HTTP Request and Supabase integration

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.

Video Guide I prepared a detailed guide explaining how to build an AI-powered meeting assistant that provides real-time transcription and insights during virtual meetings. Youtube Link Who is this for? This workflow is ideal for business professionals, project managers, and team leaders who require effective transcription of meetings for improved documentation and note-taking. It's particularly beneficial for those who conduct frequent virtual meetings across various platforms like Zoom and Google Meet. What problem does this workflow solve? Transcribing meetings manually can be tedious and prone to error. This workflow automates the transcription process in real-time, ensuring that key discussions and decisions are accurately captured and easily accessible for later review, thus enhancing productivity and clarity in communications. What this workflow does The workflow employs an AI-powered assistant to join virtual meetings and capture discussions through real-time transcription. Key functionalities include: Automatic joining of meetings on platforms like Zoom, Google Meet, and others with the ability to provide real-time transcription. Integration with transcription APIs (e.g., AssemblyAI) to deliver seamless and accurate capture of dialogue. Structuring and storing transcriptions efficiently in a database for easy retrieval and analysis. Real-Time Transcription: The assistant captures audio during meetings and transcribes it in real-time, allowing participants to focus on discussions. Keyword Recognition: Key phrases can trigger specific actions, such as noting important points or making prompts to the assistant. Structured Data Management: The assistant maintains a database of transcriptions linked to meeting details for organized storage and quick access later. Setup Preparation Create Recall.ai API key Setup Supabase account and table create table public.data ( id uuid not null default gen_random_uuid (), date_created timestamp with time zone not null default (now() at time zone 'utc'::text), input jsonb null, output jsonb null, constraint data_pkey primary key (id), ) tablespace pg_default; Create OpenAI API key Development Bot Creation: Use a node to create the bot that will join meetings. Provide the meeting URL and set transcription options within the API request. Authentication: Configure authentication settings via a Bearer token for interacting with your transcription service. Webhook Setup: Create a webhook to receive real-time transcription updates, ensuring timely data capture during meetings. Join Meeting: Set the bot to join the specified meeting and actively listen to capture conversations. Transcription Handling: Combine transcription fragments into cohesive sentences and manage dialog arrays for coherence. Trigger Actions on Keywords: Set up keyword recognition that can initiate requests to the OpenAI API for additional interactions based on captured dialogue. Output and Summary Generation: Produce insights and summary notes from the transcriptions that can be stored back into the database for future reference.

This workflow with AI agent is designed to navigate through the page to retrieve specific type of information (in this example: social media profile links). The agent is equipped with 2 tools: text tool:** to retrieve all the text from the page, URLs tool:** to extract all possible links from the page. 💡 You can edit prompt and JSON schema connected to the agent in order to return other data then social media profile links. 👉 This workflow uses Supabase as storage (input/output). Feel free to change it to any other database of your choice. 🎬 See this workflow in action in my YouTube video. How it works? The workflow uses the input URL (website) as a starting point to retrieve the data (e.g. example.com). Using the "URLs tool", the agent is able to retrieve all links from the page and navigate to them. For example, if you want to retrieve contact information, agent will try to find a subpage that might contain this information (e.g. example.com/contact) and extract the information using the text tool. Set up steps Connect database with input data (website addresses) or pin sample data to trigger node. Configure the crawling agent to retrieve the desired data (e.g. modify prompt and/or parsing schema). Set credentials for OpenAI. Optionally: split agent tools to separate workflows. If you like this workflow, please subscribe to my YouTube channel and/or my newsletter.

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.

