AI Workflows
Artificial Intelligence tools and workflows
Automate Content Idea Generation and Storage with Google Gemini and Sheets
This n8n workflow automates the creation of content ideas using Google Gemini and stores them in Google Sheets. It expands each idea into detailed content, streamlining the content creation process.
n8n$9.99Automate AI News Scraping to Markdown and Google Drive
This n8n workflow automates the collection of AI news from multiple RSS feeds, scrapes the full content, and saves it as Markdown files in Google Drive. Ideal for content curation, blog research, and news archiving.
n8n$9.99Comprehensive LLM Usage Tracker & Cost Monitor with Node-Level Analytics
# LLM Cost Monitor & Usage Tracker for n8n ## What This Workflow Does This workflow provides comprehensive monitoring and cost tracking for all LLM/AI agent usage across your n8n workflows. It extracts detailed token usage data from any workflow execution and calculates precise costs based on current model pricing. ### The Problem It Solves When running LLM nodes in n8n workflows, the token usage and intermediate data are not directly accessible within the same workflow. This monitoring workflow bridges that gap by: - Retrieving execution data using the execution ID - Extracting all LLM usage from any nested structure - Calculating costs with customizable pricing - Providing detailed analytics per node and model - **WARNING**: It works after the full execution of the workflow (i.e., you can't get this data before completion of all tasks in the workflow) ## ℹ️ Setup Instructions ### Prerequisites 1. **Experience Required**: Basic familiarity with n8n LLM nodes and AI agents 2. **Agent Configuration**: In your monitored workflows, go to agent settings and enable **Return Intermediate Steps** 3. For getting execution data, you need to set up the n8n API in your instance (also available on the free version) ### Installation Steps 1. Import this monitoring workflow into your n8n instance 2. Go to Settings >> select n8n API from the left bar >> define an API. Now you can add this as the credential for your Get an Execution node 3. Configure your model name mappings in the **Standardize Names** node 4. Update model pricing in the **Model Prices** node (prices per 1M tokens) 5. To monitor a workflow: - Add an **Execute Workflow** node at the end of your target workflow - Select this monitoring workflow - **Important**: Turn OFF Wait For Sub-Workflow Completion - Pass the execution ID as input ## ✒️ Customization ### When You See Errors If the workflow enters the error path, it means an undefined model was detected. Simply: 1. Add the model name to the **standardize_names_dict** 2. Add its pricing to the **model_price_dict** 3. Re-run the workflow ### Configurable Elements - **Model Name Mapping**: Standardize different model name variations (e.g., gpt-4-0613 → gpt-4) - **Pricing Dictionary**: Set costs per million tokens for input/output - **Extraction Depth**: Captures tokens from any nesting level automatically ## 📊 Output Data ### Per LLM Call - **Cost Breakdown**: Prompt, completion, and total costs in USD - **Token Metrics**: Prompt tokens, completion tokens, total tokens - **Performance**: Execution time, start time, finish reason - **Content Preview**: First 100 chars of input/output for debugging - **Model Parameters**: Temperature, max tokens, timeout, retry count - **Execution Context**: Workflow name, node name, execution status - **Flow Tracking**: Previous nodes chain ### Summary Statistics - Total executions and costs - Breakdown by model type - Breakdown by node - Average cost per call - Total execution time ## 🔑 Key Benefits - **No External Dependencies**: Everything runs within n8n - **Universal Compatibility**: Works with any workflow structure - **Automatic Detection**: Finds LLM usage regardless of nesting - **Real-time Monitoring**: Track costs as workflows execute - **Debugging Support**: Preview actual prompts and responses - **Scalable**: Handles multiple models and complex workflows ## ✨ Example Use Cases - **Cost Optimization**: Identify expensive nodes and optimize prompts - **Usage Analytics**: Track token consumption across teams/projects - **Budget Monitoring**: Set alerts based on cost thresholds - **Performance Analysis**: Find slow-running LLM calls - **Debugging**: Review actual inputs/outputs without logs - **Compliance**: Audit AI usage across your organization ## 🚀 Quick Start 1. Import workflow 2. Update model prices (if needed) 3. Add monitoring to any workflow with the Execute Workflow node 4. View detailed cost breakdowns instantly --- *Note: Prices are configured per million tokens. Default includes GPT-4, GPT-3.5, Claude, and other popular models. Add custom models as needed.*
n8n$14.99Automate Video Creation Using Text Descriptions with Wan 2.2 T2V Fast and Replicate
This workflow automates video generation using the Wan 2.2 T2V Fast AI model via the Replicate API, streamlining the process of creating videos from text descriptions within n8n.
