mirror of
https://github.com/block/goose.git
synced 2026-07-17 12:56:20 +02:00
docs: GCP Vertex AI org policy filtering & update OnboardingProviderSetup component (#7125)
This commit is contained in:
@@ -255,13 +255,15 @@ goose works with [supported LLM providers][providers] that give goose the AI int
|
||||
|
||||
<Tabs groupId="interface">
|
||||
<TabItem value="ui" label="goose Desktop" default>
|
||||
On the welcome screen, choose how to configure a provider:
|
||||
On the welcome screen the first time you open goose, choose how to configure a provider:
|
||||
<OnboardingProviderSetup />
|
||||
</TabItem>
|
||||
<TabItem value="cli" label="goose CLI">
|
||||
The CLI automatically enters configuration mode where you can choose how to configure a provider:
|
||||
|
||||
<OnboardingProviderSetup />
|
||||
- **OpenRouter Login** - Sign in with OpenRouter to automatically configure models
|
||||
- **Tetrate Agent Router Service Login** - Sign in with Tetrate Agent Router Service to automatically configure models
|
||||
- **Manual Configuration** - Choose a provider and enter credentials manually
|
||||
|
||||
Example configuration flow:
|
||||
|
||||
@@ -312,6 +314,10 @@ goose works with [supported LLM providers][providers] that give goose the AI int
|
||||
<ModelSelectionTip />
|
||||
:::
|
||||
|
||||
:::info Free Credits Offer
|
||||
You'll receive $10 in free credits the first time you automatically authenticate with Tetrate through goose. This offer is available to both new and existing Tetrate users.
|
||||
:::
|
||||
|
||||
## Update Provider
|
||||
You can change your LLM provider and/or model or update your API key at any time.
|
||||
|
||||
|
||||
@@ -7,6 +7,7 @@ import Tabs from '@theme/Tabs';
|
||||
import TabItem from '@theme/TabItem';
|
||||
import { PanelLeft } from 'lucide-react';
|
||||
import { ModelSelectionTip } from '@site/src/components/ModelSelectionTip';
|
||||
import { OnboardingProviderSetup } from '@site/src/components/OnboardingProviderSetup';
|
||||
|
||||
# Supported LLM Providers
|
||||
|
||||
@@ -29,7 +30,7 @@ goose is compatible with a wide range of LLM providers, allowing you to choose a
|
||||
| [Databricks](https://www.databricks.com/) | Unified data analytics and AI platform for building and deploying models. | `DATABRICKS_HOST`, `DATABRICKS_TOKEN` |
|
||||
| [Docker Model Runner](https://docs.docker.com/ai/model-runner/) | Local models running in Docker Desktop or Docker CE with OpenAI-compatible API endpoints. **Because this provider runs locally, you must first [download a model](#local-llms).** | `OPENAI_HOST`, `OPENAI_BASE_PATH` |
|
||||
| [Gemini](https://ai.google.dev/gemini-api/docs) | Advanced LLMs by Google with multimodal capabilities (text, images). | `GOOGLE_API_KEY` |
|
||||
| [GCP Vertex AI](https://cloud.google.com/vertex-ai) | Google Cloud's Vertex AI platform, supporting Gemini and Claude models. **Credentials must be [configured in advance](https://cloud.google.com/vertex-ai/docs/authentication).** | `GCP_PROJECT_ID`, `GCP_LOCATION` and optionally `GCP_MAX_RATE_LIMIT_RETRIES` (5), `GCP_MAX_OVERLOADED_RETRIES` (5), `GCP_INITIAL_RETRY_INTERVAL_MS` (5000), `GCP_BACKOFF_MULTIPLIER` (2.0), `GCP_MAX_RETRY_INTERVAL_MS` (320_000). |
|
||||
| [GCP Vertex AI](https://cloud.google.com/vertex-ai) | Google Cloud's Vertex AI platform, supporting Gemini and Claude models. **Credentials must be [configured in advance](https://cloud.google.com/vertex-ai/docs/authentication).** Filters for allowed models by organization policy (if configured). | `GCP_PROJECT_ID`, `GCP_LOCATION` and optionally `GCP_MAX_RATE_LIMIT_RETRIES` (5), `GCP_MAX_OVERLOADED_RETRIES` (5), `GCP_INITIAL_RETRY_INTERVAL_MS` (5000), `GCP_BACKOFF_MULTIPLIER` (2.0), `GCP_MAX_RETRY_INTERVAL_MS` (320_000). |
