Extract text from PDF and image using Vertex AI (Gemini) into CSV
Workflow JSON
{"id": "sUIPemKdKqmUQFt6", "meta": {"instanceId": "558d88703fb65b2d0e44613bc35916258b0f0bf983c5d4730c00c424b77ca36a", "templateCredsSetupCompleted": true}, "name": "Extract text from PDF and image using Vertex AI (Gemini) into CSV", "tags": [], "nodes": [{"id": "f60ef5f9-bc08-4cc9-804e-697ae6f88b9b", "name": "Google Gemini Chat Model", "type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini", "position": [980, 920], "parameters": {"options": {}, "modelName": "models/gemini-1.5-pro-latest"}, "credentials": {"googlePalmApi": {"id": "", "name": "[Your googlePalmApi]"}}, "typeVersion": 1}, {"id": "81d3f7b8-20cb-4aac-82a9-d4e8e6581105", "name": "Get PDF or Images", "type": "n8n-nodes-base.googleDriveTrigger", "position": [220, 420], "parameters": {"event": "fileCreated", "options": {}, "pollTimes": {"item": [{"mode": "everyMinute"}]}, "triggerOn": "specificFolder", "folderToWatch": {"__rl": true, "mode": "list", "value": "1HOeRP5iwccg93UPUYmWYD7DyDmRREkhj", "cachedResultUrl": "https://drive.google.com/drive/folders/1HOeRP5iwccg93UPUYmWYD7DyDmRREkhj", "cachedResultName": "Actual Budget"}, "authentication": "serviceAccount"}, "credentials": {"googleApi": {"id": "", "name": "[Your googleApi]"}}, "typeVersion": 1}, {"id": "fe9a8228-7950-4e2c-8982-328e03725782", "name": "Route based on PDF or Image", "type": "n8n-nodes-base.switch", "position": [480, 420], "parameters": {"rules": {"rules": [{"value2": "application/pdf", "outputKey": "pdf"}, {"value2": "image/", "operation": "contains", "outputKey": "image"}]}, "value1": "={{$json.mimeType}}", "dataType": "string"}, "typeVersion": 2}, {"id": "f62b71e5-af17-4f85-abff-7cee5100affc", "name": "Download PDF", "type": "n8n-nodes-base.googleDrive", "position": [740, 320], "parameters": {"fileId": {"__rl": true, "mode": "id", "value": "={{ $('Get PDF or Images').item.json.id }}"}, "options": {}, "operation": "download", "authentication": "serviceAccount"}, "credentials": {"googleApi": {"id": "", "name": "[Your googleApi]"}}, "executeOnce": true, "typeVersion": 3}, {"id": "fa99fbcf-1353-410d-a0db-48cea1178a76", "name": "Download Image", "type": "n8n-nodes-base.googleDrive", "position": [740, 740], "parameters": {"fileId": {"__rl": true, "mode": "id", "value": "={{ $('Get PDF or Images').item.json.id }}"}, "options": {}, "operation": "download", "authentication": "serviceAccount"}, "credentials": {"googleApi": {"id": "", "name": "[Your googleApi]"}}, "executeOnce": true, "retryOnFail": false, "typeVersion": 3, "alwaysOutputData": true}, {"id": "e4979746-44bb-493e-b5eb-f9646b510888", "name": "Extract data from PDF", "type": "n8n-nodes-base.extractFromFile", "position": [980, 320], "parameters": {"options": {}, "operation": "pdf"}, "typeVersion": 1}, {"id": "6549c335-e749-4b95-b77d-096a5e77af5e", "name": "Send data to A.I.", "type": "n8n-nodes-base.httpRequest", "position": [1180, 320], "parameters": {"url": "https://openrouter.ai/api/v1/chat/completions", "method": "POST", "options": {}, "jsonBody": "={\n \"model\": \"meta-llama/llama-3.1-70b-instruct:free\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"You are given a bank statement.{{encodeURIComponent($json.text)}}. Read the PDF and export all the transactions as CSV. Add a column called category and based on the information assign a category name. Return only the CSV data starting with the header row.\"\n }\n ]\n}", "sendBody": true, "specifyBody": "json", "authentication": "genericCredentialType", "genericAuthType": "httpHeaderAuth"}, "credentials": {"httpHeaderAuth": {"id": "", "name": "[Your httpHeaderAuth]"}}, "typeVersion": 4.2, "alwaysOutputData": false}, {"id": "42341f03-c9fc-4290-963e-1a723202a739", "name": "Convert to CSV", "type": "n8n-nodes-base.convertToFile", "position": [1400, 320], "parameters": {"options": {}}, "typeVersion": 1.1}, {"id": "bb446447-3f46-47e7-96a2-3fc720715828", "name": "Upload to Google Drive", "type": "n8n-nodes-base.googleDrive", "position": [1640, 320], "parameters": {"name": "={{$today}}", "driveId": {"__rl": true, "mode": "list", "value": "My Drive", "cachedResultUrl": "https://drive.google.com/drive/my-drive", "cachedResultName": "My