0+ Years in IT
0 Live Projects
0+ Technologies
0 Certifications

Skills & Technologies

Python Python
FastAPI FastAPI
Flask Flask
Quart Quart
Pandas Pandas
NumPy NumPy
Azure AI Azure AI
Qdrant Qdrant
LLM LLM
SQLAlchemy SQLAlchemy
MS SQL MS SQL
ETL
Azure DevOps Azure DevOps
GitHub GitHub
Automation Automation
Windows Server Windows Server
Linux Linux
VS Code VS Code

Featured Projects

Examples of technical solutions I have developed, with special emphasis on AI/LLMs, Python, and system architecture.

Filter by technology:

Document Intelligence Pipeline

Local document processing pipeline for PDF, DOCX and scanned images: OCR (Tesseract), text extraction, table detection & extraction, key-value parsing, entity recognition (spaCy), layout analysis and summarization. Results are produced as structured JSON suitable for downstream ingestion (data lakes, BI, search indexes). Repository is private — contact guch79@gmail.com for access and commercial options.

Python Quart OCR Tesseract spaCy PDF processing NLP

Professional Portfolio & CV Generator

Fully asynchronous Quart web application with auto-generated PDF CV from dynamic content. Features intelligent HTML-to-PDF conversion with structured data extraction, professional formatting, and clickable links. Built with modern async Python patterns.

Quart Uvicorn FPDF2 Async Python Jinja2

Apology-as-a-Service (MCP Server)

A live Model Context Protocol (MCP) server that provides context-aware crisis communication for AI agents. Test it live right here with the 'Generate Live Apology' button, or download the config to connect your own agent. Features multiple severity levels, styles (including Haiku), and SSE support.

Python MCP Protocol SSE Docker Async FastMCP

View Code

ETL Data Pipeline - Dataverse to SQL Server

Complete ETL pipeline for extracting data from Microsoft Dataverse, transforming with business logic, and loading to SQL Server. Includes fake data generation with Faker for testing before production deployment. Features parallel processing, connection pooling, and circuit breakers.

Python Pandas SQLAlchemy Dataverse Faker

Code Sample

~/projects/lifecycle.py — Python
1from typing import Optional
2from qdrant_client import QdrantClient
3
4class LifeCycleManager:
5 # Singleton to manage long-lived resources (Qdrant, background tasks)
6 _instance = None
7 _qdrant_client: Optional[QdrantClient] = None
8
9 def __new__(cls):
10 if cls._instance is None:
11 cls._instance = super(LifeCycleManager, cls).__new__(cls)
12 return cls._instance
13
14 @property
15 def qdrant_client(self) -> Optional[QdrantClient]:
16 return self._qdrant_client
17
18 async def startup(self):
19 """Initialize resources on application startup and schedule background tasks."""
20 logger.info("Starting up application resources...")
21 # Run Qdrant connection in a separate thread to avoid blocking startup
22 await asyncio.to_thread(self._connect_qdrant)
23 await embeddings.preload_embedding_models()
24
25 def _connect_qdrant(self):
26 # Synchronous helper executed in a thread; keep configuration external.
27 try:
28 self._qdrant_client = QdrantClient(# configuration passed from settings)
29 logger.info("Qdrant client connected")
30 except Exception as e:
31 logger.exception("Failed to connect Qdrant: %s", e)
32
33 # Usage example: lifecycle = LifeCycleManager(); await lifecycle.startup()

Want to know more?

Take a look at my background, download my CV, or explore my projects on GitHub.