{"repo":"Azure-Samples/chat-with-your-data-solution-accelerator","free":true,"listed":false,"github":"https://github.com/Azure-Samples/chat-with-your-data-solution-accelerator","clone":"git clone https://github.com/Azure-Samples/chat-with-your-data-solution-accelerator.git","description":"A Solution Accelerator for the RAG pattern running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences. This includes most common requirements and best practices.","language":"Python","stars":1174,"topics":["ai-search","azd-templates","azure","azure-openai","openai"],"license":"MIT","category":"ai-agents","readme_excerpt":"Chat with Your Data Ground a conversational assistant in your own documents and get answers with inline citations back to the source. Organizations hold vast unstructured knowledge in contracts, policies, product manuals, and benefit guides that is hard to search and slow to answer questions from. Chat with Your Data indexes that content and puts a natural-language chat experience in front of it, so people find grounded answers in seconds instead of digging through files. Everything deploys into your own Azure subscription with a single azd up . SOLUTION OVERVIEW     QUICK DEPLOY     BUSINESS SCENARIO     SUPPORTING DOCUMENTATION [!NOTE] With any AI solution you create using these templates, you are responsible for assessing all associated risks and complying with all applicable laws and safety standards. This accelerator is a starting point, not a turnkey production system. Evaluate retrieval quality, answer accuracy, and responsible-AI considerations against your own data before you rely on it. See the Responsible AI Transparency FAQ. Solution overview Architecture The solution runs entirely on Azure Container Apps: a React single-page app, a FastAPI backend, and an Azure Functions ingestion worker. The backend calls Azure AI Foundry for models and retrieval, and reads and writes its index and chat history in either Azure AI Search with Cosmos DB or PostgreSQL with pgvector, chosen at deploy time. A user-assigned managed identity authorizes eve","default_branch":null,"files":null,"tree":[],"storefront":"/r/Azure-Samples","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/Azure-Samples/chat-with-your-data-solution-accelerator/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."}