diff --git a/packages/web/src/content/docs/providers.mdx b/packages/web/src/content/docs/providers.mdx index 654e434a..496b382b 100644 --- a/packages/web/src/content/docs/providers.mdx +++ b/packages/web/src/content/docs/providers.mdx @@ -119,12 +119,6 @@ To use Amazon Bedrock with OpenCode: AWS_ACCESS_KEY_ID=XXX opencode ``` - Or add it to a `.env` file in the project root. - - ```bash title=".env" - AWS_ACCESS_KEY_ID=XXX - ``` - Or add it to your bash profile. ```bash title="~/.bash_profile" @@ -225,12 +219,6 @@ Or if you already have an API key, you can select **Manually enter API Key** and AZURE_RESOURCE_NAME=XXX opencode ``` - Or add it to a `.env` file in the project root: - - ```bash title=".env" - AZURE_RESOURCE_NAME=XXX - ``` - Or add it to your bash profile: ```bash title="~/.bash_profile" @@ -422,6 +410,42 @@ Some models need to be manually enabled in your [GitHub Copilot settings](https: --- +### Google Vertex AI + +To use Google Vertex AI with OpenCode: + +1. Head over to the **Model Garden** in the Google Cloud Console and check the + models available in your region. + + :::tip + You need to have a Google Cloud project with Vertex AI API enabled. + ::: + +1. You'll need to set the following environment variables: + - `GOOGLE_VERTEX_PROJECT`: Your Google Cloud project ID + - `GOOGLE_VERTEX_REGION` (optional): The region for Vertex AI (defaults to us-east5) + - One of these authentication options: + - `GOOGLE_APPLICATION_CREDENTIALS`: Path to your service account JSON key file + - Or authenticate using gcloud CLI with `gcloud auth application-default login` + + Once you have these, set them while running opencode. + + ```bash + GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account.json GOOGLE_VERTEX_PROJECT=your-project-id opencode + ``` + + Or add them to your bash profile. + + ```bash title="~/.bash_profile" + export GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account.json + export GOOGLE_VERTEX_PROJECT=your-project-id + export GOOGLE_VERTEX_REGION=us-central1 + ``` + +1. Run the `/models` command to select the model you want. + +--- + ### LM Studio You can configure opencode to use local models through LM Studio.