HTTP Request and Postgres integration

This is the first version of a template for a RAG/GenAI App using WordPress content. As creating, sharing, and improving templates brings me joy 😄, feel free to reach out on LinkedIn if you have any ideas to enhance this template! How It Works This template includes three workflows: Workflow 1**: Generate embeddings for your WordPress posts and pages, then store them in the Supabase vector store. Workflow 2**: Handle upserts for WordPress content when edits are made. Workflow 3**: Enable chat functionality by performing Retrieval-Augmented Generation (RAG) on the embedded documents. Why use this template? This template can be applied to various use cases: Build a GenAI application that requires embedded documents from your website's content. Embed or create a chatbot page on your website to enhance user experience as visitors search for information. Gain insights into the types of questions visitors are asking on your website. Simplify content management by asking the AI for related content ideas or checking if similar content already exists. Useful for internal linking. Prerequisites Access to Supabase for storing embeddings. Basic knowledge of Postgres and pgvector. A WordPress website with content to be embedded. An OpenAI API key Ensure that your n8n workflow, Supabase instance, and WordPress website are set to the same timezone (or use GMT) for consistency. Workflow 1 : Initial Embedding This workflow retrieves your WordPress pages and posts, generates embeddings from the content, and stores them in Supabase using pgvector. Step 0 : Create Supabase tables Nodes : Postgres - Create Documents Table: This table is structured to support OpenAI embedding models with 1536 dimensions Postgres - Create Workflow Execution History Table These two nodes create tables in Supabase: The documents table, which stores embeddings of your website content. The n8n_website_embedding_histories table, which logs workflow executions for efficient management of upserts. This table tracks the workflow execution ID and execution timestamp. Step 1 : Retrieve and Merge WordPress Pages and Posts Nodes : WordPress - Get All Posts WordPress - Get All Pages Merge WordPress Posts and Pages These three nodes retrieve all content and metadata from your posts and pages and merge them. Important: * *Apply filters to avoid generating embeddings for all site content. Step 2 : Set Fields, Apply Filter, and Transform HTML to Markdown Nodes : Set Fields Filter - Only Published & Unprotected Content HTML to Markdown These three nodes prepare the content for embedding by: Setting up the necessary fields for content embeddings and document metadata. Filtering to include only published and unprotected content (protected=false), ensuring private or unpublished content is excluded from your GenAI application. Converting HTML to Markdown, which enhances performance and relevance in Retrieval-Augmented Generation (RAG) by optimizing document embeddings. Step 3: Generate Embeddings, Store Documents in Supabase, and Log Workflow Execution Nodes: Supabase Vector Store Sub-nodes: Embeddings OpenAI Default Data Loader Token Splitter Aggregate Supabase - Store Workflow Execution This step involves generating embeddings for the content and storing it in Supabase, followed by logging the workflow execution details. Generate Embeddings: The Embeddings OpenAI node generates vector embeddings for the content. Load Data: The Default Data Loader prepares the content for embedding storage. The metadata stored includes the content title, publication date, modification date, URL, and ID, which is essential for managing upserts. ⚠️ Important Note : Be cautious not to store any sensitive information in metadata fields, as this information will be accessible to the AI and may appear in user-facing answers. Token Management: The Token Splitter ensures that content is segmented into manageable sizes to comply with token limits. Aggregate: Ensure the last node is run only for 1 item. Store Execution Details: The Supabase - Store Workflow Execution node saves the workflow execution ID and timestamp, enabling tracking of when each content update was processed. This setup ensures that content embeddings are stored in Supabase for use in downstream applications, while workflow execution details are logged for consistency and version tracking. This workflow should be executed only once for the initial embedding. Workflow 2, described below, will handle all future upserts, ensuring that new or updated content is embedded as needed. Workflow 2: Handle document upserts Content on a website follows a lifecycle—it may be updated, new content might be added, or, at times, content may be deleted. In this first version of the template, the upsert workflow manages: Newly added content** Updated content** Step 1: Retrieve WordPress Content with Regular CRON Nodes: CRON - Every 30 Seconds Postgres - Get Last Workflow Execution WordPress - Get Posts Modified After Last Workflow Execution WordPress - Get Pages Modified After Last Workflow Execution Merge Retrieved WordPress Posts and Pages A CRON job (set to run every 30 seconds in this template, but you can adjust it as needed) initiates the workflow. A Postgres SQL query on the n8n_website_embedding_histories table retrieves the timestamp of the latest workflow execution. Next, the HTTP nodes use the WordPress API (update the example URL in the template with your own website’s URL and add your WordPress credentials) to request all posts and pages modified after the last workflow execution date. This process captures both newly added and recently updated content. The retrieved content is then merged for further processing. Step 2 : Set fields, use filter Nodes : Set fields2 Filter - Only published and unprotected content The same that Step 2 in Workflow 1, except that HTML To Makrdown is used in further Step. Step 3: Loop Over Items to Identify and Route Updated vs. Newly Added Content Here, I initially aimed to use 'update documents' instead of the delete + insert approach, but encountered challenges, especially with updating both content and metadata columns together. Any help or suggestions are welcome! :) Nodes: Loop Over Items Postgres - Filter on Existing Documents Switch Route existing_documents (if documents with matching IDs are found in metadata): Supabase - Delete Row if Document Exists: Removes any existing entry for the document, preparing for an update. Aggregate2: Used to aggregate documents on Supabase with ID to ensure that Set Fields3 is executed only once for each WordPress content to avoid duplicate execution. Set Fields3: Sets fields required for embedding updates. Route new_documents (if no matching documents are found with IDs in metadata): Set Fields4: Configures fields for embedding newly added content. In this step, a loop processes each item, directing it based on whether the document already exists. The Aggregate2 node acts as a control to ensure Set Fields3 runs only once per WordPress content, effectively avoiding duplicate execution and optimizing the update process. Step 4 : HTML to Markdown, Supabase Vector Store, Update Workflow Execution Table The HTML to Markdown node mirrors Workflow 1 - Step 2. Refer to that section for a detailed explanation on how HTML content is converted to Markdown for improved embedding performance and relevance. Following this, the content is stored in the Supabase vector store to manage embeddings efficiently. Lastly, the workflow execution table is updated. These nodes mirros the **Workflow 1 - Step 3 nodes. Workflow 3 : An example of GenAI App with Wordpress Content : Chatbot to be embed on your website Step 1: Retrieve Supabase Documents, Aggregate, and Set Fields After a Chat Input Nodes: When Chat Message Received Supabase - Retrieve Documents from Chat Input Embeddings OpenAI1 Aggregate Documents Set Fields When a user sends a message to the chat, the prompt (user question) is sent to the Supabase vector store retriever. The RPC function match_documents (created in Workflow 1 - Step 0) retrieves documents relevant to the user’s question, enabling a more accurate and relevant response. In this step: The Supabase vector store retriever fetches documents that match the user’s question, including metadata. The Aggregate Documents node consolidates the retrieved data. Finally, Set Fields organizes the data to create a more readable input for the AI agent. Directly using the AI agent without these nodes would prevent metadata from being sent to the language model (LLM), but metadata is essential for enhancing the context and accuracy of the AI’s response. By including metadata, the AI’s answers can reference relevant document details, making the interaction more informative. Step 2: Call AI Agent, Respond to User, and Store Chat Conversation History Nodes: AI Agent** Sub-nodes: OpenAI Chat Model Postgres Chat Memories Respond to Webhook** This step involves calling the AI agent to generate an answer, responding to the user, and storing the conversation history. The model used is gpt4-o-mini, chosen for its cost-efficiency.

