AI Workflows
Artificial Intelligence tools and workflows
Create and Interact with an OpenAI Assistant Using Google Drive Files
This workflow automates the creation of an OpenAI Assistant using a file from Google Drive, enabling seamless interaction with the assistant.
n8n$9.99Automate Blog Creation and Publishing with AI and Dev.to
Transform your article ideas into complete blog posts with images, automatically published as drafts on Dev.to using AI and cloud services.
n8n$14.99Interactive PDF Chatbot in Telegram Using Pinecone and OpenAI
This workflow enables a Telegram chatbot to interact with users by answering questions about the content of PDFs. It uses Pinecone for vector storage and OpenAI for generating embeddings, providing a seamless question-and-answer experience.
n8n$14.99Automate Business Idea Extraction from Upwork Listings to Google Sheets
This workflow automatically fetches high-budget job listings from Upwork, extracts core business ideas using AI, and records them in a Google Sheet. It streamlines the process of identifying and documenting potential business opportunities.
n8n$14.99Automate Meeting Minutes Creation from Telegram to Airtable, Slack, and Gmail
Streamline your meeting documentation process by automatically transcribing Telegram messages or voice notes into structured meeting minutes with GPT, storing them in Airtable, and notifying your team via Slack and Gmail.
n8n$14.99Automate Job Listings Extraction from Hacker News to Airtable with AI
This workflow automates the extraction and structuring of job listings from Hacker News using AI, and saves them into Airtable for easy access and management.
n8n$14.99Automate Project Summaries from Meeting Transcripts Using GPT-4 and Google Docs
Streamline the creation of project summaries by automatically generating structured documents from meeting transcripts using GPT-4 and storing them in Google Docs.
n8n$9.99Generate YouTube Video Summaries with SearchAPI Transcripts and LLM
## Summarize YouTube Videos using SearchApi & LLM ### Who is this for? This workflow is ideal for **content creators**, **students**, **digital marketers**, **educators**, and **researchers** who want to quickly summarize YouTube videos. ### What problem does this workflow solve? Manually extracting important information from lengthy YouTube videos can be tedious and prone to errors. This workflow streamlines the process by automatically fetching video transcripts using [SearchApi.io](https://www.searchapi.io/) and producing concise, informative summaries through a summarization chain powered by any LLM provider. This allows users to quickly access crucial information without the need for manual transcription or detailed viewing. ### What this workflow does - Fetches the complete transcript of a YouTube video using SearchApi. - Combines the retrieved transcript into a single, continuous text. - Utilizes a **Summarization Chain** with an LLM (e.g., OpenAI models) to create a concise summary of the video content. ### 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., OpenAI 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 meet your needs - Adjust the summarization model or modify text-splitter parameters to accommodate different lengths and complexities of video transcripts. - Integrate additional nodes to export summaries directly into your preferred tools, such as Google Drive, Slack, or email. - Customize prompt templates in the summarization chain to obtain various summary styles (bullet points, paragraphs, etc.). - Modify the trigger to suit your workflow. ### Example Usage 1. **Input**: YouTube video ID (`wBuULAoJxok`). 2. **Output**: A concise, actionable summary that highlights key ideas, recommendations, and insights from the video.
