feat(extend): add Extend AI document processing integration

Author: waleedlatif1

apps/docs/components/icons.tsx

@@ -2041,6 +2041,15 @@ export function Mem0Icon(props: SVGProps<SVGSVGElement>) {
   )
 }
 
+export function ExtendIcon(props: SVGProps<SVGSVGElement>) {
+  return (
+    <svg {...props} xmlns='http://www.w3.org/2000/svg' viewBox='0 0 24 24' fill='none'>
+      <rect width='24' height='24' rx='4' fill='#1A1A2E' />
+      <path d='M7 8h10M7 12h10M7 16h6' stroke='#FFFFFF' strokeWidth='2' strokeLinecap='round' />
+    </svg>
+  )
+}
+
 export function EvernoteIcon(props: SVGProps<SVGSVGElement>) {
   return (
     <svg {...props} xmlns='http://www.w3.org/2000/svg' viewBox='0 0 32 32' fill='#7fce2c'>

apps/docs/components/ui/icon-mapping.ts

@@ -45,6 +45,7 @@ import {
   EnrichSoIcon,
   EvernoteIcon,
   ExaAIIcon,
+  ExtendIcon,
   EyeIcon,
   FathomIcon,
   FirecrawlIcon,
@@ -221,6 +222,7 @@ export const blockTypeToIconMap: Record<string, IconComponent> = {
   enrich: EnrichSoIcon,
   evernote: EvernoteIcon,
   exa: ExaAIIcon,
+  extend_v2: ExtendIcon,
   fathom: FathomIcon,
   file_v3: DocumentIcon,
   firecrawl: FirecrawlIcon,

apps/docs/content/docs/en/tools/extend.mdx

@@ -0,0 +1,61 @@
+---
+title: Extend
+description: Parse and extract content from documents using Extend AI
+---
+
+import { BlockInfoCard } from "@/components/ui/block-info-card"
+
+<BlockInfoCard
+  type="extend_v2"
+  color="#000000"
+/>
+
+## Description
+
+The Extend block connects to [Extend AI](https://www.extend.ai/) to parse and extract structured content from documents. It supports a wide range of file formats including PDFs, images (JPEG, PNG, TIFF, GIF, BMP, WebP), and Office documents (Word, PowerPoint, Excel).
+
+Extend uses advanced document understanding to convert unstructured documents into clean, structured output — returning parsed chunks and block-level elements with content type classification and spatial metadata.
+
+### Key Capabilities
+
+- **Document Parsing**: Extract text, tables, figures, and structured content from uploaded documents or URLs.
+- **Multiple Output Formats**: Choose between Markdown (default) for clean text output, or Spatial for layout-preserving extraction.
+- **Chunking Strategies**: Split output by page, document, or section depending on your downstream use case.
+- **Engine Selection**: Use the default `Performance` engine for best quality, or `Light` for faster processing on simpler documents.
+
+### Authentication
+
+An Extend API key is required. You can generate one from the [Extend Developer Dashboard](https://dashboard.extend.ai).
+
+### Supported File Types
+
+PDF, JPEG, PNG, TIFF, GIF, BMP, WebP, HEIC/HEIF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx), XML, HTML, CSV, TXT.
+
+## Tools
+
+### `extend_parser`
+
+#### Input
+
+| Parameter | Type | Required | Description |
+| --------- | ---- | -------- | ----------- |
+| `filePath` | string | No | URL to a document to be processed |
+| `file` | file | No | Document file to be processed |
+| `fileUpload` | object | No | File upload data from file-upload component |
+| `outputFormat` | string | No | Target output format \(markdown or spatial\). Defaults to markdown. |
+| `chunking` | string | No | Chunking strategy \(page, document, or section\). Defaults to page. |
+| `engine` | string | No | Parsing engine \(parse_performance or parse_light\). Defaults to parse_performance. |
+| `apiKey` | string | Yes | Extend API key |
+
+#### Output
+
+| Field | Type | Description |
+| ----- | ---- | ----------- |
+| `id` | string | Unique identifier for the parser run |
+| `status` | string | Processing status |
+| `chunks` | json | Parsed document content chunks |
+| `blocks` | json | Block-level document elements with type and content |
+| `pageCount` | number | Number of pages processed |
+| `creditsUsed` | number | API credits consumed |
+
+

