6 things you can do with azure_ai & PostgreSQL on Azure | POSETTE 2024
190 بار بازدید -
2 ماه پیش
-
Video of a conference talk
Video of a conference talk about what you can do with azure_ai & PostgreSQL on Azure presented by Denzil Ribeiro at POSETTE: An Event for Postgres 2024. Are you looking to spin up on how to leverage AI in Postgres in the cloud? This session will show you 6 things you can do today with the azure_ai and pgvector extensions combined with the Azure Database for PostgreSQL managed service. The session will cover how the azure_ai extension gives you the ability to call Azure OpenAI LLMS using SQL, plus how to use it in conjunction with pgvector from within your Postgres database. You’ll also see how the new AI features in Azure Database for PostgreSQL give you capabilities for text analytics, natural language processing, sentiment analysis, real-time translation, as well as how real-time scoring can invoke trained ML models. You will learn how easy it is to integrate your application with the Azure AI ecosystem.
Denzil is a Principal PM manager in the Azure Data PostgreSQL team. Most of his career has been at Microsoft and on databases building products or architecting scalable solutions to customer problems with data. Prior roles include several years in the Azure SQL product team, architecting highly scalable solutions in SQL CAT/ Azure Customer Advisory team as well as field facing roles working with tier-1 strategic customers.
Chapters:
00:00 - Intro
04:56 - Create embeddings with Azure OpenAI
07:02 - In-database create embeddings
09:01 - DEMO: Generate embeddings within the database
13:58 - DEMO: Same scenario with local embeddings
16:37 - Sentiment analysis
17:23 - Summarization & phrase extraction
17:59 - Real-time text translation
19:31 - DEMO: AI language & translation
22:26 - Real-time predictions with Azure Machine Learning
23:19 - DEMO: Azure Machine Learning integration
26:50 - Resources
📕 Everything you need to know about POSETTE: An Event for Postgres 2024 can be found at: https://aka.ms/posette
✅ Learn more:
Watch more POSETTE talks: https://aka.ms/posette-playlist-2024
📌 Let’s connect:
X – @PosetteConf https://x.com/PosetteConf
Mastodon - @posetteconf https://mastodon.social/@posetteconf
Threads – @posetteconf https://www.threads.net/@posetteconf
🔔 Subscribe to the POSETTE News: https://aka.ms/posette-subscribe
#PosetteConf #PostgreSQL #AI
Presenters:
Denzil Ribeiro, Principal PM Manager @ Azure Database for PostgreSQL
Connect:
Denzil Ribeiro: Twitter: denzilribeiro, LinkedIn: denzilribeiro
Denzil is a Principal PM manager in the Azure Data PostgreSQL team. Most of his career has been at Microsoft and on databases building products or architecting scalable solutions to customer problems with data. Prior roles include several years in the Azure SQL product team, architecting highly scalable solutions in SQL CAT/ Azure Customer Advisory team as well as field facing roles working with tier-1 strategic customers.
Chapters:
00:00 - Intro
04:56 - Create embeddings with Azure OpenAI
07:02 - In-database create embeddings
09:01 - DEMO: Generate embeddings within the database
13:58 - DEMO: Same scenario with local embeddings
16:37 - Sentiment analysis
17:23 - Summarization & phrase extraction
17:59 - Real-time text translation
19:31 - DEMO: AI language & translation
22:26 - Real-time predictions with Azure Machine Learning
23:19 - DEMO: Azure Machine Learning integration
26:50 - Resources
📕 Everything you need to know about POSETTE: An Event for Postgres 2024 can be found at: https://aka.ms/posette
✅ Learn more:
Watch more POSETTE talks: https://aka.ms/posette-playlist-2024
📌 Let’s connect:
X – @PosetteConf https://x.com/PosetteConf
Mastodon - @posetteconf https://mastodon.social/@posetteconf
Threads – @posetteconf https://www.threads.net/@posetteconf
🔔 Subscribe to the POSETTE News: https://aka.ms/posette-subscribe
#PosetteConf #PostgreSQL #AI
Presenters:
Denzil Ribeiro, Principal PM Manager @ Azure Database for PostgreSQL
Connect:
Denzil Ribeiro: Twitter: denzilribeiro, LinkedIn: denzilribeiro
2 ماه پیش
در تاریخ 1403/03/24 منتشر شده
است.
190
بـار بازدید شده