AI & LLM Integration
I integrate language models into real products: GPT-4 powered personalised recommendations replacing static suggestions on a tourism platform, and an on-premise assistant built on Ollama (Qwen 2.5) and the Qdrant vector database.
The assistant runs a nightly RAG indexer over files, knowledge-base articles and announcements (PDF and DOCX extraction), partitioned per tenant to keep data isolated.
Tools and technologies
- OpenAI GPT-4
- Ollama
- Qwen 2.5
- Qdrant
- RAG
- Prompt engineering
RAG Pipelines
Scheduled indexing and retrieval over private company content.
Data Isolation
Tenant-partitioned vector storage for multi-tenant products.
Let's Work Together.
Tell me about your project. I'll reply with questions, a first approach and honest advice.
Copyright © 2026 Nauman Majeed