Read File Node

The Read File node reads the text content from files. Got a PDF you need to analyze? An email attachment to process? An image with text in it? This node extracts the text so you can work with it.

Read File node configuration form — Read File configuration — point at a file URL or a variable from a previous node, then pick the output variable for the extracted text.

When to Use

Reading documents - Get the text from PDFs, Word docs, PowerPoints
Processing attachments - Read files that came with emails
Reading text from images - Extract words from photos, scans, screenshots
Importing data - Read CSV or Excel files
Processing forms - Get the filled-in data from PDF forms

Read a file from Workspace files

Read File can read a file straight from Workspace files, the folder your team and coworkers share. Set Read to Workspace file, then Find it by:

Path: a path in the workspace folder, like Inbox/Invoices/invoice-1043.pdf, matched ignoring case. It may use {{…}}, worked out when the workflow runs. The folder button beside the field lets you pick the file.
Id or earlier step: a file’s id, or a workspace file an earlier step passed on, like {{file_added_to_folder_1.file}}, {{workspace_files_1.file}} or {{loop_1.currentItem}}. An id still finds the file after it is renamed or moved.

Read File form with Read set to Workspace file, Find it by Path, and Workspace file Inbox/Invoices/invoice-1043.pdf — Read File reading an invoice from Workspace files by its path.

Files up to 50 MB can be read. Besides the text, the step outputs file: the workspace file it read, ready for a Workspace Files step or an AI attachment. The Read choice shows only where your workspace has Workspace files.

Supported File Types

Documents

Format	Extension	Notes
PDF	.pdf	Text and image-based (via OCR)
Word	.docx, .doc	Modern and legacy formats
PowerPoint	.pptx, .ppt	Extracts slide text
Text	.txt, .md, .rtf	Plain text files

Spreadsheets

Format	Extension	Notes
Excel	.xlsx, .xls	Returns structured data
CSV	.csv	Parsed into rows/columns

Images

Format	Extension	Notes
Images	.png, .jpg, .jpeg, .gif, .webp	OCR extraction
TIFF	.tiff	Often used for scans

Example: Email Attachment Processor

Extract and analyze content from email attachments:

Receive email with attachment

Use App Trigger (Gmail) to trigger on emails with attachments.

Parse each attachment

Add a Loop node to iterate over {{event_from_app_1.email.attachments}}:

├── Loop (over attachments)
│   └── Read File (fileReference: {{loop_1.currentItem}})

Analyze content

Use LLM node to analyze or summarize:

Summarize this document in 3 bullet points:
{{parse_file_1.content}}

Store results

Add to a spreadsheet or send via Slack.

Example: Invoice Data Extraction

Extract structured data from PDF invoices:

Workflow: Invoice Processor
├── App Trigger (Gmail: emails from billing@vendor.com)
├── Read File (attachment, mode: structured)
├── LLM (extract invoice data into JSON)
│   Prompt:
│   "Extract from this invoice:
│   - Invoice number
│   - Date
│   - Vendor name
│   - Line items (description, quantity, amount)
│   - Total
│
│   Document: {{parse_file_1.content}}"
├── Execute Code (validate and format data)
└── Integration Action (add to accounting system)

Example: Resume Scanner

Process job applications:

Workflow: Resume Scanner
├── Webhook (from careers page upload)
├── Read File (from upload)
├── LLM (extract candidate info)
│   "Extract:
│   - Name
│   - Email
│   - Phone
│   - Years of experience
│   - Key skills
│   - Education
│
│   Resume: {{parse_file_1.content}}"
├── Integration Action (HubSpot: create contact)
└── Integration Action (Slack: notify recruiting team)

Working with Multi-Page Documents

Process All Pages Together

Summary of the entire document:
{{parse_file_1.content}}

Process Pages Individually

├── Read File (PDF)
├── Loop (over {{parse_file_1.pages}})
│   ├── LLM (analyze page {{loop_1.currentIndex + 1}})
│   └── Update Variable (append results)
└── LLM (synthesize all page analyses)

Extract Specific Pages

Configuration: pages: "1,5-10" Only extracts pages 1 and 5 through 10.

Handling Tables

For documents with tables, use structured extraction mode:

├── Read File (mode: structured)
├── Execute Code
│   # Access tables
│   tables = parse_file_1["tables"]
│
│   # First table, first row
│   header = tables[0]["rows"][0]
│
│   # Convert to records
│   records = []
│   for row in tables[0]["rows"][1:]:
│       record = dict(zip(header, row))
│       records.append(record)
│
│   return {"records": records}
└── Loop (over records)

Reading Text from Images and Scans

If your file is an image or a scanned document, use OCR mode to read the text: Set extraction mode to: ocr

OCR takes longer (usually 2-5 seconds per page) and isn’t always perfect. Double-check important extractions.