Drive"}, "options": {}, "folderId": {"__rl": true, "mode": "list", "value": "1Zo4OFCv1qWRX1jo0VL_iqUBf4v0fZEXe", "cachedResultUrl": "https://drive.google.com/drive/folders/1Zo4OFCv1qWRX1jo0VL_iqUBf4v0fZEXe", "cachedResultName": "CSV Exports"}, "authentication": "serviceAccount"}, "credentials": {"googleApi": {"id": "", "name": "[Your googleApi]"}}, "typeVersion": 3}, {"id": "843bc9c1-79a6-4f42-b9ee-fbec5f30b18d", "name": "Convert to CSV2", "type": "n8n-nodes-base.convertToFile", "position": [1360, 740], "parameters": {"options": {}}, "typeVersion": 1.1}, {"id": "6404bf65-3a7e-4be9-9b7f-98a23dca2ffd", "name": "Upload to Google Drive1", "type": "n8n-nodes-base.googleDrive", "position": [1640, 740], "parameters": {"name": "={{$today}}", "driveId": {"__rl": true, "mode": "list", "value": "My Drive", "cachedResultUrl": "https://drive.google.com/drive/my-drive", "cachedResultName": "My Drive"}, "options": {}, "folderId": {"__rl": true, "mode": "list", "value": "1Zo4OFCv1qWRX1jo0VL_iqUBf4v0fZEXe", "cachedResultUrl": "https://drive.google.com/drive/folders/1Zo4OFCv1qWRX1jo0VL_iqUBf4v0fZEXe", "cachedResultName": "CSV Exports"}, "authentication": "serviceAccount"}, "credentials": {"googleApi": {"id": "", "name": "[Your googleApi]"}}, "typeVersion": 3}, {"id": "5dd5771f-6ccb-47ab-acbb-d6cbec60d22b", "name": "Sticky Note", "type": "n8n-nodes-base.stickyNote", "position": [220, -40], "parameters": {"width": 589.0376569037658, "height": 163.2468619246862, "content": "## How to extract PDF and image text into CSV using n8n (without manual data entry)\n\nThis workflow will extract text data from PDF and images, then store it as CSV.\n\n[\ud83d\udca1 You can read more about this workflow here](https://rumjahn.com/how-to-create-an-a-i-agent-to-analyze-matomo-analytics-using-n8n-for-free/)"}, "typeVersion": 1}, {"id": "37416630-9b52-4ce6-98d0-1bdd39ff0d6b", "name": "Sticky Note1", "type": "n8n-nodes-base.stickyNote", "position": [160, 160], "parameters": {"color": 4, "width": 248.11715481171547, "height": 432.7364016736402, "content": "## Get PDF or image\nYou need to create a new folder inside Google Drive for uploading your PDF and images.\n\nOnce you create a folder, you need to add your Google cloud user by going to Share -> Add user. The user email should be like: n8n-server@n8n-server-435232.iam.gserviceaccount.com"}, "typeVersion": 1}, {"id": "3ab10f17-de8f-4263-aef8-cc2fb090ffe5", "name": "Sticky Note2", "type": "n8n-nodes-base.stickyNote", "position": [1120, 52.864368048917754], "parameters": {"color": 5, "height": 446.3929762816575, "content": "## Send to Openrouter\nYou need to set up an Openrouter account to use this. It sends the data to openrouter to extract text.\n\nUse Header Auth. Name is \"Authorization\" and value is \"Bearer {API token}\"."}, "typeVersion": 1}, {"id": "e966f95c-c54e-4d11-895d-d5f75c53aca5", "name": "Sticky Note3", "type": "n8n-nodes-base.stickyNote", "position": [920, 540], "parameters": {"color": 6, "width": 399.0962343096232, "height": 517.154811715481, "content": "## Vertex AI for image recogniztion\nWe 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. \n- Enable Vertex API\n- Add vertex to user account"}, "typeVersion": 1}, {"id": "daa3ab66-fa14-4792-96d0-3bcbeffd5d60", "name": "Vertex A.I. extract text", "type": "@n8n/n8n-nodes-langchain.chainLlm", "position": [980, 740], "parameters": {"text": "=Extract the transactions from the image", "messages": {"messageValues": [{"message": "=You are given a screenshot of payment transactions. Read the image and export all the transactions as CSV. Add a column called category and based on the information assign a category name. Return only the CSV data starting with the header row."}, {"type": "HumanMessagePromptTemplate", "messageType": "imageBinary"}]}, "promptType": "define", "hasOutputParser": true}, "typeVersion": 1.4}], "active": false, "pinData": {}, "settings": {"executionOrder": "v1"}, "versionId": "80635382-3d1c-4e46-a753-84b033cfc3a7", "connections": {"Download PDF": {"main": [[{"node": "Extract data from PDF", "type": "main", "index": 0}]]}, "Convert to CSV": {"main": [[{"node": "Upload to Google Drive", "type": "main", "index": 0}]]}, "Download Image": {"main": [[{"node": "Vertex A.I. extract text", "type": "main", "index": 0}]]}, "Convert to CSV2": {"main": [[{"node": "Upload to Google Drive1", "type": "main", "index": 