n8n$9.99Automate YouTube Video Analysis with Google Gemini AI for Summaries and Transcripts
This workflow automates the extraction of summaries, transcripts, and metadata from YouTube videos using Google Gemini AI, saving time and ensuring accuracy for content creators and marketers.
n8n$19.99AI Voice Chat Using Webhook, Memory Manager, OpenAI, Google Gemini & ElevenLabs
## Who is this for? This workflow is designed for businesses or developers looking to integrate voice-based chat applications with dynamic responses and conversational memory. ## What problem does this solve? It automates AI-powered voice conversations, maintaining context between sessions and converting speech-to-text and text-to-speech. ## What this workflow does: The workflow receives audio input, transcribes it using OpenAI, and processes the conversation using Google Gemini Chat Model (you can use the OpenAI Chat Model). Responses are converted back to speech using ElevenLabs. ## Prerequisites: You'll need API keys for: * OpenAI (you can obtain it from the OpenAI website) * ElevenLabs (you can obtain it from their website) * Google Gemini (You can obtain it from `Google AI Studio`) ## Setup: * Configure your API keys * Ensure that the value `(voice_message)` in the `Path` parameter in the Webhook node is used as the name of the parameter that will contain the voice message you are sending via the HTTP Post request.
n8n$9.99Automate Trello Board Summarization with OpenAI GPT-5-Nano
This workflow retrieves data from a Trello board, including lists and cards, and uses OpenAI's GPT-5-Nano to generate a concise summary of the board's contents.
n8n$9.99Write a WordPress Post with AI (Starting from a Few Keywords)
This n8n workflow template allows you to write WordPress posts by just providing a few keywords. It uses AI technology to write the text and to create the post's featured image. The text includes an introduction, chapters, and conclusions. Each chapter is written independently and this allows you to create also very long articles. The workflow uses technologies provided by Open AI: Chat GPT for the text and Dall-E for the image. I suggest reviewing the created posts before publishing them on your WordPress website. The article generation might take some minutes as each chapter is created independently. ### Features - **Easy to use:** Easy web interface to start the generation of the WordPress post - **AI-powered:** Text and image generation is done by artificial intelligence - **Long-text ready:** Possibility to create very long articles - **Configurable:** Possibility to provide as many keywords as you want, to choose the number of chapters and the length of the article - **Plugs into your WordPress:** Easily integrates with your WordPress website - **Tweak it as you want:** Fine-tune the Open AI prompts and the workflow as you want ### Workflow Steps - **User form:** An n8n form is used to trigger the post creation - **Settings:** This node is used to set your WordPress URL (which is used later in the workflow) - **Article structure:** First AI action that writes the introduction, the conclusions, and the chapter structure. - **Data check:** Check that the data provided by the AI is valid - **Chapters split/Chapters text:** Splits the data for each chapter in a separate item and generates each chapter's text with AI - **Content preparation:** Prepares the text for posting, merging the introduction, the chapters, and the conclusions. Adds some basic HTML formatting - **Draft on WordPress:** Creates the draft post on WordPress - **Featured image:** Creates a featured image and adds it to the post on WordPress - **User feedback:** Sends feedback to the user on the n8n form ### Getting Started To deploy and use this template: 1. Import the workflow into your n8n workspace 2. Set your WordPress URL in the `wordpress_url` field in the Settings node. Include the slash (`/`) at the end of the URL 3. Set up your Open AI n8n credentials by following [this guide](https://docs.n8n.io/integrations/builtin/credentials/openai/). The Open AI credentials are used by the Open AI nodes (Create post title and structure, Create chapters text, and Generate featured image) 4. Set up your WordPress n8n credentials by following [this guide](https://docs.n8n.io/integrations/builtin/credentials/wordpress/). The WordPress credentials are used by the WordPress and HTTP Request nodes (Post on WordPress, Upload media, and Set image ID for the post). Pay attention that the Password in the WordPress credentials is not the user's password but the Application Password ### How to use the workflow to create a WordPress post 1. Activate the workflow 2. Open the Form node and copy the Production URL. This is the public URL of the form to AI-write the post 3. Open the URL in a browser and fill in the form 4. Wait a few minutes till you get the feedback in the form that the post was created 5. Go to WordPress and check the newly created draft post. Review and publish your post!