*Smartlead to HubSpot Performance Analytics A streamlined workflow to analyze your Smartlead performance metrics by tracking lifecycle stages in HubSpot and generating automated reports.* Who is this for? (Outbound) Automation Agencies, Sales and marketing teams using Smartlead for outreach campaigns who want to track their performance metrics and lead progression in HubSpot. What problem does this workflow solve? Manual tracking of lead performance across Smartlead and HubSpot is time-consuming and error-prone. This workflow automates performance reporting by connecting your Smartlead data with HubSpot lifecycle stages, providing clear insights into your outreach campaign effectiveness. What this workflow does Automatically pulls performance data from your Smartlead campaigns Cross-references contact status with HubSpot lifecycle stages Generates comprehensive performance reports in Google Sheets Provides customizable reporting schedules to match your team's needs Setup Requirements PostgreSQL Database Set up your PostgreSQL instance (includes $300 free GCP credits) Follow our step-by-step setup guide: Find a step-by-step guide here Google Account Integration Connect your Google Account to n8n Find the guide here Smartlead Configuration Connect your Smartlead instance: Detailed connection guide included in workflow How to customize this workflow Configure the Trigger node to adjust report frequency Modify the Google Sheets template to match your specific KPIs Customize HubSpot lifecycle stage mapping in the Function node Adjust PostgreSQL queries to track additional metrics Need assistance or have suggestions? lmk here

