Google Gemini Chat Model and Postgres integration

Who Is This For? This workflow is designed for marketers, content creators, agencies, and solo founders who want to publish long‑form posts with visuals on autopilot using n8n and AI agents. ​ Whether you run a blog, SaaS, personal brand, newsletter, or client accounts, this tool helps you keep a consistent content pipeline without manually writing every article, creating images, and posting to each platform one by one. ​ ​ 💪🏼 While the template is wired around classic blog + social media distribution, the underlying logic is universal. You can easily adapt it to any niche by editing prompts, swapping models, and re‑wiring nodes. You can plug in any LLM you like, from ChatGPT to Claude, Gemini, Mistral, DeepSeek, OpenRouter, or even local models through Ollama. ​ What Problem Is This Workflow Solving? 🤯 Most teams waste hours on the same repetitive loop: research a topic, gather links, write a blog post, craft social captions, generate visuals, upload everything to multiple platforms, and archive assets. ​ ​ 💎 This workflow solves that by automating the full content chain—from research and blog‑post generation to image creation, publishing across channels, and logging everything in your content database—so your feeds stay active while you focus on strategy, not busywork. ​ What This Workflow Does ✨ Generates in‑depth blog posts tailored to your topic and target audience, enriched with fresh references from the web via Tavily/SerpAPI search tools. ​ ✨ Creates an image prompt and title from the article, generates the visual with OpenAI Images (gpt-image-1), and converts it into a ready‑to‑use image file. ​ ✨ Automatically publishes content to your connected platforms (WordPress for blog posts, Telegram, X/Twitter, Facebook, LinkedIn) while saving images to Google Drive and logging each publication in Google Sheets for tracking. ​ How It Works? Surprisingly simple ☺️ The workflow is triggered by another n8n workflow or by one of several triggers (Facebook, RSS, Google Sheets, Airtable, Postgres) that pass in the blogTopic, targetAudience, and Telegram chatID. ​ ​ The Blog Post Agent (LLM with access to Tavily/SerpAPI) researches the topic, writes a structured article for the specified audience, and sends its output to the Image Prompt Agent, which turns the content into a visual prompt and title. ​ 🎯 The end result: you provide a topic, run the workflow, and receive a complete blog post, matching image, and ready‑made social posts shipped directly to your channels and archives—no manual copy‑paste. ​ How to Customize This Workflow to Your Needs 🎨 Switch AI models and fine‑tune prompts so the agent can handle your exact formats: tutorials, case studies, listicles, product updates, thought‑leadership pieces, or campaign landing posts. 🔍 Refine research sources inside Tavily/SerpAPI to prioritize the domains, blogs, and docs your audience trusts, keeping posts accurate and up to date. ⏰ Adjust posting cadence and schedules to align with peak engagement for your audience, mixing automated slots with manual “launch” runs for special announcements. 📱 Expand or trim channels as needed: keep just WordPress + LinkedIn, add Telegram as a content feed, or plug the workflow into additional automations like email campaigns or RSS feeds. 📊 Use Google Sheets as your content hub to store ideas, angles, CTAs, references, and performance notes so you can double‑down on topics and formats that perform best. 🎬 Swap images for video by replacing the image generation node with video tools (for example, Runway‑style APIs) if your strategy is video‑first while keeping the same prompt pipeline. 💾 Build a reusable prompt library in Sheets, Notion, or Airtable so you can rotate proven prompt patterns each month and keep quality high without reinventing the wheel. 🤖 The system will continuously generate blog posts, visuals, and social updates and publish them across your selected platforms while archiving everything in Drive and Sheets—keeping your brand visible, consistent, and professional with minimal ongoing effort.

How can you find your target market if you don't know what your product is. This simple philosophy changes the way we think about automated sales agents. Context changes everything. In this 4-part workflow, we start by creating a knowledge base that will act as context across the workflow. This context will guide and provide our AI Agents across the workflow to locate better leads and perform market research based on what the product actually offers. Use Case: Lead generation for Product-based Sales Tech Required Neon DB**: For storing Research and Lead Data. You can use Google sheets but it has a rate limiting problem. Google Serper**: As a web search tool for our AI. Google Drive**: For storing our knowledge base documents. Pinecone**: Vector DB for converting our knowledge base into context for AI. Hunter.io**: For finding emails for outreach. Email Client**: An email client, maybe gmail or anything that can send an email on your behalf. Gemini**: Our trusty AI LLM. Good to know All of the tools that I use in this workflow are either free or have an extremely generous free-tier. How it works We start by converting our knowledge base into context for AI. Take in the documents from Google drive and convert it into embeddings and store them in a vector store like Pinecone. This needs to be only run once, or whenever you have a new document in your knowledge base. Then we pass this context to an AI agent and tell it to generate search queries for locating companies that actually need my services. Then for each company that we've located, we determine the company staff that we need to reach out to for selling our product. This will be done by a combination of Google Serper and Hunter.io Once we have the list of employees and their emails, we start creating personalized emails based on the data we've collected for each of the employee and send them outreach emails.

