Google Drive to InfraNodus Knowledge Graph Sync - n8n Workflow

Knowledge workers and researchers who organize documents in Google Drive.
Users of InfraNodus looking to automate content ingestion.
Developers seeking complex file handling n8n templates.
Anyone needing an automated n8n workflow for continuous knowledge base updates.

Keeping a knowledge graph updated manually is time-consuming. This powerful n8n workflow solves this problem by automating the entire pipeline. It monitors a specific Google Drive folder for newly added files (including PDFs, markdown, and plain text) and automatically processes the content, saving it instantly to your designated InfraNodus graph.

This robust n8n automation leverages the flexibility of the n8n node structure to manage different file types via a Switch node, ensuring accurate text extraction before committing the data. It is a perfect example of how an n8n solution can bridge cloud storage and semantic analysis tools, providing real-time data synchronization.

This n8n workflow operates in several key stages:

1. Trigger: The process begins with the New File Created in the Google Folder? n8n trigger. This Google Drive n8n trigger constantly monitors a user-specified folder for any new file uploads.


2. Iteration: The data moves to the Loop Over Items n8n node, ensuring each file is processed sequentially and individually, even if multiple files are uploaded simultaneously.


3. Retrieval: The Retrieve File Google Drive n8n node downloads the actual file content and metadata based on the file ID provided by the trigger.


4. Routing: The Switch n8n node examines the file's MIME type (e.g., PDF, text/plain, markdown). This is crucial for routing the binary data to the correct extraction path.


5. Extraction & Conversion: Based on the file type, a specialized extractFromFile n8n node processes the content. For PDFs, the data is extracted and then mapped using the Map PDF to Text n8n node to standardize the output format.


6. Synchronization: Finally, the extracted text hits the InfraNodus Save to Graph n8n node (an HTTP Request). This node sends the content, along with the original filename as a category tag, to the InfraNodus API, updating the knowledge graph instantly. The loop then continues for the next file item.

To deploy this expert n8n workflow, follow these steps:

1. Import the n8n Templates: Copy the provided JSON and import it directly into your n8n instance via the 'New' menu -> 'Import Workflow from JSON'.


2. Google Drive Setup: Configure the New File Created in the Google Folder? n8n trigger. You must create or select a Google Drive credential and specify the exact folder ID you wish to watch.


3. InfraNodus API Key: Set up the credentials for the InfraNodus Save to Graph n8n node. This requires an HTTP Bearer Auth credential containing your InfraNodus API Key.


4. Optional: ConvertAPI: If you choose to use the disabled but recommended ConvertAPI n8n node for higher-quality PDF conversion, you will need to set up a separate API key for that service.


5. Activation: Once credentials are set for all required n8n nodes, save and activate the n8n workflow.

This n8n workflow uses several critical nodes to achieve file synchronization and text extraction:

New File Created in the Google Folder? (Google Drive Trigger): The initiating n8n trigger. Monitors a specific folder ID (e.g., 1NFekB1H3ADF8C5o4eNl893d6INbfRA) for file creation events.
Loop Over Items (Split In Batches): Ensures sequential processing of multiple files found by the n8n trigger.
Retrieve File (Google Drive n8n node): Downloads the binary data of the file using the dynamic fileId provided by the preceding nodes (={{ $json.id }}).
Switch (Core Logic n8n node): Routes the execution path based on the file's mimeType. It supports application/pdf, text/plain, text/markdown, and others, demonstrating powerful flow control within n8n templates.
Extract from PDF / Extract from Text File (extractFromFile n8n node): Dedicated n8n nodes used for converting binary file contents into readable text data.
Map PDF to Text (Set n8n node): Standardizes the output schema for PDF files (={{ $json.text }} is mapped to data), ensuring consistency before the final API call.

• InfraNodus Save to Graph (HTTP Request n8n node): The final action. Sends a POST request to the InfraNodus API. Key configurations include setting the graph name, the text content (={{ $json.data }}), and setting categories using the filename, making this a highly customized n8n solution.