AI Workflows
Artificial Intelligence tools and workflows
Automate Brand Mention Tracking and Sentiment Analysis with Bright Data and OpenAI
This workflow automates the tracking of brand mentions across online platforms by scraping blog posts and articles. It uses Bright Data for content access and OpenAI for sentiment analysis, saving time and providing insights into brand perception.
n8n$9.99Auto-translate Blog Articles with Google Translate and Airtable Storage
## How it works - Fetches a blog post HTML from your blog URL using an HTTP request node - Extracts readable content using Cheerio (code node) - Saves the raw blog text to Airtable - Translates the content to a language of your choice using Google Translate - Updates the same Airtable record with the translated version in a different column ## Set up steps - **Estimated setup time:** 15-20 minutes (includes connecting Airtable and Google Translate credentials) - You'll need an Airtable base with `HTML` and `TRANSLATED` fields - Or use this pre-made base: [Airtable Template](https://airtable.com/appP62U5MtSww1eeP/shrXwvYdN7EXPvsp) - Simply add your blog post URL inside the **HTTP Request** node
n8n$9.99Explore Sequential, Agent-Based, and Parallel LLM Processing with Claude 3.7
This workflow showcases three methods for chaining LLM operations using Claude 3.7: sequential, agent-based, and parallel processing. Each method offers unique benefits in terms of implementation, performance, and context management.
n8n$24.99Firecrawl Website Content Extractor
# Firecrawl Website Content Extractor (n8n Workflow) This n8n automation workflow uses **Firecrawl API** to extract structured data (e.g., quotes and authors) from web pages - such as [Quotes to Scrape](https://quotes.toscrape.com/) - and handles retries in case of delayed extraction. --- ## Workflow Overview ### Purpose: - Crawl and extract **structured web data** using Firecrawl - Wait for asynchronous scraping to complete - Retrieve and validate results - Support retries if content is not ready --- ## Step-by-Step Node Breakdown ### 1. **Manual Trigger** - Node: `When clicking test workflow` - Used to **manually test** or execute the workflow during setup or debugging. --- ### 2. **Firecrawl Extract API Request** - Node: `Extract` - Sends a `POST` request to `https://api.firecrawl.dev/v1/extract` - Payload includes: - `urls`: List of pages to crawl (`https://quotes.toscrape.com/`) - `prompt`: Extract all quotes and their corresponding authors from the website. - `schema`: JSON schema defining expected structure (`quotes[]`, each with `text` and `author`) > Uses an **HTTP Header Auth** credential for Firecrawl API --- ### 3. **Wait for 30 Seconds** - Node: `30 Secs` - Gives Firecrawl time to finish processing in the background - Prevents hitting the API before results are ready --- ### 4. **Get Results** - Node: `Get Results` - Performs a `GET` request to the status URL using `{{ $(Extract).item.json.id }}` to retrieve extraction results. --- ### 5. **Condition Check** - Node: `If` - Checks if the `data` array is empty (i.e., no results yet) - If **data is empty**: - Waits **10 more seconds** and retries - If **data is available**: - Passes data to the next step (e.g., processing or storage) --- ### 6. **Retry Delay** - Node: `10 Seconds` - Waits briefly before sending another `GET` request to Firecrawl --- ### 7. **Edit Fields (Optional Output Formatting)** - Node: `Edit Fields` - Placeholder to structure or format the extracted results (quotes and authors) --- ## Sticky Note: Firecrawl Setup Guide Included as an embedded reference: - [10% Firecrawl Discount](https://firecrawl.link/nateherk) - Instructions to: - Add Firecrawl API credentials in **n8n** - Use Firecrawl Community Node for **self-hosted** instances - Set up the schema and prompt for targeted data extraction --- ## Key Features - API-based crawling with schema-structured output - Smart waiting + retry mechanism - AI prompt integration for intelligent data parsing - Flexible for different URLs, prompts, and schemas --- ## Sample Output Schema ```json { "quotes": [ { "text": "The world as we have created it is a process of our thinking. It cannot be changed without changing our thinking.", "author": "Albert Einstein" }, { "text": "It is our choices, Harry, that show what we truly are, far more than our abilities.", "author": "J.K. Rowling" } ] } ```
n8n$4.99Automate GDPR-Compliant AI Model Selection with Requesty and Google Sheets
This n8n workflow automates the selection of AI models while ensuring GDPR compliance by leveraging Requesty's European-based AI routing service. It dynamically updates model options in real-time and persists selections in Google Sheets.
