# Send Message — DopplerAI

> Dispatches a message to the artificial intelligence. See the documentation

- Key: `dopplerai-send-message`
- Type: Action (Write)
- Version: 0.0.2
- App: DopplerAI (`dopplerai`) — https://pipedream.com/apps/dopplerai.md
- This page (HTML): https://pipedream.com/apps/dopplerai/actions/send-message
- Hints: open-world
- Source: https://github.com/PipedreamHQ/pipedream/blob/master/components/dopplerai/actions/send-message/send-message.mjs

## Description

Dispatches a message to the artificial intelligence. [See the documentation](https://api.dopplerai.com/docs/reference#tag/Messages/operation/send_message_v1_messages_post)

## Props

| Prop | Type | Required | Description |
|---|---|---|---|
| `prompt` | `string` | Yes | Prompt that is added prior to the content |
| `content` | `string` | Yes | The content of the message |
| `memorize` | `boolean` | Yes | Memorize the conversation to memory |
| `remember` | `boolean` | Yes | Remember past conversations that have been memorized |
| `chatUuid` | `string` | Yes | The UUID of the chat that the message will belong to Options are loaded from the connected account. |
| `collectionUuid` | `string` | No | The UUID of the collection to extract embeddings from Options are loaded from the connected account. |
| `modelName` | `string` | No | The name of the large language model. Default: gpt-3.5-turbo |
| `temperature` | `integer` | No | The temperature of the large language model. Default: 0 |
| `frequencyPenalty` | `string` | No | The frequency penalty of the large language model. Default: 0.7 |

## 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": "dopplerai",
      },
    },
  },
)

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: "dopplerai-send-message",
  arguments: {
    prompt: "Prompt",
    content: "Content",
  },
})
```

**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: "dopplerai-send-message",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    dopplerai: { authProvisionId: "apn_xxxxxxx" },
    prompt: "Prompt",
    content: "Content",
  },
})

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": "dopplerai-send-message",
    "configured_props": {
      "dopplerai": { "authProvisionId": "apn_xxxxxxx" },
      "prompt": "Prompt",
      "content": "Content"
    }
  }'
```

---

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