Building a custom documentation assistant using AI has become achievable with the help of GPT, LangChain and other AI tools. But how can we control the content quality of the coffee chat made to our document assistant, from the user to the assistant’s response? What options do we have to enhance the content safety in our question-and-answer flow, while scaling our project to handle further scenarios?
Chapters:
00:08 Welcome and Intro
01:20 Document Q&A Chat intro
03:37 Disclaimer - potentially sensitive content
05:00 Content Moderation - Responsible AI
06:44 Azure AI Content Safety
09:33 Demo
16:43 Integrate into an orchestration flow
17:49 Azure OpenAI - Content Filters
19:14 Azure AI Content Safety vs. Azure Open AI Content Filters
21:44 Next Steps
23:29 Wrap
Links:
Repo aka.ms/contoso-real-estate/gi...
Learn Collection aka.ms/JavaScriptDay
Featuring: Maya Shavin, Senior Software Engineer
Follow us on social:
Blog - aka.ms/azuredevelopers/blog
Twitter - aka.ms/azuredevelopers/twitter
LinkedIn - aka.ms/azuredevelopers/linkedin
Twitch - aka.ms/azuredevelopers/twitch
#azuredeveloper #azure
Негізгі бет Ғылым және технология Have a safe coffee chat with your documentation using Azure AI Services | JavaScript Dev Day
Пікірлер: 1