🧠 Multimodal Retrieval-Augmented Generation that "weaves" together text and images seamlessly. 🪡

AI-Powered Job Recommendation System An intelligent job recommendation system that analyzes PDF resumes and suggests the best job opportunities using NLP, FAISS, and Sentence Transformers.

Este projeto permite realizar perguntas em linguagem natural sobre o conteúdo de arquivos PDF. Utiliza a abordagem RAG (Retrieval-Augmented Generation)

It allows users to upload PDFs and ask questions about the content within these documents.

Metallum/Metal-Archives scrapers, datasets, analysis and recommendations website

This project uses the CrewAI framework to automate stock analysis, enabling AI agents to collaborate and execute complex tasks efficiently. Example stock: Nvidia. Technologies include Python, CrewAI, Unstructured, PyOWM, Tools, Wikipedia, yFinance, SEC-API, tiktoken, faiss-cpu, python-dotenv, langchain-community, langchain-core, and OpenAI.

Document Responder - Multi Agent AI - Powered By OpenSource LLM (Llama3 - 8b)

A sophisticated transformer-based language model with integrated Retrieval-Augmented Generation (RAG) capabilities for intelligent question answering and conversation.

A CBIR based Galaxy Morphology Classifier Intelligence

Efficiently search and retrieve information from PDF documents using a Retrieval-Augmented Generation (RAG) approach. This project leverages DeepSeek-R1 (1.5B) for advanced language understanding, FAISS for high-speed vector search, and Hugging Face’s ecosystem for enhanced NLP capabilities. With an intuitive Streamlit interface and Ollama for mode

A modular, production-ready Retrieval-Augmented Generation (RAG) backend that scrapes website content using Scrapling, chunks and embeds the text, and answers questions with an LLM (Groq API). Comes with a React frontend for seamless QA over any website.

Budget Buddy is a finance chatbot built using Chainlit and the LLaMA language model. It analyzes PDF documents, such as bank statements and budget reports, to provide personalized financial advice and insights. The chatbot is integrated with Hugging Face for model management, offering an interactive way to manage personal finances.

Built an agentic RAG chatbot with FAISS + MiniLM enabling accurate retrieval and grounded responses via Azure OpenAI

KnowMore is an AI-powered knowledge repository designed to organize, retrieve, and reason over large collections of institutional knowledge using modern Retrieval-Augmented Generation (RAG) techniques.

Developed an intelligent AI chatbot utilizing the DeepSeek LLM, designed for efficient interaction with large documents such as textbooks and study materials. Integrated Docling for parsing and processing large files, and implemented a Retrieval-Augmented Generation (RAG) pipeline using FAISS and Sentence Transformers to optimize context retrieval

A semantic movie recommendation system using NLP via (sentence-transformers + FAISS index).

An advanced Retrieval-Augmented Generation (RAG) pipeline with integrated sentiment analysis, user-selectable LLMs (GPT-2 or LLaMA), FAISS vector search, and RLHF-inspired reward scoring. It supports conversational memory with SQLite logging and features a dynamic Gradio UI for end-user interaction.

A modular, local AI companion featuring a RAG pipeline with FAISS and SentenceTransformers for semantic long-term memory. Powered by GGUF models via llama-cpp-python

This is a reasoning AI chatbot that uses Deepseek R1

AI-Powered Document Q&A Bot Stack: Python, LangChain, OpenAI, FAISS, Streamlit, FastAPI Highlights: Upload PDF → Chunk → Vectorize → Search → Answer using GPT Shows LLM, vector DB, chatbot flow Production-quality backend with LangChain and caching