This is an advanced n8n workflow for transforming product concepts into 3D showcase videos with AI packaging design and auto-rotation rendering. Workflow Features: 🎯 Core Capabilities: AI Product Concept Generation - Uses Claude Sonnet 4 to analyze product prompts and generate comprehensive 3D specifications Automated Packaging Design - DALL-E 3 generates professional packaging visuals Texture Map Generation - Creates PBR-ready texture maps for realistic materials 3D Scene Script Generation - Produces complete Blender Python scripts with: Product geometry based on shape Professional 3-point lighting (key, fill, rim) 360° rotation animation (8 seconds) Camera setup and render settings Preview Rendering - Generates photorealistic 3D preview images Video Processing - Handles encoding and upload to video hosting services Database Storage - Saves all showcase data for tracking Status Monitoring - Checks render progress with automatic retry logic 📋 Required Setup: API Credentials needed: Anthropic API (for Claude AI) OpenAI API (for DALL-E image generation) Replicate API (optional for additional rendering) Video hosting service (Cloudflare Stream or similar) PostgreSQL database 🔧 How to Use: Import the JSON - Copy the artifact content and import directly into n8n Configure Credentials - Add your API keys in n8n credentials manager Activate Workflow - Enable the webhook trigger Send Request to webhook endpoint: POST /product-showcase { "productPrompt": "A premium organic energy drink in a sleek aluminum can with nature-inspired graphics" } 📤 Output Includes: Product specifications (dimensions, materials, colors) Packaging design image URL Texture map URLs Downloadable Blender script 3D preview render Video showcase URL Rendering metadata

How it works A complete AI-powered study assistant system that lets you chat naturally with your documents stored in Google Drive: The system has two connected workflows: Document Indexing Pipeline (Sub-workflow): • Accepts Google Drive folder URLs • Automatically fetches all files from the folder • Converts documents to plain text • Generates 768-dimensional embeddings using Google Gemini • Stores everything in Supabase vector database for semantic search Study Chat Agent (Main workflow): • Provides a conversational chat interface • Automatically detects and processes Google Drive links shared in chat • Searches your indexed documents using semantic similarity • Maintains conversation history across sessions • Includes calculator for math problems • Responds naturally using Google Gemini 2.5 Pro Use Cases: Students studying for exams, researchers managing papers, professionals building knowledge bases, anyone needing to query large document collections conversationally. Set up steps Prerequisites: • Google Drive OAuth2 credentials • Google Gemini API key (free tier available) • Supabase account with Postgres connection • ~15 minutes setup time Complete Setup: Part 1: Document Indexing Workflow Add Google Drive OAuth2 credentials to the Drive nodes Configure Supabase Postgres credentials in the SQL node Add Supabase API credentials to the Vector Store node Add Google Gemini API key to the Embeddings node Part 2: Study Agent Workflow Import the Study Agent workflow Verify the "Folder all file to vector" tool links to the indexing workflow Add Google Gemini API credentials to both Gemini nodes Configure Supabase API credentials in the Vector Store node Add Postgres credentials for Chat Memory Deploy and access the chat via webhook URL How to Use: Open the chat interface (webhook URL) Paste a Google Drive folder link in the chat Wait for indexing to complete (~1-2 minutes) Start asking questions about your documents The AI will search and answer from your materials Note: The indexing workflow runs automatically when you share Drive links in chat, or you can run it manually to pre-load documents. System Components: Main Agent:** Gemini 2.5 Pro with conversational AI Vector Search:** Supabase with pgvector (768-dim embeddings) Memory:** Postgres chat history (10-message context window) Tools:** Document retrieval, Drive indexing, calculator Embedding Model:** Google Gemini text-embedding-004

This template creates a comprehensive, production-ready Retrieval-Augmented Generation (RAG) system. It builds a sophisticated AI agent that can answer questions based on documents stored in a specific Google Drive folder, and it automatically keeps its knowledge base up-to-date as you add, update, or remove files. Who’s it for? This workflow is perfect for developers, businesses, and AI agencies looking to: Create an internal knowledge base chatbot for employees (e.g., for HR policies, technical documentation, or project information). Build an intelligent support agent that uses your company's official documents as its source of truth. Develop advanced AI solutions for clients that require a self-maintaining knowledge base. How it works? This workflow is divided into three distinct, powerful systems: The RAG Agent: This is the core chatbot. It receives a user's question, uses a Supabase Vector Store to find the most relevant document snippets, leverages a Cohere Reranker to improve accuracy, and uses a Postgres database to maintain conversation history (memory). It then