Multi AI agents for customer support email automation built with Langchain & Langgraph

RAG-API: A production-ready Retrieval Augmented Generation API leveraging LLMs, vector databases, and hybrid search for accurate, context-aware responses with citation support.

🛡️ Web3 Guardian is a comprehensive security suite for Web3 that combines browser extension and backend services to provide real-time transaction analysis, smart contract auditing, and risk assessment for decentralized applications (dApps).

pdfKotha.AI - Interact with PDFs using AI! Upload, ask questions, and get instant answers from Google's Gemini model. Streamline your research and information retrieval tasks effortlessly

BetterRAG: Powerful RAG evaluation toolkit for LLMs. Measure, analyze, and optimize how your AI processes text chunks with precision metrics. Perfect for RAG systems, document processing, and embedding quality assessment.

A supportive server to handle telegram messages using telegram bot API, return back the response to the user with RAG application techniques

Ask questions. Get answers. Unlock insights from SEC 10-K filings with Generative AI.

A custom Agentic Retrieval-Augmented Generation (RAG) model that is an expert in cell culture techniques and knowledge.

🤖 NoCapGenAI is a Retrieval-Augmented Generation (RAG) chatbot built with Streamlit, Ollama, MongoDB, and ChromaDB. It features a clean, modern UI and persistent vector memory for context-aware conversations. Easily integrates with Ollama-supported models like phi3:mini, llama3, mistral, and more. Designed to support customizable assistant modes

This project processes and retrieves information from PDF file or PDF collection. It leverages Qdrant as a vector database for similarity searches and employs a Retrieval-Augmented Generation (RAG).

A Customizable RAG (Retrieval Augmented Generation) App

A command-line RAG Chatbot application built from scratch

RAG-powered PDF QA system with self-reflection and multiple retrieval strategies (Stuff/Map Reduce/Refine). Includes monitoring via Langfuse & LangSmith and containerization with Docker

This project utilizes advanced Large Language Models (LLMs) and vector database technologies to extract structured information about characters from literary texts. It is designed to analyze a given text, identify key characters, and determine their summaries, relationships, and roles (e.g., Protagonist, Antagonist, or Side character)