Skip to content
View mesutdmn's full-sized avatar
🏠
Working from home
🏠
Working from home
41 followers · 33 following

Achievements

Achievement: Starstruck

Achievements

Achievement: Starstruck

Organizations

@we-bears

Block or report mesutdmn

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
mesutdmn/README.md

Hi there, I'm Mesut Duman

About me

Hello, I am experienced in developing data science and artificial intelligence applications. I strive to continuously improve myself in this dynamic and ever-evolving field, staying updated on the latest innovations. By leveraging my analytical thinking and problem-solving skills, I create effective solutions and innovative projects.

If you would like to connect in this field, feel free to reach out to me on LinkedIn. I look forward to creating new opportunities together!

Feel free to explore my repositories and don't hesitate to reach out for collaborations or opportunities! 🌟

Polar Bear Coding

🛠  Tech Stack

Python  HTML  CSS 
Microsoft SQL Server  SQLite 
Git  Docker  MLflow 
AWS  Azure  Streamlit 
Pandas Tensorflow  Keras  Sklearn  PyTorch 

📈  Projects

  • In this project we developed a fully automated system which generates questions and answers from various multimedia inputs—including PDF, DOCX, PPTX, EPUB, ENEX (evernote), TXT, MP3, MP4, MPEG4, PNG, JPG, JPEG, URLs, YouTube, Spotify, Wikipedia, and direct text input. Users can interact with the interface to answer questions and receive detailed performance feedback with suggestions for improvement. https://github.com/mesutdmn/Digi-Did-I-Get-It
  • Developed an AI-powered multi-agent essay writing system using CrewAI and LangChain. Integrated web scraping and summarization tools to gather real-time data from the web, allowing agents to autonomously generate essays based on user prompts. https://github.com/mesutdmn/Autonomous-Multi-Agent-Systems-with-CrewAI-Essay-Writer
  • Created a Retrieval-Augmented Generation (RAG)-based AI chatbot, capable of querying PDF documents using the OpenAI API integrated with LangChain. With LangGraph and FAISS, vector-based data queries are performed on PDF files, allowing natural language interaction with the data. https://github.com/mesutdmn/Chat-With-Your-PDF
  • Created an application that allows users to describe images using their voice, converting the audio input into text with the OpenAI Whisper-1 model, and then generating an image from that text using the DALL-E model. Users can also obtain descriptions of their generated images via GeminiAI. https://github.com/mesutdmn/Speech-to-Image-With-LLMs
  • For the Teknofest NLP competition, I developed a model with 85% accuracy using only 8MB of data by employing a transformer-encoder architecture with PyTorch to extract sentiment and brand names from Turkish customer reviews. Despite not using a pre-trained model, we ranked 18th out of 90 teams, competing against others who used pre-trained models. https://github.com/mesutdmn/NLP-Turkish-Brand-Entity-Sentiment-Recognizer
  • The Carbon Footprint Calculator project is a user-friendly web application designed to empower individuals to assess and understand their environmental impact. https://github.com/mesutdmn/Carbon-Footprint-Calculator-App

📚  Important Certificates

Connect with me

Pinned Loading

  1. Digi-Did-I-Get-It Digi-Did-I-Get-It Public

    Fully automated system that generates questions and answers from various input sources—including PDF, TXT, MP3, ENEX, MP4, DOCX, PNG, JPG, PPTX, EPUB, JPEG, MPEG4, URL, YouTube, Spotify, Wikipedia,…

    Python 3

  2. Autonomous-Multi-Agent-Systems-with-CrewAI-Essay-Writer Autonomous-Multi-Agent-Systems-with-CrewAI-Essay-Writer Public

    This repository contains the source code for an autonomous multi-agent system built with CrewAI and LangChain. The project enables AI agents to collaborate on tasks such as researching, writing, an…

    Python 20 4

  3. Chat-With-Your-PDF Chat-With-Your-PDF Public

    LLM-based application leveraging LangChain for Retrieval-Augmented Generation (RAG) on imported PDF documents. Enables users to interactively query and converse with PDF content using vector-based …

    Python 2

  4. Speech-to-Image-With-LLMs Speech-to-Image-With-LLMs Public

    This project demonstrates a pipeline that converts speech input into images by leveraging Large Language Models (LLMs) and image generation modelss

    Python 2

  5. NLP-Turkish-Brand-Entity-Sentiment-Recognizer NLP-Turkish-Brand-Entity-Sentiment-Recognizer Public

    2024 Teknofest, Türkçe Doğal Dil İşleme Yarışması – Doğal Dil İşleme Senaryosu #Acıkhack2024TDDİ

    Jupyter Notebook 2

  6. Carbon-Footprint-Calculator-App Carbon-Footprint-Calculator-App Public

    The Carbon Footprint Calculator project is a user-friendly web application designed to empower individuals to assess and understand their environmental impact.

    Python 16 22