SmartRAG is a modular Python library designed for retrieval-augmented generation (RAG) workflows with large language models. It combines document ingestion, vector indexing, and state-of-the-art LLM APIs to deliver accurate, context-rich responses. Users can import PDFs, text files, or web pages, index them using popular vector stores like FAISS or Chroma, and define custom prompt templates. SmartRAG orchestrates the retrieval, prompt assembly, and LLM inference, returning coherent answers grounded in source documents. By abstracting the complexity of RAG pipelines, it accelerates development of knowledge base Q&A systems, chatbots, and research assistants. Developers can extend connectors, swap LLM providers, and fine-tune retrieval strategies to fit specific knowledge domains.

Contoso Creative Writer is an open-source sample project demonstrating how to build and deploy an AI-driven creative writing assistant using Azure AI services. Leveraging Azure OpenAI models, Bot Framework, and optional Semantic Kernel integration, this agent engages users through conversational prompts to generate story ideas, character backstories, dialogue suggestions, and plot outlines. Developers can customize prompt templates, adjust tone and writing style, and integrate additional data sources. The application includes a web-based chat interface powered by Azure Bot Service, enabling real-time interactions and seamless cloud deployment. With modular architecture and clear code examples, Contoso Creative Writer serves as a foundation for creating tailored writing solutions, from fiction storytelling to marketing copy generation, enhancing creativity and productivity.

LangChain RAG Agent Chatbot sets up a pipeline that ingests documents, converts them into embeddings with OpenAI models, and stores them in a FAISS vector database. When a user query arrives, the LangChain retrieval chain fetches relevant passages, and the agent executor orchestrates between retrieval and generation tools to produce contextually rich answers. This modular architecture supports custom prompt templates, multiple LLM providers, and configurable vector stores, making it ideal for building knowledge-driven chatbots.