using sentence-transformer model for embeddings and streamlit for frontend

Exploring topic modeling techniques, sentiment analysis, and classification algorithms using the Kaggle dataset "Tripadvisor Reviews 2023"

Generates AI-driven responses using the Ollama API with the Phi3 mini model from Microsoft. Heavyweight implementation with memory for language generation, featuring remote RAG and Pinecone for persistent memory

🤖 Retrieval-Augmented Generation pipeline для TARS — соединяем поиск и генерацию знаний.

最小構成で動く日本語RAGシステム | Minimal Japanese RAG with FastAPI + Chroma + SentenceTransformers + Ollama

Log classification using hybrid classification framework

Simple API to upload images, store them in S3 and find other similar images among the uploaded ones. Created for a take home interview assignment.

Lemone: the API for french tax law and embeddings computation 🇫🇷

🧠 Enhance AI conversations with Cognio, a persistent memory server that retains context and enables meaningful semantic search across sessions.

A simple app to help you find relevant machine learning papers to read.

Collection of some of my works during my internship period at Salahkart for preview and educational purpose only.

Data ingestion pipeline using dlt to load data from a REST API into LanceDB.

Implementing Vector Database on CoNaLa dataset to retrieve program snippets relevant to user queries. This is a very simple simulation of a Vector Database.

To make LLM faster we need faster retrieval system. Here comes Embedding Quantization. Embedding quantization is great technique to save cost on Vector DB, significantly faster retrieval while preserving retrieval performance.

Build a search engine using FAISS (Facebook AI Similarity Search) that can help us find the most related book to our quotes or queries, both in English and Italian books

A multimodal movie search engine using RAG techniques. It allows users to search for movies using both text queries and images.

An interactive, privacy-first application for querying the European Union’s AI Act using a local Retrieval-Augmented Generation (RAG) pipeline. Combines semantic search (FAISS) and a quantized TinyLlama LLM for fast, accurate, and context-aware answers—all running on your own hardware.

A movie recommendation system that utilizes FastAPI and Sentence Transformers to suggest films based on plot similarity.

PageSage is a modular web scraping and semantic retrieval system using BeautifulSoup for extraction, SentenceTransformers for dense embeddings, and ChromaDB for scalable vector search—enabling efficient data indexing for advanced RAG pipelines.