Switch to English?
Yes
Переключитись на українську?
Так
Переключиться на русскую?
Да
Przełączyć się na polską?
Tak

Dmytro Zahorui

Швидко, не дорого, якiсно
Offer Dmytro work on your next project.

Ukraine Zhitomir, Ukraine
12 minutes back
Available for hire available for hire
2 proposals made
age 18 years
on the service 1 day 14 hours
  • web developer
  • python
  • telegram bot

Rating

Successful projects
No data
Average rating
No data
Rating
340
AI & Machine Learning
156 place out of 2887
Web Programming 2
1590 place out of 6485

Language proficiency level

English English: advanced

Skills and abilities

Programming

Services

Administration


Translation

  • English
    from 11 USD for project

Portfolio


  • Website with authorization, search, and booking capabilities

    Javascript and Typescript
    Short project description
    Demonstration project (Proof of Concept) that visualizes and technically implements one of the key business processes of medical and mental platforms — a seamless transition for an unauthorized user from viewing a specialist's profile to final session booking. The project focuses on the correct security architecture and maintaining a high level of UX.
    Main functionality:

    Public interface: Page with the psychologist's profile and an interactive button to start booking a session.

    Smart redirect (Deep Linking): An intelligent authentication mechanism. If the client is not logged in, the application redirects them to the login page but automatically remembers their intent. After successful login, the user returns to the application process without delay.

    Protected Routes: Access to confidential steps (choosing the type of therapy: Individual or Couple) is strictly controlled at the Middleware level.

    Technical advantages of the project for the developer:

    Modular architecture: Clear separation of business logic, routing, and access rights checks, making the code easy to read and maintain.

    Scalability: The service selection logic is designed so that new formats (e.g., group or corporate therapy) can be integrated without rewriting existing code.

    Stability of the user scenario: Complete elimination of dead ends during authorization, which directly impacts the platform's conversion.
  • Autonomous AI RAG system with vector knowledge base

    AI & Machine Learning
    Designed and implemented from scratch an asynchronous RAG system (Retrieval-Augmented Generation) for intelligent analysis and search of complex technical documentation or internal company knowledge bases.

    What was implemented in the project:
    • Asynchronous backend: High-performance API on FastAPI with runtime validation of input data through Pydantic v2.
    • Vector core: Native semantic search in the Qdrant database using cosine similarity metric with local embeddings (vector dimension — 384, float32).
    • AI orchestration: The agent's logic is built on graph structures LangGraph (StateGraph) with a single thread-safe state, allowing easy addition of regeneration cycles or response validation nodes.
    • Chunking strategy: Implemented intelligent text chunking (400 characters) with overlap (100 characters), completely eliminating context loss at sentence boundaries and removing model hallucinations.

    The system is flexible: it can work with both local models (via Ollama) and cloud APIs (Gemini, Claude, OpenAI). The entire infrastructure is fully containerized using Docker Compose and ready for deployment on a server.

Activity

  Latest proposals 2
Integration of respond and CRM for sending the report on the first message
16 USD
Creation of a platform for finding psychologists
335 USD