+13
Upsert huge documents in a vector store with Supabase and Notion
Published 1 month ago
Created by
Mario
Categories
Template description
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.
Share Template
More Building Blocks workflow templates
Creating an API endpoint
Task:
Create a simple API endpoint using the Webhook and Respond to Webhook nodes
Why:
You can prototype or replace a backend process with a single workflow
Main use cases:
Replace backend logic with a workflow
Jonathan
Very quick quickstart
Want to learn the basics of n8n? Our comprehensive quick quickstart tutorial is here to guide you through the basics of n8n, step by step.
Designed with beginners in mind, this tutorial provides a hands-on approach to learning n8n's basic functionalities.
Deborah
Pulling data from services that n8n doesn’t have a pre-built integration for
You still can use the app in a workflow even if we don’t have a node for that or the existing operation for that. With the HTTP Request node, it is possible to call any API point and use the incoming data in your workflow
Main use cases:
Connect with apps and services that n8n doesn’t have integration with
Web scraping
How it works
This workflow can be divided into three branches, each serving a distinct purpose:
1.Splitting into Items (HTTP Request - Get Mock Albums):
The workflow initiates with a manual trigger (On clicking 'execute').
It performs an HTTP request to retrieve mock albums data from "https://jsonplaceholder.typicode.com/albums."
The obtained data is split into items using the Item Lists node, facilitating easier management.
2.Data Scraping (HTTP Request - Get Wikipedia Page and HTML Extract):
Another branch of the workflow involves fetching a random Wikipedia page using an HTTP request to "https://en.wikipedia.org/wiki/Special:Random."
The HTML Extract node extracts the article title from the fetched Wikipedia page.
3.Handling Pagination (The final branch deals with handling pagination for a GitHub API request):
It sends an HTTP request to "https://api.github.com/users/that-one-tom/starred," with parameters like the page number and items per page dynamically set by the Set node.
The workflow uses conditions (If - Are we finished?) to check if there are more pages to retrieve and increments the page number accordingly (Set - Increment Page).
This process repeats until all pages are fetched, allowing for comprehensive data retrieval.
Jonathan
Joining different datasets
Task:
Merge two datasets into one based on matching rules
Why:
A powerful capability of n8n is to easily branch out the workflow in order to process different datasets. Even more powerful is the ability to join them back together with SQL-like joining logic.
Main use cases:
Appending data sets
Keep only new items
Keep only existing items
Jonathan
+11
Back Up Your n8n Workflows To Github
This workflow will backup your workflows to Github. It uses the public api to export all of the workflow data using the n8n node.
It then loops over the data checks in Github to see if a file exists that uses the workflow name. Once checked it will then update the file on Github if it exists, Create a new file if it doesn't exist and if it's the same it will ignore the file.
Config Options
repo_owner - Github owner
repo_name - Github repository name
repo_path - Path within the Github repository
>This workflow has been updated to use the n8n node and the code node so requires at least version 0.198.0 of n8n
Jonathan
+10
Building Your First WhatsApp Chatbot
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.
Jimleuk
More AI workflow templates
AI agent chat
This workflow employs OpenAI's language models and SerpAPI to create a responsive, intelligent conversational agent. It comes equipped with manual chat triggers and memory buffer capabilities to ensure seamless interactions.
To use this template, you need to be on n8n version 1.50.0 or later.
n8n Team
+7
Scrape and summarize webpages with AI
This workflow integrates both web scraping and NLP functionalities. It uses HTML parsing to extract links, HTTP requests to fetch essay content, and AI-based summarization using GPT-4o. It's an excellent example of an end-to-end automated task that is not only efficient but also provides real value by summarizing valuable content.
Note that to use this template, you need to be on n8n version 1.50.0 or later.
n8n Team
+5
AI agent that can scrape webpages
⚙️🛠️🚀🤖🦾
This template is a PoC of a ReAct AI Agent capable of fetching random pages (not only Wikipedia or Google search results).
On the top part there's a manual chat node connected to a LangChain ReAct Agent. The agent has access to a workflow tool for getting page content.
The page content extraction starts with converting query parameters into a JSON object. There are 3 pre-defined parameters:
url** – an address of the page to fetch
method** = full / simplified
maxlimit** - maximum length for the final page. For longer pages an error message is returned back to the agent
Page content fetching is a multistep process:
An HTTP Request mode tries to get the page content.
If the page content was successfuly retrieved, a series of post-processing begin:
Extract HTML BODY; content
Remove all unnecessary tags to recude the page size
Further eliminate external URLs and IMG scr values (based on the method query parameter)
Remaining HTML is converted to Markdown, thus recuding the page lengh even more while preserving the basic page structure
The remaining content is sent back to an Agent if it's not too long (maxlimit = 70000 by default, see CONFIG node).
NB:
You can isolate the HTTP Request part into a separate workflow.
Check the Workflow Tool description, it guides the agent to provide a query string with several parameters instead of a JSON object.
Please reach out to Eduard is you need further assistance with you n8n workflows and automations!
Note that to use this template, you need to be on n8n version 1.19.4 or later.
Eduard
+2
Telegram AI Chatbot
The workflow starts by listening for messages from Telegram users. The message is then processed, and based on its content, different actions are taken. If it's a regular chat message, the workflow generates a response using the OpenAI API and sends it back to the user. If it's a command to create an image, the workflow generates an image using the OpenAI API and sends the image to the user. If the command is unsupported, an error message is sent. Throughout the workflow, there are additional nodes for displaying notes and simulating typing actions.
Eduard
+4
OpenAI GPT-3: Company Enrichment from website content
Enrich your company lists with OpenAI GPT-3 ↓
You’ll get valuable information such as:
Market (B2B or B2C)
Industry
Target Audience
Value Proposition
This will help you to:
add more personalization to your outreach
make informed decisions about which accounts to target
I've made the process easy with an n8n workflow.
Here is what it does:
Retrieve website URLs from Google Sheets
Extract the content for each website
Analyze it with GPT-3
Update Google Sheets with GPT-3 data
Lucas Perret
+5
Ask questions about a PDF using AI
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.
David Roberts
