RAG on Living Data
This workflow implements a Retrieval-Augmented Generation (RAG) function through real-time data updates, automatically retrieving the latest content from the Notion knowledge base. It performs text chunking and vectorization, storing the results in the Supabase vector database. By integrating OpenAI's GPT-4 model, it provides contextually relevant intelligent Q&A, significantly enhancing the efficiency and accuracy of knowledge base utilization. This is applicable in scenarios such as enterprise knowledge management, customer support, and education and training, ensuring that users receive the most up-to-date information.
Tags
Workflow Name
RAG on Living Data
Key Features and Highlights
This workflow implements a Retrieval-Augmented Generation (RAG) process based on real-time updated data. It automatically fetches the latest content from a Notion knowledge base, performs text chunking and vectorization, and stores the vectors in a Supabase vector database. By integrating OpenAI’s GPT-4 model, it enables context-aware intelligent Q&A, significantly enhancing the utilization efficiency and accuracy of knowledge base content.
Core Problem Addressed
It solves the challenge of efficiently synchronizing and updating vectorized data following dynamic updates in the knowledge base, while supporting context-based intelligent Q&A. The workflow automatically detects updates in Notion pages, deletes outdated vector data, and inserts new vectors to ensure that Q&A is based on the most current information, avoiding data redundancy and information obsolescence.
Application Scenarios
- Enterprise Knowledge Management: Automatically synchronize and enrich internal documents, manuals, and FAQs to enable intelligent Q&A.
- Customer Support Systems: Provide accurate, real-time response support for customer service based on a dynamic knowledge base.
- Education and Training: Integrate teaching material repositories to assist students and educators with intelligent Q&A and content retrieval.
- Product Documentation Queries: Offer users an up-to-date Q&A service for product usage guides.
Main Workflow Steps
- Data Trigger
- Use a schedule trigger to pull the most recently updated pages from the Notion knowledge base every minute.
- Data Retrieval and Processing
- Retrieve all content blocks of the updated pages (Get page blocks).
- Concatenate page content into a single string.
- Split the text into chunks based on a set token count (Token Splitter) for easier processing and vectorization.
- Old Data Cleanup
- Delete old vector embeddings corresponding to the page from Supabase vector storage to prevent data redundancy.
- Vectorization and Storage
- Convert text chunks into vectors using the OpenAI Embeddings node.
- Store vectors along with metadata in the Supabase vector database.
- Intelligent Q&A Trigger
- Initiate the Q&A process via a chat message trigger.
- Retrieve relevant content from the vector database using a vector store retriever.
- Generate context-aware answers by combining OpenAI GPT-4 chat model with a question-and-answer chain.
- Result Output
- Return intelligent Q&A results based on the latest knowledge base content.
Systems and Services Involved
- Notion: Serves as the knowledge base data source, providing real-time access to pages and content blocks.
- OpenAI: Provides text embedding generation (Embeddings) and chat language model support (GPT-4).
- Supabase: Acts as the vector storage database for storing and retrieving text vector data.
- n8n: An automation workflow platform that orchestrates node executions to realize process automation.
Target Users and Value
- Knowledge managers and enterprise digital transformation teams aiming to build intelligent knowledge bases.
- Customer service and support teams seeking to improve response efficiency and accuracy.
- Educational institutions and trainers facilitating intelligent content retrieval and interactive Q&A.
- Developers and automation enthusiasts looking to rapidly build intelligent Q&A systems based on real-time data.
By combining Notion’s dynamic data source with OpenAI’s powerful language understanding capabilities and Supabase’s efficient vector storage, this workflow delivers a real-time, intelligent, and automated knowledge base Q&A solution that greatly enhances the convenience and precision of information retrieval.
A/B Split Testing
This workflow implements a session-based A/B split testing, which can randomly assign different prompts (baseline and alternative) to users in order to evaluate the effectiveness of language model responses. By integrating a database to record sessions and allocation paths, and combining it with the GPT-4o-mini model, it ensures continuous management of conversation memory, enhancing the scientific rigor and accuracy of the tests. It is suitable for AI product development, chatbot optimization, and multi-version effectiveness verification, helping users quickly validate prompt strategies and optimize interaction experiences.
Get Airtable Data in Obsidian Notes
This workflow enables real-time synchronization of data from the Airtable database to Obsidian notes. Users simply need to select the relevant text in Obsidian and send a request. An intelligent AI agent will understand the query intent and invoke the OpenAI model to retrieve the required data. Ultimately, the results will be automatically inserted into the notes, streamlining the process of data retrieval and knowledge management, thereby enhancing work efficiency and user experience. It is suitable for professionals and team collaboration users who need to quickly access structured data.
CoinMarketCap_AI_Data_Analyst_Agent
This workflow builds a multi-agent AI analysis system that integrates real-time data from CoinMarketCap, providing comprehensive insights into the cryptocurrency market. Users can quickly obtain analysis results for cryptocurrency prices, exchange holdings, and decentralized trading data through Telegram. The system can handle complex queries and automatically generate reports on market sentiment and trading data, assisting investors and researchers in making precise decisions, thereby enhancing information retrieval efficiency and streamlining operational processes.
Generate AI-Ready llms.txt Files from Screaming Frog Website Crawls
This workflow automatically processes CSV files exported from Screaming Frog to generate an `llms.txt` file that meets AI training standards. It supports multilingual environments and features intelligent URL filtering and optional AI text classification, ensuring that the extracted content is of high quality and highly relevant. Users simply need to upload the file to obtain structured data, facilitating AI model training and website content optimization, significantly enhancing work efficiency and the accuracy of data processing. The final file can be easily downloaded or directly saved to cloud storage.
Building RAG Chatbot for Movie Recommendations with Qdrant and OpenAI
This workflow builds an intelligent movie recommendation chatbot that utilizes Retrieval-Augmented Generation (RAG) technology, combining the Qdrant vector database and OpenAI language model to provide personalized movie recommendations for users. By importing rich IMDb data, it generates text vectors and conducts efficient similarity searches, allowing for a deep understanding of users' movie preferences, optimizing recommendation results, and enhancing user interaction experience. It is particularly suitable for online film platforms and movie review communities.
Competitor Research Intelligent Agent
This workflow utilizes an automated intelligent agent to help users efficiently conduct competitor research. Users only need to input the target company's official website link, and the system can automatically identify similar companies, collect and analyze their basic information, products and services, and customer reviews. Ultimately, all data will be consolidated into a detailed report, stored in Notion, significantly enhancing research efficiency and addressing the issues of scattered information and cumbersome organization found in traditional research methods, thereby supporting market analysis and strategic decision-making.
RAG & GenAI App With WordPress Content
This workflow automates the extraction of article and page content from WordPress websites to create an intelligent question-and-answer system based on retrieval-augmented generative artificial intelligence. It filters, transforms, and vectorizes the content, storing the data in a Supabase database to support efficient semantic retrieval and dynamic questioning. By integrating OpenAI's GPT-4 model, users can enjoy a more precise query experience while achieving persistent management of chat memory, enhancing the contextual continuity of interactions and increasing the intelligent utilization value of the website's content.
Slack AI Chatbot with RAG for Company Staff
This workflow builds an intelligent chatbot integrated into the Slack platform, utilizing RAG technology to connect in real-time with the company's internal knowledge base. It helps employees quickly query company documents, policies, and processes. The chatbot supports natural language interaction, accurately extracting relevant information and responding in a friendly format to ensure the information is accurate and reliable. This system not only enhances the efficiency of information retrieval but also automates responses to IT support and human resources-related inquiries, significantly improving employees' work experience and communication efficiency.