|
||||
| [GitHub Copilot](https://docs.github.com/en/copilot/using-github-copilot/ai-models) | Access to AI models from OpenAI, Anthropic, Google, and other providers through GitHub's Copilot infrastructure. **GitHub account with Copilot access required.** | No manual key. Uses [device flow authentication](#github-copilot-authentication) for both CLI and Desktop. |
|
||||
| [Groq](https://groq.com/) | High-performance inference hardware and tools for LLMs. | `GROQ_API_KEY` |
|
||||
| [LiteLLM](https://docs.litellm.ai/docs/) | LiteLLM proxy supporting multiple models with automatic prompt caching and unified API access. | `LITELLM_HOST`, `LITELLM_BASE_PATH` (optional), `LITELLM_API_KEY` (optional), `LITELLM_CUSTOM_HEADERS` (optional), `LITELLM_TIMEOUT` (optional) |
|
||||
@@ -72,11 +73,9 @@ To configure your chosen provider, see available options, or select a model, vis
|
||||
**First-time users:**
|
||||
|
||||
On the welcome screen the first time you open goose, you have these options:
|
||||
- **Quick Setup with API Key** - goose will automatically configure your provider based on your API key
|
||||
- **[ChatGPT Subscription](https://chatgpt.com/codex)** - Sign in with your ChatGPT Plus/Pro credentials to access GPT-5 Codex models
|
||||
- **[Agent Router by Tetrate](https://tetrate.io/products/tetrate-agent-router-service)** - Access multiple AI models with automatic setup
|
||||
- **[OpenRouter](https://openrouter.ai/)** - Access 200+ models with one API using pay-per-use pricing
|
||||
- **Other Providers** - Manually configure additional providers through settings
|
||||
|
||||
<OnboardingProviderSetup />
|
||||
|
||||
<Tabs groupId="setup">
|
||||
<TabItem value="apikey" label="Quick Setup" default>
|
||||
1. Choose `Quick Setup with API Key`.
|
||||
|
||||
@@ -8,6 +8,7 @@ import Link from "@docusaurus/Link";
|
||||
import { IconDownload } from "@site/src/components/icons/download";
|
||||
import { RateLimits } from '@site/src/components/RateLimits';
|
||||
import { ModelSelectionTip } from '@site/src/components/ModelSelectionTip';
|
||||
import { OnboardingProviderSetup } from '@site/src/components/OnboardingProviderSetup';
|
||||
import YouTubeShortEmbed from '@site/src/components/YouTubeShortEmbed';
|
||||
import MacDesktopInstallButtons from '@site/src/components/MacDesktopInstallButtons';
|
||||
import WindowsDesktopInstallButtons from '@site/src/components/WindowsDesktopInstallButtons';
|
||||
@@ -115,11 +116,8 @@ goose works with [supported LLM providers](/docs/getting-started/providers) that
|
||||
<Tabs groupId="interface">
|
||||
<TabItem value="ui" label="goose Desktop" default>
|
||||
On the welcome screen, you have these options:
|
||||
- **Quick Setup with API Key** - goose will automatically configure your provider based on your API key
|
||||
- **[ChatGPT Subscription](https://chatgpt.com/codex)** - Sign in with your ChatGPT Plus/Pro credentials to access GPT-5 Codex models
|
||||
- **[Agent Router by Tetrate](https://tetrate.io/products/tetrate-agent-router-service)** - Access multiple AI models with automatic setup
|
||||
- **[OpenRouter](https://openrouter.ai/)** - Access 200+ models with one API using pay-per-use pricing
|
||||
- **Other Providers** - Manually configure additional providers through settings
|
||||
|
||||
<OnboardingProviderSetup />
|
||||
|
||||
For this quickstart, choose **Agent Router by Tetrate**. Tetrate provides access to multiple AI models with built-in rate limiting and automatic failover. For more information about other providers, see [Configure LLM Provider](/docs/getting-started/providers).