Video Guide I prepared a detailed guide that showed the whole process of building an AI bot, from the simplest version to the most complex in a template. .png) Who is this for? This workflow is ideal for developers, chatbot enthusiasts, and businesses looking to build a dynamic Telegram bot with memory capabilities. The bot leverages OpenAI's assistant to interact with users and stores user data in Supabase for personalized conversations. What problem does this workflow solve? Many simple chatbots lack context awareness and user memory. This workflow solves that by integrating Supabase to keep track of user sessions (via What this workflow does This Telegram bot template connects with OpenAI to answer user queries while storing and retrieving user information from a Supabase database. The memory component ensures that the bot can reference past interactions, making it suitable for use cases such as customer support, virtual assistants, or any application where context retention is crucial. 1.Receive New Message: The bot listens for incoming messages from users in Telegram. Check User in Database: The workflow checks if the user is already in the Supabase database using the Create New User (if necessary): If the user does not exist, a new record is created in Supabase with the telegram_id and a unique Start or Continue Conversation with OpenAI: Based on the user’s context, the bot either creates a new thread or continues an existing one using the stored Merge Data: User-specific data and conversation context are merged. Send and Receive Messages: The message is sent to OpenAI, and the response is received and processed. Reply to User: The bot sends OpenAI’s response back to the user in Telegram. Setup Create a Telegram Bot using the Botfather and obtain the bot token. Set up Supabase: Create a new project and generate a Create a new table named create table public.telegram_users ( id uuid not null default gen_random_uuid (), date_created timestamp with time zone not null default (now() at time zone 'utc'::text), telegram_id bigint null, openai_thread_id text null, constraint telegram_users_pkey primary key (id) ) tablespace pg_default; OpenAI Setup: Create an OpenAI assistant and obtain the Customize your assistant’s personality or use cases according to your requirements. Environment Configuration in n8n: Configure the Telegram, Supabase, and OpenAI nodes with the appropriate credentials. Set up triggers for receiving messages and handling conversation logic. Set up OpenAI assistant ID in "++OPENAI - Run assistant++" node.

Video Guide I prepared a detailed guide that showed the whole process of building a call analyzer. .png) Who is this for? This workflow is ideal for sales teams, customer support managers, and online education services that conduct follow-up calls with clients. It’s designed for those who want to leverage AI to gain deeper insights into client needs and upsell opportunities from recorded calls. What problem does this workflow solve? Many follow-up sales calls lack structured analysis, making it challenging to identify client needs, gauge interest levels, or uncover upsell opportunities. This workflow enables automated call transcription and AI-driven analysis to generate actionable insights, helping teams improve sales performance, refine client communication, and streamline upselling strategies. What this workflow does This workflow transcribes and analyzes sales calls using AssemblyAI, OpenAI, and Supabase to store structured data. The workflow processes recorded calls as follows: Transcribe Call with AssemblyAI: Converts audio into text with speaker labels for clarity. Analyze Transcription with OpenAI: Using a predefined JSON schema, OpenAI analyzes the transcription to extract metrics like client intent, interest score, upsell opportunities, and more. Store and Access Results in Supabase: Stores both transcription and analysis data in a Supabase database for further use and display in interfaces. Setup Preparation Create Accounts: Set up accounts for N8N, Supabase, AssemblyAI, and OpenAI. Get Call Link: Upload audio files to public Supabase storage or Dropbox to generate a direct link for transcription. Prepare Artifacts for OpenAI: Define Metrics: Identify business metrics you want to track from call analysis, such as client needs, interest score, and upsell potential. Generate JSON Schema: Use GPT to design a JSON schema for structuring OpenAI’s responses, enabling efficient storage, analysis, and display. Create Analysis Prompt: Write a detailed prompt for GPT to analyze calls based on your metrics and JSON schema. Scenario 1: Transcribe Call with AssemblyAI Set Up Request: Header Authentication: Set Authorization with AssemblyAI API key. URL: POST to https://api.assemblyai.com/v2/transcript/. Parameters: audio_url: Direct URL of the audio file. webhook_url: URL for an N8N webhook to receive the transcription result. Additional Settings: speaker_labels (true/false): Enables speaker diarization. speakers_expected: Specify expected number of speakers. language_code: Set language (default: en_us). Scenario 2: Process Transcription with OpenAI Webhook Configuration: Set up a POST webhook to receive AssemblyAI’s transcription data. Get Transcription: Header Authentication: Set Authorization with AssemblyAI API key. URL: GET https://api.assemblyai.com/v2/transcript/<transcript_id>. Send to OpenAI: URL: POST to https://api.openai.com/v1/chat/completions. Header Authentication: Set Authorization with OpenAI API key. Body Parameters: Model: Use gpt-4o-2024-08-06 for JSON Schema support, or gpt-4o-mini for a less costly option. Messages: system: Contains the main analysis prompt. user: Combined speakers’ utterances to analyze in text format. Response Format: type: json_schema. json_schema: JSON schema for structured responses. Save Results in Supabase: Operation: Create a new record. Table Name: demo_calls. Fields: Input: Transcription text, audio URL, and transcription ID. Output: Parsed JSON response from OpenAI’s analysis.