Loading page
Build a 100% local RAG with n8n, Ollama and Qdrant. This agent uses a semantic database (Qdrant) to answer questions about PDF files. Tutorial Click here to view the YouTube Tutorial How it works Build a chatbot that answers based on documents you provide it (Retrieval Augmented Generation). You can upload as many PDF files as you want to the Qdrant database. The chatbot will use its retrieval tool to fetch the chunks and use them to answer questions. Installation 1. Install n8n + Ollama + Qdrant using the Self-hosted AI starter kit 2. Make sure to install Llama 3.2 and mxbai-embed-large as embeddings model. How to use it 1. First run the "Data Ingestion" part and upload as many PDF files as you want 2. Run the Chatbot and start asking questions about the documents you uploaded
by Thomas JanssenThis template quickly shows how to use RAG in n8n. Who is this for? This template is for everyone who wants to start giving knowledge to their Agents through RAG. Requirements Have a PDF with custom knowledge that you want to provide to your agent. Setup No setup required. Just hit Execute Workflow, upload your knowledge document and then start chatting. How to customize this to your needs 1. Add custom instructions to your Agent by changing the prompts in it. 2. Add a different way to load in knowledge to your vector store, e.g. by looking at some Google Drive files or loading knowledge from a table. 2. Exchange the Simple Vector Store nodes with your own vector store tools ready for production. 3. Add a more sophisticated way to rank files found in the vector store. For more information read our docs on RAG in n8n.
by n8n TeamWho this is for This workflow is for digital marketing agencies or sales teams who want to automatically find business leads based on industry & location, gather their contact details, and send personalized cold emails — all from one form submission. --- What this workflow does This workflow starts every time someone submits the Lead Machine Form. It then: Scrapes business data (company name, website, phone, address, category) using Apify based on business type & location. Extracts the best email address from each business website using Google Gemini AI. Stores valid leads in Google Sheets. Generates cold email content (subject + body) with AI based on your preferred tone (Friendly, Professional, Simple). Sends the cold email via Gmail. Updates the sheet with send status & timestamp. --- Setup To set this workflow up: 1. Form Trigger – Customize the “Lead Machine” form fields if needed (Business Type, Location, Lead Number, Email Style). 2. Apify API – Add your Apify Actor Endpoint URL in the HTTP Request node. 3. Google Gemini – Add credentials for extracting email addresses. 4. Google Sheets – Connect your sheet for storing leads & email status. 5. OpenAI – Add your credentials for cold email generation. 6. Gmail – Connect your Gmail account for sending cold emails. --- How to customize this workflow to your needs Change the AI email prompt to reflect your brand’s voice and offer. Add filters to only target leads that meet specific criteria (e.g., website must exist, email must be verified). Modify the Google Sheets structure to track extra info like “Follow-up Date” or “Lead Source”. Switch Gmail to another email provider if preferred. ---
by Rakin JakariaThis automation template turns any long video into multiple viral-ready short clips and auto-schedules them to TikTok, Instagram Reels, and YouTube Shorts. It works with both vertical and horizontal inputs and respects the original input resolution (no unnecessary upscaling), cropping or letterboxing intelligently when needed. The workflow automatically extracts between 3 and 6 clips (based on video length and the most engaging segments) and schedules one short per consecutive day—e.g., 3 clips → the next 3 days, 6 clips → the next 6 days. Note: This workflow uses OpenAI Whisper for word-level transcription, Google’s Gemini for clip selection and metadata, and Upload-Post’s FFmpeg API for GPU-accelerated cutting/cropping and social scheduling. You can use the same Upload-Post API token for both FFmpeg jobs and publishing uploads. Upload-Post also offers a generous free trial with no credit card required. Who Is This For? Creators & Editors: Batch-convert long talks/podcasts into daily Shorts/Reels/TikToks. Agencies & Social Teams: Turn webinars/interviews into a reliable short-form stream. Brands & Founders: Maintain a steady posting cadence with minimal hands-on editing. What Problem Does This Workflow Solve? Manual clipping is slow and inconsistent. This workflow: Finds Hooks Automatically: AI picks 3–6 high-retention segments from transcript + timestamps (count scales with video length/quality). Cuts Cleanly: Absolute-second FFmpeg timing to avoid mid-word cuts. Vertical & Horizontal Friendly: Handles both orientations and respects source resolution. Schedules for You: Posts one clip per day on consecutive days. How It Works 1. Form Upload: Submit your long video. 2. Audio Extraction: FFmpeg job extracts audio for accurate ASR. 3. Whisper Transcription: Word-level timestamps enable precise clipping. 4. AI Clip Mining (Gemini): Detects 3–6 “viral” moments (15–60s) and generates titles/descriptions. 5. Cut & Crop (FFmpeg): GPU pipeline produces clean clips; preserves input resolution/orientation when possible and crops/pads appropriately for target platforms. 6. Status & Download: Polls job status and retrieves the final clips. 7. Auto-Scheduling (Consecutive Days): Schedules one short per day starting tomorrow, for as many days as clips were produced (e.g., 3 clips → 3 days, 6 clips → 6 days) at a configurable time (default 20:00 Europe/Madrid). Setup 1. OpenAI (Whisper): Add your OpenAI API credentials. 2. Google Gemini: Add Gemini credentials used by the AI Agent node. 3. Upload-Post (free trial no credit card required): Generate your api token https://app.upload-post.com/ connect your social media accounts and add your API token credentials in n8n (same token works for FFmpeg jobs and publishing). 