Google Docs Reader
Read content and metadata from one or multiple Google Docs documents
What does this node do?
The Google Docs Reader node reads content and metadata from one or multiple Google Docs documents. It supports multi-document selection via Google Drive Picker, per-document tab selection, and three output formats (JSON, plain text, markdown).
Common uses:
- Extract documents for AI-powered summarization
- Read content for SEO analysis and optimization
- Pull documentation for automated translation workflows
Quick setup
Connect your Google account
Go to Builder → Integrations → Google and authenticate with the google_docs scope
Add the Google Docs Reader node
Find it in Integrations → Google → Docs Reader
Select your documents
Use the Google Drive Picker to select one or multiple documents, then configure output format and tab selection
Configuration
Version: 1.1 | Integration: google_docs
Parameters
integration_id string required The Google Docs integration to use. Select from your configured Google integrations.
document_ids string[] required The Google Doc IDs to read. Use the built-in Google Drive Picker to select one or multiple documents. Supports multi-select.
document_names string[] Display names of the selected documents. Auto-filled when documents are selected via the Picker.
output_type select default: markdown The format for the extracted content.
| Value | Description |
|---|---|
json | Structured JSON with full document metadata |
plain_text | Raw text content without formatting |
markdown | Markdown-formatted content (recommended for LLM processing) |
read_all_tabs boolean default: true Whether to read all tabs in each document. When enabled, content from every tab is included in the output.
selected_tabs object Per-document tab selection. When read_all_tabs is disabled, use the tab selection modal to choose specific tabs for each document. Useful for large documents where only certain tabs are relevant.
Inputs
This node has no inputs. It reads directly from Google Docs using the configured parameters.
Output
document_data string JSON string containing the document content and metadata for all selected documents.
{
"documents": [
{
"document_id": "1aBcDeFgHiJkLmNoPqRsTuVwXyZ",
"title": "Q1 Marketing Report",
"tabs": [
{
"tab_id": "t.0",
"tab_name": "Overview",
"content": "# Q1 Marketing Report\n\nThis quarter saw a 25% increase..."
}
],
"url": "https://docs.google.com/document/d/1aBcDeFgHiJkLmNoPqRsTuVwXyZ"
}
]
}
Access the output: {{Google_Docs_Reader_0.document_data}}
Examples
Extract documents for AI summarization
Read multiple marketing reports and summarize them with an LLM:
graph LR
A[Google Docs Reader] --> B[LLM]
B --> C[Email Sender]
Setup:
- Select 3-5 marketing reports via the Google Drive Picker
- Set
output_typetomarkdownfor optimal LLM processing - Connect to an LLM node with instructions: “Summarize each document in 3 bullet points”
- Send the summary via email
Read documentation for translation
Pull technical documentation and translate it using AI:
graph LR
A[Google Docs Reader] --> B[LLM Translate]
B --> C[Google Docs Writer]
Setup:
- Select the source documents to translate
- Set
output_typetomarkdownto preserve formatting - Use an LLM node to translate the content
- Write the translated content to new documents with Google Docs Writer
Best practices
- Use markdown format for LLM processing. The
markdownoutput type preserves document structure (headings, lists, links) while remaining easy for AI models to interpret. - Select specific tabs for large documents. Disable
read_all_tabsand choose only the tabs you need to reduce processing time and token usage. - Use JSON output for programmatic processing. When you need to extract specific metadata or process documents programmatically, the
jsonformat provides the most structured data.
Common issues
No content returned for a document
Verify that the Google integration has the correct permissions. The google_docs scope must be enabled. Also check that the authenticated account has read access to the selected documents.
Tab content is missing or incomplete
If read_all_tabs is disabled, ensure the correct tabs are selected in the tab selection modal. Some documents may have tabs with empty content or content that requires specific permissions.