Mistir Nigusse's repositories
mistir-nigusse
Config files for my GitHub profile.
LLM_Prompt_Engine
AI-driven prompt generation and evaluation system, designed to optimize the use of Language Models (LLMs) in various industries. The project consists of both frontend and backend components, facilitating prompt generation, automatic evaluation data generation, and prompt testing.
pNEUMA_Traffic_data_warehouse
This project is aimed at creating a scalable data warehouse to manage vehicle trajectory data collected by swarm UAVs and static roadside cameras. The data will be used by the city's traffic department to improve traffic flow and support other undisclosed projects.
Contract_advisor_RAG
A Retrieval-Augmented Generation (RAG) system for contract Q&A, enabling to pose questions and receive relevant answers. Implemented using langchain, chroma db, GPT-4 model and RAGAS for evaluating performance
Scalable-Backtesting-Infrastructure
This project aims to design and build a reliable, large-scale trading data pipeline for a startup called Mela, which wants to make it simple for everyone to enter the world of cryptocurrencies. The pipeline will enable investors to run backtests that simulate current and past particular situations as well as their trend over time.
Logistic-optimization-with-casual-inference
This project aims to optimize the placement of Gokada drivers in Lagos, Nigeria, using causal inference and machine learning techniques to reduce the number of unfulfilled delivery requests.
LLM_Fine-Tunning_Amharic
This GitHub repository contains notebooks that use the Amharic news category classification dataset to fine-tune various models for a text classification task.
LLM_fine_tunning_API
This repository contains scripts for scraping data and performing preprocessing tasks necessary for fine-tuning large language models (LLMs). It is designed to provide a flexible and scalable foundation for future development of an API for fine-tuning LLMs.
Redash_chatbot_add-on
This repository is contains an AI powered chat add-on for Redash, that transforms complex data analysis into simple conversations. By converting natural language queries into SQL and automating dashboard creation, It makes it easier to data access and empower users to uncover hidden insights.
Telecom_data_analysis_10Academy_week_1
The repository analyzes Tellco (a telecom) company's performance, identify areas for improvement, and provide recommendations to enhance customer satisfaction, retention, and to give suggestion whether or not to invest on it after analyzing the overall profitability.