n8n$9.99PostgreSQL Conversational Agent with Claude & DeepSeek (Multi-KPI, Secure)
# Conversational PostgreSQL Agent Enable AI-driven conversations with your PostgreSQL database using a secure and visual-free agent powered by n8n's Model Context Protocol (MCP). This template allows users to ask multiple KPIs in a single message, returning consolidated insights - more efficient than the original Conversing with Data template. --- ## Why This Template Unlike the Conversing with Data workflow, which handles one KPI per message, this version: - Supports multi-KPI questions - Returns structured, human-readable reports - Uses fewer AI calls, making it faster and cheaper - Avoids raw SQL execution for enhanced security **Estimated cost per full multi-request run: ~$0.01** This template is optimized for efficiency. Each message can return 2-4 KPIs (You can change the MaxIteration of the Agent to make it more, it is currently set up at 30 iterations) using a single Claude 3.5 Haiku session and DeepSeek-based SQL generation - balancing speed, reasoning, and affordability. --- ## Sample Use Case **User:** "Can you show product performance, revenue trends, and top 5 customers?" **Agent:** - Uses `Listables` and `GetableSchema` - Generates three SQL queries using `get_query_and_data` - Returns: **Product Performance** 1. High-Waist Jeans - 10 units, $1,027 revenue 2. Denim Jacket - 10 units, $783 revenue **Sales Trends** - Peak Month: January 2024 - 32 units, $2,378 - Average Monthly Units: 10-16 **Customer Insights** 1. Bob Brown - $1,520 spent 2. Diana Wilson - $925 spent All from one natural prompt. --- ## Real-World Interaction Screenshot  --- ## What's Inside | Node | Purpose | |----------------------------|-----------------------------------------------------------| | MCP Server Trigger | Receives user queries via `/mcp/...` | | AI Agent + Memory | Understands and plans multi-step queries | | Think Tool | Breaks down the user's question into structured goals | | get_query_and_data | Generates SQL securely from natural language | | Listables, GetSchema | AI tools to explore DB safely | | Read/Insert/Update Tools | Execute structured operations (never raw SQL) | | checkdatabase Subflow | Validates SQL, formats response as clean text | --- ## Model Selection Recommendations This template uses two types of models, selected for cost-performance balance and role alignment: **1. Claude 3.5 Haiku (Anthropic) - for the MCP Agent** The main conversational agent uses Claude 3.5 Haiku, ideal for MCP because it was built by Anthropic - the creators of the MCP standard. It's fast, affordable, and performs excellently in tool-calling and reasoning tasks. **2. DeepSeek - for the SQL subworkflow** The subworkflow that turns natural language into SQL uses DeepSeek. It's one of the most affordable and performant models available today for structured outputs like SQL, making it a perfect fit for utility logic. This setup provides top-tier reasoning + low-cost execution. --- ## Security Benefits - No raw SQL accepted from the user or LLM - All queries are parameterized - Schema is dynamically retrieved - Final output is clean, safe, and human-readable --- ## Try a Prompt > "Show me the top 5 products by units sold and revenue, total monthly sales trend, and top 5 customers by spending." In one message, the agent will: - Generate and run multiple queries - Use the schema to validate logic - Return a single, comprehensive answer --- ## How to Use 1. Upload both workflow files into your n8n instance: - `Build_your_own_PostgreSQL_MCP_server_No_visuals_.json` - `checkdatabase.json` 2. Set up PostgreSQL credentials (e.g., "Postgres account 3") 3. Confirm model setup: - Claude 3.5 Haiku for the main agent - DeepSeek for the subflow 4. Use the `/mcp/...` URL from the MCP Server Trigger to connect your frontend or chatbot 5. Ask questions naturally - the agent takes care of planning, querying, and formatting --- ## Customization Ideas - Swap Claude or DeepSeek for OpenAI, Mistral, Gemini, etc. - Export insights to Slack, Notion, or Google Sheets - Add Switch nodes to control access to specific tables - Integrate with any front-end app, internal dashboard, or bot --- ## What's Included - `Build_your_own_PostgreSQL_MCP_server_No_visuals_.json` - MCP agent logic - `checkdatabase.json` - SQL generation and formatting utility workflow These must be uploaded into your n8n workspace for the template to function. --- ## Comparison: Conversing with Data vs This Workflow | Feature | Conversing with Data | This Workflow |
n8n$14.99Automate YouTube Comment Analysis and Video Insights with AI
This workflow automates the extraction and analysis of YouTube comments and video insights using AI, helping content creators and marketers optimize their strategies.
n8n$14.99Tracking LLM Token Costs per Customer Using the Langchain Code Node
 *Note: This template only works for self-hosted n8n.* ### This n8n template demonstrates how to use the Langchain code node to track token usage and cost for every LLM call. This is useful if your templates handle multiple clients or customers and you need a cheap and easy way to capture how much of your AI credits they are using. ### How it works - In our mock AI service, we're offering a data conversion API to convert Resume PDFs into JSON documents. - A form trigger is used to allow for PDF upload and the file is parsed using the Extract from File node. - An Edit Fields node is used to capture additional variables to send to our log. - Next, we use the Information Extractor node to organize the Resume data into the given JSON schema. - The LLM subnode attached to the Information Extractor is a custom one we've built using the Langchain Code node. - With our custom LLM subnode, we're able to capture the usage metadata using lifecycle hooks. - We've also attached a Google Sheet tool to our LLM subnode, allowing us to send our usage metadata to a Google Sheet. - Finally, we demonstrate how you can aggregate from the Google Sheet to understand how much AI tokens/costs your clients are liable for. **Check out the example Client Usage Log** - [https://docs.google.com/spreadsheets/d/1AR5mrxz2S6PjAKVM0edNG-YVEc6zKL7aUxHxVcffnlw/edit?usp=sharing](https://docs.google.com/spreadsheets/d/1AR5mrxz2S6PjAKVM0edNG-YVEc6zKL7aUxHxVcffnlw/edit?usp=sharing) ### How to use - **SELF-HOSTED N8N ONLY** - The Langchain Code node is only available in the self-hosted version of n8n. It is not available in n8n cloud. - The LLM subnode can only be attached to non-AI agent nodes; Basic LLM node, Information Extractor, Question & Answer Chain, Sentiment Analysis, Summarization Chain, and Text Classifier. ### Requirements - Self-hosted version of n8n - OpenAI for LLM - Google Sheets to store usage metadata ### Customizing this template - Bring the custom LLM subnode into your own templates! In many cases, it can be a drop-in replacement for the regular OpenAI subnode. - Not using Google Sheets? Try other databases or an API call to pipe into your CRM.
