Getting started with generative AI using Azure OpenAI Service
summary
Announces concrete tooling: a chat completions API for multi-turn Copilots, an easy “Azure OpenAI on your data” workflow to ground GPT-3.5/GPT-4 on private content inside an Azure tenant, and interoperable plugins for Bing, Translator, and Cognitive Search. Azure Cognitive Search adds native vector search (HNSW, cosine/dot/EU metrics) and hybrid ranking; embeddings + RAG is demoed powering a document QA app (customer Schroders runs “Genie” to 6,000 users). Preview features include configurable content filters and limited Provision Throughput for large-scale production.
AI-written summary · about
chapters (11)
- 0:00Azure AI introduction
- 2:44GPT-4 and enterprise
- 5:21Emerging AI use cases
- 7:52New Azure OpenAI features
- 12:05Demo: OpenAI on your data
- 20:39Retrieval augmented generation
- 25:51Vector search integration
- 30:41Demo: Vector search
- 35:22Customer case study
- 39:00Azure OpenAI plugins
- 44:55Control and next steps
related talks
24mInfuse Generative AI in your apps using
39mDisrupt and Grow with Microsoft Azure AI
37mHarnessing OpenAI to help millions
01h 01mUnlocking the Potential of AI
16mUnlocking AI Innovation: A Conversation with Eric Boyd and Asha Sharma
51mThe Next Frontier: Azure OpenAI Models and the Arrival of GPT-4
47mAccessibility in the era of generative AI
59mOrchestrate your AI with Semantic Kernel