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

What this template does This template serves as a Chatbot that enables you to ask questions about the content of a PDF directly in Telegream. It checks incoming Telegram messages if they contain a document. If they do, it stores the PDF in a Pinecone Vector store. If there's no document, it will search the Vector Store for information and try to answer your question. Setup Open the Telegram app and search for the BotFather user (@BotFather) Start a chat with the BotFather Type /newbot to create a new bot Follow the prompts to name your bot and get a unique API token Save your access token and username Once you set your bot, you can send the pdf, and then ask questions about the content. How to adjust it to your needs You can exchange the Groq chat model with any model that you like Exchange Pinecone with any other vector store tool you like (e.g. Supabase, Postgres or QDrant) #Telegram, #Pinecone, #Openai, #GroQ

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 [email protected]

Video Guide I prepared a detailed guide explaining how to set up and implement this scenario, enabling you to chat with your documents stored in Supabase using n8n. Youtube Link Who is this for? This workflow is ideal for researchers, analysts, business owners, or anyone managing a large collection of documents. It's particularly beneficial for those who need quick contextual information retrieval from text-heavy files stored in Supabase, without needing additional services like Google Drive. What problem does this workflow solve? Manually retrieving and analyzing specific information from large document repositories is time-consuming and inefficient. This workflow automates the process by vectorizing documents and enabling AI-powered interactions, making it easy to query and retrieve context-based information from uploaded files. What this workflow does The workflow integrates Supabase with an AI-powered chatbot to process, store, and query text and PDF files. The steps include: Fetching and comparing files to avoid duplicate processing. Handling file downloads and extracting content based on the file type. Converting documents into vectorized data for contextual information retrieval. Storing and querying vectorized data from a Supabase vector store. File Extraction and Processing: Automates handling of multiple file formats (e.g., PDFs, text files), and extracts document content. Vectorized Embeddings Creation: Generates embeddings for processed data to enable AI-driven interactions. Dynamic Data Querying: Allows users to query their document repository conversationally using a chatbot. Setup N8N Workflow Fetch File List from Supabase: Use Supabase to retrieve the stored file list from a specified bucket. Add logic to manage empty folder placeholders returned by Supabase, avoiding incorrect processing. Compare and Filter Files: Aggregate the files retrieved from storage and compare them to the existing list in the Supabase files table. Exclude duplicates and skip placeholder files to ensure only unprocessed files are handled. Handle File Downloads: Download new files using detailed storage configurations for public/private access. Adjust the storage settings and GET requests to match your Supabase setup. File Type Processing: Use a Switch node to target specific file types (e.g., PDFs or text files). Employ relevant tools to process the content: For PDFs, extract embedded content. For text files, directly process the text data. Content Chunking: Break large text data into smaller chunks using the Text Splitter node. Define chunk size (default: 500 tokens) and overlap to retain necessary context across chunks. Vector Embedding Creation: Generate vectorized embeddings for the processed content using OpenAI's embedding tools. Ensure metadata, such as file ID, is included for easy data retrieval. Store Vectorized Data: Save the vectorized information into a dedicated Supabase vector store. Use the default schema and table provided by Supabase for seamless setup. AI Chatbot Integration: Add a chatbot node to handle user input and retrieve relevant document chunks. Use metadata like file ID for targeted queries, especially when multiple documents are involved. Testing Upload sample files to your Supabase bucket. Verify if files are processed and stored successfully in the vector store. Ask simple conversational questions about your documents using the chatbot (e.g., "What does Chapter 1 say about the Roman Empire?"). Test for accuracy and contextual relevance of retrieved results.

The workflow first populates a Pinecone index with vectors from a Bitcoin whitepaper. Then, it waits for a manual chat message. When received, the chat message is turned into a vector and compared to the vectors in Pinecone. The most similar vectors are retrieved and passed to OpenAI for generating a chat response. Note that to use this template, you need to be on n8n version 1.19.4 or later.

