Francisco Bay areas in Californi convo_context = """Human: Hello, how are you? AI: I'm good, what can I help you with? -Human: What is the captital of California? +Human: What is the capital of California? AI: Sacramento Human: Thanks! AI: You are welcome!""" @@ -352,7 +352,7 @@ probabilities and based on its training data. Gift cards are delivered via US Mail. ``` -## Retrieval Augmentated Generation (RAG) +## Retrieval-Augmented Generation (RAG) ![Retrieval augmented generation](rag.png) @@ -595,8 +595,8 @@ RESPONSE: A single patch should solve one problem at a time. You can also try these examples using the other official SDKs: -[Python](/sdk-docs/software-development-kits/sd-ks), -[Go](/sdk-docs/software-development-kits/sd-ks), -[Rust](/sdk-docs/software-development-kits/sd-ks), -[JS](/sdk-docs/software-development-kits/sd-ks), +[Python](/sdk-docs/software-development-kits/sdks), +[Go](/sdk-docs/software-development-kits/sdks), +[Rust](/sdk-docs/software-development-kits/sdks), +[JS](/sdk-docs/software-development-kits/sdks), [HTTP](/api-reference) diff --git a/fern/docs/pages/usingllms/chat_completions.mdx b/fern/docs/pages/usingllms/chat_completions.mdx index f918fc4..18eb5ce 100644 --- a/fern/docs/pages/usingllms/chat_completions.mdx +++ b/fern/docs/pages/usingllms/chat_completions.mdx @@ -131,8 +131,8 @@ while True: You can also try these examples using the other official SDKs: -[Python](/sdk-docs/software-development-kits/sd-ks), -[Go](/sdk-docs/software-development-kits/sd-ks), -[Rust](/sdk-docs/software-development-kits/sd-ks), -[JS](/sdk-docs/software-development-kits/sd-ks), +[Python](/sdk-docs/software-development-kits/sdks), +[Go](/sdk-docs/software-development-kits/sdks), +[Rust](/sdk-docs/software-development-kits/sdks), +[JS](/sdk-docs/software-development-kits/sdks), [HTTP](/api-reference) diff --git a/fern/docs/pages/usingllms/prompt_engineering.mdx b/fern/docs/pages/usingllms/prompt_engineering.mdx index 7d61938..96f0e73 100644 --- a/fern/docs/pages/usingllms/prompt_engineering.mdx +++ b/fern/docs/pages/usingllms/prompt_engineering.mdx @@ -408,8 +408,8 @@ ValueError: Could not make prediction. failed toxicity check You can also try these examples using the other official SDKs: -[Python](/sdk-docs/software-development-kits/sd-ks), -[Go](/sdk-docs/software-development-kits/sd-ks), -[Rust](/sdk-docs/software-development-kits/sd-ks), -[JS](/sdk-docs/software-development-kits/sd-ks), +[Python](/sdk-docs/software-development-kits/sdks), +[Go](/sdk-docs/software-development-kits/sdks), +[Rust](/sdk-docs/software-development-kits/sdks), +[JS](/sdk-docs/software-development-kits/sdks), [HTTP](/api-reference) diff --git a/fern/docs/pages/usingllms/streaming.mdx b/fern/docs/pages/usingllms/streaming.mdx index 3146164..b9e5763 100644 --- a/fern/docs/pages/usingllms/streaming.mdx +++ b/fern/docs/pages/usingllms/streaming.mdx @@ -92,8 +92,8 @@ for res in client.chat.completions.create( You can also try these examples using the other official SDKs: -[Python](/sdk-docs/software-development-kits/sd-ks), -[Go](/sdk-docs/software-development-kits/sd-ks), -[Rust](/sdk-docs/software-development-kits/sd-ks), -[JS](/sdk-docs/software-development-kits/sd-ks), +[Python](/sdk-docs/software-development-kits/sdks), +[Go](/sdk-docs/software-development-kits/sdks), +[Rust](/sdk-docs/software-development-kits/sdks), +[JS](/sdk-docs/software-development-kits/sdks), [HTTP](/api-reference) diff --git a/fern/docs/pages/usingllms/tool_calling.mdx b/fern/docs/pages/usingllms/tool_calling.mdx index 46eb39d..e9425cd 100644 --- a/fern/docs/pages/usingllms/tool_calling.mdx +++ b/fern/docs/pages/usingllms/tool_calling.mdx @@ -359,7 +359,7 @@ tools = [ ## Next Steps -- Explore our [SDK examples](../sdk-docs/software-development-kits/sd-ks) for language-specific implementations +- Explore our [SDK examples](../sdk-docs/software-development-kits/sdks) for language-specific implementations --- diff --git a/fern/docs/pages/welcome.mdx b/fern/docs/pages/welcome.mdx index 52649ca..064d288 100644 --- a/fern/docs/pages/welcome.mdx +++ b/fern/docs/pages/welcome.mdx @@ -10,14 +10,14 @@ layout: custom - Deploy and manage your Prediction Guard platform with comprehensive admin tools, cluster management, and security monitoring. + Build and govern sovereign AI systems across any infrastructure without compromising security, using Prediction Guard's Admin Console. \ \ - [**Get Started** →](/deployment-administration/getting-started/quick-start) + [**Get Started** →](/admin/getting-started/quick-start) {" "} @@ -64,7 +64,7 @@ Started**→](/api-reference/api-reference/chat-completions) {" "} @@ -72,7 +72,7 @@ Started**→](/api-reference/api-reference/chat-completions) \ \ [**Get Started** -→](/sdk-docs/software-development-kits/sd-ks) +→](/sdk-docs/software-development-kits/sdks)