Analyze images, videos, documents & audio with Gemini Tools and Qwen LLM Agent
📁 Analyze uploaded images, videos, audio, and documents with specialized tools — powered by a lightweight language-only agent. --- 🧭 What It Does This workflow enables multimodal file analysis using Google Gemini tools connected to a text-only LLM agent. Users can upload images, videos, audio files, or documents via a chat interface. The workflow will: Upload each file to Google Gemini and obtain an accessible URL. Dynamically generate contextual prompts based on the file(s) and user message. Allow the agent to invoke Gemini tools for specific media types as needed. Return a concise, helpful response based on the analysis. --- 🚀 Use Cases Customer support: Let users upload screenshots, documents, or recordings and get helpful insights or summaries. Multimedia QA: Review visual, audio, or video content for correctness or compliance. Educational agents: Interpret content from PDFs, diagrams, or audio recordings on the fly. Low-cost multimodal assistants: Achieve multimodal functionality without relying on large vision-language models. --- 🎯 Why This Architecture Matters Unlike end-to-end multimodal LLMs (like Gemini 1.5 or GPT-4o), this template: Uses a text-only LLM (Qwen 32B via Groq) for reasoning. Delegates media analysis to specialized Gemini tools. ✅ Advantages | Feature | Benefit | | ----------------------- | --------------------------------------------------------------------- | | 🧩 Modular | LLM + Tools are decoupled; can update them independently | | 💸 Cost-Efficient | No need to pay for full multimodal models; only use tools when needed | | 🔧 Tool-based Reasoning | Agent invokes tools on demand, just like OpenAI’s Toolformer setup | | ⚡ Fast | Groq LLMs offer ultra-fast responses with low latency | | 📚 Memory | Includes context buffer for multi-turn chats (15 messages) | --- 🧪 How It Works 🔹 Input via Chat Users submit a message and (optionally) files via the chatTrigger. 🔹 File Handling If no files: prompt is passed directly to the agent. If files are included: Files are split, uploaded to Gemini (to get public URLs). Metadata (name, type, URL) is collected and embedded into the prompt. 🔹 Prompt Construction A new chatInput is dynamically generated: User message Media: [array of file data] 🔹 Agent Reasoning The Langchain Agent receives: The enriched prompt File URLs Memory context (15 turns) Access to 4 Gemini tools: IMG: analyze image VIDEO: analyze video AUDIO: analyze audio DOCUMENT: analyze document The agent autonomously decides whether and how to use tools, then responds with concise output. --- 🧱 Nodes & Services | Category | Node / Tool | Purpose | | --------------- | ---------------------------- | ------------------------------------- | | Chat Input | chatTrigger | User interface with file support | | File Processing | splitOut, splitInBatches | Process each uploaded file | | Upload | googleGemini | Uploads each file to Gemini, gets URL | | Metadata | set, aggregate | Builds structured file info | | AI Agent | Langchain Agent | Receives context + file data | | Tools | googleGeminiTool | Analyze media with Gemini | | LLM | lmChatGroq (Qwen 32B) | Text reasoning, high-speed | | Memory | memoryBufferWindow | Maintains session context | --- ⚙️ Setup Instructions 🔑 Required Credentials Groq API key (for Qwen 32B model) Google Gemini API key (Palm / Gemini 1.5 tools) 🧩 Nodes That Need Setup Replace existing credentials on: Upload a file Each GeminiTool (IMG, VIDEO, AUDIO, DOCUMENT) lmChatGroq ⚠️ File Size & Format Considerations Some Gemini tools have file size or format restrictions. You may add validation nodes before uploading if needed. --- 🛠️ Optional Improvements Add logging and error handling (e.g., for upload failures). Add MIME-type filtering to choose the right tool explicitly. Extend to include OCR or transcription services pre-analysis. Integrate with Slack, Telegram, or WhatsApp for chat delivery. --- 🧪 Example Use Case > "Hola, ¿qué dice este PDF?" Uploads a document → Agent routes it to Gemini DOCUMENT tool → Receives extracted content → LLM summarizes it in Spanish. --- 🧰 Tags multimodal, agent, langchain, groq, gemini, image analysis, audio analysis, document parsing, video analysis, file uploader, chat assistant, LLM tools, memory, AI tools --- 📂 Files This template is ready to use as-is in n8n. No external webhooks or integrations required.
