Full-Stack RAG System
Fredy Alexander Rivera Acevedo
The demo is here:
🔍 How it Works:
Document Ingestion: Upload PDFs, Word docs, or Excel sheets seamlessly
Content Processing: Extract text, split into chunks, generate embeddings with OpenAI
Vector Storage: Secure storage in Supabase pgvector with Row Level Security
Similarity Search: Top-K vector search retrieves most relevant passages
Answer Generation: GPT-4o-mini produces context-aware, concise answers
🛠️ Tech Stack:
FastAPI
OpenAI Embeddings
Supabase pgvector
Jinja2
TailwindCSS
GPT-4o-mini
✓ Async Performance & Secure Indexing
⚡ Rapid Deployment Ready
Like this project
Posted Jun 21, 2025
Developed a document ingestion and processing system using various tech tools.
Likes
1
Views
0
