Architected and developed a high-performance, distributed AI attendance system designed for scalability and real-time performance. This full-stack project features a React/TSX admin panel and a robust Python/FastAPI backend.
Loading repository data…
Loading repository data…
RobinElysia / repository
A high-performance Python backend service built with FastAPI, Transformers, and FAISS, designed for seamless remote model inference from Java backend systems. This module provides a scalable RESTful API for machine learning model serving with vector search capabilities.
This project is a high-performance Python backend service built with FastAPI, Transformers, and FAISS, designed to seamlessly integrate remote model inference from Java backend systems. The module provides a scalable RESTful API for efficient model inference services.
zh: README_ZH
The entry point main.py file handles basic configuration by prompting the user for essential settings, such as choosing between remote API invocation or local models.(√)
uv is installed in your environment, then run uv sync..env file and fill in the required parameters:# Remote Configuration
KEY="YOUR_API_KEY"
SECRET="YOUR_API_SECRET"
URL="URL"
# Choose either Remote or Local
# Local Configuration
PATH="PATH" # Model path (specify the folder only)
Selected from shared topics, language and repository description—not editorial ratings.
Architected and developed a high-performance, distributed AI attendance system designed for scalability and real-time performance. This full-stack project features a React/TSX admin panel and a robust Python/FastAPI backend.
Cerno-AI /
High-performance RAG system for intelligent document Q&A with hybrid retrieval, GPU acceleration, and citation-backed answers. Upload docs, ask questions, get precise responses.
Aaryan2304 /
An AI-powered visual search engine that finds visually similar fashion items from a dataset of over 100,000 images with sub-100ms latency. The system uses CLIP embeddings for semantic understanding and a high-performance FAISS vector database for efficient similarity search. It features a Streamlit UI for user interaction and scalable FastAPI back.
viochris /
🚀 High-performance RAG Backend for Silvio's Portfolio. Built with FastAPI, LangChain, FAISS, and Google Gemini to provide an interactive AI chat experience.
neeraliacharya /
A professional-grade Retrieval-Augmented Generation (RAG) platform that transforms your documents into an interactive knowledge base. Built for high-performance semantic search and context-aware conversations.
tedjjj /
An intelligent agentic debugger for Python developers. Powered by LangGraph, Groq, and FAISS, this tool analyzes tracebacks, performs automated documentation lookups, and generates corrected code snippets with detailed explanations. Includes a sleek React interface and a high-performance FastAPI backend for seamless debugging workflows.