inderjeet Bhambra
I am on a journey to learn and spread the automations through n8n workflows.
Templates by inderjeet Bhambra
Transform travel photos into narrative stories with GPT-4O Vision
Who is this for? This workflow is designed for travel bloggers, content creators, social media managers, and anyone who wants to transform their travel photos into engaging written narratives. It's perfect for travelers looking to create compelling stories from their photo collections without spending hours crafting content manually, families wanting to document memorable trips, and digital nomads who need to produce travel content efficiently. What problem is this workflow solving? Converting travel photos into engaging stories is time-consuming and requires both creative writing skills and the ability to analyze visual content meaningfully. This workflow solves the challenge of: Transforming visual memories into compelling written narratives Organizing photos chronologically to create logical story flow Generating professional-quality travel content without writing expertise Analyzing photo content to extract meaningful themes and emotions Creating day-by-day structured narratives from unorganized photo collections Reducing the time spent on manual content creation for travel documentation What this workflow does This AI-powered photo storyteller takes your travel photos and automatically generates immersive, first-person travel narratives. The workflow: Accepts multiple photos through a webhook endpoint Uses OpenAI Vision API (GPT-4o) to analyze each photo's content, emotions, and themes Automatically organizes photos chronologically by date and timestamp Groups photos by travel days and extracts daily themes Leverages GPT-4.1 (minimum required) to craft engaging, first-person travel stories with creative day titles Generates structured narratives with sensory details, cultural observations, and emotional insights Outputs JSON formatted content ready for formatting Creates day-by-day story structure with memorable moments and reflective conclusions Setup Required Credentials: OpenAI API key configured in n8n for both Vision Analysis and Story Generation nodes Ensure you have sufficient OpenAI credits for image analysis and text generation Webhook Configuration: The workflow creates a webhook endpoint at /tripteller-upload Configure your photo upload interface to POST photos array to this endpoint Photos should be sent as base64 encoded data with filename and metadata Photo Requirements: Supported formats: Standard image formats (JPEG, PNG, etc.) Photos should include timestamp metadata for chronological organization Caution Do not upload all photos at once. Start with a small number of photos, like 5 at a time. How to customize this workflow to your needs Story Style Customization: Modify the system prompt in the "Generate Travel Story" node to adjust writing tone (nostalgic, adventurous, poetic, etc.) Customize the story structure by editing the output format requirements Add specific cultural or geographical context prompts for location-specific storytelling Photo Analysis Enhancement: Adjust the Vision Analysis node prompt to focus on specific elements (architecture, food, people, landscapes) Modify the grouping logic in the "Group Photos by Day" node for different time-based organization Add location extraction from EXIF data for geographical context Output Format Adjustment: Customize the final response structure in the "Format Final Response" node Add integration with publishing platforms (blog APIs, social media, etc.) Include additional metadata like location tags, travel duration, or trip statistics Performance Optimization: Adjust the execution timeout based on your typical photo volume Modify the parallel processing approach for large photo collections Add progress tracking for longer processing workflows
By inderjeet BhambraAI-powered social media content generator with strategic approach using GPT-4 models
This workflow contains community nodes that are only compatible with the self-hosted version of n8n. How it works? The Content Strategy AI Pipeline is an intelligent, multi-stage content creation system that transforms simple user prompts into polished, ready-to-publish content. The system intelligently extracts platform requirements, audience insights, and brand tone from user requests, then develops strategic reasoning and emotional connection strategies before crafting compelling content outlines and final publication-ready posts or articles. Supporting both social media platforms (Instagram, LinkedIn, X, Facebook, TikTok) and blog content. Key Differentiators: Strategic thinking approach, emotional intelligence integration, platform-native optimization, zero-editing-required output, and professional content strategist-level quality through multi-model AI orchestration. Technical Points Multi-model AI orchestration for specialized tasks Emotional psychology integration for audience connection Platform algorithm optimization built-in Industry-standard content strategy methodology automated Enterprise-grade reliability with session management and memory API-ready architecture for integration into existing workflows Test Inputs Sample Request: "Create an Instagram post for a fitness coach targeting busy moms, tone should be motivational and relatable" Expected Flow: Platform: Instagram → Niche: Fitness → Audience: Busy Moms → Tone: Motivational → Output: 125-150 word post with hashtags
By inderjeet BhambraAutomated Slack IT helpdesk with GPT, Supabase vector search, and JIRA ticketing
