Integrate Embeddings OpenAI in your LLM apps and 422+ apps and services

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.

This workflow allows you to ask questions about a PDF document. The answers are provided by an AI model of your choice, and the answer includes a citation pointing to the information it used. You can use n8n’s built-in chat interface to ask the questions, or you could customise this workflow to use another one (e.g. Slack, Teams, etc.) Example The workflow is set up with the Bitcoin whitepaper. So you could ask things like: Question: “Which email provider does the creator of Bitcoin use?“ Answer: “GMX [Bitcoin whitepaper.pdf, lines 1-35]” Requirements A Pinecone account (they have a free tier at the time of writing that is easily enough for this workflow) Access to a large language model (e.g. an OpenAI account) Customizing this workflow The workflow only reads in one document, but you could customise it to read in all the documents in a folder (or more). The workflow is set up to use GPT 3.5, but you could swap that out for any other model (including self-hosted ones).

This is a demo workflow to showcase how to use Supabase to embed a document, retrieve information from the vector store via chat and update the database. Setup steps: set your credentials for Supabase set your credentials for an AI model of your choice set credentials for any service you want to use to upload documents please follow the guidelines in the workflow itself (Sticky Notes) Feedback & Questions If you have any questions or feedback about this workflow - Feel free to get in touch at ria@n8n.io

This n8n template builds a simple WhatsApp chabot acting as a Sales Agent. The Agent is backed by a product catalog vector store to better answer user's questions. This template is intended to help introduce n8n users interested in building with WhatsApp. How it works This template is in 2 parts: creating the product catalog vector store and building the WhatsApp AI chatbot. A product brochure is imported via HTTP request node and its text contents extracted. The text contents are then uploaded to the in-memory vector store to build a knowledgebase for the chatbot. A WhatsApp trigger is used to capture messages from customers where non-text messages are filtered out. The customer's message is sent to the AI Agent which queries the product catalogue using the vector store tool. The Agent's response is sent back to the user via the WhatsApp node. How to use Once you've setup and configured your WhatsApp account and credentials First, populate the vector store by clicking the "Test Workflow" button. Next, activate the workflow to enable the WhatsApp chatbot. Message your designated WhatsApp number and you should receive a message from the AI sales agent. Tweak datasource and behaviour as required. Requirements WhatsApp Business Account OpenAI for LLM Customising this workflow Upgrade the vector store to Qdrant for persistance and production use-cases. Handle different WhatsApp message types for a more rich and engaging experience for customers.

Are you a popular tech startup accelerator (named after a particular higher order function) overwhelmed with 1000s of pitch decks on a daily basis? Wish you could filter through them quickly using AI but the decks are unparseable through conventional means? Then you're in luck! This n8n template uses Multimodal LLMs to parse and extract valuable data from even the most overly designed pitch decks in quick fashion. Not only that, it'll also create the foundations of a RAG chatbot at the end so you or your colleagues can drill down into the details if needed. With this template, you'll scale your capacity to find interesting companies you'd otherwise miss! Requires n8n v1.62.1+ How It Works Airtable is used as the pitch deck database and PDF decks are downloaded from it. An AI Vision model is used to transcribe each page of the pitch deck into markdown. An Information Extractor is used to generate a report from the transcribed markdown and update required information back into pitch deck database. The transcribed markdown is also uploaded to a vector store to build an AI chatbot which can be used to ask questions on the pitch deck. Check out the sample Airtable here: https://airtable.com/appCkqc2jc3MoVqDO/shrS21vGqlnqzzNUc How To Use This template depends on the availability of the Airtable - make a duplicate of the airtable (link) and its columns before running the workflow. When a new pitchdeck is received, enter the company name into the Name column and upload the pdf into the File column. Leave all other columns blank. If you have the Airtable trigger active, the execution should start immediately once the file is uploaded. Otherwise, click the manual test trigger to start the workflow. When manually triggered, all "new" pitch decks will be handled by the workflow as separate executions. Requirements OpenAI for LLM Airtable For Database and Interface Qdrant for Vector Store Customising This Workflow Extend this starter template by adding more AI agents to validate claims made in the pitch deck eg. Linkedin Profiles, Page visits, Reviews etc.

This n8n template demonstrates an approach to image embeddings for purpose of building a quick image contextual search. Use-cases could for a personal photo library, product recommendations or searching through video footage. How it works A photo is imported into the workflow via Google Drive. The photo is processed by the edit image node to extract colour information. This information forms part of our semantic metadata used to identify the image. The photo is also processed by a vision-capable model which analyses the image and returns a short description with semantic keywords. Both pieces of information about the image are combined with the metadata of the image to form a document describing the image. This document is then inserted into our vector store as a text embedding which is associated with our image. From here, the user can query the vector store as they would any document and the relevant image references and/or links should be returned. Requirements Google account to download image files from Google Drive. OpenAI account for the Vision-capable AI and Embedding models. Customise this workflow Text summarisation is just one of many techniques to generate image embeddings. If the results are unsatisfactory, there are dedicated image embedding models such as Google's vertex AI multimodal embeddings.