|
||||
|
||||
|
||||
@@ -62,7 +62,7 @@ In goose, we use a structured RPI workflow using recipes to systematically tackl
|
||||
│ RPI WORKFLOW │
|
||||
├─────────────────────────────────────────────────────────────────────────────-┤
|
||||
│ │
|
||||
│ /research_codebase "topic" │
|
||||
│ /research_codebase "topic" │
|
||||
│ │ │
|
||||
│ ├──► Spawns parallel sub-agents: │
|
||||
│ │ • find_files (rpi-codebase-locator) │
|
||||
@@ -71,7 +71,7 @@ In goose, we use a structured RPI workflow using recipes to systematically tackl
|
||||
│ │ │
|
||||
│ └──► Output: thoughts/research/YYYY-MM-DD-HHmm-topic.md │
|
||||
│ │
|
||||
│ /create_plan "feature/task" │
|
||||
│ /create_plan "feature/task" │
|
||||
│ │ │
|
||||
│ ├──► Reads research docs │
|
||||
│ ├──► Asks clarifying questions │
|
||||
@@ -79,7 +79,7 @@ In goose, we use a structured RPI workflow using recipes to systematically tackl
|
||||
│ │ │
|
||||
│ └──► Output: thoughts/plans/YYYY-MM-DD-HHmm-description.md │
|
||||
│ │
|
||||
│ /implement_plan "plan path" │
|
||||
│ /implement_plan "plan path" │
|
||||
│ │ │
|
||||
│ ├──► Executes phase by phase │
|
||||
│ ├──► Runs verification after each phase │
|
||||
@@ -87,7 +87,7 @@ In goose, we use a structured RPI workflow using recipes to systematically tackl
|
||||
│ │ │
|
||||
│ └──► Working code │
|
||||
│ │
|
||||
│ /iterate_plan "plan path" + feedback │
|
||||
│ /iterate_plan "plan path" + feedback │
|
||||
│ │ │
|
||||
│ ├──► Researches only what changed │
|
||||
│ ├──► Updates the plan surgically │
|
||||
|
||||
@@ -4,26 +4,11 @@ export const OnboardingProviderSetup = () => {
|
||||
return (
|
||||
<>
|
||||
<ul>
|
||||
<li>
|
||||
<strong>Tetrate Agent Router</strong> - One-click OAuth authentication provides instant access to multiple AI models, starting credits, and built-in rate limiting. See the <a href="/goose/docs/quickstart#configure-provider"> goose quickstart guide</a> for a walkthrough of this setup.
|
||||
<div className="admonition admonition-info alert alert--info" style={{marginTop: '0.5rem', marginBottom: '0.5rem'}}>
|
||||
<div className="admonition-heading">
|
||||
<h5>
|
||||
<span className="admonition-icon" style={{marginRight: '0.5rem'}}>
|
||||
<svg viewBox="0 0 14 16" width="21" height="23" style={{transform: 'translateY(1px)'}}>
|
||||
<path fillRule="evenodd" d="M7 2.3c3.14 0 5.7 2.56 5.7 5.7s-2.56 5.7-5.7 5.7A5.71 5.71 0 0 1 1.3 8c0-3.14 2.56-5.7 5.7-5.7zM7 1C3.14 1 0 4.14 0 8s3.14 7 7 7 7-3.14 7-7-3.14-7-7-7zm1 3H6v5h2V4zm0 6H6v2h2v-2z"></path>
|
||||
</svg>
|
||||
</span>
|
||||
INFO
|
||||
</h5>
|
||||
</div>
|
||||
<div className="admonition-content" style={{paddingBottom: '1rem'}}>
|
||||
<p style={{marginBottom: '0'}}>You'll receive $10 in free credits the first time you automatically authenticate with Tetrate through goose. This offer is available to both new and existing Tetrate users.</p>
|
||||
</div>
|
||||
</div>
|
||||
</li>
|
||||
<li><strong>OpenRouter</strong> - One-click OAuth authentication provides instant access to multiple AI models with built-in rate limiting.</li>
|
||||
<li><strong>Other Providers</strong> - Choose from a selection of <a href="/goose/docs/getting-started/providers">~20 supported providers</a> including OpenAI, Anthropic, Google Gemini, and others through manual configuration. If you don't see your provider in the list, you can add a custom provider. Be ready to provide your API key, API Host address, or other optional parameters depending on provider.</li>
|
||||
<li><strong>Quick Setup with API Key</strong> - goose will automatically configure your provider based on your API key</li>
|
||||
<li><strong><a href="https://chatgpt.com/codex">ChatGPT Subscription</a></strong> - Sign in with your ChatGPT Plus/Pro credentials to access GPT-5 Codex models</li>
|
||||
<li><strong><a href="https://tetrate.io/products/tetrate-agent-router-service">Agent Router by Tetrate</a></strong> - Access multiple AI models with automatic setup</li>
|
||||
<li><strong><a href="https://openrouter.ai/">OpenRouter</a></strong> - Access 200+ models with one API using pay-per-use pricing</li>
|
||||
<li><strong>Other Providers</strong> - Manually configure additional providers through settings</li>
|
||||
</ul>
|
||||
</>
|
||||
);
|
||||
|
||||
Reference in New Issue
Block a user