An advertisement system based on Java spring cloud microservices and C++ FAISS embedding search

Final project for the master's degree in Computer Science course "Cloud Computing" at the University of Rome "La Sapienza" (A.Y. 2022-2023)

Chatbot Memo - Backend is a chatbot server which uses langchain framework

Web application built using Retrieval-Augmented Generation (RAG) architecture

Facebook's Faiss CPU example with Dockerfile ready and tested for Deepnote so you don't have to try and fail like I did 😎

Connexion is a social media platform in its infancy. Users are matched based on personality type and common interests/hobbies.

Welcome to BluBasilico-ai, an intelligent chatbot designed to aid you in all your culinary adventures. With a vast database of over 6000 recipes, BluBasilico-ai helps you decide what to cook based on your current pantry or fridge ingredients. You can also create new recipes with guidance from our AI.

python-fastapi-vector-search

Sentence alignment tools using LASER and FAISS

Flask-based web application designed for similarity searches on news articles, which can be generalized to any text corpus. Input a paragraph or url and returns the most similar news articles from the database.

Python full-stack application that leverages technologies such as Python, PyPDF2, Langchain, Firebase, Lottie, Faiss, Hugginface embedding models, and Streamlit to facilitate multi-PDF analysis through natural language processing, providing users with a seamless and intuitive experience for processing PDFs and obtaining content-related insights

Just playing around with LLMs

The Llama2 Medical Bot is a powerful tool designed to provide medical information by answering user queries

A chatbot developed with Langchain, Streamlit, OpenAI, and FAISS enables users to input the URL of any article and pose questions related to its content.

tutorial: https://www.youtube.com/watch?v=a89vqgK-Qcs

Image Retrieval

A Q-A Chat Assistant based on the FAQ

The Document Question and Answering RAG Application is designed to provide intelligent and accurate responses to questions based on the content of uploaded documents. By combining state-of-the-art machine learning models and cloud technologies, this application offers a seamless and scalable

I have implemented the common operations in NLP domain (实现NLP中各种常规操作，如分词、句法、命名实体识别、语义话题模型、爬虫、ElasticSearch和Faiss向量检索，huggingface-transformers完成各种任务，2023)