4. Scheduling: Adjust posting time/intervals and timezone (Europe/Madrid by default). 5. Metadata Mapping: Titles/descriptions are auto-generated per platform; tweak as needed. Requirements Accounts: n8n, OpenAI, Google (Gemini), Upload-Post, and social platform connections. API Keys: OpenAI token, Gemini credentials, Upload-Post token. Budget: Whisper + Gemini inference + FFmpeg compute + optional posting costs. Features Word-Accurate Cuts: Absolute-second timecodes with subtle pre/post-roll. Orientation-Aware: Supports vertical and horizontal inputs; preserves source resolution where possible. Platform-Optimized Output: 9:16-ready delivery with smart crop/pad behavior. Consecutive-Day Scheduler: 3–6 clips → 3–6 consecutive posting days, automatically. Retry & Polling: Built-in waits and status checks for robust processing. Modular: Swap models, adjust clip count/length, or add/remove platforms quickly. Turn long-form video into a consistent sequence of Shorts/Reels/TikToks—automatically, day after day, while respecting your source resolution.
by Juan Carlos Cavero GraciaThis workflow contains community nodes that are only compatible with the self-hosted version of n8n. Description See the transformation in action! Here's an example of what this workflow can achieve: This automation template is designed for content creators, social media managers, and anyone looking to breathe new life into old family photos and historical images. It transforms any old black and white or sepia photograph into a colorized, animated video using cutting-edge AI technology, then automatically publishes the results across multiple social media platforms including Facebook, Instagram, YouTube, and X (Twitter). The workflow combines powerful AI services to create engaging content from vintage photographs: first enhancing and colorizing the image using FLUX Kontext, then bringing it to life with realistic animations using Kling Video AI, and finally distributing the results across your social media channels automatically. Note: The estimated cost per workflow execution is approximately $0.29 USD, covering the AI processing for both image colorization and video animation. The upload-post node only works for self-hosted n8n instances, but you can use the standard HTTP request node for uploading content on n8n Cloud. Who Is This For? Content Creators & Social Media Managers: Transform historical content into engaging videos that capture audience attention and drive engagement across platforms. Family History Enthusiasts: Bring old family photos to life by adding color and motion, creating emotional connections with your audience. Marketing Professionals: Leverage nostalgic content for brand storytelling, using vintage aesthetics to create compelling social media campaigns. Digital Artists & Photo Restorers: Streamline the process of enhancing and sharing restored vintage photographs with automated AI enhancement. Social Media Influencers: Create unique, eye-catching content from historical images that stands out in crowded social feeds. What Problem Does This Workflow Solve? Creating engaging social media content from old photos typically requires multiple manual steps: photo restoration, colorization, animation, and then individual posting to each platform. This workflow addresses these challenges by: Automating Photo Enhancement: Uses advanced AI (FLUX Kontext) to automatically colorize and enhance old photographs, removing artifacts and improving quality. Creating Dynamic Content: Transforms static images into animated videos using Kling Video AI, making historical photos come alive with natural movements. Streamlining Multi-Platform Publishing: Automatically distributes the final animated videos across Facebook, Instagram, YouTube, and X with a single workflow execution. Saving Time & Effort: Eliminates the need for manual photo editing, video creation, and individual social media posting. How It Works 1. Photo Upload: Users submit old photographs through a simple web form, with optional custom animation descriptions. 2. Image Enhancement: The workflow uploads the photo to imgbb, then sends it to FLUX Kontext AI for colorization and quality enhancement. 3. Animation Creation: The colorized image is processed by Kling Video AI to create a 5-second animated video with natural movements. 4. Cloud Storage: The final video is automatically saved to Google Drive for backup and easy access. 5. Multi-Platform Publishing: The animated video is simultaneously posted to Facebook, Instagram, YouTube, and X using the upload-post service. Setup 1. FAL.AI API Key: Sign up at fal.ai and add your API key to the HTTP Request nodes for both FLUX Kontext and Kling Video AI services. 2. ImgBB API Token: Create a free account at api.imgbb.com to get an API token for image hosting, then update the "Upload Image to imgbb" node. 3. Google Drive Connection: Connect your Google Drive account to enable automatic video storage and backup. 4. Upload-Post Service: Create an account at upload-post.com to get your API credentials for multi-platform social media posting. Important: The upload-post node currently only works with self-hosted n8n instances. For n8n Cloud users, replace the upload-post node with standard HTTP request nodes to publish to each social media platform individually. 5. Form Customization: (Optional) Modify the form fields in the "Photo Upload Form" node to collect additional information or customize the user experience. Requirements Accounts: n8n, FAL.AI, ImgBB, Google Drive, upload-post.com API Keys & Credentials: FAL.AI API Key, ImgBB API Token, Google Drive OAuth2, Upload-post.com API Token & User ID File Types: Supports JPG, PNG image formats for photo uploads Cost: Approximately $0.29 USD per workflow execution for AI processing Transform your old photographs into viral social media content with this powerful AI-driven workflow that handles everything from restoration to distribution automatically.