apps/docs/content/docs/en/tools/meta.json

@@ -39,6 +39,7 @@
     "enrich",
     "evernote",
     "exa",
+    "extend",
     "fathom",
     "file",
     "firecrawl",

apps/sim/app/(landing)/integrations/data/icon-mapping.ts

@@ -45,6 +45,7 @@ import {
   EnrichSoIcon,
   EvernoteIcon,
   ExaAIIcon,
+  ExtendIcon,
   EyeIcon,
   FathomIcon,
   FirecrawlIcon,
@@ -221,6 +222,7 @@ export const blockTypeToIconMap: Record<string, IconComponent> = {
   enrich: EnrichSoIcon,
   evernote: EvernoteIcon,
   exa: ExaAIIcon,
+  extend_v2: ExtendIcon,
   fathom: FathomIcon,
   file_v3: DocumentIcon,
   firecrawl: FirecrawlIcon,

apps/sim/app/(landing)/integrations/data/integrations.json

@@ -2939,6 +2939,24 @@
     "integrationType": "search",
     "tags": ["web-scraping", "enrichment"]
   },
+  {
+    "type": "extend_v2",
+    "slug": "extend",
+    "name": "Extend",
+    "description": "Parse and extract content from documents",
+    "longDescription": "Integrate Extend AI into the workflow. Parse and extract structured content from documents or file references.",
+    "bgColor": "#1A1A2E",
+    "iconName": "ExtendIcon",
+    "docsUrl": "https://docs.sim.ai/tools/extend",
+    "operations": [],
+    "operationCount": 0,
+    "triggers": [],
+    "triggerCount": 0,
+    "authType": "api-key",
+    "category": "tools",
+    "integrationType": "ai",
+    "tags": ["document-processing", "ocr"]
+  },
   {
     "type": "fathom",
     "slug": "fathom",