Use case Slackbots are super powerful. At n8n, we have been using them to get a lot done.. But it can become hard to manage and maintain many different operations that a workflow can do. This is the base workflow we use for our most powerful internal Slackbots. They handle a lot from running e2e tests for Github branch to deleting a user. By splitting the workflow into many subworkflows, we are able to handle each command seperately, making it easier to debug as well as support new usecases. In this template, you can find eveything to setup your own Slackbot (and I made it simple, there's only one node to configure 😉). After that, you need to build your commands directly. This bot can create a new thread on an alerts channel and respond there. Or reply directly to the user. It responds for help request to return a help page. It automatically handles unknown commands. It also supports flags and environment variables. For example /cloudbot-test info mutasem --full-info -e env=prod would give you the following info, when calling subworkflow. How to setup Add Slack command and point it up to the webhook. For example. Add the following to the Set config node alerts_channel with alerts channel to start threads on instance_url with this instance url to make it easy to debug slack_token with slack bot token to validate request slack_secret_signature with slack secret signature to validate request help_docs_url with help url to help users understand the commands Build other workflows to call and add them to commands in Set Config. Each command must be mapped to a workflow id with an Execute Workflow Trigger node Activate workflow 🚀 How to adjust Add your own commands. Depending on your need, you might need to lock down who can call this.

The template allows to make Dropcontact batch requests up to 250 requests every 10 minutes (1500/hour). Valuable if high volume email enrichment is expected. Dropcontact will look for email & basic email qualification if first_name, last_name, company_name is provided. +++++++++++++++++++++++++++++++++++++++++ Step 1: Node "Profiles Query" Connect your own source (Airtable, Google Sheets, Supabase,...) the template is using Postgres by default. Note I: Be careful your source is only returning a maximum of 250 items. Note II: The next node uses the next variables, make sure you can map these from your source file: first_name last_name website (company_name would work too) full_name (see note) Note III: This template is using the Dropcontact Batch API, which works in a POST & GET setup. Not a GET request only to retrieve data, as Dropcontact needs to process the batch data load properly. +++++++++++++++++++++++++++++++++++++++++ Step 2: Node "Data Transformation" Will transform the input variables in the proper json format. This json format is expected from the Dropcontact API to make a batch request. "full_name" is being used as a custom identifier to update the returned email to the proper contact in your source database. To make things easy, use a unique identiefer in the full_name variable. +++++++++++++++++++++++++++++++++++++++++ Step3: Node: "Bulk Dropcontact Requests". Enter your Dropcontact credentials in the node: Bulk Dropcontact Requests. +++++++++++++++++++++++++++++++++++++++++ Step4: Connect your output source by mapping the data you like to use. +++++++++++++++++++++++++++++++++++++++++ Step5: Node: "Slack" (OPTIONAL) Connect your slack account, if an error occur, you will be notified. TIP: Try to run the workflow with a batch of 10 (not 250) as it might need to run initially before you will be able to map the data to your final destination. Once the data fields are properly mapped, adjust back to 250.

This n8n workflow is designed for security monitoring and incident response when suspicious login events are detected. It can be initiated either manually from within the n8n UI for testing or automatically triggered by a webhook when a new login event occurs. The workflow first extracts relevant data from the incoming webhook payload, including the IP address, user agent, timestamp, URL, and user ID. It then splits into three parallel processing paths. In the first path, it queries GreyNoise's Community API to retrieve information about the investigated IP address. Depending on the classification and trust level received from GreyNoise, the alert is given a High, Medium, or Low priority. This priority is assigned based on the best practices documentation from GreyNoise on how to apply their data to analysis. Once a priority is assigned, a message is sent to a Slack channel to notify users about the alert. The second path involves fetching geolocation data about the IP address using IP-API's Geolocation API and merging it with data from the UserParser node. This data is then combined with the data obtained from GreyNoise. In the third path, the UserParser node queries the Userparser IP address and user agent lookup API to obtain information about the user's IP and user agent. This data is merged with the IP-API data and GreyNoise data. The workflow then checks if the IP address is considered an unknown threat by examining both the noise and riot fields from GreyNoise. If it is considered an unknown threat, the workflow proceeds to retrieve the last 10 login records for the same user from a Postgres database. If there are any discrepancies in the login information, indicating a new location or device/browser, the user is informed via email. Potential issues when setting up this workflow include ensuring that credentials are correctly entered for GreyNoise and UserParser nodes, and addressing any discrepancies in the data sources that could lead to false positives or negatives in threat detection. Additionally, the usage of hardcoded API keys should be replaced with credentials for security and flexibility. Thorough testing and validation with sample data are crucial to ensure the workflow performs as expected and aligns with security incident response procedures.

query data from two different databases handle and unify in a single return