Code Interpreter v2.0

[Vasek Mlejnsky]

The current version of the code interpreter SDK allows to run Python code but each run has its own separate context. That means that subsequent runs can't reference to variables, definitions, etc from past code execution runs.

This is suboptimal for a lot of Python use cases with LLMs. Especially GPT-3.5 and 4 expects it runs in a Jupyter Notebook environment. Even when ones tries to convince it otherwise. In practice, LLMs will generate code blocks which have references to previous code blocks. This becomes an issue if a user wants to execute each code block separately which often is the use case.

Related #326

[Kelvin Wong]

What's the status on this?

[Vasek Mlejnsky]

We have new code interpreter in works and some users are already using it. You can go ahead and start using it here - #326

It'll be soon released on the main branch.

If you give it a try, please share your feedback, it's tremendously helpful for us

[Vasek Mlejnsky]

@im-calvin let me know if you're asking about anything specific such as a feature that's blocking you

[Kelvin Wong]

Thanks for the update. I'm trying it out right now, I'm getting this error

RPC Error (-32000): error reading file '/root/.jupyter/kernel_id': open /root/.jupyter/kernel_id: no such file or directory

EDIT: I'm using version 0.12.6-stateful-code-interpreter.8 and calling sandbox.execPython(code) from within Typescript

[Vasek Mlejnsky]

@im-calvin Can you share the code? Are you using custom sandbox template?

[Kelvin Wong]

Here's my code & Dockerfile

# e2b.Dockerfile

# You can use most of the Debian-based base images
FROM ubuntu:22.04

# Install the ffmpeg tool/
RUN apt update \
  && apt install -y ffmpeg

const sandbox = await CodeInterpreterV2.create({
  template: "custom-sandbox",
  apiKey: process.env["E2B_API_KEY"],
});

const result = await sandbox.execPython(code);

[Jakub Novák]

I added section to the PR about custom templates. If there's anything unclear, let me know :)
#326

[Vasek Mlejnsky]

Implemented in a separate SDK - https://github.com/e2b-dev/code-interpreter