Este projeto permite realizar perguntas em linguagem natural sobre o conteúdo de arquivos PDF. Utiliza a abordagem RAG (Retrieval-Augmented Generation)
-
Updated
Jul 27, 2025 - Python
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.
CICD Answering-Question Chatbot for RAG (Retrieval-Augmented Generation) using Streamlit
🧠 Multimodal Retrieval-Augmented Generation that "weaves" together text and images seamlessly. 🪡
Creating basic microservices project structure for basic RAG chatbot
RAG-based chatbot for financial report analysis using LangChain, FAISS, and Groq LLM.
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
A web app that converts audio to text and enhances transcription with Retrieval-Augmented Generation (RAG). Upload audio, get accurate transcriptions with contextual enrichment using external knowledge sources
This is a reasoning AI chatbot that uses Deepseek R1
Multi Document RAG Application
A lightweight image search engine that lets you upload a dataset and find similar images using either text queries or image queries, powered by CLIP embeddings, FAISS vector search, FastAPI, and a Streamlit UI.
Survey & Experimental Analysis of Maximum Inner Product Search (MIPS) Methods
Successfully developed a Healthcare AI Clinical Decision Support System, leveraging LangGraph, GPT-4o-mini, and PubMed to deliver real-time patient risk stratification, evidence-based treatment recommendations, and personalized clinical road maps with integrated drug safety validations.
It is an ML_Chatbot that explains concepts and terminologies using open-source tools. Used Hugging Face for embeddings, FAISS CPU for vector storage, and Mistral with streamlit for a conversational interface.
A high-performance image deduplication pipeline using ResNet50 features, FAISS vector search, and Graph Clustering. Optimized for 100k+ datasets on Apple Silicon & CUDA.
Research Mate is a end to end LLM model using langchain, designed to assist researchers, students, and professionals in efficiently processing and extracting insights from research articles and online content. Users can input multiple research URLs, which the app processes and converts into useful information.
Metallum/Metal-Archives scrapers, datasets, analysis and recommendations website
FAQ_Chatbot is a Bangla‑language FAQ chatbot powered by a Retrieval‑Augmented Generation (RAG) pipeline. It combines semantic‑search over a curated FAQ knowledge base with large‑language‑model inference to provide contextual, human‑like answers to user queries
GenAI-Powered Document Assistant: Architected a conversational AI assistant using LangChain to answer natural language questions from a 500+ page knowledge base. Implemented a RAG pipeline with a FAISS vector DB and a cross-encoder re-ranker, improving answer relevance by 18% over standard vector-search baseline
Add a description, image, and links to the faiss-cpu topic page so that developers can more easily learn about it.
To associate your repository with the faiss-cpu topic, visit your repo's landing page and select "manage topics."