n8n$24.99Automate Restaurant Orders and Menu Management via WhatsApp and AI
Streamline your restaurant's order and menu management by leveraging WhatsApp and AI. This workflow automates customer interactions, order processing, and delivery coordination, enhancing efficiency and customer satisfaction.
n8n$14.99Automate Real-Time Research and Fact-Checking with AI and SerpAPI
Leverage AI and SerpAPI to automate live information gathering, fact-checking, and trend analysis in response to chat messages, providing instant, accurate data.
n8n$9.99Allow Users to Send a Sequence of Messages to an AI Agent in Telegram
### Use Case When creating chatbots that interface through applications such as **Telegram** and **WhatsApp**, users can often send multiple shorter messages in quick succession, in place of a single, longer message. This workflow accounts for this behavior. ### What it Does This workflow allows users to send several messages in quick succession, treating them as one coherent conversation instead of separate messages requiring individual responses. ### How it Works 1. When messages arrive, they are stored in a **Supabase PostgreSQL** table. 2. The system waits briefly to see if additional messages arrive. 3. If no new messages arrive within the waiting period, all queued messages are: - Combined and processed as a single conversation. - Responded to with one unified reply. - Deleted from the queue. ### Setup 1. Create a table in Supabase called **message_queue**. It needs to have the following columns: **user_id** (`uint8`), **message** (`text`), and **message_id** (`uint8`). 2. Add your **Telegram**, **Supabase**, **OpenAI**, and **PostgreSQL** credentials. 3. Activate the workflow and test by sending multiple messages to the Telegram bot in one go. 4. Wait ten seconds after which you will receive a single reply to all of your messages. ### How to Modify it to Your Needs - Change the value of **Wait Amount** in the **Wait 10 Seconds** node in order to modify the buffering window. - Add a **System Message** to the **AI Agent** to tailor it to your specific use case. - Replace the **OpenAI** sub-node to use a different language model.
n8n$14.99Building a RAG Chatbot for Movie Recommendations with Qdrant and OpenAI
Create a recommendation tool without hallucinations based on RAG with the Qdrant Vector database. This example is based on movie recommendations on the IMDB-top1000 dataset. You can provide your wishes and your big nos to the chatbot, for example: A movie about wizards but not Harry Potter, and get top-3 recommendations. ## How it works - [A video with the full design process](https://www.youtube.com/watch?v=O5m8M7rqQQ) - Upload IMDB-1000 dataset to Qdrant Vector Store, embedding movie descriptions with OpenAI; - Set up an AI agent with a chat. This agent will call a workflow tool to get movie recommendations based on a request written in the chat; - Create a workflow which calls [Qdrant's Recommendation API](https://qdrant.tech/articles/new-recommendation-api/) to retrieve top-3 recommendations of movies based on your positive and negative examples. ## Set Up Steps - You'll need to create a free tier [Qdrant Cluster](https://cloud.qdrant.io/) (Qdrant can also be used locally; it's open-sourced) and set up API credentials. - You'll need OpenAI credentials. - You'll need GitHub credentials & to upload the [IMDB Kaggle dataset](https://www.kaggle.com/datasets/omarhanyy/imdb-top-1000) to your GitHub.
