No video
Build gen AI features powered by your data with Firebase and PostgreSQL
Рет қаралды 9,533
Күн бұрынLearn how Firebase Data Connect uses PostgreSQL to increase velocity at every stage of app development including powerful new gen AI capabilities with Genkit. Learn how tool calling and structured output can make programming with LLMs feel more like programming with any other API. Learn how to safely use your application's data to drive AI-powered experiences.
Speaker: Michael Bleigh
Watch more:
Check out all the Web videos at Google I/O 2024 → goo.gle/io24-w...
Check out out all the Firebase sessions from Google I/O → goo.gle/io24-f...
Subscribe to Firebase → goo.gle/Firebase
#GoogleIO
Products Mentioned: Firebase Data Connect, Firebase Genkit, Firebase App Hosting, Remote Config
Event: Google I/O 2024
@mralek5720 3 ай бұрын
Amazing demo! Really impressed by the seamless integration between Data Connect & GenKit and the associated dev tools. This is hands-down the easiest way to integrate RAG into an app I've seen, well done! 👏
@michaelbleigh8737 3 ай бұрын
Thanks, that's kind of you to say!
@ArielPettyjohn 3 ай бұрын
We've climbed to a dizzying level of abstraction and automation! Amazing 👏
@missedme0063 25 күн бұрын
VERY cool demo, thank you!
@rahulgupta7720 2 ай бұрын
Very Informative tutorial! Genkit is truly the future of building AI driven apps. Would love to get much more tutorials in the future
@robinryf5 3 ай бұрын
Very awesome introduction! This is doable for everybody who is interested and eager to learn. Thank you. I wonder what other use cases there could be besides search 🤔
@kevingrondin974 3 ай бұрын
@Michael Bleigh you can share your code on your github ?
@michaelbleigh8737 3 ай бұрын
A version of the Compass app will be published to GitHub in the coming weeks (I think)...stay tuned! You can also go through this codelab which covers much of the same content but uses Firestore (since it's generally available): firebase.google.com/codelabs/ai-genkit-rag#0
@samario_torres 2 ай бұрын
is this easy to integrate with cloud firestore? is there a simple way to connect my firestore database to data connect and have both databases collecting data?
@michaelbleigh8737 2 ай бұрын
Firestore integration is something we're looking at for the future. You can vote on it here: firebase.uservoice.com/forums/948424-general/suggestions/48434618-cloud-firestore-datasource
@samario_torres 2 ай бұрын
@@michaelbleigh8737 awesome thank you for replying, just voted!
@vijayjangid8967 3 ай бұрын
Finally!!!!!!!!!!!!!!!
@user-xv8dn4nm5k 3 ай бұрын
👍
@nickjunes 3 ай бұрын
Is the error you're getting because you already did a vector comparison search with your searchDestinations function? If not why do you need a retriever if you already did a vector comparison search in searchDestinations with plain text? It seems like the vector comparison search can already understand plain text. What am I missing?
@michaelbleigh8737 3 ай бұрын
The error was actually because I forgot to alias deatinations_embedding_similarity to "destinations". The database doesn't store embeddings as text or have the ability to natively query text against vectors -- instead you have to use an embedding model to convert text into a vector then compare vector to vector. That's what _embed does.
@nickjunes 3 ай бұрын
@@michaelbleigh8737 So what does destinations_embed_simlarity do then? At 26:44 you pass it a query with plain text and are able to get some results from the database. How can you do that without first converting the query into a vector?
@michaelbleigh8737 3 ай бұрын
@@nickjunes destinations_embed_similarity performs a vector similarity search, compare_embed generates an embedding from the provided query.
@jerryf196 3 ай бұрын
how do you generate the embeddings? You ran a script but does it use the vertex firebase SDK?
@mbleigh 3 ай бұрын
The embeddings were generated using the Vertex AI API through Firebase Genkit.
@jerryf196 3 ай бұрын
@@mbleigh Thanks. I got it running with my project. Is it possible to add words that refine searches. For example: good exploration board game that plays best at 2 players. In my firestore data, I have a field that contains number of player count
@jerryf196 3 ай бұрын
@@mbleigh also for the dreamVacation.ts how do you run this flow? Like thiis? const response = await runFlow(dreamVacationFlow, 'Some input');
@mbleigh 3 ай бұрын
@@jerryf196 runFlow(dreamVacationFlow, {imageUrls: [...], description: "..."})
@mbleigh 3 ай бұрын
@@jerryf196 to do something like that you'd probably want function calling - you use defineTool to create a tool with parameters like "maxPlayers" then map that to a Firestore combined vector + filtering query. It looks like we don't have great docs for function calling yet for Genkit, will take note to improve that.
@darthvader4899 3 ай бұрын
what's that .prompt file? is it special to idx?
@michaelbleigh8737 3 ай бұрын
It's part of the Firebase Genkit framework, see firebase.google.com/docs/genkit/dotprompt
@darthvader4899 3 ай бұрын
@@michaelbleigh8737 really cool. Is this going to be standardized?
@ruandupreez6144 3 ай бұрын
His shirt?
@__user__name__ 3 ай бұрын
Despite the bit of dirt on his shirt, he carried on without a care. That's what kept me watching the entire video and earned my respect for him.
@ArielPettyjohn 3 ай бұрын
That's how you know he's pro. There used to be a place that sold hip boutique t-shirts with arty wine stains and tire tracks on them. I'm sure, sooner or later, pre-stained t-shirts will become a thing like pre-torn blue jeans. He's just flexing because he's ahead of the curve 😎
@k-c 3 ай бұрын
Your priorities?
@JohnMcclaned 2 ай бұрын
I'd trust a dev with stains on their shirt over a corporate goon any day of the week.
Google for Developers
Рет қаралды 53 М.
Chrome for Developers
Рет қаралды 9 М.