diff --git a/public/sitemap.xml b/public/sitemap.xml index 603d3412..d4fefb82 100644 --- a/public/sitemap.xml +++ b/public/sitemap.xml @@ -212,7 +212,14 @@ https://kagent.dev/docs/kagent/supported-providers/azure-openai - 2025-09-10 + 2025-09-09 + weekly + 0.8 + + + + https://kagent.dev/docs/kagent/supported-providers/byo-openai + 2025-09-09 weekly 0.8 diff --git a/src/app/docs/kagent/supported-providers/byo-openai/page.mdx b/src/app/docs/kagent/supported-providers/byo-openai/page.mdx new file mode 100644 index 00000000..be40af41 --- /dev/null +++ b/src/app/docs/kagent/supported-providers/byo-openai/page.mdx @@ -0,0 +1,57 @@ +--- +title: "BYO OpenAI-compatible model" +pageOrder: 7 +description: "Bring your own OpenAI-compatible model to kagent." +--- + +export const metadata = { + title: "BYO OpenAI-compatible model", + description: "Bring your own OpenAI-compatible model to kagent.", + author: "kagent.dev" +}; + +You can bring your own model from an [OpenAI API-compatible](https://platform.openai.com/docs/api-reference/introduction) LLM provider. The example integrates with [Cohere AI](https://cohere.com/). + +1. Save your API key from the OpenAI-compatible provider as an environment variable. For example, navigate to the [Cohere AI dashboard](https://dashboard.cohere.com/api-keys). + + ```bash + export PROVIDER_API_KEY=Dgs... + ``` + +2. Create a Kubernetes secret that stores your API key. Make sure to create the secret in the same namespace as you plan to create your agent, such as `kagent`. + + ```bash + kubectl create secret generic kagent-my-provider -n kagent --from-literal PROVIDER_API_KEY=$PROVIDER_API_KEY + ``` + +3. Create a ModelConfig resource. + + ```yaml + kubectl apply -f - <