Passing files

A file moves through a workflow as a standardized file object. Blocks receive it, act on it, and pass it on — this page covers the object's shape, how to reference it between blocks, and how files enter and leave through the API.

File Objects

When blocks output files (like Gmail attachments, generated images, or parsed documents), they return a standardized file object:

{
  "id": "f_8c2...",
  "name": "report.pdf",
  "url": "https://...",
  "size": 245678,
  "type": "application/pdf",
  "base64": "JVBERi0xLjQK..."
}

You can access any of these properties when referencing files from previous blocks.

The File Block

The File block brings a file into a workflow. It accepts files from any source and outputs standardized file objects every block understands.

Inputs:

• Uploaded files - Drag and drop or select files directly
• External URLs - Any publicly accessible file URL
• Files from other blocks - Pass files from Gmail attachments, Slack downloads, etc.

Outputs:

• A list of UserFile objects with consistent structure (id, name, url, size, type, base64)
• contents - Extracted text per file (the Get Content operation)
• combinedContent - All fetched files' text merged into one string (the Fetch operation)

Example usage:

// Get all files from the File block
<file.files>

// Get the first file
<file.files[0]>

// Get the first file's extracted text (Get Content operation)
<file.contents[0]>

The File block automatically:

• Detects file types from URLs and extensions
• Extracts text from PDFs, CSVs, and documents
• Generates base64 encoding for binary files
• Creates presigned URLs for secure access

Use the File block when you need to normalize files from different sources before passing them to other blocks like Vision, STT, or email integrations.

Passing Files Between Blocks

Reference files from previous blocks using the tag dropdown. Click in any file input field and type < to see available outputs.

Common patterns:

// Single file from a block
<gmail.attachments[0]>

// Pass the whole file object
<file_parser.files[0]>

// Access specific properties
<gmail.attachments[0].name>
<gmail.attachments[0].base64>

Most blocks accept the full file object and extract what they need automatically. You don't need to manually extract base64 or url in most cases.

Triggering Workflows with Files

When calling a workflow via API that expects file input, include files in your request:

curl -X POST "https://sim.ai/api/workflows/YOUR_WORKFLOW_ID/execute" \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -d '{
    "document": {
      "name": "report.pdf",
      "base64": "JVBERi0xLjQK...",
      "type": "application/pdf"
    }
  }'

curl -X POST "https://sim.ai/api/workflows/YOUR_WORKFLOW_ID/execute" \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -d '{
    "document": {
      "name": "report.pdf",
      "url": "https://example.com/report.pdf",
      "type": "application/pdf"
    }
  }'

The workflow's Start block should have an input field configured to receive the file parameter.

Receiving Files in API Responses

When a workflow outputs files, they're included in the response:

{
  "success": true,
  "output": {
    "generatedFile": {
      "name": "output.png",
      "url": "https://...",
      "base64": "iVBORw0KGgo...",
      "type": "image/png",
      "size": 34567
    }
  }
}

Use url for direct downloads or base64 for inline processing.

Blocks That Work with Files

File inputs:

• File - Parse documents, images, and text files
• Agent - Read images with a vision-capable model, or documents as text
• Mistral Parser - Extract text from PDFs

File outputs:

• Gmail - Email attachments
• Slack - Downloaded files
• TTS - Generated audio files
• Video Generator - Generated videos
• Image Generator - Generated images

File storage:

• Supabase - Upload/download from storage
• S3 - AWS S3 operations
• Google Drive - Drive file operations
• Dropbox - Dropbox file operations

Best Practices

1. Use file objects directly - Pass the full file object rather than extracting individual properties. Blocks handle the conversion automatically.

2. Check file types - Ensure the file type matches what the receiving block expects. An Agent using a vision-capable model can read images, while the File block handles documents.

3. Consider file size - Large files increase run time. For very large files, consider using storage blocks (S3, Supabase) for intermediate storage.