apps/sim/app/api/tools/extend/parse/route.ts

@@ -0,0 +1,179 @@
+import { createLogger } from '@sim/logger'
+import { type NextRequest, NextResponse } from 'next/server'
+import { z } from 'zod'
+import { checkInternalAuth } from '@/lib/auth/hybrid'
+import {
+  secureFetchWithPinnedIP,
+  validateUrlWithDNS,
+} from '@/lib/core/security/input-validation.server'
+import { generateRequestId } from '@/lib/core/utils/request'
+import { RawFileInputSchema } from '@/lib/uploads/utils/file-schemas'
+import { isInternalFileUrl } from '@/lib/uploads/utils/file-utils'
+import { resolveFileInputToUrl } from '@/lib/uploads/utils/file-utils.server'
+
+export const dynamic = 'force-dynamic'
+
+const logger = createLogger('ExtendParseAPI')
+
+const ExtendParseSchema = z.object({
+  apiKey: z.string().min(1, 'API key is required'),
+  filePath: z.string().optional(),
+  file: RawFileInputSchema.optional(),
+  outputFormat: z.enum(['markdown', 'spatial']).optional(),
+  chunking: z.enum(['page', 'document', 'section']).optional(),
+  engine: z.enum(['parse_performance', 'parse_light']).optional(),
+})
+
+export async function POST(request: NextRequest) {
+  const requestId = generateRequestId()
+
+  try {
+    const authResult = await checkInternalAuth(request, { requireWorkflowId: false })
+
+    if (!authResult.success || !authResult.userId) {
+      logger.warn(`[${requestId}] Unauthorized Extend parse attempt`, {
+        error: authResult.error || 'Missing userId',
+      })
+      return NextResponse.json(
+        {
+          success: false,
+          error: authResult.error || 'Unauthorized',
+        },
+        { status: 401 }
+      )
+    }
+
+    const userId = authResult.userId
+    const body = await request.json()
+    const validatedData = ExtendParseSchema.parse(body)
+
+    logger.info(`[${requestId}] Extend parse request`, {
+      fileName: validatedData.file?.name,
+      filePath: validatedData.filePath,
+      isWorkspaceFile: validatedData.filePath ? isInternalFileUrl(validatedData.filePath) : false,
+      userId,
+    })
+
+    const resolution = await resolveFileInputToUrl({
+      file: validatedData.file,
+      filePath: validatedData.filePath,
+      userId,
+      requestId,
+      logger,
+    })
+
+    if (resolution.error) {
+      return NextResponse.json(
+        { success: false, error: resolution.error.message },
+        { status: resolution.error.status }
+      )
+    }
+
+    const fileUrl = resolution.fileUrl
+    if (!fileUrl) {
+      return NextResponse.json({ success: false, error: 'File input is required' }, { status: 400 })
+    }
+
+    const extendBody: Record<string, unknown> = {
+      fileUrl,
+    }
+
+    const config: Record<string, unknown> = {}
+
+    if (validatedData.outputFormat) {
+      config.targetFormat = validatedData.outputFormat
+    }
+
+    if (validatedData.chunking) {
+      config.chunking = { strategy: validatedData.chunking }
+    }
+
+    if (validatedData.engine) {
+      config.engine = validatedData.engine
+    }
+
+    if (Object.keys(config).length > 0) {
+      extendBody.config = config
+    }
+
+    const extendEndpoint = 'https://api.extend.ai/parse'
+    const extendValidation = await validateUrlWithDNS(extendEndpoint, 'Extend API URL')
+    if (!extendValidation.isValid) {
+      logger.error(`[${requestId}] Extend API URL validation failed`, {
+        error: extendValidation.error,
+      })
+      return NextResponse.json(
+        {
+          success: false,
+          error: 'Failed to reach Extend API',
+        },
+        { status: 502 }
+      )
+    }
+
+    const extendResponse = await secureFetchWithPinnedIP(
+      extendEndpoint,
+      extendValidation.resolvedIP!,
+      {
+        method: 'POST',
+        headers: {
+          'Content-Type': 'application/json',
+          Accept: 'application/json',
+          Authorization: `Bearer ${validatedData.apiKey}`,
+          'x-extend-api-version': '2025-04-21',
+        },
+        body: JSON.stringify(extendBody),
+      }
+    )
+
+    if (!extendResponse.ok) {
+      const errorText = await extendResponse.text()
+      logger.error(`[${requestId}] Extend API error:`, errorText)
+      return NextResponse.json(
+        {
+          success: false,
+          error: `Extend API error: ${extendResponse.statusText}`,
+        },
+        { status: extendResponse.status }
+      )
+    }
+
+    const extendData = await extendResponse.json()
+
+    logger.info(`[${requestId}] Extend parse successful`)
+
+    return NextResponse.json({
+      success: true,
+      output: {
+        id: extendData.id ?? null,
+        status: extendData.status ?? 'PROCESSED',
+        chunks: extendData.chunks ?? [],
+        blocks: extendData.blocks ?? [],
+        pageCount: extendData.pageCount ?? extendData.page_count ?? null,
+        creditsUsed: extendData.creditsUsed ?? extendData.credits_used ?? null,
+      },
+    })
+  } catch (error) {
+    if (error instanceof z.ZodError) {
+      logger.warn(`[${requestId}] Invalid request data`, { errors: error.errors })
+      return NextResponse.json(
+        {
+          success: false,
+          error: 'Invalid request data',
+          details: error.errors,
+        },
+        { status: 400 }
+      )
+    }
+
+    logger.error(`[${requestId}] Error in Extend parse:`, error)
+
+    return NextResponse.json(
+      {
+        success: false,
+        error: error instanceof Error ? error.message : 'Internal server error',
+      },
+      { status: 500 }
+    )
+  }
+}