This workflow contains community nodes that are only compatible with the self-hosted version of n8n. Who is this for? IT teams and support organizations looking to automate Level 1 support with AI-powered assistance while maintaining proper ticket management workflows. What problem does this solve? Eliminates repetitive manual support tasks by providing instant, context-aware assistance that references organizational knowledge and creates structured tickets when needed. What this workflow does RAG Pipeline: Processes PDF/CSV documents into searchable vector database Intelligent Slack Bot: This AI-helpdesk assistant handles support requests with thread-aware conversations Vector Knowledge Search: Searches embedded knowledge base articles and historical case data JIRA Integration: Creates, searches, and manages support tickets automatically Emoji Reactions: Users can trigger actions (create tickets, escalate) via emoji reactions Requirements Required Accounts: n8n Cloud or self-hosted instance Slack workspace with admin access Supabase account (vector database) JIRA Cloud instance OpenAI API key Technical Prerequisites: Basic n8n workflow knowledge Slack app creation experience Understanding of vector databases Setup Steps Slack App Configuration Create new Slack app with Bot Token Scopes: app_mentions:read, channels:history, channels:read, groups:history, groups:read, im:history, im:read, mpim:history, mpim:read, users:read Configure Event Subscriptions: appmention, message.channels, message.groups, reactionadded Set Request URL to your n8n Slack Trigger webhook Supabase Vector Database Setup Create new Supabase project Enable pgvector extension Create documents table with vector column (1536 dimensions for OpenAI embeddings) Configure RLS policies for secure access JIRA Configuration Generate API token from JIRA Cloud Create helpdesk project with appropriate issue types Note project ID and issue type IDs for workflow configuration n8n Workflow Configuration Import workflow and configure credentials Update Slack channel IDs in trigger nodes Set OpenAI API key in all OpenAI nodes Configure Supabase connection in vector store nodes Update JIRA project settings in MCP server nodes Knowledge Base Data Format Supported file formats: PDF, CSV CSV Structure: Structure your data with columns, but not limited to, Ticket, Issue Description, Issue Summary, Resolution Provided, Case Status, Contact User PDF Content: Technical documentation, troubleshooting guides, policy documents Upload documents via the form trigger to automatically embed in vector database. Customization Options AI Agent Behavior Modify system prompt in AIHelpdesk Agent node Adjust conversation memory window (default: 20 messages) Change AI model (GPT-4o, GPT-3.5-turbo, etc.) Reaction Mappings Customize emoji-to-action mappings in Reaction Handler code Add new reaction types for department-specific workflows Configure escalation rules and priority levels JIRA Integration Customize ticket templates and fields Add auto-assignment rules based on issue type Configure SLA and priority mappings Vector Search Adjust similarity thresholds for knowledge retrieval Modify search result limits and relevance scoring Add metadata filtering for departmental knowledge bases Advanced Features Thread-aware conversation memory Automatic bot loop prevention Context-preserving ticket creation Multi-modal file processing (PDF + CSV) Scalable MCP architecture for tool integration Use Cases Level 1 IT Support: Automate common troubleshooting workflows Employee Onboarding: Answer policy and procedure questions Internal Help Desk: Route and track internal service requests Knowledge Management: Make organizational knowledge searchable and actionable Template includes Complete Slack integration with thread support RAG pipeline for document processing Vector similarity search implementation JIRA ticket lifecycle management Emoji reaction-based user interactions Comprehensive error handling and validation
By inderjeet BhambraPrevent prompt injection attacks with a GPT-4O security defense system
AI Security Pipeline - Prompt Injection Defense System using GPT-4O Protect your AI workflows from prompt injection attacks, XSS attempts, and malicious content with this multi-layer security sanitization system. > Important: The n8n workflow template uploader did not allow me to upload the complete system prompt for the Input Validation & Pattern Detection. Copy the complete System Prompt from here What it does This workflow acts as a security shield for AI-powered automations, preventing indirect prompt injection and other threats. It processes content through a multi-layered defense pipeline that detects malicious patterns, sanitizes markdown, validates URLs, and provides comprehensive security assessments. How it works Receives content via webhook endpoint Detects threats including prompt injections, XSS attempts, and data URI attacks Sanitizes markdown by removing HTML, dangerous protocols, and suspicious links Validates URLs blocking suspicious IP addresses, domains, and URL shorteners Returns security report with risk assessment and sanitized content Setup Import and activate the workflow Use the generated webhook URL: /webhook/security-sanitize Send POST requests with JSON: {"content": "your_text", "source": "identifier"} Use cases Secure AI chatbots and LLM integrations Process user-generated content before AI processing Protect RAG systems from data poisoning Sanitize external webhook payloads Ensure compliance with security standards Perfect for any organization using AI that needs to prevent prompt manipulation, data exfiltration, and injection attacks while maintaining audit trails for compliance.
