# Analyze Image/Video — Google Vertex AI

> Examines an image or video following given instructions. Results will contain the analysis findings. See the documentation

- Key: `google_vertex_ai-analyze-image-video`
- Type: Action (Read-only)
- Version: 0.0.3
- App: Google Vertex AI (`google_vertex_ai`) — https://pipedream.com/apps/google-vertex-ai.md
- This page (HTML): https://pipedream.com/apps/google-vertex-ai/actions/analyze-image-video
- Hints: read-only · open-world
- Source: https://github.com/PipedreamHQ/pipedream/blob/master/components/google_vertex_ai/actions/analyze-image-video/analyze-image-video.mjs

## Description

Examines an image or video following given instructions. Results will contain the analysis findings. [See the documentation](https://cloud.google.com/vertex-ai/docs/reference/rest/v1/projects.locations.publishers.models/generateContent)

## Props

| Prop | Type | Required | Description |
|---|---|---|---|
| `projectId` | `string` | Yes | Identifier of a project Options are loaded from the connected account. |
| `instructions` | `string` | Yes | The rules for analysis of the input image/video |
| `url` | `string` | Yes | The URL of the file or video to analyze. Only GCS URIs are supported. Please make sure that the path is a valid GCS path. Example: gs://cloud-samples-data/generative-ai/image/mount_fuji.jpg |
| `mimeType` | `string` | No | The mimeType of the image or video to analyze |

## Run it

**MCP**

```ts
import { Client } from "@modelcontextprotocol/sdk/client/index.js"
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js"
import { PipedreamClient } from "@pipedream/sdk"

const pd = new PipedreamClient({
  projectId: process.env.PIPEDREAM_PROJECT_ID!,
  clientId: process.env.PIPEDREAM_CLIENT_ID!,
  clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
  projectEnvironment: "production",
})

const accessToken = await pd.rawAccessToken

const transport = new StreamableHTTPClientTransport(
  new URL("https://remote.mcp.pipedream.net/v3"),
  {
    requestInit: {
      headers: {
        Authorization: `Bearer ${accessToken}`,
        "x-pd-project-id": process.env.PIPEDREAM_PROJECT_ID!,
        "x-pd-environment": "production",
        "x-pd-external-user-id": "{external_user_id}", // any stable ID for this user in your system
        "x-pd-app-slug": "google_vertex_ai",
      },
    },
  },
)

const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)

const { tools } = await mcp.listTools()

// listTools() hands your model this tool's input schema, so it can
// fill the arguments itself:
const result = await mcp.callTool({
  name: "google_vertex_ai-analyze-image-video",
  arguments: {
    projectId: "Project ID",
    instructions: "Instructions",
  },
})
```

**TypeScript**

```ts
import { PipedreamClient } from "@pipedream/sdk"

const pd = new PipedreamClient({
  projectId: process.env.PIPEDREAM_PROJECT_ID!,
  clientId: process.env.PIPEDREAM_CLIENT_ID!,
  clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
  projectEnvironment: "production",
})

const result = await pd.actions.run({
  id: "google_vertex_ai-analyze-image-video",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    google_vertex_ai: { authProvisionId: "apn_xxxxxxx" },
    projectId: "Project ID",
    instructions: "Instructions",
  },
})

console.log(result)
```

**cURL**

```bash
curl -X POST https://api.pipedream.com/v1/connect/{project_id}/actions/run \
  -H "Content-Type: application/json" \
  -H "X-PD-Environment: production" \
  -H "Authorization: Bearer {access_token}" \
  -d '{
    "external_user_id": "{external_user_id}",
    "id": "google_vertex_ai-analyze-image-video",
    "configured_props": {
      "google_vertex_ai": { "authProvisionId": "apn_xxxxxxx" },
      "projectId": "Project ID",
      "instructions": "Instructions"
    }
  }'
```

---

- App: https://pipedream.com/apps/google-vertex-ai.md · All apps: https://pipedream.com/apps