n8n$14.99Extract Data from YAPE Receipts via Telegram OCR and Store in Google Sheets
## Detailed Technical Description This **n8n** workflow automates [Yape](https://www.yape.com.pe/) payment receipt processing, integrating [Telegram bot](https://core.telegram.org/bots), AI-powered OCR, and [Google Sheets](https://support.google.com/docs/answer/6000292) automation. By leveraging **[ChatGPT](https://chatgpt.com/)** Vision Computing, it extracts and structures transaction details, eliminating the need for manual entry. Ideal for freelancers, businesses, and finance teams, this workflow ensures error-free, real-time financial tracking. The AI agent powered by **[DeepSeek](https://www.deepseek.com/)** refines and formats the extracted text, storing it in [Google Sheets](https://support.google.com/docs/answer/6000292) for easy accessibility and reporting. Users can track payments, monitor cash flow, and generate financial reports without any manual work. This seamless integration boosts efficiency, reduces errors, and automates financial record-keeping with 100% accuracy. ### Technologies Used: - **n8n** - Workflow orchestrator. - **Telegram** - Handles image reception and notifications. - **Google Drive** - Manages file creation and storage. - **Google Sheets** - Automatically logs extracted data into spreadsheets. ### Artificial Intelligence: - **ChatGPT** Vision Computing - Performs OCR on payment receipts. - **DeepSeek** AI - Organizes and converts extracted data into a structured format. --- ## Pre-conditions: - `A Telegram Bot` - Must be created to receive images. [Setup Guide](https://core.telegram.org/bots/features#creating-a-new-bot) - `Google Sheets API Key` - Required to store extracted data. [Setup Guide](https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-base.googlesheets/) - `ChatGPT API Key` - Used for OCR and AI text extraction. [Get it here](https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key) - `DeepSeek API Key` - Processes extracted text into structured data. [Get it here](https://platform.deepseek.com/api_keys) #### 1. Image Reception & OCR Processing The user attaches a Yape payment receipt image to the Telegram bot conversation.  #### 2. Analyze Image (OCR) A **ChatGPT** Vision Computing model processes the image and extracts all visible text, ensuring high-accuracy OCR for structured data extraction.  #### 3. Analyze and format text Intelligent Data Processing with AI The extracted text is sent to a **DeepSeek-based** AI agent that: - Identifies and structures key transaction details (amount, date, sender, transaction ID, etc.). - Converts the data into a structured JSON format.  #### 4. Data Storage in Google Sheets **Google Drive** integration is established. If the Google Sheets file does not exist, it is automatically created. Extracted data is automatically recorded in the corresponding spreadsheet, enabling effortless tracking and streamlined financial organization.  ## Benefits: - Time-saving - Eliminates manual payment processing. - Error-free data entry - Reduces human mistakes in record-keeping. - 100% automation - No manual intervention required. - Seamless integration - Easily connects with other workflows. **NOTE**: _The extracted transaction data will be stored in a Google Sheets file with the following columns:_ | Column Name | Description | |:---------------------:|-----------------------------------------------------------| | **id** | Unique identifier for each transaction. | | **beneficiaryName** | Name of the recipient of the payment. | | **amount** | Payment amount in the specified currency. | | **currency** | Currency used for the transaction (e.g., PEN, USD). | | **company** | The entity or service handling the transaction. | | **date** | Date of the transaction in a human-readable format. | | **hour** | Time of the transaction. | | **originalDate** | The exact date extracted from the receipt. | | **dateISO** | Standardized ISO 8601 date format. | | **operation** | Type of financial operation (e.g., deposit, transfer). | | **operationNumber** | Unique operation number provided by the payment system. | | **beneficiaryNumber** | Account or phone number of the recipient. | | **commission** | Any commission or fee charged for the transaction. | | **account** | Account number or reference used for the payment. | | **channel** | Payment method used (e.g., app, POS, bank transfer). | | **agentCode** | Identifier of the agent or entity processing the payment. | --- This workflow is perfect for
n8n$24.99Automate Daily AI-Generated Quotes and Images to Telegram
This n8n workflow delivers AI-generated quotes and cinematic images to your Telegram chat every morning, using GPT-4 and Flux-Pro for content creation.
n8n$9.99Automate Tool Execution via Chat with Bright Data MCP and OpenAI
This workflow enables users to trigger and execute Bright Data MCP tools through natural language chat inputs, leveraging OpenAI for intent classification and tool matching.
n8n$14.99Automate Sentiment Analysis of Google Sheets Feedback with ChatGPT
Automatically analyze customer feedback stored in Google Sheets using ChatGPT to determine sentiment, enhancing your data insights with AI.