By inderjeet BhambraAnalyze blog SEO with AI: complete assessment using GPT-4 and ethical scraping
This workflow contains community nodes that are only compatible with the self-hosted version of n8n. How it works? This workflow is an intelligent SEO analysis pipeline that ethically scrapes blog content and performs comprehensive SEO evaluation using AI. It receives blog URLs via webhook, validates permissions through robots.txt compliance, extracts content, and generates detailed SEO insights across four strategic dimensions: Content Optimization, Keyword Strategy, Technical SEO, and Backlink Building potential. The system prioritizes ethical web scraping by checking robots.txt permissions before proceeding, ensuring compliance with website policies. Upon successful analysis, it returns a structured JSON report with actionable SEO recommendations, performance scores, and optimization strategies. Technical Specifications Trigger: HTTP POST webhook Processing Time: 30-60 seconds depending on content size AI Model: GPT-4.1 minimum with specialized SEO analysis prompt. Output Format: Structured JSON Error Handling: Graceful failure with informative messages Compliance: Respects website robots.txt policies
By inderjeet BhambraTransform long content into bite-sized learning modules with GPT-4 & Google Docs
Who's it for Content creators, trainers, and educators who need to convert lengthy documents into digestible micro-learning experiences. How it works This workflow takes your source content (PDFs, articles, handbooks) and uses GPT-4 to intelligently break it into 2-3 minute learning modules. Each module includes a key concept, explanation, practical example, and knowledge check question. How to set up Configure OpenAI credentials with GPT-4 access Connect Slack workspace (optional) Set up Google Docs integration Optionally, Send content via webhook or paste directly Requirements OpenAI API key with GPT-4 access Google Docs account (for document creation) Slack workspace (optional, for notifications) How to customize the workflow Adjust module count and length in AI prompts Modify output formats (email, mobile, Slack) Change document structure and styling Add custom delivery channels Perfect for converting employee handbooks, training materials, and documentation into engaging micro-learning courses that people actually complete.
By inderjeet BhambraAutomated AI media creation with MagicHour AI and GPT-4 prompt optimization
This workflow automates AI-powered image and video generation using MagicHour.ai's API, enhanced by GPT-4.1 for intelligent prompt optimization. It processes webhook requests, refines prompts using AI, generates media content, and returns the final output. Who's it for Content creators, marketers, social media managers, and developers who need automated AI media generation at scale. Perfect for teams building applications that require on-demand image or video creation without manual intervention. How it works The workflow receives a webhook POST request containing generation parameters (type, orientation, style, duration). GPT-4.1 analyzes and optimizes the user's prompt based on the request type (image or video), then sends it to MagicHour.ai's API. The workflow monitors the generation status through polling loops, downloads the completed media, and returns it via webhook response. Error handling ensures failed requests are captured and reported. Requirements n8n instance (self-hosted or cloud) MagicHour.ai account with API access (Bearer token) OpenAI API account for GPT-4.1 access Basic understanding of webhooks and JSON How to set up Configure credentials: Add MagicHour.ai Bearer token in HTTP Request nodes (ai-image-generator, text-to-video, Get Image Details, Get Video Details) Add OpenAI API credentials in both Generate Image Prompt and Generate video Prompt nodes Activate the workflow: Enable the workflow to activate the webhook endpoint Copy the webhook URL from the Webhook trigger node Test the workflow: Download the n8n-magichour HTML tester Click here to download For image generation, send a POST request with this structure: json { "action": "generate", "type": "image", "parameters": { "name": "My Image", "image_count": 1, "orientation": "landscape", "style": { "prompt": "A serene mountain landscape at sunset", "tool": "realistic" } } } For video generation, use: json { "action": "generate", "type": "video", "parameters": { "name": "My Video", "end_seconds": 5, "orientation": "landscape", "resolution": "1080p", "style": { "prompt": "A dog running through a field" } } } How to customize the workflow Adjust AI prompt optimization: Modify the system prompts in Generate Image Prompt or Generate video Prompt nodes to change how GPT-4.1 refines user inputs. Current prompts enforce strict character limits and avoid unauthorized content. Change polling intervals: Modify the Wait nodes to adjust how frequently the workflow checks generation status (useful for longer video renders). Modify response format: Update the Respond to Webhook node to customize the output structure sent back to the caller. Add multiple output formats: Extend Download Image/Video nodes to save files to cloud storage (Google Drive, S3) instead of just returning via webhook. Implement queue management: Add a database node before MagicHour.ai calls to queue requests and prevent API rate limiting.
By inderjeet Bhambra