# Create Vector Search Index — Databricks

> Creates a new vector search index in Databricks. See the documentation

- Key: `databricks-create-vector-search-index`
- Type: Action (Write)
- Version: 0.0.3
- App: Databricks (`databricks`) — https://pipedream.com/apps/databricks.md
- This page (HTML): https://pipedream.com/apps/databricks/actions/create-vector-search-index
- Hints: open-world
- Source: https://github.com/PipedreamHQ/pipedream/blob/master/components/databricks/actions/create-vector-search-index/create-vector-search-index.mjs

## Description

Creates a new vector search index in Databricks. [See the documentation](https://docs.databricks.com/api/workspace/vectorsearchindexes/createindex)

## Props

| Prop | Type | Required | Description |
|---|---|---|---|
| `name` | `string` | Yes | A unique name for the index (e.g., main_catalog.docs.en_wiki_index). |
| `endpointName` | `string` | Yes | The name of the vector search endpoint Options are loaded from the connected account. |
| `indexType` | `string` | Yes | Type of index (DELTA_SYNC or DIRECT_ACCESS). |
| `primaryKey` | `string` | Yes | The primary key column for the index. |
| `sourceTable` | `string` | No | The Delta table backing the index (required for DELTA_SYNC). |
| `columnsToSync` | `string[]` | No | List of columns to sync from the source Delta table. Example: ["id", "text"] (required for DELTA_SYNC). |
| `embeddingSourceColumns` | `string[]` | No | List of embedding source column configs. Each entry is a JSON object string like { "embedding_model_endpoint_name": "e5-small-v2", "name": "text" }.Provide when Databricks computes embeddings (DELTA_SYNC). |
| `schemaJson` | `string` | No | The schema of the index in JSON format. Example: { "columns": [{ "name": "id", "type": "string" }, { "name": "text_vector", "type": "array<double>" }] }. Required for DIRECT_ACCESS indexes. |
| `pipelineType` | `string` | No | Pipeline type for syncing (default: TRIGGERED). |

## 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": "databricks",
      },
    },
  },
)

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: "databricks-create-vector-search-index",
  arguments: {
    name: "Index Name",
    endpointName: "Endpoint Name",
  },
})
```

**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: "databricks-create-vector-search-index",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    databricks: { authProvisionId: "apn_xxxxxxx" },
    name: "Index Name",
    endpointName: "Endpoint Name",
  },
})

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": "databricks-create-vector-search-index",
    "configured_props": {
      "databricks": { "authProvisionId": "apn_xxxxxxx" },
      "name": "Index Name",
      "endpointName": "Endpoint Name"
    }
  }'
```

---

- App: https://pipedream.com/apps/databricks.md · All apps: https://pipedream.com/apps