Uh oh!
There was an error while loading.Please reload this page.
- Notifications
You must be signed in to change notification settings - Fork35.9k
Editor: Added agent#30761
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to ourterms of service andprivacy statement. We’ll occasionally send you account related emails.
Already on GitHub?Sign in to your account
base:dev
Are you sure you want to change the base?
Editor: Added agent#30761
Uh oh!
There was an error while loading.Please reload this page.
Conversation
Nice! Time to InstructPipe / Idea2Reality to three.js :)https://duruofei.com/papers/Zhou_InstructPipe-BuildingVisualProgrammingPipelinesInVisualBlocksWithHumanInstructionsUsingLLMs_CHI2025.pdf |
Uh oh!
There was an error while loading.Please reload this page.
…rt, function or classCo-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
Uh oh!
There was an error while loading.Please reload this page.
editor/js/Agent.js Outdated
@@ -192,7 +192,7 @@ class Agent { | |||
async init() { | |||
// Initialize Google AI | |||
const ai = new GoogleGenAI( { apiKey: 'GENAI_API_KEY' } ); | |||
const ai = new GoogleGenAI( { apiKey: 'AIzaSyAHEPxUn9Ow4Lk8oXM4jl3u_stzOIxkkGM' } ); |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others.Learn more.
@mrdoob any problem on exposing this key?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others.Learn more.
I was exposing it intentionally, but seems like githack doesn't like serving stuff with keys...
Description
I thought it would be interesting to try to add an agent to the editor.
This is how it currently looks like:
Screen.Recording.2025-03-20.at.15.30.19.mov
Currently I'm building it using@google/genai.
Ideally we would just use the AI that comes with the browser using the Prompt API:
https://developer.chrome.com/docs/extensions/ai/prompt-api