added mistral v2, files v2, and finalized textract

Author: waleedlatif1

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

@@ -154,7 +154,7 @@ export const blockTypeToIconMap: Record<string, IconComponent> = {
   elasticsearch: ElasticsearchIcon,
   elevenlabs: ElevenLabsIcon,
   exa: ExaAIIcon,
-  file: DocumentIcon,
+  file_v2: DocumentIcon,
   firecrawl: FirecrawlIcon,
   fireflies: FirefliesIcon,
   github_v2: GithubIcon,
@@ -196,7 +196,7 @@ export const blockTypeToIconMap: Record<string, IconComponent> = {
   microsoft_excel_v2: MicrosoftExcelIcon,
   microsoft_planner: MicrosoftPlannerIcon,
   microsoft_teams: MicrosoftTeamsIcon,
-  mistral_parse: MistralIcon,
+  mistral_parse_v2: MistralIcon,
   mongodb: MongoDBIcon,
   mysql: MySQLIcon,
   neo4j: Neo4jIcon,

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

@@ -6,7 +6,7 @@ description: Read and parse multiple files
 import { BlockInfoCard } from "@/components/ui/block-info-card"
 
 <BlockInfoCard 
-  type="file"
+  type="file_v2"
   color="#40916C"
 />
 
@@ -48,7 +48,7 @@ Parse one or more uploaded files or files from URLs (text, PDF, CSV, images, etc
 
 | Parameter | Type | Description |
 | --------- | ---- | ----------- |
-| `files` | array | Array of parsed files |
-| `combinedContent` | string | Combined content of all parsed files |
+| `files` | array | Array of parsed files with content, metadata, and file properties |
+| `combinedContent` | string | All file contents merged into a single text string |
 
 

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

@@ -6,7 +6,7 @@ description: Extract text from PDF documents
 import { BlockInfoCard } from "@/components/ui/block-info-card"
 
 <BlockInfoCard 
-  type="mistral_parse"
+  type="mistral_parse_v2"
   color="#000000"
 />
 
@@ -57,15 +57,5 @@ Parse PDF documents using Mistral OCR API
 | `success` | boolean | Whether the PDF was parsed successfully |
 | `content` | string | Extracted content in the requested format \(markdown, text, or JSON\) |
 | `metadata` | object | Processing metadata including jobId, fileType, pageCount, and usage info |
-| ↳ `jobId` | string | Unique job identifier |
-| ↳ `fileType` | string | File type \(e.g., pdf\) |
-| ↳ `fileName` | string | Original file name |
-| ↳ `source` | string | Source type \(url\) |
-| ↳ `pageCount` | number | Number of pages processed |
-| ↳ `model` | string | Mistral model used |
-| ↳ `resultType` | string | Output format \(markdown, text, json\) |
-| ↳ `processedAt` | string | Processing timestamp |
-| ↳ `sourceUrl` | string | Source URL if applicable |
-| ↳ `usageInfo` | object | Usage statistics from OCR processing |
 
 

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

@@ -423,7 +423,12 @@ export async function POST(request: NextRequest) {
 
     let fileUrl = validatedData.filePath
 
-    if (validatedData.filePath?.includes('/api/files/serve/')) {
+    const isInternalFilePath =
+      validatedData.filePath?.startsWith('/api/files/serve/') ||
+      (validatedData.filePath?.startsWith('/') &&
+        validatedData.filePath?.includes('/api/files/serve/'))
+
+    if (isInternalFilePath) {
       try {
         const storageKey = extractStorageKey(validatedData.filePath)
         const context = inferContextFromKey(storageKey)

apps/sim/blocks/blocks/file.ts

@@ -1,13 +1,14 @@
 import { createLogger } from '@sim/logger'
 import { DocumentIcon } from '@/components/icons'
 import type { BlockConfig, SubBlockType } from '@/blocks/types'
+import { createVersionedToolSelector } from '@/blocks/utils'
 import type { FileParserOutput } from '@/tools/file/types'
 
 const logger = createLogger('FileBlock')
 
 export const FileBlock: BlockConfig<FileParserOutput> = {
   type: 'file',
-  name: 'File',
+  name: 'File (Legacy)',
   description: 'Read and parse multiple files',
   longDescription: `Integrate File into the workflow. Can upload a file manually or insert a file url.`,
   bestPractices: `
@@ -17,6 +18,7 @@ export const FileBlock: BlockConfig<FileParserOutput> = {
   category: 'tools',
   bgColor: '#40916C',
   icon: DocumentIcon,
+  hideFromToolbar: true,
   subBlocks: [
     {
       id: 'inputMethod',
@@ -123,3 +125,92 @@ export const FileBlock: BlockConfig<FileParserOutput> = {
     },
   },
 }
+
+export const FileV2Block: BlockConfig<FileParserOutput> = {
+  ...FileBlock,
+  type: 'file_v2',
+  name: 'File',
+  description: 'Read and parse multiple files',
+  hideFromToolbar: false,
+  subBlocks: [
+    {
+      id: 'file',
+      title: 'Files',
+      type: 'file-upload' as SubBlockType,
+      canonicalParamId: 'fileInput',
+      acceptedTypes:
+        '.pdf,.csv,.doc,.docx,.txt,.md,.xlsx,.xls,.html,.htm,.pptx,.ppt,.json,.xml,.rtf',
+      placeholder: 'Upload files to process',
+      multiple: true,
+      mode: 'basic',
+      maxSize: 100,
+    },
+    {
+      id: 'filePath',
+      title: 'Files',
+      type: 'short-input' as SubBlockType,
+      canonicalParamId: 'fileInput',
+      placeholder: 'File URL or reference from previous block',
+      mode: 'advanced',
+    },
+  ],
+  tools: {
+    access: ['file_parser_v2'],
+    config: {
+      tool: createVersionedToolSelector({
+        baseToolSelector: () => 'file_parser',
+        suffix: '_v2',
+        fallbackToolId: 'file_parser_v2',
+      }),
+      params: (params) => {
+        const fileInput = params.file || params.filePath || params.fileInput
+        if (!fileInput) {
+          logger.error('No file input provided')
+          throw new Error('File is required')
+        }
+
+        if (typeof fileInput === 'string') {
+          return {
+            filePath: fileInput.trim(),
+            fileType: params.fileType || 'auto',
+            workspaceId: params._context?.workspaceId,
+          }
+        }
+
+        if (Array.isArray(fileInput) && fileInput.length > 0) {
+          const filePaths = fileInput.map((file) => file.path)
+          return {
+            filePath: filePaths.length === 1 ? filePaths[0] : filePaths,
+            fileType: params.fileType || 'auto',
+          }
+        }
+
+        if (fileInput?.path) {
+          return {
+            filePath: fileInput.path,
+            fileType: params.fileType || 'auto',
+          }
+        }
+
+        logger.error('Invalid file input format')
+        throw new Error('Invalid file input')
+      },
+    },
+  },
+  inputs: {
+    fileInput: { type: 'json', description: 'File input (upload or URL reference)' },
+    filePath: { type: 'string', description: 'File URL (advanced mode)' },
+    file: { type: 'json', description: 'Uploaded file data (basic mode)' },
+    fileType: { type: 'string', description: 'File type' },
+  },
+  outputs: {
+    files: {
+      type: 'json',
+      description: 'Array of parsed file objects with content, metadata, and file properties',
+    },
+    combinedContent: {
+      type: 'string',
+      description: 'All file contents merged into a single text string',
+    },
+  },
+}