📅 2025-01-30 — Session: Development of n8n-based RAG System
🕒 14:10–17:45
🏷️ Labels: N8N, RAG, Supabase, Vectorization, Workflow, Document Processing
📂 Project: Dev
⭐ Priority: MEDIUM
Session Goal
To develop and enhance a Retrieval-Augmented Generation (RAG) system using n8n and Supabase, focusing on workflow setup, document processing, and vectorization.
Key Activities
- Set up the RAG workflow in n8n, integrating Supabase for document processing and vectorization.
- Created a SQL function for similarity-based document retrieval using vector embeddings.
- Evaluated the use of n8n vs Python for chunkization and vector storage.
- Developed a dynamic vectorstore management system allowing on-the-fly updates.
- Enhanced the directory selection UI with checkboxes for multi-directory processing.
- Fixed issues related to Chroma
persist()in LangChain. - Migrated to a better storage structure for RAG processing.
Achievements
- Successfully integrated Supabase with n8n for document processing.
- Implemented a dynamic vectorstore management system.
- Improved UI/UX for directory selection and processing.
Pending Tasks
- Further evaluate the performance of n8n vs Python for vector storage.
- Continue refining the UI for better user experience.