By Mauricio PereraMove a Nextcloud folder file by file
Description: This template facilitates the transfer of a folder, along with all its files and subfolders, within a Nextcloud instance. The Nextcloud user must have access to both the source and destination folders. While Nextcloud allows folder movement, complications may arise when dealing with external storage that has rate limits. This workflow ensures the individual transfer of each file to avoid exceeding rate limits, particularly useful for setups involving external storage with rate limitations. How it works: Identify all files and subfolders within the specified source folder. Recursive search within subfolders for additional files. Replicate the folder structure in the target folder. Individually move each identified file to the corresponding location in the target folder. Set up steps: Set Nextcloud credentials for all Nextcloud nodes involved in the process. -Edit the trigger settings. Detailed instructions can be found within the respective trigger configuration. Initiate the workflow to commence the folder transfer process. Help If you need assistance with applying this template, feel free to reach out to me. You can find additional information about me and my services here. => https://nicokowalczyk.de/links I have also produced a video where I explain the workflow and provide an example. You can find this video over here. https://youtu.be/K1kmGQjRk Cheers. Nico Kowalczyk
By Nico KowalczykGet email notifications for newly uploaded Google Drive files
This workflow sends out email notifications when a new file has been uploaded to Google Drive. The workflow uses two nodes: Google Drive Trigger: This node will trigger the workflow whenever a new file has been uploaded to a given folder Send Email: This node sends out the email using data from the previous Google Drive Trigger node.
By TomBatch scrape website URLs from Google Sheets to Google Docs with Firecrawl
This workflow contains community nodes that are only compatible with the self-hosted version of n8n. Firecrawl batch scraping to Google Docs Who's it for AI chatbot developers, content managers, and data analysts who need to extract and organize content from multiple web pages for knowledge base creation, competitive analysis, or content migration projects. What it does This workflow automatically scrapes content from a list of URLs and converts each page into a structured Google Doc in markdown format. It's designed for batch processing multiple pages efficiently, making it ideal for building AI knowledge bases, analyzing competitor content, or migrating website content to documentation systems. How it works The workflow follows a systematic scraping process: URL Input: Reads a list of URLs from a Google Sheets template Data Validation: Filters out empty rows and already-processed URLs Batch Processing: Loops through each URL sequentially Content Extraction: Uses Firecrawl to scrape and convert content to markdown Document Creation: Creates individual Google Docs for each scraped page Progress Tracking: Updates the spreadsheet to mark completed URLs Final Notification: Provides completion summary with access to scraped content Requirements Firecrawl API key (for web scraping) Google Sheets access Google Drive access (for document creation) Google Sheets template (provided) How to set up Step 1: Prepare your template Copy the Google Sheets template Create your own version for personal use Ensure the sheet has a tab named "Page to doc" List all URLs you want to scrape in the "URL" column Step 2: Configure API credentials Set up the following credentials in n8n: Firecrawl API: For web content scraping and markdown conversion Google Sheets OAuth2: For reading URLs and updating progress Google Drive OAuth2: For creating content documents Step 3: Set up your Google Drive folder The workflow saves scraped content to a specific Drive folder Default folder: "Contenu scrapé" (Content Scraped) Folder ID: 1ry3xvQ9UqM2Rf9C4-AoJdg1lfB9inh_5 (customize this to your own folder) Create your own folder and update the folder ID in the "Create file markdown scraping" node Step 4: Choose your trigger method Option A: Chat interface Use the default chat trigger Send your Google Sheets URL through the chat interface Option B: Manual trigger Replace chat trigger with manual trigger Set the Google Sheets URL as a variable in the "Get URL" node How to customize the workflow URL source customization Sheet name: Change "Page to doc" to your preferred tab name Column structure: Modify field mappings if using different column names URL validation: Adjust filtering criteria for URL format requirements Batch size: The workflow processes all URLs sequentially (no batch size limit) Scraping configuration Firecrawl options: Add specific scraping parameters (wait times, JavaScript rendering) Content format: Currently outputs markdown (can be modified for other formats) Error handling: The workflow continues processing even if individual URLs fail Retry logic: Add retry mechanisms for failed scraping attempts Output customization Document naming: Currently uses the URL as document name (customizable) Folder organization: Create subfolders for different content types File format: Switch from Google Docs to other formats (PDF, TXT, etc.) Content structure: Add headers, metadata, or formatting to scraped content Progress tracking enhancements Status columns: Add more detailed status tracking (failed, retrying, etc.) Metadata capture: Store scraping timestamps, content length, etc. Error logging: Track which URLs failed and why Completion statistics: Generate summary reports of scraping results Use cases