End-to-End Chatbot Web App with Your Own Data
summary
A step‑by‑step build of an end‑to‑end chatbot that actually ingests PDFs, creates embeddings with an OpenAI deployment, registers a vector index in Azure AI Search, wires a PromptFlow with lookup logic and three system‑message variants, and publishes an authenticated real‑time endpoint consumed by a simple Flask web app. Demonstration shows upload → indexing → compute run → variant testing → endpoint deployment, includes API key use, quota warnings (free $200/30d, CPU/VM limits), and copy‑paste consume code for C#/Python/JS.
AI-written summary · about
chapters (15)
- 0:00Introduction to Azure AI and Chatbot Overview
- 1:03Meet the Presenter: Konstantinos Pasalis
- 1:52Setting Up Your Azure Environment
- 3:08Creating and Deploying PromptFlow
- 7:00Understanding Azure AI Hub and Projects
- 10:59Uploading and Indexing Data
- 16:19Building and Testing Your PromptFlow
- 24:55Setting Up the Semantic Configuration
- 25:17Registering and Selecting the Index
- 25:47Configuring the Lookup Function
- 26:41System Message and Variants
- 28:34Testing the Prompt Flow
- 31:25Deploying the Prompt Flow
- 36:59Integrating with a Web Application
- 46:35Final Thoughts and Recap
related talks
54mDeveloping Sophisticated Conversational Experiences w/ Microsoft AI Platform
42mLet’s Chat-Bots using Azure AI
48mTake an Azure OpenAI chat application from PoC to enterprise-ready
01h 12mBuild Your Own AI Chatbot with OpenAI & LangChain
01h 27mBuilding Contextual ChatBot using LLMs, Vector Databases & Python
20mBuild Intelligent Apps with .NET and Azure
01h 00mYour next app might be a bot! Building conversational UX with API.AI
27mLet's Chat-Bots using Azure AI