n8n$14.99Find Step-by-Step Recipes from API Ninjas Recipe API in an n8n AI Agent
## Who's it for Makers who want a tiny, understandable AI agent that turns chat prompts into real recipe results. Great for demos, tutorials, or as a starting point for tool-using agents. ## How it works / What it does - Listens for chat messages and keeps a short recent-history window. - Uses a simple system hint to prefer the recipe tool for cooking queries. - Calls API Ninjas recipe endpoint and returns ingredients and instructions. - Replies concisely with a title, bullet ingredients, and numbered steps. ## How to set up 1. Add your OpenAI API key to the OpenAI Chat node. 2. Add your API Ninjas key to the HTTP Request node used by the recipe tool. 3. Deploy the chat trigger and send a message like "find me a pasta recipe." ## Requirements - n8n environment - OpenAI API key - API Ninjas API key for the recipe endpoint ## How to customize the workflow - Swap API Ninjas for any GE or POS recipe API without changing the agent pattern. - Save results to a database or Google Sheets for later use. - Add optional fields like servings, time, or nutrition. - Introduce basic guardrails for tone, length, or ingredient safety checks.
n8n$4.99Create a Dynamic Telegram AI Bot with LangChain and DALL-E Integration
Develop a flexible Telegram bot that leverages LangChain nodes and DALL-E for advanced AI interactions and image generation.
n8n$4.99Automate Daily AI News Summaries with GPT-4 and Telegram
This workflow fetches the latest AI news articles every morning, summarizes them using GPT-4, translates them into Traditional Chinese, and delivers the digest to your Telegram account.
n8n$9.99Automate AI Image Generation and Google Drive Upload with DALL·E 2
This workflow automates the creation of multiple AI-generated images using OpenAI's DALL·E 2 and uploads them to a specified Google Drive folder. Ideal for creative projects, it efficiently handles multiple image variations from a single prompt.
n8n$9.99Chat with a Database Using AI
This workflow allows you to ask questions about data stored in a database using AI. To use it, you'll need an OpenAI API key (although you could also swap in a model from another service). Supported databases: - Postgres - MySQL - SQLite The workflow uses n8n's embedded chat, but you could also modify it to work with a chat service such as Slack, MS Teams, or WhatsApp. Note that to use this template, you need to be on n8n version 1.19.4 or later.
n8n$4.99Automate Pizza Ordering with GPT-3.5 Chatbot in n8n
Streamline your pizza store's order processing with an AI-powered chatbot that handles menu inquiries, order placements, and status tracking using OpenAI and n8n.
n8n$4.99Transform RSS Feed Articles into Social Media Content
Automatically convert articles from an RSS feed into engaging social media content. This workflow enriches articles with research and expert insights, then formats them for platforms like LinkedIn, Instagram, and Twitter.