Make$3.99AI-Driven Business Model Canvas Generator
Generate a comprehensive Business Model Canvas in seconds using AI, streamlining the creation process into a single, formatted HTML file.
n8n$14.99Calculate AI Model Carbon Footprint Using Ecologits.ai
This workflow estimates the carbon footprint of AI model outputs by calculating the grams of CO₂ equivalent per token, using the Ecologits.ai methodology. It helps developers and organizations track and reduce the environmental impact of their AI applications.
n8n$4.99Interactive XML File Analysis and Chat Using OpenAI and LangChain
This workflow enables interactive conversations with XML file content by leveraging OpenAI and LangChain. It retrieves an XML feed from a specified URL, parses it, and allows an AI agent to answer user queries based on the XML's structure and data.
n8n$9.99YouTube RAG Search with Frontend Using Apify, Qdrant, and AI
### Ever wanted to build your own RAG search over Youtube videos? Well, now you can! This n8n template shows how you can build a very capable Youtube search engine powered by Apify, Qdrant, and your LLM of choice to quickly and efficiently browse over many videos for research. I originally started this template to ask questions on the n8n @ scale office-hours livestream videos but then extended it to include the latest videos on the official channel. **Check out a demo here**: [https://jimleuk.app.n8n.cloud/webhook/n8n_videos](https://jimleuk.app.n8n.cloud/webhook/n8n_videos) ## How it works * Stage 1 is to collect the Youtube video transcripts and push them into a vector database. For this, I've used Apify to scrape Youtube and Qdrant to store the embeddings. * Transcripts are broken down into smaller chunks and carefully tagged with metadata to assist in later search and filtering. * Stage 2 is to build a web frontend for the user to query the vectorized transcripts. I'm using a webhook to serve a simple web app and API to dynamically fetch the results. * When searching for a video, I've opted to use Qdrant's search groups API which, in this use-case, performs better as it returns a wider range of video results. * In the web frontend, when the user clicks on the results, the matching Youtube video plays in an embedded video player. ## How to use * Once credentials are all set, first run steps 1 - 3 to populate your vector store. * Next, set the workflow to active to expose the web frontend. Visit the webhook URL in your browser to use it. * If only for personal use, you may want to remove the rate limiting mechanism in step 4. ## Requirements * Apify for Youtube Channel and Video Scraping * Qdrant for Vector store * OpenAI for LLM and Embeddings ## Customizing the template * Not interested in official n8n videos? Swap to a different channel - this template will work on many as long as videos are not private or set to prevent embeds. * Technically any vector store should work but may not have the same grouping API. Use the simple vector store node and revert back to basic searching instead.
n8n$24.99Automate AI-Ready Vector Dataset Creation from Web Content
This n8n workflow automates the extraction, structuring, vectorization, and storage of web content into AI-ready vector datasets using advanced tools like Scrapeless, Claude AI, Ollama, and Qdrant.
n8n$14.99Evaluation Metric Example: String Similarity
## AI Evaluation in n8n This is a template for n8n's [evaluation feature](https://docs.n8n.io/advanced-ai/evaluations/overview). Evaluation is a technique for getting confidence that your AI workflow performs reliably, by running a test dataset containing different inputs through the workflow. By calculating a metric (score) for each input, you can see where the workflow is performing well and where it isn't. ## How it Works This template shows how to calculate a workflow evaluation metric: **text similarity, measured character-by-character**. The workflow takes images of hand-written codes, extracts the code, and compares it with the expected answer from the dataset. The images look like this:  The workflow works as follows: - We use an evaluation trigger to read in our dataset. - It is wired up in parallel with the regular trigger so that the workflow can be started from either one. [More info](https://docs.n8n.io/advanced-ai/evaluations/tips-and-common-issues/#combining-multiple-triggers) - We download the image and use AI to extract the code. - If we're evaluating (i.e., the execution started from the evaluation trigger), we calculate the string distance metric. - We pass this information back to n8n as a metric.
n8n$9.99Integrate Open-Source LLM with Hugging Face for Chat Automation
Automate chat responses using an open-source language model from Hugging Face, integrated with n8n's Basic LLM Chain. Customize the model and prompts to suit your needs.
