> ## Documentation Index > Fetch the complete documentation index at: https://docs.getcollate.io/llms.txt > Use this file to discover all available pages before exploring further. # BYOC Prerequisites > Review the software, access, hardware, AWS Bedrock, Azure OpenAI, and GCP Gemini requirements before deploying the Collate AI Proxy with Helm. # Prerequisites Your team must include individuals with strong expertise in Kubernetes and your chosen cloud provider. Before deploying the Collate AI Proxy, ensure you have the following requirements in place. ## Required software ### Kubernetes cluster A running Kubernetes cluster, version `1.19` or later. Verify your cluster version with: ```shell theme={null} kubectl version --client ``` ### Helm 3 The Helm package manager for Kubernetes. Download from the [Helm installation guide](https://helm.sh/docs/intro/install/). Verify the installation: ```shell theme={null} helm version ``` ### kubectl The Kubernetes command-line tool. Download from the [kubectl installation guide](https://kubernetes.io/docs/tasks/tools/). Verify the installation: ```shell theme={null} kubectl cluster-info ``` ### Existing Collate installation An existing Collate deployment must already be running in your cluster. * CAIP communicates with the Collate server over gRPC. * Any communication from CAIP to Collate uses the user's PAT to authenticate to Collate. This means CAIP agents only have as many permissions as the user, thanks to RBAC integration. * CAIP provides the backend for applications such as AskCollate, Documentation Agent, Tier Agent, and DQ Generation Agent. * Identify the service account used by the Collate server, since it will be needed for the Collate AI Proxy installation. ## Required access * **Docker images:** Since you already have a Collate installation in place, use the same image-pulling strategy for the Collate AI Proxy Docker images. You can reuse the same credentials, whether you are pulling the images from Collate's ECR or from your own container registry. * **Kubernetes access:** Permissions to create and manage resources in your cluster. Verify access, replacing `` with the namespace where Collate is deployed: ```shell theme={null} kubectl auth can-i create deployments -n ``` * **LLM provider credentials:** Depending on your chosen LLM provider, such as AWS Bedrock, OpenAI, Anthropic, Google, or Ollama. * **AWS Bedrock:** AWS access key ID and secret access key, or an IAM role with Bedrock permissions, plus an active Anthropic model subscription. * **OpenAI:** OpenAI API key. * **Google Gemini:** Google Generative AI API key for the GCP project that will be used by your GKE deployment. ## Hardware requirements The Collate AI Proxy pod requires at least the following resources: * CPU: `300m` * Memory: `2Gi` * Storage: No persistent storage required; the service is stateless. Ensure that the Kubernetes node where the pod runs can satisfy these requirements. ## Provider setup Use the following provider-specific setup guidance before deployment. ### Set up Amazon Bedrock 1. Sign in to the AWS console and open Amazon Bedrock in a supported commercial region. 2. Ensure the IAM role or user used for setup has the required AWS Marketplace permissions to enable third-party models. 3. Confirm that your AWS account has a valid payment method configured for AWS Marketplace purchases. 4. Open the model catalog in Amazon Bedrock and select the model you want to use. 5. For Anthropic models, complete the first-time use case form the first time you enable them in the account. 6. If your team prefers explicit approval before first use, review the model license terms and control access with IAM or SCP policies before invoking the model. ### Bedrock access notes * Access to foundation models is enabled by default in commercial AWS regions when the required AWS Marketplace permissions are present. * The first invocation of a third-party model can trigger an automatic subscription flow in the background. * During the initial setup period, Bedrock access can take a few minutes to become fully available. * If prerequisites are missing, subsequent calls can fail with `AccessDeniedException`. ### Recommended model setup For Collate AI Platform, use Anthropic chat models through Bedrock and ensure your chosen AWS region supports the model and inference option you plan to use. For semantic search or embeddings, confirm that the embedding model you plan to use is available in the same or intended Bedrock region. ### Create and configure the service 1. Sign in to the [Azure portal](https://portal.azure.com/). 2. Create a dedicated resource group. 3. Navigate to Azure OpenAI (Microsoft Foundry) Service and create a new one. Create an Azure OpenAI Foundry resource 4. Fill in the resource group name created earlier, the resource name, and the region. Keep the remaining settings as default, then select **Review + create** and wait for Azure to generate the service. 5. Navigate to the service you created and select **Go to Foundry portal**. Azure OpenAI service overview with link to Foundry portal 6. Under **Shared resources**, select **Deployments**, then **Deploy model**, and choose **Deploy base model**. You need two separate deployments: one base model for Collate AI Platform and one embedding model for Collate Server. Azure OpenAI model deployments page 7. Select a suitable model such as `gpt-4o`. Once the deployment is created, capture the `apiKey`, `deploymentName`, `apiVersion`, and `azure_endpoint` or `baseUrl` from the deployment preview. Azure OpenAI deployment preview showing endpoint and deployment details 8. Repeat the model deployment process for the vector embedding model used by Collate Server for semantic search. For this deployment, select `text-embedding-3-small` under **Embeddings** and capture the same credentials. ### Supported models All OpenAI models, including `gpt-4o`, are supported and the model list is loaded automatically from the OpenAI API. Collate recommends using `gpt-4o` for Collate AI Platform. ### Set up Gemini API access for GKE 1. Sign in to the Google Cloud console and select the project used by your GKE cluster. 2. Open **APIs & Services** > **Library**. 3. Search for **Gemini API**. 4. Select **Gemini API**, then click **Enable**. Enable the Gemini API service in the Google Cloud console 5. Wait until the API is enabled for the project. 6. Navigate to **APIs & Services** > **Credentials** and create an API key for Google Generative AI. Navigate to credentials for the Gemini API service in Google Cloud Create an API key for Gemini API in Google Cloud 7. Restrict the API key to the Gemini API, and apply any organization-required network or application restrictions. 8. Store the API key in your secret management system, such as an external secrets provider or a Kubernetes Secret in the Collate namespace. You can also enable the API with the Google Cloud CLI: ```shell theme={null} gcloud services enable generativelanguage.googleapis.com --project ``` As an alternative, you can create and manage Gemini API keys from Google AI Studio. If the GCP project used by your GKE cluster is not visible in Google AI Studio, import the project first, then create the API key for that project. For more information, see the official [Gemini API key documentation](https://ai.google.dev/gemini-api/docs/api-key). ### Recommended model setup For Collate AI Platform on GCP, use Gemini chat models with `gemini-2.5-pro` as the primary chat model and `gemini-2.5-flash` as the smaller model variant. For semantic search or embeddings, configure embeddings in the Collate application for now. ## Navigation \< Previous Next >