Activepieces$2.99Generate and Store AI Images with Sora GPT, Google Drive, and Sheets
# **Automation Flow: Image to Image Using GP Sora** This flow automates the process of generating images using a provided prompt and reference image via the **Sora GP Image API** from [RapidAPI](https://rapidapi.com/skdeveloper/api/sora-gpt-image). The generated images are stored in **Google Drive**, and details are logged in **Google Sheets**. ## **Nodes Overview** ### 1. **On Form Submission** - **Type**: `n8n-nodes-base.formTrigger` - **Description**: This node triggers when a user submits the form containing the prompt and image URL. It ensures the form fields are filled in and ready for processing. - **Form Fields**: - **Prompt**: A text description of the desired image. - **Image URL**: The URL of the reference image to be used. - **Webhook ID**: Unique identifier for form submission. --- ### 2. **HTTP Request to Sora GP Image API** - **Type**: `n8n-nodes-base.httpRequest` - **Description**: Sends the prompt and image URL to the **Sora GP Image API** to generate a new image based on the provided inputs. - **API Endpoint**: [Sora GP Image API](https://sora-gpt-image.p.rapidapi.com/ai-img/img-to-img.php) (via **RapidAPI**) - **Method**: `POST` - **Body Parameters**: - **Prompt**: User-provided text. - **Image URL**: The reference image URL. - **Width & Height**: Image size is set to `1024x1024`. --- ### 3. **Code (Base64 Conversion)** - **Type**: `n8n-nodes-base.code` - **Description**: This node processes the base64-encoded image data returned from the API. It decodes and formats the image to be uploaded to Google Drive. - **Output**: Converts the base64 string into a binary JPEG file. --- ### 4. **Upload Image to Google Drive** - **Type**: `n8n-nodes-base.googleDrive` - **Description**: Uploads the generated image to **Google Drive**, storing it in a designated folder. - **Authentication**: Google Service Account. - **File Name**: The image file name is dynamically set from the previous node. --- ### 5. **Log Details to Google Sheets** - **Type**: `n8n-nodes-base.googleSheets` - **Description**: This node logs the **Prompt**, **Generated Image**, and **Generation Date** into a **Google Sheets** document for tracking and auditing purposes. - **Columns Mapped**: - **Prompt**: The user's input text. - **Image**: The name of the generated image file. - **Generated Date**: Date and time of image generation. --- ## **Flow Summary** 1. **User Submits Form**: Triggered when the form with the prompt and image URL is submitted. 2. **Image Generation**: The data is sent to the **Sora GP Image API** from [RapidAPI](https://rapidapi.com/skdeveloper/api/sora-gpt-image) to generate the image. 3. **Image Processing**: The generated image (base64 format) is decoded and saved as a file. 4. **Google Drive Upload**: The image is uploaded to **Google Drive** for storage. 5. **Google Sheets Logging**: All relevant details (Prompt, Image, Date) are saved in **Google Sheets**. --- ## **Benefits** - **Automated Image Creation**: Quickly generate images using AI based on a simple prompt and reference image via **RapidAPI**. - **Efficient Workflow**: The entire process from form submission to image generation and storage is automated, saving time and reducing manual work. - **Centralized Storage**: Generated images are stored in **Google Drive**, ensuring easy access and organization. - **Audit Trail**: The details of each generated image are logged in **Google Sheets**, making it easy to track, review, and manage past creations. - **Scalable and Reusable**: Can be adapted to multiple use cases, such as creative design, marketing materials, or social media content generation. --- ## **Problems Solved** - **Manual Image Editing**: Eliminates the need for manual image manipulation and creation, allowing for automatic generation based on user inputs. - **Disorganized File Storage**: With automatic uploads to **Google Drive**, the images are stored in a centralized and organized manner. - **Lack of Record-Keeping**: By logging image generation details in **Google Sheets**, there's always a record of past creations, improving tracking and management. - **Time-Consuming Processes**: The automation drastically reduces the time spent on manual tasks, allowing users to focus on other aspects of their work or creative processes. --- This flow simplifies the process of creating AI-generated images based on user inputs, leveraging the power of the **Sora GP Image API** via [RapidAPI](https://rapidapi.com/skdeveloper/api/sora-gpt-image), making it a powerful tool for creative, design, and marketing purposes.