AI knowledge base creation E-commerce product pages: Scrape product descriptions and specifications for chatbot training Documentation sites: Convert help articles into structured knowledge base content FAQ pages: Extract customer service information for automated support systems Company information: Gather about pages, services, and team information Content analysis and migration Competitor research: Analyze competitor website content and structure Content audits: Extract existing content for analysis and optimization Website migrations: Backup content before site redesigns or platform changes SEO analysis: Gather content for keyword and structure analysis Research and documentation Market research: Collect information from multiple industry sources Academic research: Gather content from relevant web sources Legal compliance: Document website terms, policies, and disclaimers Brand monitoring: Track content changes across multiple sites Workflow features Smart processing logic Duplicate prevention: Skips URLs already marked as "Scrapé" (scraped) Empty row filtering: Automatically ignores rows without URLs Sequential processing: Handles one URL at a time to avoid rate limiting Progress updates: Real-time status updates in the source spreadsheet Error handling and resilience Graceful failures: Continues processing remaining URLs if individual scrapes fail Status tracking: Clear indication of completed vs. pending URLs Completion notification: Summary message with link to scraped content folder Manual restart capability: Can resume processing from where it left off Results interpretation Organized content output Each scraped page creates: Individual Google Doc: Named with the source URL Markdown formatting: Clean, structured content extraction Metadata preservation: Original URL and scraping timestamp Organized storage: All documents in designated Google Drive folder Progress tracking The source spreadsheet shows: URL list: Original URLs to be processed Status column: "OK" for completed, empty for pending Real-time updates: Progress visible during workflow execution Completion summary: Final notification with access instructions Workflow limitations Sequential processing: Processes URLs one at a time (prevents rate limiting but slower for large lists) Google Drive dependency: Requires Google Drive for document storage Firecrawl rate limits: Subject to Firecrawl API limitations and quotas Single format output: Currently outputs only Google Docs (easily customizable) Manual setup: Requires Google Sheets template preparation before use No content deduplication: Creates separate documents even for similar content
By Growth AIManage Slack channel and users automatically
No description available.
By Harshil AgrawalCheck which AI models are used in your workflows
How it works Fetch all workflows from your n8n instance. Filter workflows that contain nodes with a modelId setting. Extract the node names, model IDs, model names, workflow names, and workflow URLs. Save the extracted information into a connected Google Sheet. Set up steps Connect your n8n API credentials. Connect your Google Sheets account. Replace "Your n8n domain" with your actual domain URL. Use this Google Sheet template to create a new sheet for results. Setup typically takes 5 minutes. Be cautious: if you have over 100 workflows, performance may be impacted. Notes Sticky notes inside the workflow provide extra guidance. This workflow clears old sheet data before writing new results. Make sure your n8n instance allows API access. Result Example Update: It didn't detect the AI model in tool originally. Now it's fixed! Update 20250429: Support 1.91.0 with open node directly! Optimize the url with node id.
By darrell_twMulti-agent personal assistant orchestration with GPT-4o & WhatsApp
Description 'Elena AI' is a powerful n8n workflow that transforms your automation platform into a full-fledged, multi-agent AI hub. 🤖✨ By combining Redis state management with specialized “tool” sub-workflows, you can build contextual, scalable, and highly personalized conversational automations for WhatsApp, Telegram, email, and more. 🔥 Key Features Unified Ingestion 📥 • Webhook trigger for text, audio, image, or document messages • Automatic extraction of remoteJid, user ID, and payload metadata Stateful Context 🔄 • Redis push/get queue to preserve conversation history • Seamless handling of follow-ups and multi-turn dialogs Dynamic Routing 🔀 • Smart Switch logic directs messages to the right agent workflow • Agents available: 🗓️ Malu: Google Calendar scheduling & reminders 💰 Maria: Expense logging & budget tracking in Baserow 👥 Mafalda: Contact CRUD operations in Baserow 📸 Marcela: Audio transcription & image analysis ✉️ Martina: Gmail send/receive & template replies Bite-Sized Responses ✂️ • Splits long AI replies into line-by-line messages • Loop node controls rate & order for best UX Flexible Output 📤 • HTTP Request node to deliver text, media, or files • Customize headers, payloads, and endpoints 🎯 Use Cases AI-powered customer support bots Automated lead qualification & follow-up Intelligent scheduling & reminders Expense approval workflows Multimedia content analysis & response 📋 Requirements n8n ≥ 1.0 with Webhook, Redis, SplitInBatches, HTTP Request & Workflow nodes Redis server (connection credentials in n8n) Service accounts / API keys for: Google Calendar (OAuth2) Baserow (API token) Gmail (OAuth2) Messaging API endpoint (HTTP) Environment variables set in n8n: REDISHOST, REDISPORT, REDIS_PASSWORD GOOGLECLIENTID, GOOGLECLIENTSECRET BASEROWAPITOKEN GMAILCLIENTID, GMAILCLIENTSECRET MSGAPIURL, MSGAPIKEY 🚀 Quick Start Import the ElenaAI.json into n8n. Configure credentials and environment variables under Settings → Credentials. Link sub-workflows (Malu, Maria, Mafalda, Marcela, Martina) by updating their Workflow IDs in the main node. Test via Execute node or send a sample webhook payload. Deploy by exposing the Webhook endpoint to your messaging platform. Unlock seamless, AI-driven conversations across any channel—get MavenBot 2.0 running in minutes! 🚀