0}]]}, "Get PDF or Images": {"main": [[{"node": "Route based on PDF or Image", "type": "main", "index": 0}]]}, "Send data to A.I.": {"main": [[{"node": "Convert to CSV", "type": "main", "index": 0}]]}, "Extract data from PDF": {"main": [[{"node": "Send data to A.I.", "type": "main", "index": 0}]]}, "Google Gemini Chat Model": {"ai_languageModel": [[{"node": "Vertex A.I. extract text", "type": "ai_languageModel", "index": 0}]]}, "Vertex A.I. extract text": {"main": [[{"node": "Convert to CSV2", "type": "main", "index": 0}]]}, "Route based on PDF or Image": {"main": [[{"node": "Download PDF", "type": "main", "index": 0}], [{"node": "Download Image", "type": "main", "index": 0}]]}}}How to Import This Workflow
- 1Copy the workflow JSON above using the Copy Workflow JSON button.
- 2Open your n8n instance and go to Workflows.
- 3Click Import from JSON and paste the copied workflow.
Don't have an n8n instance? Start your free trial at n8nautomation.cloud
Related Templates
ETL pipeline
Automate your data extraction, transformation, and loading with this robust ETL pipeline, designed to efficiently process and analyze information from various sources. This workflow begins on a schedule, fetching tweets from Twitter/X, then storing them in MongoDB for initial processing. The MongoDB data is then sent to Google Cloud Natural Language for sentiment analysis or entity extraction, with the results subsequently prepared and stored in PostgreSQL. A conditional check on the PostgreSQL data determines whether to send an alert to Slack, ensuring timely notifications for critical insights or anomalies. This powerful automation is ideal for marketing teams monitoring brand sentiment, researchers analyzing public opinion, or businesses tracking competitor activity, providing actionable intelligence without manual data handling. By automating data ingestion, enrichment, and storage, this workflow significantly reduces the time and effort spent on data preparation, allowing teams to focus on analysis and strategic decision-making while ensuring data consistency and accessibility.
SQL agent with memory
Empower your data analysis with the SQL agent with memory workflow, automating the process of querying databases using natural language. This powerful workflow connects OpenAI's advanced language models with your local SQL databases, allowing you to interact with your data through a conversational interface. Initially, the workflow downloads a chinook.zip example database, extracts it, and saves the chinook.db file locally, making it immediately available for querying. The AI Agent, powered by OpenAI Chat Model and supported by a Window Buffer Memory, interprets your natural language questions, translates them into SQL queries, executes them against your local chinook.db, and provides the results back to you. This is incredibly useful for data analysts, business intelligence professionals, or anyone needing quick insights from their databases without writing complex SQL queries, significantly reducing the time and specialized knowledge required for data exploration. By leveraging the Chat Trigger, users can easily initiate conversations and receive immediate, intelligent responses, streamlining data access and accelerating decision-making.
Prepare CSV files with GPT-4
Transform raw, unstructured text into perfectly formatted CSV files using the power of GPT-4 with this n8n workflow. This automation connects OpenAI's advanced language model to process your input, then meticulously structures the output into a usable CSV format. Ideal for data analysts, marketers, or researchers, this workflow helps you extract specific information from large text datasets, such as customer reviews, survey responses, or article summaries, and prepare it for analysis in spreadsheets or databases. By automating the extraction and formatting of data, you significantly reduce manual data entry errors and save countless hours of tedious work, allowing you to focus on insights rather than data preparation. The workflow manually triggers, sending your text to OpenAI, then splits the responses into manageable batches, parses the JSON output, converts it into a structured table, and finally saves a clean, UTF-8 encoded CSV file to disk, ensuring compatibility across various systems.