Pinned Repositories
6.046J-ps-solutions
berkecanrizai.github.io
Personal Website
llm-stuff
A collection of findings, documents and code snippets about LLMs
Medical-Data-Visualizer
This projects aim is to visualize the medical data provided by the FCC to make a better understanding of the correlation between things like cholesterol, glucose, age, weight and understand the effects of cardio, alcohol intake and smoking habits between those medical observations. Data is handled using python, pandas and graphs are made with seaborn and mathplotlib. This project is written by Berke Can Rizai for one of the end projects of Data analysis with python course. Big part of the code can be understood clearly with the explanations in code. You are free to use and change the code however you like, it could be used in different datasheets with some changes obviously. It's not really big project however could be used as a starting point for other projects. There are two images to show what is expected result of the code so you can try with your own writing. You can run it directly from this link: https://repl.it/@CanRizai/fcc-medical-data-visualizer#medical_data_visualizer.py Thanks.
mlflow
Open source platform for the machine learning lifecycle
two-phase-solver
Java app that takes objective function and constraints from user in a GUI and outputs solution step by step with two phase simplex method
llm-app
Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. 🐳Docker-friendly.⚡Always in sync with Sharepoint, Google Drive, S3, Kafka, PostgreSQL, real-time data APIs, and more.
pathway
Python ETL framework for stream processing, real-time analytics, LLM pipelines, and RAG.
clickbait-spoiling-nlp-project
scikit-learn
scikit-learn: machine learning in Python
berkecanrizai's Repositories
berkecanrizai/llm-stuff
A collection of findings, documents and code snippets about LLMs
berkecanrizai/Medical-Data-Visualizer
This projects aim is to visualize the medical data provided by the FCC to make a better understanding of the correlation between things like cholesterol, glucose, age, weight and understand the effects of cardio, alcohol intake and smoking habits between those medical observations. Data is handled using python, pandas and graphs are made with seaborn and mathplotlib. This project is written by Berke Can Rizai for one of the end projects of Data analysis with python course. Big part of the code can be understood clearly with the explanations in code. You are free to use and change the code however you like, it could be used in different datasheets with some changes obviously. It's not really big project however could be used as a starting point for other projects. There are two images to show what is expected result of the code so you can try with your own writing. You can run it directly from this link: https://repl.it/@CanRizai/fcc-medical-data-visualizer#medical_data_visualizer.py Thanks.
berkecanrizai/two-phase-solver
Java app that takes objective function and constraints from user in a GUI and outputs solution step by step with two phase simplex method
berkecanrizai/6.046J-ps-solutions
berkecanrizai/berkecanrizai.github.io
Personal Website
berkecanrizai/mlflow
Open source platform for the machine learning lifecycle
berkecanrizai/COMP411
Implementations for Comp411 Assignments
berkecanrizai/covid-cfr-analysis
Analysis of Covid CFR (Case Fatality Rate) and different estimators such as (GDP per capita, CVD, Air pollution, Number of hospitals per capita, number of hospital beds per capita, diabetes among population etc.)
berkecanrizai/devportfolio
A lightweight, customizable single-page personal portfolio website template built with JavaScript and Sass
berkecanrizai/Discord-Java-Bot
This is a Discord Bot made with java. This was my first discord bot and it is not really an advanced one however people new to the subject may use this as a starter code to build something bigger. Have Fun!
berkecanrizai/ENGR421
My homework solutions for the ENGR421 - Introduction to Machine Learning course in Koç University.
berkecanrizai/function_vectors
Function Vectors in Large Language Models
berkecanrizai/GenAIComps
GenAI components at micro-service level; GenAI service composer to create mega-service
berkecanrizai/google-research
Google Research
berkecanrizai/langchain
⚡ Building applications with LLMs through composability ⚡
berkecanrizai/linux-shell
Linux Shell Implementation
berkecanrizai/litellm
Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)
berkecanrizai/llama_index
LlamaIndex (formerly GPT Index) is a data framework for your LLM applications
berkecanrizai/llambda
(WIP) Create natural language mappers with few examples
berkecanrizai/llm-app
LLM App is a production framework for building and serving AI applications and LLM-enabled real-time data pipelines.
berkecanrizai/NeoGPT-Recommender
Context-aware knowledge-graph based chatbot using GPT4 and Neo4j
berkecanrizai/podwhisperer
Pod transcription with OpenAI Whisper and AWS
berkecanrizai/privacy-assignments
berkecanrizai/ragflow
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
berkecanrizai/scikit-learn
scikit-learn: machine learning in Python
berkecanrizai/tile-runner-2d
2D platformer game created on Unity Engine.
berkecanrizai/tv-program-simulator
berkecanrizai/txt-visualizer
Author: Berke Can Rizai. This project takes any txt file, no matter how long it may be and visualizes the most frequent words, except common ones like he, she, the etc. and outputs a image. Below is visualization of most frequent words used in War and Peace by Tolstoy. You can add any txt to directory and with some changes you can inspect that file. Under that, visualization of most frequent colors in the book with a pie chart. There is explaination of each block of code under them or somewhere near them. Feel free to take, change any of the code below however you want.
berkecanrizai/virtual-memory-manager
berkecanrizai/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs