d25d482dc2
Publish CLI Package / publish-npm (push) Waiting to run
Publish Python SDK / publish-pypi (push) Waiting to run
Publish TypeScript SDK / publish-npm (push) Waiting to run
CI / Migrate Dev DB (push) Has been skipped
CI / Detect Version (push) Has been cancelled
CI / Migrate DB (push) Has been cancelled
CI / Build Dev ECR (./docker/app.Dockerfile, ECR_APP) (push) Has been cancelled
CI / Build Dev ECR (./docker/db.Dockerfile, ECR_MIGRATIONS) (push) Has been cancelled
CI / Build Dev ECR (./docker/pii.Dockerfile, ECR_PII) (push) Has been cancelled
CI / Build Dev ECR (./docker/realtime.Dockerfile, ECR_REALTIME) (push) Has been cancelled
CI / Deploy Trigger.dev (Dev) (push) Has been cancelled
CI / Build AMD64 (./docker/app.Dockerfile, ECR_APP, ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Build AMD64 (./docker/db.Dockerfile, ECR_MIGRATIONS, ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Build AMD64 (./docker/pii.Dockerfile, ECR_PII, ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Build AMD64 (./docker/realtime.Dockerfile, ECR_REALTIME, ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/app.Dockerfile, ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/db.Dockerfile, ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/pii.Dockerfile, ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/realtime.Dockerfile, ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Check Docs Changes (push) Has been cancelled
CI / Process Docs (push) Has been cancelled
CI / Create GitHub Release (push) Has been cancelled
CI / Test and Build (push) Has been cancelled
80 lines
2.5 KiB
TypeScript
80 lines
2.5 KiB
TypeScript
import { GoogleGenAI } from '@google/genai'
|
|
import { createLogger } from '@sim/logger'
|
|
import { OAuth2Client } from 'google-auth-library'
|
|
import { env } from '@/lib/core/config/env'
|
|
import type { StreamingExecution } from '@/executor/types'
|
|
import { executeGeminiRequest } from '@/providers/gemini/core'
|
|
import { getProviderDefaultModel, getProviderModels } from '@/providers/models'
|
|
import type { ProviderConfig, ProviderRequest, ProviderResponse } from '@/providers/types'
|
|
|
|
const logger = createLogger('VertexProvider')
|
|
|
|
/**
|
|
* Vertex AI provider
|
|
*
|
|
* Uses the @google/genai SDK with Vertex AI backend and OAuth authentication.
|
|
* Shares core execution logic with Google Gemini provider.
|
|
*
|
|
* Authentication:
|
|
* - Uses OAuth access token passed via googleAuthOptions.authClient
|
|
* - Token refresh is handled at the OAuth layer before calling this provider
|
|
*/
|
|
export const vertexProvider: ProviderConfig = {
|
|
id: 'vertex',
|
|
name: 'Vertex AI',
|
|
description: "Google's Vertex AI platform for Gemini models",
|
|
version: '1.0.0',
|
|
models: getProviderModels('vertex'),
|
|
defaultModel: getProviderDefaultModel('vertex'),
|
|
|
|
executeRequest: async (
|
|
request: ProviderRequest
|
|
): Promise<ProviderResponse | StreamingExecution> => {
|
|
const vertexProject = request.vertexProject || env.VERTEX_PROJECT
|
|
const vertexLocation = request.vertexLocation || env.VERTEX_LOCATION || 'us-central1'
|
|
|
|
if (!vertexProject) {
|
|
throw new Error(
|
|
'Vertex AI project is required. Please provide it via VERTEX_PROJECT environment variable or vertexProject parameter.'
|
|
)
|
|
}
|
|
|
|
if (!request.apiKey) {
|
|
throw new Error(
|
|
'Access token is required for Vertex AI. Run `gcloud auth print-access-token` to get one, or use a service account.'
|
|
)
|
|
}
|
|
|
|
// Strip 'vertex/' prefix from model name if present
|
|
const model = request.model.replace('vertex/', '')
|
|
|
|
logger.info('Creating Vertex AI client', {
|
|
project: vertexProject,
|
|
location: vertexLocation,
|
|
model,
|
|
})
|
|
|
|
// Create an OAuth2Client and set the access token
|
|
// This allows us to use an OAuth access token with the SDK
|
|
const authClient = new OAuth2Client()
|
|
authClient.setCredentials({ access_token: request.apiKey })
|
|
|
|
// Create client with Vertex AI configuration
|
|
const ai = new GoogleGenAI({
|
|
vertexai: true,
|
|
project: vertexProject,
|
|
location: vertexLocation,
|
|
googleAuthOptions: {
|
|
authClient,
|
|
},
|
|
})
|
|
|
|
return executeGeminiRequest({
|
|
ai,
|
|
model,
|
|
request,
|
|
providerType: 'vertex',
|
|
})
|
|
},
|
|
}
|