About This Project
The RAG Agent [MongoDB] workflow automates the process of transforming uploaded PDFs into intelligent, searchable knowledge sources. Using n8n automation, it fetches documents from Google Drive, generates embeddings via Hugging Face, and stores them in MongoDB Atlas. The system integrates Groq LLM to create an AI-powered chat agent capable of retrieving accurate, context-based responses directly from the stored PDFs. This workflow demonstrates the power of combining automation, vector search, and AI for real-time document intelligence.
Key Features
- Auto-imports pdfs from google drive into the system.
- Generates text embeddings using hugging face for semantic understanding.
- Stores vector data efficiently in mongodb atlas.
- Ai-powered chat interface using groq llm for accurate, document-aware answers.
- Fully automated n8n workflow, requiring no manual setup.
- Scalable and modular design for expanding ai document retrieval capabilities.
Technologies Used
Project Snapshot
- Status: Completed
- Duration: 2 Months
- Category: Media, Marketing
Project Team
Golakiya Vraj
Developer
Vraj developed and optimized an AI-integrated RAG workflow using n8n. He automated the entire pipeline — from PDF import and embedding generation to vector storage and intelligent query response. He ensured smooth Groq LLM integration with MongoDB Atlas for high-speed retrieval and designed a scalable, modular architecture supporting continuous updates and flexible data handling.
YBAI SOLUTION BOT