For better results:

Use higher quality images
Make sure the text is clear and readable
Note that handwriting usually doesn’t work well

When Things Go Wrong

File reading can fail because:

The file is damaged
The file type isn’t supported
The file is password-protected
The file is too big

You can check if it worked:

├── Read File
├── If / else (did it work?)
│   ├── Yes: Continue processing
│   └── No: Send alert about the problem

Password-protected PDFs can’t be read. Ask users to provide files without passwords.

File Size Limits

File Type	Max Size
PDF	50 MB
Word/PowerPoint	25 MB
Images	10 MB
CSV/Excel	25 MB

For larger files, consider splitting or pre-processing.

Tips

For long documents, extract text first and then use LLM to summarize or answer specific questions. Don’t try to process entire books in one go.

Use structured mode when you need to preserve tables. Use text mode when you just need the words and don’t care about formatting.

Store parsed content in a variable if you need to reference it multiple times. Parsing is compute-intensive.

Settings

string

default:"Read File"

What to call this node (shown on the canvas).

string

default:"parse_file_1"

A short code to reference this node’s content.

string

required

Where the file is coming from:

url - Download it from a web address
base64 - The file content encoded as text
previous_node - A file from an earlier step (like an email attachment)

string

The web address to download from (if using URL source).

string

The encoded file content (if using base64 source).

string

Reference to a file from an earlier node (if using previous_node source).

string

default:"input"

Read: input (the file or web address above) or workspace (Workspace file).

string

default:"path"

Find it by, for a workspace file: path or id (Id or earlier step).

string

The Workspace file’s path, like contracts/{{start_1.client}}.pdf, when finding it by path.

string

The Workspace file’s id, or a workspace file from an earlier step such as {{workspace_files_1.file}}, when finding it by id.

string

default:"text"

How to read the file:

text - Just get the words
structured - Try to keep tables and lists intact
ocr - Read text from images or scanned documents

string

Which pages to read (for documents with multiple pages). Examples: 1-5, 1,3,5, or all.

Outputs

string

The extracted text content.

array

Array of page contents (for multi-page documents).

object

File metadata:

pageCount - Number of pages
fileType - Detected file type
fileSize - Size in bytes
title - Document title (if available)
author - Document author (if available)
createdAt - Creation date (if available)

array

Extracted tables (when using structured mode).

boolean

Whether extraction completed successfully.

object

Only when reading from Workspace files: the workspace file that was read, to pass to a Workspace Files step or an AI attachment.

LLM

Analyze and extract insights from parsed content.

Loop

Process multiple files or pages.

Workspace Files

Write, list, move and copy files in Workspace files.

File Added to Folder

Start a workflow when a file arrives in a folder.

Overview

Triggers

Actions

Logic

Communication

When to Use

Read a file from Workspace files

Supported File Types

Documents

Spreadsheets

Images

Example: Email Attachment Processor

Example: Invoice Data Extraction

Example: Resume Scanner

Working with Multi-Page Documents

Process All Pages Together

Process Pages Individually

Extract Specific Pages

Handling Tables

Reading Text from Images and Scans

When Things Go Wrong

File Size Limits

Tips

Settings

Outputs

LLM

Loop

Workspace Files

File Added to Folder

​When to Use

​Read a file from Workspace files

​Supported File Types

​Documents

​Spreadsheets

​Images

​Example: Email Attachment Processor

​Example: Invoice Data Extraction

​Example: Resume Scanner

​Working with Multi-Page Documents

​Process All Pages Together

​Process Pages Individually

​Extract Specific Pages

​Handling Tables

​Reading Text from Images and Scans

​When Things Go Wrong

​File Size Limits

​Tips

​Settings

​Outputs

​Related Nodes

LLM

Loop

Workspace Files

File Added to Folder

When to Use

Read a file from Workspace files

Supported File Types

Documents

Spreadsheets

Images

Example: Email Attachment Processor

Example: Invoice Data Extraction

Example: Resume Scanner

Working with Multi-Page Documents

Process All Pages Together

Process Pages Individually

Extract Specific Pages

Handling Tables

Reading Text from Images and Scans

When Things Go Wrong

File Size Limits

Tips

Settings

Outputs

Related Nodes