LAB
AI-Powered

The Data Lab

Query my experience, skills, and projects in natural language. Powered by Python, RAG, vector embeddings, and a local LLM — wired directly into this website.

Try: GCP experience RAG projects Marketing data AI tools built Education His Love story
AI Answer
⬡ phi3 Response
phi3:latest · local
Top Retrieval Results
⬡

Enter a query above to search my profile.

phi3 will answer first, then the top matching profile sections appear here.

System Status
API Server OFFLINE
RAG Engine OFFLINE
Vector DB OFFLINE
LLM Engine OFFLINE
Capabilities

What's Running in This Lab

This portfolio isn't just a static page — it's a live demonstration of my engineering capabilities. New features ship continuously.

Building ⬡

RAG-Powered Profile Search

Natural language search over my CV, work history, and projects using vector embeddings (pgvector / Pinecone) and an LLM for answer generation.

FastAPIpgvectorOpenAILangChain
Planned ◎

Local LLM Chatbot

An on-device chatbot powered by a locally-running LLM (Ollama + Mistral/Llama) so you can have a full conversation about my profile without external API calls.

OllamaMistralLlamaFastAPI
Planned ⟳

Airflow Jobs Monitor

Live dashboard of Apache Airflow DAGs running locally — show data refresh schedules, last run status, and pipeline health in real time.

AirflowPythonREST API
Planned ◈

Image Processing Lab

Upload an image and apply AI-powered transformations — OCR extraction, object detection, trend analysis — powered by Python and Hugging Face models.

PillowTesseractHuggingFaceFastAPI
Planned ⊠

RabbitMQ Async Queue

Asynchronous job processing with RabbitMQ — background tasks like PDF generation, report creation, and email sending via a message queue.

RabbitMQasyncioCeleryPython
Planned ⛁

Live Data Dashboard

Real-time analytics on site usage, search queries, and content popularity — piped through a local BigQuery-style aggregation layer.

PostgreSQLFastAPIChart.jsPython
API Reference

Backend Endpoints

Start the FastAPI server and explore the full OpenAPI docs at http://www.mdaminulhaque.com/

GET /api/health Service health and component status
POST /api/search RAG-powered semantic search over profile data
POST /api/chat Conversational LLM chat (streaming) — planned
POST /api/image/process Image OCR, object detection, transformations — planned
GET /api/airflow/dags List Airflow DAGs and their run status — planned
POST /api/queue/submit Submit a background job to RabbitMQ — planned