n8n$9.99Extract Invoice Data from PDFs with AI - Google Sheets Email Alerts
Built by Setidure Technologies This smart n8n automation extracts invoice details from PDF files uploaded to Google Drive using AI, logs them to a Google Sheet, and notifies the billing team via email - all without manual intervention. Note: This workflow requires a self-hosted n8n instance with LangChain, LLM, and Google integrations configured. **What This Workflow Does** - Monitors a Google Drive folder for new invoice uploads - Extracts text and parses key invoice details using LLM via LangChain - Logs extracted data into a Google Sheet (Invoice Database) - Generates a summary email using GPT-4O-MINI (Greenie) - Sends the email to the billing team via Gmail **Prerequisites** - A Google Drive folder to monitor for PDF uploads - A Google Sheet named Invoice Database with the following columns: - Invoice Number, Client Name, Client Email, Client Address, Client Phone, Invoice Date, Due Date, Total Amount - Service account or OAuth credentials for: - Google Drive - Google Sheets - Gmail - LangChain + Ollama integration for LLM responses **Step-by-Step Setup Instructions** 1. Clone this workflow into your self-hosted n8n instance 2. Set up credentials: - Google Drive (for folder trigger) - Google Sheets (for data logging) - Gmail (for sending email) - Ollama (local LLM) or any connected LangChain provider 3. Configure the trigger node to watch your specific Invoice Uploads folder 4. Update the Google Sheet node with your Invoice Database sheet URL and column mapping 5. Test with a sample invoice to validate the AI extraction and email generation **Workflow Steps** ## Step 1: Trigger on New File in Google Drive Node Name: Watch for New Invoices Type: Google Drive Trigger Event: fileCreated Triggers when a new PDF file is uploaded to a designated folder ## Step 2: Download the Uploaded File Node Name: Download Invoice PDF Type: Download Binary Downloads the invoice file from Google Drive ## Step 3: Extract Raw Text from PDF Node Name: Extract PDF Text Type: Extract from File Extracts unstructured text content from the downloaded PDF ## Step 4: Parse Invoice Fields Using AI Node Name: Parse Invoice Data with LLM Type: LangChain Agent LLM is prompted to extract: - Invoice Number - Client Name, Email, Address, Phone - Invoice Date, Due Date, Total Amount Fields not found are skipped ## Step 5: Log Extracted Data to Google Sheet Node Name: Log to Invoice Database Type: Google Sheets Appends a new row with the extracted fields to the Invoice Database spreadsheet ## Step 6: Create Email Notification via LLM Node Name: Generate Billing Email Summary Type: LangChain Agent (GPT-4O-MINI) Prompt instructs AI to: - Act as "Greenie" from Green Grass Corp - Inform billing that a new invoice was processed - Confirm logging into the Invoice Database ## Step 7: Send the Email to Billing Team Node Name: Email Billing Team Type: Gmail Send To: billing@example.com Subject and body injected from LLM output ## Step 8: End Workflow Gracefully Node Name: End Type: No Operation Used to cleanly terminate the flow ## Example Output (Email) Subject: New Invoice Logged - Client: ABC Corp Hi Billing Team, A new invoice has been received and processed automatically. The following details have been extracted and logged into the Invoice Database: - Invoice Number: INV-1024 - Client: ABC Corp - Amount: $1,450 - Due Date: July 15, 2025 Please review the [Invoice Database](https://docs.google.com/spreadsheets/d/14FtgVUjy0tw4EQOB28wuCYOe6CELtt3Ujn-GsuDWY/edit?gid=0#gid=0) for full details. Regards, Greenie Green Grass Corp
n8n$9.99AI Agent Web Search Using SearchAPI & LLM
## AI Agent Web Search using SearchApi & LLM ### Who is this for? This workflow is ideal for anyone conducting **online research**, including **students**, **researchers**, **content creators**, and professionals looking for accurate, up-to-date, and verifiable information. It also serves as an excellent foundation for building more sophisticated AI-driven applications. ### What problem does this workflow solve? / Use case This workflow automates web searches by enabling an AI agent to efficiently retrieve and summarize external, verifiable information, ensuring accuracy through source citations. ### What this workflow does - Connects an AI agent node to [SearchApi.io](https://www.searchapi.io/) as an