| Author(s) | Kristopher Overholt |
Data Store Agent is a feature within Vertex AI Conversation that is built on top of functionality in Dialogflow CX.
With a Data Store Agent, you can provide a website domain, structured data, or unstructured data, then the Data Store Agent parses your content and creates a virtual agent that is powered by data stores and large language models. Your customers and end users can then have conversations with the agent and ask questions about the content. Refer to the Data Store Agent documentation and codelab to Create a Generative Chat App with Vertex AI Conversation for more information.
- Install Node.js using your preferred method or package manager
- From this directory, run
npm install - Run
npm run buildto generate the static site in thebuilddirectory
-
Navigate to the Firebase console
-
Provision Firebase on a new or existing GCP project
-
In Firebase console, go to Hosting and add a new site (e.g.,
your-firebase-app-name) -
Install the firebase CLI
-
Run
firebase initin the app root and follow the prompts to selectHosting, use thebuilddirectory, and confirmNto the followup questions about rewrites, deploys, and the 404 and index pages. -
Run
firebase target:apply hosting your-firebase-app-name your-firebase-app-namewhereyour-firebase-app-nameis the name of the Firebase Hosting site that you created in an earlier step -
To configure the default deploy target, add a line to your
firebase.jsonwith the name of your Firebase Hosting site, such as:{ "hosting": { "target": "your-firebase-app-name", # <--- Add this line "public": "build", "ignore": [ "firebase.json", "**/.*", "**/node_modules/**" ] } } -
Run
firebase deploy
In your browser, navigate to your deployed app using a URL similar to:
https://vertex-ai-conversation.web.app/
Congratulations, you've successfully deployed the Vertex AI Conversation Demo!
You can continue learning about conversational AI and generative AI with these guides and resources:
