What is the database behind ChatGPT?

  Рет қаралды 10,622

Microsoft Mechanics

Microsoft Mechanics

Күн бұрын

Take advantage of Azure Cosmos DB for your AI-driven applications. Seamlessly integrate with large language models like ChatGPT, for real-time operational efficiency and limitless scalability. With its built-in vector search engine and multi-model support, Azure Cosmos DB for MongoDB vCore optimizes for just-in-time data retrieval, so you can build cutting-edge solutions at any scale.
Kirill Gavrylyuk, General Manager for the Azure Cosmos DB team, joins Jeremy Chapman to share how you can increase performance and cost-effectiveness, whether managing millions of users globally or building smaller-scale apps.
► QUICK LINKS:
00:00 - Get your database ready for AI with Azure Cosmos DB
02:33 - Solve for real-time data access requirements
03:39 - Automatic scaling
05:35 - How Azure CosmosDB works for copilot-style apps
06:38 - App using vectorized data
07:24 - Jupyter notebook demo
09:19 - Vector indexing and search in Azure Cosmos DB
10:14 - Building a small copilot-style app
12:10 - Run smaller apps serverless
12:35 - Set maximum throughput thresholds
13:39 - Auto scale using Azure Cosmos DB
14:38 - Wrap Up
► Link References:
See how Cosmos DB vector search capabilities work at aka.ms/CosmosVector
Get a free trial at aka.ms/trycosmosdb
► Unfamiliar with Microsoft Mechanics?
As Microsoft's official video series for IT, you can watch and share valuable content and demos of current and upcoming tech from the people who build it at Microsoft.
• Subscribe to our KZfaq: / microsoftmechanicsseries
• Talk with other IT Pros, join us on the Microsoft Tech Community: techcommunity.microsoft.com/t...
• Watch or listen from anywhere, subscribe to our podcast: microsoftmechanics.libsyn.com...
► Keep getting this insider knowledge, join us on social:
• Follow us on Twitter: / msftmechanics
• Share knowledge on LinkedIn: / microsoft-mechanics
• Enjoy us on Instagram: / msftmechanics
• Loosen up with us on TikTok: / msftmechanics
#AzureCosmosDB #GenerativeAI #VectorSearch #chatgpt #CosmosDB

Пікірлер: 11
@synthwave7
@synthwave7 3 ай бұрын
Wow -this is the best video on how AI actually works. I like how Kirill explains the stuff. Impressive. MS TEAMS one of the largest tranactional DB's was also interesting.
@OliverFisy
@OliverFisy 22 күн бұрын
Great video! Underrated
@yourbossdonpely
@yourbossdonpely 4 ай бұрын
Awesome always wondered how the latency issue was optimized wow
@vgupta4760
@vgupta4760 4 ай бұрын
Excellent explanation! Thanks.
@MSFTMechanics
@MSFTMechanics 4 ай бұрын
Glad it was helpful!
@Joe-tk8cx
@Joe-tk8cx 4 ай бұрын
Awesome, can this notebook be shared ?
@astatine0085
@astatine0085 4 ай бұрын
can you auto-adjust the throughput thresholds, or does someone have to manually set / reset them?
@KirillGavrylyuk
@KirillGavrylyuk 4 ай бұрын
the min/max instant Autoscale window can be programmatically adjusted at any time, as frequently as needed.
@nickadams2361
@nickadams2361 4 ай бұрын
Like a hundred database accounts on this guy's AD. Would love to see the costs section
@Build5Nines
@Build5Nines Ай бұрын
I heard him mention five 9's of availability! 🥳
@MSFTMechanics
@MSFTMechanics Ай бұрын
That's what you want 😉 it's good to stay under 315 seconds per year
How vector search and semantic ranking improve your GPT prompts
15:09
Microsoft Mechanics
Рет қаралды 18 М.
БОЛЬШОЙ ПЕТУШОК #shorts
00:21
Паша Осадчий
Рет қаралды 8 МЛН
孩子多的烦恼?#火影忍者 #家庭 #佐助
00:31
火影忍者一家
Рет қаралды 40 МЛН
Get Copilot responses based on your own files (no copy/paste)
13:33
Microsoft Mechanics
Рет қаралды 9 М.
Why Donut Media Is Falling Apart: An Explainer
17:07
Alanis King
Рет қаралды 177 М.
Google Releases AI AGENT BUILDER! 🤖 Worth The Wait?
34:21
Matthew Berman
Рет қаралды 219 М.
Extend your data security to Microsoft Fabric
8:48
Microsoft Mechanics
Рет қаралды 9 М.
Vector Databases simply explained! (Embeddings & Indexes)
4:23
AssemblyAI
Рет қаралды 292 М.
Secret Wireless charger 😱 #shorts
0:28
Mr DegrEE
Рет қаралды 2,5 МЛН
В России ускорили интернет в 1000 раз
0:18
Короче, новости
Рет қаралды 1,3 МЛН