by Juan Carlos Cavero GraciaGenerate product images with NanoBanana Pro to Veo videos and Blotato Who is this for? This workflow is designed for: Content creators and marketers E-commerce and product-based businesses Agencies producing social media visuals and videos Automation builders looking for AI-powered creative pipelines It is ideal for anyone who wants to automate product image and video creation using AI and publish content without manual work. --- What problem is this workflow solving? / Use case Creating product visuals and marketing videos usually requires multiple tools, manual prompt writing, and repetitive steps. This workflow solves: Manual image and video creation Inconsistent visual quality across assets Time-consuming prompt iteration Manual video publishing to social platforms The workflow automates the entire process from image generation to video publishing using AI. --- What this workflow does This workflow provides an end-to-end automation pipeline: 1. Generates high-quality product images using NanoBanana Pro 2. Applies Contact Sheet Prompting to explore multiple visual variations 3. Converts selected images into short marketing videos using Veo 3.1 4. Automatically publishes the final videos via BLOTATO The result is a fully automated creative workflow that turns AI prompts into ready-to-publish video content. --- Setup To use this workflow, you need the following services and credentials: OpenAI API Used for image analysis and prompt generation NanoBanana Pro (fal.ai) Product image generation API: https://fal.ai/models/fal-ai/nano-banana-pro/edit/api Veo 3.1 (fal.ai) Video generation API: https://fal.ai/models/fal-ai/veo3.1/first-last-frame-to-video Blotato Video publishing to social platforms Sign up at BLOTATO All credentials must be added in n8n before running the workflow. --- How to customize this workflow to your needs You can easily adapt this workflow by: Modifying AI prompts to match your brand style Adjusting image composition and realism parameters in NanoBanana Pro Changing video motion, pacing, and aspect ratio in Veo 3.1 Selecting different social platforms or publishing rules in Blotato Replacing or extending individual steps while keeping the same architecture The workflow is modular and can be reused for multiple products or campaigns. Watch This Tutorial --- Need help or want to customize this? Contact: LinkedIn YouTube: @DRFIRASS Workshops: Mes Ateliers n8n --- Documentation: Notion Guide Need help customizing? Contact me for consulting and support : Linkedin / Youtube / Mes Ateliers n8n
by Dr. FirasUse the n8n Data Tables feature to store, retrieve, and analyze survey results — then let OpenAI automatically recommend the most relevant course for each respondent. --- What this workflow does This workflow demonstrates how to use n8n’s built-in Data Tables to create an internal recommendation system powered by AI. It: Collects survey responses through a Form Trigger Saves responses to a Data Table called Survey Responses Fetches a list of available courses from another Data Table called Courses Passes both Data Tables into an OpenAI Chat Agent, which selects the most relevant course Returns a structured recommendation with: course: the course title reasoning: why it was selected > Trigger: Form submission (manual or public link) --- Who it’s for Perfect for educators, training managers, or anyone wanting to use n8n Data Tables as a lightweight internal database — ideal for AI-driven recommendations, onboarding workflows, or content personalization. --- How to set it up 1 Create your n8n Data Tables This workflow uses two Data Tables — both created directly inside n8n. Table 1: Survey Responses Columns: Name Q1 — Where did you learn about n8n? Q2 — What is your experience with n8n? Q3 — What kind of automations do you need help with? To create: 1. Add a Data Table node to your workflow. 2. From the list, click “Create New Data Table.” 3. Name it Survey Responses and add the columns above. --- Table 2: Courses Columns: Course Description To create: 1. Add another Data Table node. 2. Click “Create New Data Table.” 3. Name it Courses and create the columns above. 