By Amanda BenksBuild comprehensive entity profiles with GPT-4, Wikipedia & vector DB for content
This n8n template demonstrates how to build an intelligent entity research system that automatically discovers, researches, and creates comprehensive profiles for business entities, concepts, and terms. Use cases are many: Try automating glossary creation for technical documentation, building standardized definition databases for compliance teams, researching industry terminology for content creation, or developing training materials with consistent entity explanations! Good to know Each entity research typically costs $0.08-$0.34, depending on the complexity and sources required. The workflow includes smart duplicate detection to minimize unnecessary API calls. The workflow requires multiple AI services and a vector database, so setup time may be longer than simpler templates. Entity definitions are stored locally in your Qdrant database and can be reused across multiple projects. How it works The workflow checks your existing knowledge base first to avoid duplicate research on entities you've already processed. If the entity is new, an AI research agent intelligently combines your vector database, Wikipedia, and live web research to gather comprehensive information. The system creates structured entity profiles with definitions, categories, examples, common misconceptions, and related entities - perfect for business documentation. AI-powered validation ensures all entity profiles are complete, accurate, and suitable for business use before storage. Each researched entity gets stored in your Qdrant vector database, creating a growing knowledge base that improves research efficiency over time. The workflow includes multiple stages of duplicate prevention to avoid unnecessary processing and API costs. How to use The manual trigger node is used as an example, but feel free to replace this with other triggers such as form submissions, content management systems, or automated content pipelines. You can research multiple related entities in sequence, and the system will automatically identify connections and relationships between them. Provide topic and audience context to get tailored explanations suitable for your specific business needs. Requirements OpenAI API account for o4-mini (entity research and validation) Qdrant vector database instance (local or cloud) Ollama with nomic-embed-text model for embeddings Automate Web Research with GPT-4, Claude & Apify for Content Analysis and Insights workflow (for live web research capabilities) Anthropic API account for Claude Sonnet 4 (used by the web research workflow) Apify account for web scraping (used by the web research workflow) Customizing this workflow Entity research automation can be adapted for many specialized domains. Try focusing on specific industries like legal terminology (targeting official legal sources), medical concepts (emphasizing clinical accuracy), or financial terms (prioritizing regulatory definitions). You can also customize the validation criteria to match your organization's specific quality standards.
By Peter Zendzian🛠️ Emelia tool MCP server 💪 all 9 operations
Need help? Want access to this workflow + many more paid workflows + live Q&A sessions with a top verified n8n creator? Join the community Complete MCP server exposing all Emelia Tool operations to AI agents. Zero configuration needed - all 9 operations pre-built. ⚡ Quick Setup Import this workflow into your n8n instance Activate the workflow to start your MCP server Copy the webhook URL from the MCP trigger node Connect AI agents using the MCP URL 🔧 How it Works • MCP Trigger: Serves as your server endpoint for AI agent requests • Tool Nodes: Pre-configured for every Emelia Tool operation • AI Expressions: Automatically populate parameters via $fromAI() placeholders • Native Integration: Uses official n8n Emelia Tool tool with full error handling 📋 Available Operations (9 total) Every possible Emelia Tool operation is included: 📢 Campaign (7 operations) • Add a contact to a campaign • Create a campaign • Duplicate a campaign • Get a campaign • Get many campaigns • Pause a campaign • Start a campaign 🔧 Contactlist (2 operations) • Add a contact list • Get many contact lists 🤖 AI Integration Parameter Handling: AI agents automatically provide values for: • Resource IDs and identifiers • Search queries and filters • Content and data payloads • Configuration options Response Format: Native Emelia Tool API responses with full data structure Error Handling: Built-in n8n error management and retry logic 💡 Usage Examples Connect this MCP server to any AI agent or workflow: • Claude Desktop: Add MCP server URL to configuration • Custom AI Apps: Use MCP URL as tool endpoint • Other n8n Workflows: Call MCP tools from any workflow • API Integration: Direct HTTP calls to MCP endpoints ✨ Benefits • Complete Coverage: Every Emelia Tool operation available • Zero Setup: No parameter mapping or configuration needed • AI-Ready: Built-in $fromAI() expressions for all parameters • Production Ready: Native n8n error handling and logging • Extensible: Easily modify or add custom logic > 🆓 Free for community use! Ready to deploy in under 2 minutes.
By David Ashby