Back to directory

ChatGPT + Enterprise data with Azure OpenAI and Azure AI Search

A TypeScript sample application demonstrating the Retrieval Augmented Generation pattern on Azure, using Azure AI Search for retrieval and Azure OpenAI to power a ChatGPT-style Q&A experience over a company's own documents.

ChatGPT + Enterprise data with Azure OpenAI and Azure AI Search

This is a sample TypeScript application that demonstrates the Retrieval Augmented Generation pattern on Azure, using Azure AI Search for indexing and retrieval and Azure OpenAI to power a ChatGPT-style chat and Q&A experience over a company's own documents.

It ships with sample data for a fictitious real-estate company, including its terms of service, privacy policy and support guide, so it can be deployed and tried end to end. It is made of a search service, an indexer service that builds the search indexes, and a web app that provides the user interface and orchestrates the interaction between the model and the retriever.

Features include citations and source tracking so users can evaluate the trustworthiness of a response, adjustable settings in the UI to experiment with retrieval and prompt behavior, and optional performance tracing with Application Insights.

More in RAG

See all 540
  • ai·rete·rag

    ai-rete-rag.com

    A platform that pairs a Rete rule engine with retrieval-augmented generation, so deterministic rules decide an outcome and grounded retrieval explains the decision in plain language.

  • Xtriever

    github.com

    A hybrid retrieval engine for retrieval-augmented generation, written in Rust to run on-device on a phone or a laptop, combining lexical BM25 search, dense embedding search, reciprocal-rank fusion and cross-encoder re-ranking with no server.

  • FileFlux

    github.com

    A .NET library that turns PDF, DOCX, HWP and other documents into optimized chunks for RAG systems, through a five-stage pipeline built on high-performance Rust FFI readers.