4. Copy course data from this Google Sheet: https://docs.google.com/spreadsheets/d/1Y0Q0CnqN0w47c5nCpbA1O3sn0mQaKXPhql2Bc1UeiFY/edit?usp=sharing This Courses Data Table is where you’ll store all available learning paths or programs for the AI to compare against survey inputs. --- 2 Connect OpenAI 1. Go to OpenAI Platform 2. Create an API key 3. In n8n, open Credentials → OpenAI API and paste your key 4. The workflow uses the gpt-4.1-mini model via the LangChain integration --- Key Nodes Used | Node | Purpose | n8n Feature | |------|----------|-------------| | Form Trigger | Collect survey responses | Forms | | Data Table (Upsert) | Stores results in Survey Responses | Data Tables | | Data Table (Get) | Retrieves Courses | Data Tables | | Aggregate + Set | Combines and formats table data | Core nodes | | OpenAI Chat Model (LangChain Agent) | Analyzes responses and courses | AI | | Structured Output Parser | Returns structured JSON output | LangChain | --- Tips for customization Add more Data Table columns (e.g., email, department, experience years) Use another Data Table to store AI recommendations or performance results Modify the Agent system message to customize how AI chooses courses Send recommendations via Email, Slack, or Google Sheets --- Why Data Tables? This workflow shows how n8n’s Data Tables can act as your internal database: Create and manage tables directly inside n8n No external integrations needed Store structured data for AI prompts Share tables across multiple workflows All user data and course content are stored securely and natively in n8n Cloud or Self-Hosted environments. --- Contact Need help customizing this (e.g., expanding Data Tables, connecting multiple surveys, or automating follow-ups)? robert@ynteractive.com Robert Breen ynteractive.com
by Robert BreenSetup & Instructions — fluidX: Create Session, Analyze & Notify Goal: This workflow demonstrates the full fluidX THE EYE integration — starting a live session, inviting both the customer (via SMS) and the service agent (via email), and then accessing the media (photos and videos) created during the session. Captured images are automatically analyzed with AI, uploaded to an external storage (such as Google Drive), and a media summary for the session is generated at the end. The agent receives an email with a link to join the live session. The customer receives an SMS with a link to start sharing their camera. Once both are connected, the agent can view the live feed, and the system automatically stores uploaded images and videos in Google Drive. When the session ends, the workflow collects all media and creates a complete AI-powered session summary (stored and updated in Google Drive). Below is an example screenshot from the customer’s phone: --- Prerequisites Developer account: https://live.fluidx.digital (activate the TEST plan, €0) API docs (Swagger): fluidX.digital API --- Required Credentials 1 fluidX API key (HTTP Header Auth) • Credential name in n8n: fluidx API key • Header name: x-api-key • Header value: YOUR_API_KEY 2 SMTP account (for outbound email) • Credential name in n8n: SMTP account • Configure host, port, username, and password according to your provider • Enable TLS/SSL as required 3 Google Drive account • Used to store photos, videos, and automatically update the session summary files. 4 OpenAI API (for AI analysis & summary) •Used in the Analyze Images (AI) and Generate Summary parts of the workflow. • Credential type: OpenAI • Credential name (suggested): OpenAI account • API Key: your OpenAI API key • Model: e.g. gpt-4.1, gpt-4o, or similar (choose in the OpenAI node settings) --- Configuration (in the “Set Config” node) BASE_URL: https://live.fluidx.digital company / project / billingcode / sku: adjust as needed emailAgent: set before running (empty in template) phoneNumberUser: set before running (empty in template) --- Flow Overview Form Trigger → Create Session → Set Session Vars → Send SMS (User) → Send Email (Agent) → Monitor Media → Analyze Images (AI) → Upload Files to Google Drive → Generate Summary → Update Summary File The workflow starts automatically when a Form submission is received. Users enter the customer’s phone number and agent’s email, and the system creates a new fluidX THE EYE session. As media is uploaded during the session, the workflow automatically retrieves, stores, analyzes, and summarizes it — providing a complete end-to-end automation example for remote inspection, support, or field-service use cases. --- Notes Do not store real personal data inside the template. Manage API keys and secrets via n8n Credentials or environment variables. Log out of https://live.fluidx.digital in the agent’s browser before testing, to ensure a clean invite flow and session creation.
by Olaf Titel