Repositório destinado ao Trabalho de Conclusão de Curso

Memsplora - An in-memory SPLADE (SParse Lexical AnD Expansion) content server with FAISS integration

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 hybrid document search engine combining BERT embeddings and TF-IDF for intelligent semantic retrieval and ranking of documents.

A semantic search engine prototype, made with SentenceBERT, ontological definitions, and full-text search.

Our next-gen search engine goes beyond keyword matching, leveraging LLMs (Large Language Models) to understand intent and find the perfect product—even if users don’t describe it exactly! 🔥

A CLIP-powered Semantic Search Engine using Pinecone, FiftyOne, and Streamlit.

PACE (Podcast AI for Chapters and Episodes) is a semantic search engine that helps you find the information you need, inter- and intra-podcasts (Project for the AssemblyAI Winter 2022 Hackathon).

Applied Word Vectorization Technique to Semantic (Web) Video Search Engine

Unstructured data refers to information that is not organised using a predetermined data model or schema and cannot be stored in a conventional relational database system. There are several methods for search unstructured data semantically- That is by taking the actual context/meaning of the sentences.One best approach is index based approach.

Cherrry Javascript SDK

Building a Custom Vector Search Engine with Weaviate : The project discusses the architecture of Weaviate, an open-source vector database and provides a tutorial implementation of a custom vector search engine using Weaviate Cloud Service(WCS).

Flask app to perform image search using semantic matching of input text and images

The code I produced in my research internship in Summer 2022. I created a search interface in streamlit to query ArXiv articles using semantic embeddings. This involved a lot of background learning and was my first experience with sentence embeddings, transformers, and machine learning.

🔍 Search Google and YouTube instantly from your clipboard with hotkeys using this lightweight tool for Windows. Toggle hotkeys on/off effortlessly.

Leveraged natural language processing and machine learning techniques to enhance the relevance and accuracy of search results by building a semantic search engine.

Contextual Memory Intelligence for AI Systems - Persistent memory, cognitive tools, and adaptive reasoning capabilities for LLMs Experimental memory system for LLMs (see MemMimic for optimized version)

AI-powered SEC filing analysis using RAG. Reduces 4-hour document analysis to 3 seconds with 90%+ accuracy. Built with Python, FastAPI, PostgreSQL, and Gemini AI.

Examples of how to use IP Street's semantic search to perform prior art search and find relevant documents

Creating a semantic search engine by making use of genism-topic modelling and flask framework