{"repo":"Azure-Samples/llama-index-vector-search-javascript","free":true,"listed":false,"github":"https://github.com/Azure-Samples/llama-index-vector-search-javascript","clone":"git clone https://github.com/Azure-Samples/llama-index-vector-search-javascript.git","description":"A sample app for the Retrieval-Augmented Generation pattern using LlamaIndex.ts, running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences using your own data.","language":"TypeScript","stars":15,"topics":["azure","azure-openai","azureai","llamaindex","nextjs","openai","rag","vector-search"],"license":"MIT","category":"ai-agents","readme_excerpt":"LlamaIndex RAG chat app with Azure OpenAI and Azure AI Search (JavaScript) This solution creates a ChatGPT-like, Retrieval Augmented Generation (RAG) agentic application, over your own documents, powered by Llamaindex (TypeScript). It uses Azure OpenAI Service to access GPT models and embedding, and Azure AI Search for data indexing and retrieval. Learn more about developing AI apps using Azure AI Services. Important Security Notice This template, the application code and configuration it contains, has been built to showcase Microsoft Azure specific services and tools. We strongly advise our customers not to make this code part of their production environments without implementing or enabling additional security features. See our productionizing guide for tips, and consult the Azure OpenAI Landing Zone reference architecture for more best practices. Table of Contents - LlamaIndex RAG chat app with Azure OpenAI and Azure AI Search (JavaScript) - Important Security Notice - Table of Contents - Architecture Diagram - Azure account requirements - Cost estimation - Getting Started - GitHub Codespaces - VS Code Dev Containers - Local environment - Deploying - Deploying again - Running the development server - Using Docker (optional) - Running application at no cost - Using the app - Clean up - Guidance The repo includes sample data so it's ready to try end to end. In this sample application we use one of Paul Graham's essays, What I Worked On, and the experience allows you to ask q","default_branch":null,"files":null,"tree":[],"storefront":"/r/Azure-Samples","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/Azure-Samples/llama-index-vector-search-javascript/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}