Skip to content
View tsejavhaa's full-sized avatar
3 followers · 23 following

Block or report tsejavhaa

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
tsejavhaa/README.md

Hi, I'm Javhaa Tse 👋

AI Engineer building practical LLM, RAG, Computer Vision, and AI Agent systems. Passionate about turning AI research into production-ready applications.

🚀 About Me

  • 🧠 AI Engineer specializing in end-to-end AI solutions (from experimentation to deployment)
  • 🤖 Deep focus on LLMs, RAG pipelines, Computer Vision, and AI Agents
  • 🌏 Actively building Mongolian-language AI tools and localized solutions
  • ⚡ Strong believer in local-first & self-hosted AI (Ollama, Docker, etc.)

🔥 Featured Projects

Project Description Key Technologies
Object_Segmentation Full-stack web app for image, video & live webcam segmentation using state-of-the-art models FastAPI, Hugging Face (SAM, Mask2Former, SegFormer), OpenCV, Vanilla JS
Object_Detection_Yolo Real-time object detection platform supporting images, videos, YouTube & webcam streams YOLOv8, FastAPI, OpenCV, MJPEG streaming
AI_Resume_Cover_Generator Advanced AI resume analyzer & cover letter generator with sync + async pipelines FastAPI, Kafka, Redis, Docker, Ollama, DeepSeek
News_Agency Intelligent news aggregator with scraping, LLM-based deduplication & editorial dashboard Flask, Ollama, BeautifulSoup, NLP
VecRAG Local Retrieval-Augmented Generation system with flexible chunking & vector search LangChain, ChromaDB, Ollama, Embeddings
AI_Interviewer Interactive AI interview simulator with speech capabilities Flask, Text-to-Speech, OpenAI/DeepSeek

More projects → View all repositories

🛠 Tech Stack

Core
Python • PyTorch • TensorFlow • Hugging Face Transformers • LangChain

Computer Vision
OpenCV • YOLOv8 • SAM • SegFormer • Mask2Former

LLM & RAG
Ollama • DeepSeek • ChromaDB • Pinecone • Weaviate • Kafka • Redis

Backend & Deployment
FastAPI • Flask • Docker • PostgreSQL • MongoDB

Others
Streamlit • Gradio • OCR (PaddleOCR, EasyOCR, GLM-OCR)

📫 Connect With Me

Always open to interesting collaborations and opportunities in AI Engineering!

Pinned Loading

  1. News_Agency News_Agency Public

    AI-powered news aggregation platform that scrapes BBC, CNN, and Al Jazeera, deduplicates stories using a local LLM (Ollama), and serves a full-featured editorial web app with source filtering, cate…

    Python

  2. Object_Segmentation Object_Segmentation Public

    A web-based object segmentation app using HuggingFace transformers (SAM, SegFormer, Mask2Former, OneFormer). Supports image, video, and live webcam segmentation with a FastAPI backend and vanilla J…

    Python

  3. Multi_engine_OCR Multi_engine_OCR Public

    Multi-engine OCR suite with Tesseract, EasyOCR, PaddleOCR, Docling, and Mistral OCR — desktop apps, web UIs, Jupyter notebooks, and a unified FastAPI hub for document text extraction.

    Jupyter Notebook

  4. AI_Resume_Cover_Generator AI_Resume_Cover_Generator Public

    AI-powered resume tailoring with sync (inline) and async (Kafka queue) pipelines, supporting both local (Ollama) and cloud (DeepSeek) LLM backends.

    Python

  5. Data_Science_Projects Data_Science_Projects Public

    10 end-to-end data science projects: regression, classification, clustering, NLP, time series, computer vision, and recommender systems with Streamlit dashboards.

    Jupyter Notebook

  6. Object_Detection_Yolo Object_Detection_Yolo Public

    A FastAPI backend + polished web frontend for real-time object detection using YOLOv8.

    HTML