Vasek Mlejnsky
cd4880eeae
This PR improves CLI messaging when building sandbox templates. Now, the used Docker commands are explicitly logged to the user like this: ``` Building docker image with the following command: docker build . \ # <--- This log is new -f e2b.Dockerfile \ --pull --platform linux/amd64 \ -t docker.e2b.dev/e2b/custom-envs/vqwjjtzwfi59d1cwww1k:ec8a819a-9666-45df-997b-e181b9fe4224 [+] Building 0.7s (5/5) FINISHED docker:desktop-linux => [internal] load build definition from e2b.Dockerfile 0.0s => => transferring dockerfile: 149B 0.0s => [internal] load metadata for docker.io/library/ubuntu:22.04 ``` and ``` Pushing docker image with the following command: docker push docker.e2b.dev/e2b/custom-envs/vqwjjtzwfi59d1cwww1k:ec8a819a-9666-45df-997b-e181b9fe4224 # <--- This log is new The push refers to repository [docker.e2b.dev/e2b/custom-envs/vqwjjtzwfi59d1cwww1k] ``` so the user can potentially debug some issues on their own.
What is E2B?
E2B is an open-source infrastructure that allows you to run AI-generated code in secure isolated sandboxes in the cloud. To start and control sandboxes, use our JavaScript SDK or Python SDK.
Note
This repository contains the core E2B SDK that's used in our main E2B Code Interpreter SDK.
Run your first Sandbox
1. Install SDK
JavaScript / TypeScript
npm i @e2b/code-interpreter
Python
pip install e2b-code-interpreter
2. Get your E2B API key
E2B_API_KEY=e2b_***
3. Execute code with code interpreter inside Sandbox
JavaScript / TypeScript
import { Sandbox } from '@e2b/code-interpreter'
const sandbox = await Sandbox.create()
await sandbox.runCode('x = 1')
const execution = await sandbox.runCode('x+=1; x')
console.log(execution.text) // outputs 2
Python
from e2b_code_interpreter import Sandbox
with Sandbox() as sandbox:
sandbox.run_code("x = 1")
execution = sandbox.run_code("x+=1; x")
print(execution.text) # outputs 2
4. Check docs
Visit E2B documentation.
5. E2B cookbook
Visit our Cookbook to get inspired by examples with different LLMs and AI frameworks.