# LLMWhisperer — Pipedream Connect

> LLMWhisperer is a technology that presents data from complex documents to LLMs in a way that they can best understand.

- API slug: `llmwhisperer` (use in MCP headers and tool keys)
- Auth: API key (Pipedream-managed)
- Categories: Artificial Intelligence (AI)
- Website: https://unstract.com/llmwhisperer/
- This page (HTML): https://pipedream.com/apps/llmwhisperer
- Tools: 4 actions · 0 triggers

## Connect via MCP (recommended)

- Endpoint: `https://remote.mcp.pipedream.net/v3`
- Headers: `Authorization: Bearer <token>` · `x-pd-project-id` · `x-pd-environment` · `x-pd-external-user-id` · `x-pd-app-slug: llmwhisperer`

```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": "llmwhisperer",
      },
    },
  },
)

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

const { tools } = await mcp.listTools()

// e.g. run Extract Text:
const result = await mcp.callTool({
  name: "llmwhisperer-extract-text",
  arguments: {
    processingMode: "Processing Mode",
    outputMode: "Output Mode",
  },
})
```

Docs: [MCP guide](https://pipedream.com/docs/connect/mcp/developers.md)

## API proxy

For a LLMWhisperer endpoint with no pre-built tool, the proxy forwards your request with the connected user's credentials attached.

```bash
# The path segment is the target URL, URL-safe base64 encoded:
# https://llmwhisperer-api.unstract.com/v1/get-usage-info

curl "https://api.pipedream.com/v1/connect/{project_id}/proxy/aHR0cHM6Ly9sbG13aGlzcGVyZXItYXBpLnVuc3RyYWN0LmNvbS92MS9nZXQtdXNhZ2UtaW5mbw?external_user_id={external_user_id}&account_id=apn_xxxxxxx" \
  -H "Authorization: Bearer {access_token}" \
  -H "x-pd-environment: production"
```

Docs: [API proxy guide](https://pipedream.com/docs/connect/api-proxy.md)

## SDK

```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: "llmwhisperer-extract-text",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    llmwhisperer: { authProvisionId: "apn_xxxxxxx" },
    processingMode: "Processing Mode",
    outputMode: "Output Mode",
  },
})
```

Docs: [Managed auth guide](https://pipedream.com/docs/connect/managed-auth/quickstart.md) · [Tools guide](https://pipedream.com/docs/connect/components.md)

## Actions (4)

### `llmwhisperer-extract-text` — Extract Text (Read-only)

Convert your PDF/scanned documents to text format which can be used by LLMs. See the documentation

Full schema: https://pipedream.com/apps/llmwhisperer/actions/extract-text.md

### `llmwhisperer-get-status` — Get Status (Read-only)

Get the status of the whisper process. This can be used to check the status of the conversion process when the conversion is done in async mode. See the documentation

Full schema: https://pipedream.com/apps/llmwhisperer/actions/get-status.md

### `llmwhisperer-highlight-locations` — Highlight Locations (Read-only)

Generate highlight locations for a search term in the document. See the documentation

Full schema: https://pipedream.com/apps/llmwhisperer/actions/highlight-locations.md

### `llmwhisperer-retrieve-text` — Retrieve Extracted Text (Read-only)

Retrieve the extracted text executed through the whisper API. This can be used to retrieve the text of the conversion process when the conversion is done in async mode. See the documentation

Full schema: https://pipedream.com/apps/llmwhisperer/actions/retrieve-text.md

---

- All apps: https://pipedream.com/apps — index: https://pipedream.com/llms.txt
- Pipedream docs for agents: https://pipedream.com/docs/llms.txt