This n8n template is one of a 3-part series exploring use-cases for clustering vector embeddings: Survey Insights Customer Insights Community Insights This template demonstrates the Customer Insights scenario where Trustpilot reviews can be quickly grouped by similarity and an AI agent can generate insights on those groupings. With this workflow, marketers can save days and even weeks of work breaking down their own or competitor reviews and identify frequently mentioned positives and negatives. Sample Output: https://docs.google.com/spreadsheets/d/e/2PACX-1vQ6ipJnXWXgr5wlUJnhioNpeYrxaIpsRYZCwN3C-fFXumkbh9TAsA_JzE0kbv7DcGAVIP7az0L46_2P/pubhtml How it works Trustpilot reviews are scraped for a particular company using the HTTP request node. Reviews are then inserted into a Qdrant collection carefully tagged with the question and Trustpilot metadata. Reviews are fetched and put through a clustering algorithm using the Python Code node. The Qdrant points are returned in clustered groups. Each group is looped to fetch the payloads of the points and feed them to the AI agent to summarise and generate insights for. The resulting insights and raw responses are then saved to the Google Spreadsheet for further analysis by the marketer. Requirements Qdrant Vectorstore for storing embeddings. OpenAI account for embeddings and LLM. Customising the Template Adjust clustering parameters which make sense for your data. Consider expanding date range of reviews for insights over common intervals: 3mth, 6mth and YTD.

This workflow was presented at the AI Developers meet up in San Fransico on 24 July, 2024. AI workflows Categorize incoming Gmail emails and assign custom Gmail labels. This example uses the Text Classifier node, simplifying this usecase. Ingest a PDF into a Pinecone vector store and chat with it (RAG example) AI Agent example showcasing the HTTP Request tool. We teach the agent how to check availability on a Google Calendar and book an appointment.

Purpose This workflow adds the capability to build a RAG on living data. In this case Notion is used as a Knowledge Base. Whenever a page is updated, the embeddings get upserted in a Supabase Vector Store. It can also be fairly easily adapted to PGVector, Pinecone, or Qdrant by using a custom HTTP request for the latter two. Demo How it works A trigger checks every minute for changes in the Notion Database. The manual polling approach improves accuracy and prevents changes from being lost between cached polling intervals. Afterwards every updated page is processed sequentially The Vector Database is searched using the Notion Page ID stored in the metadata of each embedding. If old entries exist, they are deleted. All blocks of the Notion Database Page are retrieved and combined into a single string The content is embedded and split into chunks if necessary. Metadata, including the Notion Page ID, is added during storage for future reference. A simple Question and Answer Chain enables users to ask questions about the embedded content through the integrated chat function Prerequisites To setup a new Vector Store in Supabase, follow this guide Prepare a simple Database in Notion with each Database Page containing at least a title and some content in the blocks section. You can of course also connect this to an existing Database of your choice. Setup Select your credentials in the nodes which require those If you are on an n8n cloud plan, switch to the native Notion Trigger by activating it and deactivating the Schedule Trigger along with its subsequent Notion Node Choose your Notion Database in the first Node related to Notion Adjust the chunk size and overlap in the Token Splitter to your preference Activate the workflow How to use Populate your Notion Database with useful information and use the chat mode of this workflow to ask questions about it. Updates to a Notion Page should quickly reflect in future conversations.

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.

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 n8n template is one of a 3-part series exploring use-cases for clustering vector embeddings: Survey Insights Customer Insights Community Insights This template demonstrates the Community Insights scenario where HN commments can be quickly grouped by similarity and an AI agent can generate insights on those groupings. With this workflow, Researchers or HN users can quickly breakdown community consensus on a particular topic and identify frequently mentioned positives and negatives. Sample Output: https://docs.google.com/spreadsheets/d/e/2PACX-1vQXaQU9XxsxnUIIeqmmf1PuYRuYtwviVXTv6Mz9Vo6_a4ty-XaJHSeZsptjWXS3wGGDG8Z4u16rvE7l/pubhtml How it works HN comments are imported via the Hacknews API node. Comments are then inserted into a Qdrant collection carefully tagged with the Hackernews API metadata. Comments are then fetched and are put through a clustering algorithm using the Python Code node. The Qdrant points are returned in clustered groups. Each group is looped to fetch the payloads of the points and feed them to the AI agent to summarise and generate insights for. The resulting insights and raw responses are then saved to the Google Spreadsheet for further analysis by the researcher or the HN user. Requirements Works best with lots of comments! Qdrant Vectorstore for storing embeddings. OpenAI account for embeddings and LLM. Customising the Template Adjust clustering parameters which make sense for your data. Adjust sentimentality setting if comments are overwhelmingly negative at times.

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.