Is Rojit Pokharel a web and web app developer in Kathmandu, Nepal?

Yes. Rojit Pokharel is a Full-Stack Web Developer and System Architect based in Kathmandu, Nepal, specializing in production web applications, e-commerce platforms, SaaS products, and API development using Laravel, Django, React, and Next.js.

What kind of websites and web apps does Rojit build?

Custom web applications, e-commerce and multi-vendor marketplaces, restaurant management SaaS, insurance claim platforms, travel booking systems, API services, and server monitoring tools.

Which technologies does Rojit Pokharel specialize in?

Laravel and PHP for the backend, React and Next.js for the frontend, Django for Python projects, and MySQL or PostgreSQL for databases. He also handles server setup with Nginx, Docker, and Linux.

How do I hire a web developer in Kathmandu?

Reach out through the contact page or email info@rojitpokharel.com.np. Rojit is open to freelance projects and full-time opportunities and typically responds within 24 hours.

Does Rojit work with clients outside Nepal?

Yes. While based in Kathmandu, Nepal, he works with local and international clients, communicating in English and delivering production-grade applications.

API Latency· 2025

Chat-bot API

Multi-modal chatbot API built with Flask and Google Gemini, featuring speech recognition, image understanding, and context-aware conversations through a clean REST interface.

Technical case study by Rojit Pokharel — Full-Stack Web Developer & System Architect, Kathmandu, Nepal

FlaskGemini APIPythonREST API

Stack diagram

Application

FlaskGemini APIPythonREST API

Client / Problem

›Teams wanted a single API to power chatbots that accept text, speech, and images — not separate integrations per modality.
›Multi-modal interactions need a clean, consistent REST interface over the raw Gemini calls.

My Role

›Backend developer — built a Flask REST API wrapping Google Gemini for text, speech, and image inputs.
›Designed the request/response contract and prompt engineering for context-aware conversations.

Architecture

›Flask REST API with blueprint-based route organization.
›Gemini API integration for multimodal generation — text, audio, and vision inputs.
›Speech recognition layer converts audio to text before prompting.
›Conversation context passed across turns for coherent multi-turn dialogue.

API Architecture

›Clean REST endpoints for chat, speech-to-text, and image understanding.
›Centralized prompt builder keeps system instructions consistent across modalities.

Authentication

›API-key authentication guarding the chat endpoints.

Deployment

›Flask app behind Nginx with SSL; environment-managed Gemini API keys.

Performance Optimization

›Streamed responses where supported to keep perceived latency low.
›Request timeouts and retries around Gemini to handle transient API failures.

Problems Encountered

›Gemini latency varies with input modality, making consistent API response times hard.
›Raw model calls scattered through routes made prompts and keys hard to manage.

How I Solved Them

›Centralized Gemini client with streaming and timeout handling per modality.
›A single prompt-builder module standardizes system context and message history.

Results

›A production-ready multi-modal chatbot API handling text, speech, and image conversations through one REST interface.

Lessons Learned

›Multimodal apps need a clean API contract before the model calls.
›Centralize provider integration — it will be replaced or versioned.

Building an AI Referee: Computer Vision for Football Player Detection and Tracking

Build an AI-powered football analytics pipeline using YOLOv5, SORT tracking, SSIM-based team classification, pitch mapping, and a Flask dashboard.

Answers

Read the Answers

Direct answers to questions about Rojit Pokharel and the technologies used across these projects.

Want a production system like this?

I build production web applications end-to-end. Let's discuss your project.

Get in Touch