n8n$14.99Automate Faceless YouTube Video Creation with AI
This workflow automates the creation of YouTube videos without requiring on-camera presence by generating audio narration, creating stock imagery, and syncing these elements into a cohesive video.
n8n$19.99Automate Google Drive Document Summarization with AI
This workflow automates the process of downloading, parsing, and summarizing documents from Google Drive using AI, ideal for efficient document processing.
n8n$4.99Automate Meeting Insights with VEXA, OpenAI, and Mem0
Streamline your meeting management by automating transcription, analysis, and memory storage using VEXA, OpenAI, and Mem0. This workflow ensures that you capture key insights and action items without manual effort.
n8n$14.99Create an AI Chatbot with Google Drive, Llama 3, and Qdrant RAG
Set up an AI chatbot that uses Google Drive documents for knowledge retrieval, powered by Llama 3 and Qdrant for context-aware responses.
n8n$9.99Interactive AI Chat with Google Search Console Data via OpenAI and Postgres
This workflow enables interactive communication with your Google Search Console data using an AI agent powered by OpenAI and Postgres. It facilitates natural language queries and retrieves data in a user-friendly chat interface.
n8n$14.99Automate AI-Enhanced FAQ Generation from Google Sheets
This n8n workflow automates the creation of comprehensive FAQ content by leveraging AI to enhance data from Google Sheets. It generates detailed Q&A documents for various services and organizes them in Google Drive.
n8n$24.99Implement Role-Based Access Control for AI Agents with Airtable and Telegram
This workflow enables precise control over AI agent tool access using Role-Based Access Control (RBAC) with Airtable and Telegram. It ensures users can only access tools they are authorized for, enhancing security and management of AI interactions.
n8n$24.99Create a Multi-Language Telegram RAG Chatbot with AI Supervision and Google Drive Automation
Develop a sophisticated multi-agent RAG chatbot that processes diverse user queries using AI agents and automates data ingestion from Google Drive and websites.
n8n$19.99Automate Bing Copilot Searches and Summarize Results with AI
Streamline your research process by automating Bing Copilot searches, extracting structured data, and generating concise summaries with AI. This workflow integrates with Bright Data and Google Gemini to enhance efficiency and accuracy.
n8n$14.99Automate Blog Creation and Publishing with Gemini AI, Google Sheets, and GitHub
This n8n workflow automates the generation and publication of technical blog posts using topics from Google Sheets. It utilizes Gemini AI for content creation, commits the content to a GitHub repository, and updates a Jekyll-powered blog, streamlining the entire process.
n8n$14.99Automate Client Transcript Analysis and Feedback Routing with AI, HubSpot, and Gmail
Streamline the process of analyzing client transcripts, logging insights in HubSpot, and routing feedback to relevant departments via Gmail using AI.
n8n$9.99AI-Driven Slack Chatbot with Contextual Memory and Information Retrieval
Leverage AI to create an interactive Slack chatbot that uses contextual memory and external information sources for enhanced responses. This workflow integrates AI models and information retrieval tools to deliver a dynamic chatbot experience.
n8n$9.99Automate PDF to Blog Post Creation on Ghost
Transform PDF documents into engaging blog posts on Ghost using AI, saving time and enhancing content quality.
n8n$9.99
Related categories
Custom AI Systems & Services
Our team of experienced AI builders will help build custom AI systems, workflows, and solutions.
Request Custom Work