n8n$4.99Automate Image Transformation with AI and Airtable
This workflow automates the process of transforming images using AI by generating prompts and storing results in Airtable.
n8n$9.99Telegram Bot with Supabase Memory and OpenAI Assistant Integration
### Video Guide I prepared a detailed guide that showed the whole process of building an AI bot, from the simplest version to the most complex in a template. [.png)](https://www.youtube.com/watch?v=QrZxuWgFqBI) ### Who is this for? This workflow is ideal for developers, chatbot enthusiasts, and businesses looking to build a dynamic Telegram bot with memory capabilities. The bot leverages OpenAI's assistant to interact with users and stores user data in Supabase for personalized conversations. ### What problem does this workflow solve? Many simple chatbots lack context awareness and user memory. This workflow solves that by integrating Supabase to keep track of user sessions (via `telegram_id` and `openai_thread_id`), allowing the bot to maintain continuity and context in conversations, leading to a more human-like and engaging experience. ### What this workflow does This Telegram bot template connects with OpenAI to answer user queries while storing and retrieving user information from a Supabase database. The memory component ensures that the bot can reference past interactions, making it suitable for use cases such as customer support, virtual assistants, or any application where context retention is crucial. 1. **Receive New Message:** The bot listens for incoming messages from users in Telegram. 2. **Check User in Database:** The workflow checks if the user is already in the Supabase database using the `telegram_id`. 3. **Create New User (if necessary):** If the user does not exist, a new record is created in Supabase with the telegram_id and a unique `openai_thread_id`. 4. **Start or Continue Conversation with OpenAI:** Based on the user's context, the bot either creates a new thread or continues an existing one using the stored `openai_thread_id`. 5. **Merge Data:** User-specific data and conversation context are merged. 6. **Send and Receive Messages:** The message is sent to OpenAI, and the response is received and processed. 7. **Reply to User:** The bot sends OpenAI's response back to the user in Telegram. ### Setup 1. **Create a Telegram Bot** using the [Botfather](https://t.me/botfather) and obtain the bot token. 2. **Set up Supabase:** 1. Create a new project and generate a `SUPABASE_URL` and `SUPABASE_KEY`. 2. Create a new table named `telegram_users` with the following SQL query: ``` create table public.telegram_users ( id uuid not null default gen_random_uuid(), date_created timestamp with time zone not null default (now() at time zone 'utc'), telegram_id bigint null, openai_thread_id text null, constraint telegram_users_pkey primary key (id) ) tablespace pg_default; ``` 3. **OpenAI Setup:** 1. Create an OpenAI assistant and obtain the `OPENAI_API_KEY`. 2. Customize your assistant's personality or use cases according to your requirements. 4. **Environment Configuration in n8n:** 1. Configure the Telegram, Supabase, and OpenAI nodes with the appropriate credentials. 2. Set up triggers for receiving messages and handling conversation logic. 3. Set up OpenAI assistant ID in **OPENAI - Run assistant** node.
n8n$14.99Automate High-Quality Audio Generation with Voxtral Model via Replicate API
This n8n workflow automates the generation of high-quality audio using the Voxtral Small 24B 2507 model from Replicate. It manages API authentication, prediction creation, status polling, and result processing to deliver structured audio outputs.
n8n$9.99Create a Document-Based AI Chatbot with OpenAI and PGVector
Build an AI chatbot that answers questions using your internal documents by integrating OpenAI and PGVector with PostgreSQL.
n8n$14.99Automate Sentiment Analysis of Customer Reviews in Google Sheets
Automatically analyze the sentiment of customer reviews added to a Google Sheet and update the sheet with the sentiment results. This workflow helps in quickly identifying customer satisfaction trends and prioritizing follow-ups.
n8n$4.99Create an Intelligent Telegram Bot with NVIDIA AI and Conversation Memory
Set up a sophisticated Telegram bot that utilizes NVIDIA's AI model for contextual responses and maintains conversation history. This workflow allows seamless integration with various AI providers, enhancing the bot's adaptability and functionality.
n8n$14.99Automate YouTube Video Analysis with AI Summaries and Email Alerts
This workflow automates the analysis of YouTube videos by extracting transcripts, generating AI-powered summaries, and sending results via email. Ideal for content creators, marketers, and researchers.
n8n$14.99Interact with QuickBooks Online via Chat Using OpenAI
Enable operators and support teams to query QuickBooks Online customer data through a chat interface powered by OpenAI, facilitating quick access to information without directly accessing QuickBooks Online.
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