milkymap

pdf2gpt-index

build gpt-index using chatgpt and sentence-transformers

map2gpt

This project is a versatile and powerful search tool that leverages state-of-the-art natural language processing models to provide relevant and contextually rich results. The primary goal of this project is to build a semantic search engine for textual content from various sources such as PDF files and Wikipedia pages.

gpt-swarm

This project provides a Python implementation for running multiple OpenAI's GPT-3 models in parallel, which is particularly useful for high-throughput applications.

mqsolver

mqsolver is a library based on (zeromq, multiprocessing, threading), it allows to build distributed strategies for IO and CPU tasks.

stable-diffusion-docker

docker-image stable diffusion v1.4

auto-nlp-classification-gpt

This project aims to provide an autonomous pipeline for creating NLP models for text classification. It is based on GPT-3.5-Turbo, Ada-Embedding, and PyTorch.

gpt-index-builder

This project is a versatile and powerful search tool that leverages state-of-the-art natural language processing models to provide relevant and contextually rich results. The primary goal of this project is to build a semantic search engine for textual content from various sources such as PDF files and Wikipedia pages.

llama-cpp-zmq-server

The 'llama-cpp-zmq-server' module is designed to distribute the capabilities of the llama-cpp-python library through a distributed system architecture, leveraging FastAPI and ZeroMQ. This system is architected with a broker-worker model, enabling it to host multiple LLM (Large Language Models) in the background.

semantic-search-xassida

async-embedding

asynchronous embedding based on zeromq and fastapi

parallel-multi-object-tracking

parallel pipeline for multi objects tracking. it is based on opencv, zeromq and multiprocessing. it can track up to 64 objetcs.

parallel-sentence-embedding

Parallel-Sentence-Embedding is a project that utilizes ZeroMQ and Sentence-Transformers to distribute sentence embeddings across multiple machines. The aim of this project is to improve the efficiency and scalability of sentence embedding tasks by allowing for parallel processing

text-embedding

compute embedding using transformers and weighted graph centrality score

whisper-server

a whisper-server based on fastapi and zeromq

chatbot-genimi

genimi chatbot for student evaluation

chatgpt-tictactoe

two chatgpt playing tic tac toe with zeromq socket

collaborative-llm

This project is a simple Python script that attempts to showcase the collaborative power of large language models in solving complex tasks. It utilizes a network of LLMs that communicate with each other to accomplish a task. The network takes the form of a deep neural network where each neuron is an LLM.

gender-recognizer-yolov8

gender recognizer api based on yolov8 and fastapi

image-classification

python image classification

image-proposal

image recommender system based on hybrid approach combining nlp embedding and image embedding

maze-gen-solver

opencv-chapter-1

opencv chapter 1

opencv-realtime-object-tracking

This project implements real-time tracking using OpenCV in Python. It provides functionalities such as video processing with a tracking algorithm, dynamic ROI selection, and alerts through sound notifications when abnormal movements are detected.

pyzmq

PyZMQ: Python bindings for zeromq

textrank-embedding

vlmtopic

vlmtopic is a project that uses advanced machine learning with CLIP and VLM models to cluster images in real-time and generate captions for those clusters. It helps you organize and describe images more easily and effectively.

voice-transcription

a tools based on transformer for voice transcription

wikipedia-gpt-index

build and deploy telegram-bot rag agent from any wikipedia page

zeromq-tuto

zmq-threading

zmq-threading is a multithreading module that can solve any io-task(copy file, database crud, http request)