uses Google Gemini to generate a final, context-aware answer. The Ingestion Pipeline: This system automates the process of learning new information. It triggers whenever a file is created or updated in your designated Google Drive folder. It intelligently detects the file type (Google Doc or PDF), extracts the text, splits it into manageable chunks, generates embeddings using Gemini, and stores them in your Supabase vector database. The Cleanup System: To ensure your knowledge base remains accurate, a scheduled process runs periodically to find and remove data from Supabase that corresponds to files that have been deleted from the Google Drive folder. This prevents the agent from using outdated information. How to set up To get this workflow running, you will need to configure the following: Credentials: Connect your accounts in the n8n credential manager for: Google Drive (OAuth2) Supabase (API Key) Postgres Google Gemini (API Key from Google AI Studio) Cohere (API Key) Google Drive Folder: In the Search files and folders node, replace the placeholder folder ID with the ID of the Google Drive folder you want to monitor. Database Setup: Ensure your Supabase and Postgres instances are set up with the necessary tables. You'll need a documents table in Supabase for the vectors and a document_metadata table in Postgres. How to customize the workflow This template is a powerful starting point. You can easily customize it by: Swapping out the LLM (e.g., use OpenAI or Anthropic instead of Gemini). Changing the vector database (e.g., Pinecone, Weaviate). Adding more data sources, such as Notion, Slack, or websites.

URL Officer - Respect robots.txt and Avoid Undesirable Sources 🎬 Overview Version : 1.0 The URL Officer workflow automates the filtering of URLs by checking them against a database of forbidden sources and the rules defined in robots.txt files. It proactively respects robot exclusion protocols and user-defined banned sources to aid in lawful and ethical web automation. Designed primarily as a sub-workflow, it serves automation pipelines with robust URL validation to avoid undesirable or restricted sources. ✨ Features Dual-layer URL Filtering**: Checks URLs against a manually maintained forbidden sources list and robots.txt restrictions. Automated robots.txt Retrieval & Update**: Automatically fetches and updates robots.txt content for new or outdated sources (older than 3 days). AI-backed robots.txt Interpretation**: Uses AI models to interpret robots.txt comments and restrictions, ensuring nuanced compliance. Configurable User-Agent Identification**: Allows customization of User-Agent strings that are checked against robots.txt directives. Sub-Workflow Ready**: Easily integrates as a sub-workflow for link validation in larger automation pipelines. Multi-Model AI Support**: Supports mistral, groq, and gemini AI models for enhanced robots.txt compliance checks. Detailed Diagnostic Outputs**: Returns comprehensive link allowance statuses and metadata for use in downstream processing. Database Integration**: Utilizes PostgreSQL to store and manage robots.txt content and banned source lists. 👤 Who is this for? Ideal for developers, data engineers, researchers, or businesses implementing web crawlers, scrapers, or any automation that processes URLs. This workflow helps your compliance with source restrictions and avoids content from blacklisted sites, reducing legal exposure and promoting ethical data use. 💡 What problem does this solve? URL Officer addresses the challenge of automating URL validation by combining manual blacklist filtering with automated and AI-assisted robots.txt parsing. It prevents accidental scraping or processing from undesirable or disallowed sources, helping automate respect for webmasters' policies and legal boundaries. 🔍 What this workflow does When given a URL, the workflow: Extracts the base URL. Checks the URL against a manually configured banned sources list (stored in database). Fetches robots.txt for new or stale sources (older than 3 days). Performs a programmatic parse and check of robots.txt directives against the URL using the specified User-Agent. Runs an AI model to analyze robots.txt content and confirm if the URL is allowed, taking into account any special comments or prohibitions relevant to the automation goal. Returns a final "allow or disallow" determination for both the URL and its base URL, along with metadata about the robots.txt fetch status and timing. 🔄 Workflow Steps Input Parsing & Base URL Extraction Accepts workflow arguments including the URL, User-Agent information, automation goal, and AI model choice. Extracts and normalizes the base URL for processing. Forbidden Source Check Queries PostgreSQL tables containing banned sources. Immediately rejects URLs matching forbidden sources. robots.txt Handling Checks if robots.txt content for the source is in the database and is recent (under 3 days old). If missing or outdated, fetches the robots.txt file from the base URL and updates the database. Code-Based robots.txt Analysis Parses robots.txt directives, matching the User-Agent to appropriate groups. Checks if the URL and base URL paths are allowed according to the parsed rules. Uses a conservative URL and agent matching algorithm for prefix-based allow/disallow checks. AI-Based robots.txt Verification Uses the selected AI model (mistral, groq, or gemini) to analyze robots.txt content and comments regarding allowed automation use. Applies AI understanding to confirm or override automated code checks based on the automation's goal. Output Preparation Produces output indicating permission statuses (allow_link and allow_baseUrl), original URLs, User-Agent info, fetch timestamps, and whether robots.txt was successfully retrieved. Designed to be consumed by other workflows as a validation step. 🔀 Expected Input / Configuration The workflow is configured primarily via workflow input arguments: | Parameter | Description | Type | |-------------------|---------------------------------------------------------------------------------------------------|---------| | link | The URL to be checked. | String | | userAgent | User-Agent string representing your automation, used for robots.txt checks. | String | | userAgent_extra | Additional User-Agent information such as version or contact info. | String | | automationGoal | Description of your automation’s purpose, used by the AI to verify suitability against robots.txt. | String | | model | AI model to use for the robots.txt compliance check. Options: mistral, groq, gemini. | String | Database Requirements PostgreSQL database configured with credentials accessible to the workflow. Two tables: one for banned sources (manually maintained) and one for robots.txt content with timestamps. The workflow auto-creates and manages these tables. Recommended to use a containerized PostgreSQL instance (Podman or Docker). 📦 Expected Output A structured JSON object containing: | Output Key | Description | |-----------------|-----------------------------------------------------------------| | link | The URL that was checked. | | baseUrl | The base URL of the checked link. | | allow_link | Boolean indicating if the link is allowed according to checks.| | allow_baseUrl | Boolean indicating if the base URL is allowed. | | userAgent | User-Agent string used in the check. | | userAgent_extra| Additional User-Agent metadata. | | robots_fetched| Boolean, true if robots.txt content was successfully fetched. | | fetched_at | Timestamp of the last robots.txt content fetch. | 📌 Example Example input payload: ⚙️ n8n Setup Used n8n version:** 1.108.2 Platform:** Podman 4.3.1 on Linux PostgreSQL:** Running in Podman 4.3.1 container LLM Models:** mistral-small-latest, llama-3.1-8b-instant (Groq), gemini-2.5-flash Date:** 2025-08-29 ⚡ Requirements to Use / Setup Self-hosted or cloud n8n instance with database connectivity. PostgreSQL database configured and accessible by n8n. Setup PostgreSQL using the recommended containerized deployment or your preferred method. Configure database credentials inside the workflow. Provide API credentials for your chosen AI model (mistral, groq, gemini). Manually maintain the banned sources list in the database. Familiarity with n8n variables and sub-workflow integration is recommended. Internet connectivity for fetching robots.txt files. ⚠️ Notes, Assumptions & Warnings Database tables used by this workflow are automatically created and managed by the workflow. robots.txt refresh interval is set to every 3 days; this can be adjusted by modifying the workflow. The robots.txt parser is relatively simple and does not support wildcard (*) or end-of-string ($) rules. User-Agent matching is substring-based and longer string matches take precedence. AI analysis adds a human-like understanding of robots.txt comments and prohibitions but depends on the quality and capability of the chosen AI model. This workflow does NOT handle: Terms of Service compliance. Preference for official APIs over HTML scraping. Rate-limiting or request throttling. Handling paywalled or restricted content. De-duplication or filtering beyond the banned sources list. Encryption or secure storage. You remain responsible for ensuring your automation complies with legal, ethical, and platform-specific rules. The workflow is designed as a sub-workflow; integrate it into larger automation processes to validate URLs. 🛠 PostgreSQL Setup Instructions (Self-Hosted Route) Available inside the Workflow Notes, alongside podman commands. ℹ️ About Us This workflow was developed by the Hybroht team. Our goal is to create tools that harness the possibilities of technology and more. We aim to continuously improve and expand functionalities based on community feedback and evolving use cases. For questions, support, or feedback, please contact us at: [email protected] ⚖️ Warranty & Legal Notice This workflow is provided "as-is" without warranties of any kind. By using this workflow, you agree that you are responsible for complying with all applicable laws, regulations, and terms of service related to your data sources and automations. Please review all relevant legal terms and use this workflow responsibly. Hybroht disclaims any liability arising from use or misuse of this workflow. This tool assists with robots.txt compliance but is not a substitute for full legal or compliance advice. You can view the full license terms here. Please review them before making your purchase. By purchasing this product, you agree to these terms.