RAG Deep Dive

11:30 下午 - 12:30 上午 (UTC)

In this serieswe'll dive deep into our most popularfully-featuredand open-source RAG solution: https://aka.ms/ragchat Join us for the kick-off sessionwhere we'll do a live demo of the RAG solution and explain how it all works. We'll step through the RAG flow from Azure AI Search to Azure OpenAIdeploy the app to Azureand discuss the Azure architecture.

11:30 下午 - 12:30 上午 (UTC)

In this serieswe'll dive deep into our most popularfully-featuredand open-source RAG solution: https://aka.ms/ragchat In our second sessionwe'll show you how to customize the RAG solution for your own domain - adding your own datamodifying the promptsand personalizing the UI. Pluswe'll give you tips for local development for faster feature iteration.

11:30 下午 - 12:30 上午 (UTC)

In this serieswe dive deep into our most popularfully-featuredand open-source RAG solution: https://aka.ms/ragchat Our RAG solution uses Azure AI Search to find matching documentsusing state-of-the-art retrieval mechanisms. We'll dive into the mechanics of vector embeddingshybrid search with RRFand semantic ranking. We'll also discuss the data ingestion processhighlighting the differences between manual ingestion and integrated vectorization

11:30 下午 - 12:30 上午 (UTC)

In this serieswe dive deep into our most popularfully-featuredand open-source RAG solution: https://aka.ms/ragchat Do your documents contain images or charts? Our RAG solution has two different approaches to handling multimedia documentsand we'll dive into both approaches in this session. The first approach is purely during ingestion timewhere it replaces media in the documents with LLM-generated descriptions. The second approach stores images of the media alongside vector embeddings of the imagesand sends both text and images to a multimodal LLM for question answering. Learn about both approaches in this session so that you can decide what to use for your app. 📌 Get more RAG resources!

11:30 下午 - 12:30 上午 (UTC)

In this serieswe dive deep into our most popularfully-featuredand open-source RAG solution: https://aka.ms/ragchat In our RAG flowthe app first searches a knowledge base for relevant matches to a user's querythen sends the results to the LLM along with the original question. What if you have documents that should only be accessed by a subset of your userslike a group or a single user? Then you need data access controls to ensure that document visibility is respected during the RAG flow. In this sessionwe'll show an approach using Azure AI Search with data access controls to only search the documents that can be seen by the logged in user. We'll also demonstrate a feature for user-uploaded documents that uses data access controls along with Azure Data Lake Storage Gen2. 📌 Get more RAG resources!

11:30 下午 - 12:30 上午 (UTC)

In this serieswe dive deep into our most popularfully-featuredand open-source RAG solution: https://aka.ms/ragchat Learn how we store chat history using either IndexedDB for client-side storage or Azure Cosmos DB for persistent storage. We'll discuss the API architecture and data schema choicesdoing both a live demo of the app and a walkthrough of the code. 📌 Get more RAG resources!

11:30 下午 - 12:30 上午 (UTC)

In this serieswe dive deep into our most popularfully-featuredand open-source RAG solution: https://aka.ms/ragchat Our RAG solution includes optional features for speech input and outputpowered either by the free browser SDKs or by the powerful Azure Speech API. We also offer a tight integration with the VoiceRAG solutionfor those of you who want a real-time voice interface. Learn about all the ways you can add speech to your RAG chat in this session! 📌 Get more RAG resources!

11:30 下午 - 12:30 上午 (UTC)

In this serieswe dive deep into our most popularfully-featuredand open-source RAG solution: https://aka.ms/ragchat To ensure that the RAG app can only be accessed within your enterprise networkyou can deploy it to an Azure virtual network with private endpoints for each Azure service used. In this sessionwe'll show how to deploy the app to a virtual network that includes AI SearchOpenAIDocument Intelligenceand Blob storage. Then we'll log in to the virtual network using Azure Bastion with a virtual machine to demonstrate that we can access the RAG app from inside the networkand only inside the network. 📌 Get more RAG resources!

11:30 下午 - 12:30 上午 (UTC)

In this serieswe dive deep into our most popularfully-featuredand open-source RAG solution: https://aka.ms/ragchat How can you be sure that the RAG chat app answers are accurateclearand well formatted? Evaluation! In this sessionwe'll show you how to generate synthetic data and run bulk evaluations on your RAG appusing the azure-ai-evaluation SDK. Learn about GPT metrics like groundedness and fluencyand custom metrics like citation matching. Plusdiscover how you can run evaluations on CI/CDto easily verify that new changes don't introduce quality regressions. 📌 Get more RAG resources!

11:30 下午 - 12:30 上午 (UTC)

In this serieswe dive deep into our most popularfully-featuredand open-source RAG solution: https://aka.ms/ragchat When your RAG app is in productionobservability is crucial. You need to know about performance issuesruntime errorsand LLM-specific issues like Content Safety filter violations. In this sessionlearn how to use Azure Monitor along with OpenTelemetry SDKs to monitor the RAG application. 📌 Get more RAG resources!

11:30 下午 - 12:30 上午 (UTC)

In this serieswe'll dive deep into our most popularfully-featuredand open-source RAG solution: https://aka.ms/ragchat For this sessionwe'll explore how we can use OpenAI function calling to extend the functionality of the RAG application. We can use function calling to retrieve data from more sources (like additional AI Search indexes or Bing API)to handle different kind of user requests (like summarization instead of searching)and even to escalate conversations to a human. With function callingour RAG can handle multiple data sources or even become agentic. 📌 Get more RAG resources!