rag-agents

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

Local RAG researcher agent built using Langgraph, DeepSeek R1 and Ollama

QueryPilot is an advanced document intelligence platform that combines Large Language Models (LLMs) with vector embeddings to enable natural language querying of your documents. The application processes various file formats (PDFs, DOCXs, TXT files, and images), extracting and embedding content for semantic search and AI-powered analysis.

This repository contains the implementation of a Retrieval-Augmented Generation (RAG) agent using Large Language Models (LLMs). RAG agents combine the power of information retrieval with text generation, enabling applications such as intelligent question-answering systems, and more.

A fully local RAG agent that parses PDFs and enables contextual Q&A using LLaMA 3.2 via Ollama, ChromaDB, and Gradio — no internet or API keys required, with faster response time.

Production-grade document-intelligence RAG agent template — AWS Bedrock Knowledge Bases, OpenSearch-backed metadata/audit, dual-mode JWT + Azure AD SSO, multi-team isolation, and LibreOffice document conversion. Advanced tier of the Document Intel Agent Template family.

This project is a complete local RAG system for answering questions over document collections such as PDFs. It indexes documents, builds vector search indexes, routes queries to the right retrieval strategy, grades candidate results, and generates final answers with an LLM.

Local RAG researcher agent built using Langgraph, DeepSeek R1 and Ollama

Conversational academic writing Copilot: LangGraph ReAct agent with citation tracing, faithfulness reviewer, RAG & Reflexion LaTeX self-repair ｜ 对话式学术写作 Copilot：LangGraph ReAct 智能体，引用溯源 + 忠实度审校 + RAG 检索 + Reflexion 编译自修复，端到端产出真实 PDF

An AI-powered brand intelligence agent designed to enforce content consistency and brand alignment. It integrates sentiment analysis, vector-based similarity search (Sentence-Transformers), and context fusion logic to retrieve brand-specific guidelines from MongoDB and generate brand-aligned responses via Google's Generative AI.

Dexy — Twin Health's first production AI agent. Monitors an IMAP inbox for Dexcom sensor-replacement emails and classifies them with an LLM (baseline + RAG).

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

AI-powered medical assistant chatbot built using Streamlit, LangChain, and Hugging Face models for interactive health queries.

Enterprise-grade Retrieval Augmented Generation (RAG) demo on Azure

Python AI Course on LLM, RAG-Agents, LangGraph

Multi-tenant LLM prompt management + evaluation platform with a RAG agent. Versioned prompts, batch evals (4 judges), live SSE streaming. FastAPI · Next.js · Postgres/pgvector.