integrated search tool. - Empowers the AI agent to perform real-time web searches using various SearchApi engines (e.g., Google, Bing). - Allows the AI agent to dynamically determine search parameters based on user interaction, delivering contextually relevant results. - Ensures responses include clearly cited sources for validation and further exploration. ### Setup 1. **Install the [SearchApi community node](https://www.npmjs.com/package/@searchapi/n8n-nodes-searchapi)**: - Open **Settings > Community Nodes** inside your self-hosted n8n instance. - Fill **npm Package Name** with `@searchapi/n8n-nodes-searchapi`. - Accept the risk prompt, and hit **Install**. - It should now appear as a node when you search for it. 2. **API Configuration**: - Set up your [SearchApi.io](https://www.searchapi.io/) credentials in n8n. - Add your preferred LLM provider credentials (e.g., OpenRouter API). 3. **Input Requirements**: - Provide the YouTube video ID (e.g., `wBuULAoJxok`). 4. **Connect LLM Integration**: - Configure the summarization chain with your chosen model and parameters for text splitting. ### How to customize this workflow to your needs - Integrate additional nodes to structure or store search results (e.g., saving to databases, Notion, Google Sheets). - Extend chatbot capabilities to integrate with messaging platforms (Slack, Discord) or email notifications. - Adjust search parameters and filters within the AI agent node to tailor information retrieval. ### Example Usage - **Input**: User asks, "What are the latest developments in AI regulation?" - **Output**: AI retrieves, summarizes, and cites recent, authoritative articles and news sources from the web.
n8n$4.99Automate PDF Image Extraction & Analysis with GPT-4o and Google Drive
**Use Case** Manually extracting images from PDF files for analysis is often slow and inefficient. Many users resort to taking screenshots of each page, uploading them to an AI tool like OpenAI for image analysis, and then manually copying the insights into a document. This manual process is time-consuming and prone to errors. This workflow streamlines the entire process by automatically extracting images from a PDF, analyzing them using the GPT-4o model, and saving the results in seconds—eliminating the need for manual effort. **What This Workflow Does** - Extracts all images from the uploaded PDF file automatically. The workflow scans each page of the PDF and identifies embedded images without manual intervention. - Uses the GPT-4o model to analyze each extracted image. Each image is processed through GPT-4o to generate descriptive insights, summaries, or context-specific analysis depending on the use case. - Saves the analysis results to a .txt file, including image URLs. The final output is a plain text file containing both the image URLs (e.g., hosted on cloud storage) and the corresponding GPT-4o analysis, ready for further use or sharing. **Setup** 1. Set up your credentials when you first open the workflow. You'll need accounts for OpenAI, Convert API, and Google Drive. 2. Convert API does not rate-limit your API; sometimes, you may receive a 503 service unavailable error. Nevertheless, it doesn't mean that you cannot convert your file. It simply means that you should retry the conversion in a few seconds. 3. Upload a PDF with images to Google Drive. 4. Remove unnecessary parts and retrieve image-related information. 5. Integrate image and image analysis information together. 6. Analyze each image using the OPENAI GPT-4o model. 7. Retrieve all image analysis content and image URL. 8. Integrate multiple image URLs and analysis content. 9. Output content to a .txt file. The template was created in n8n v1.83.2. **How to Customize** - Replace the manual trigger with a Google Drive trigger or other automation triggers. - Change the image analysis model (e.g., switch or fine-tune GPT-4o). - Send the results to other platforms (e.g., Slack, Telegram, LINE, etc.) instead of saving to a .txt file.
n8n$9.99Automate AI-Driven Research with Jina AI Deep Search
Streamline your research process with Jina AI's Deep Search, automating the querying, analysis, and formatting of research reports without the need for API keys.
n8n$4.99
Related categories
Custom AI Systems & Services
Our team of experienced AI builders will help build custom AI systems, workflows, and solutions.
Request Custom Work