Extract text from PDF and image using Vertex AI (Gemini) into CSV
Configured with Chain LLM, Convert To File, Extract From File, Google Drive, and additional nodes. Review the connections and setup before adapting this template.
Node categories in this workflow
- AI & models
- Trigger
- Routing
- Files / media
- Transform
- Web / API
Icons describe general node roles, inferred from node types. Inspect the parameters for the configured action.
Drag to pan; use + and − to zoom. Reconstructed from the exported node positions; nothing runs here. Dashed lines represent non-main connections. Full node names and notes appear below.
How it works
The exported workflow contains the following configured nodes. Their connections are shown above; inspect the JSON for the complete logic, expressions, and external actions.
| Node | Category | Type | Operation |
|---|---|---|---|
| Google Gemini Chat Model | AI & models | LM Chat Google Gemini | See node parameters |
| Get PDF or Images | Trigger | Google Drive Trigger | See node parameters |
| Route based on PDF or Image | Routing | Switch | See node parameters |
| Download PDF | Files / media | Google Drive | download |
| Download Image | Files / media | Google Drive | download |
| Extract data from PDF | Transform | Extract From File | |
| Send data to A.I. | Web / API | HTTP Request | POST |
| Convert to CSV | Transform | Convert To File | See node parameters |
| Upload to Google Drive | Files / media | Google Drive | See node parameters |
| Convert to CSV2 | Transform | Convert To File | See node parameters |
| Upload to Google Drive1 | Files / media | Google Drive | See node parameters |
| Vertex A.I. extract text | AI & models | Chain LLM | See node parameters |
Setup
- Download the JSON and import it into an isolated n8n instance. Leave the workflow inactive.
- Connect your own credentials through n8n’s credential store. Replace
REPLACE_WITH_*values with your resource identifiers. - Inspect API destinations, Code nodes, database queries, file paths, and outbound actions.
- Run with synthetic data and harmless destinations. Enable triggers only after checking the actual outputs.
Requirements
An n8n instance with the listed node types and compatible versions. Service-connected workflows may require accounts, credentials, or paid APIs.
Credential types declared in the source
googleApigooglePalmApihttpHeaderAuth
Workflow notes
How to extract PDF and image text into CSV using n8n (without manual data entry)
How to extract PDF and image text into CSV using n8n (without manual data entry)
This workflow will extract text data from PDF and images, then store it as CSV.
Get PDF or image
Get PDF or image
You need to create a new folder inside Google Drive for uploading your PDF and images.
Once you create a folder, you need to add your Google cloud user by going to Share -> Add user. The user email should be like: user@example.com
Send to Openrouter
Send to Openrouter
You need to set up an Openrouter account to use this. It sends the data to openrouter to extract text.
Use Header Auth. Name is "Authorization" and value is "Bearer {API token}".
Vertex AI for image recogniztion
Vertex AI for image recogniztion
We send the photo to Vertex AI to extract text. You'll need to activate Vertex AI and add the correct rights to your Google cloud credentials.
- Enable Vertex API
- Add vertex to user account
Extract text from PDF and image using Vertex AI (Gemini) into CSV
Extract text from PDF and image using Vertex AI (Gemini) into CSV
Purpose and structure
This folder contains the Extract text from PDF and image using Vertex AI (Gemini) into CSV workflow. Its executable nodes use chainLlm, convertToFile, extractFromFile, googleDrive, googleDriveTrigger, httpRequest, lmChatGoogleGemini, switch. The table and connection map below are derived from the JSON, not an inferred guarantee of behavior.
Setup
Import inactive. Configure your own credentials and replace REPLACE_WITH_* values. Review external destinations and Code nodes before running.
Entry points
Get PDF or Images
Verification
Sanitized source candidate; not runtime-tested. This overview is generated from node metadata. Read the folder README for the connection map, credential types, and license.
Attribution
https://github.com/Zie619/n8n-workflows/blob/94007c1445d9258a7da116646b79473e7c7c3282/workflows/Extractfromfile/1444_Extractfromfile_Converttofile_Automation_Webhook.json MIT; preserve source notices.