Conversation
|
Thanks. I will be reviewing this over the weekend. |
|
@mishushakov hi! Can i get a review here pls? Thanks! |
There was a problem hiding this comment.
Hey @D1m7asis, some points:
-
I have tried running the JS example with my own API key and got this:
❌ Error: 2 | import { castToError } from "./core.mjs"; 3 | export class OpenAIError extends Error { 4 | } 5 | export class APIError extends OpenAIError { 6 | constructor(status, error, message, headers) { 7 | super(`${APIError.makeMessage(status, error, message)}`); ^ error: 403 status code (no body)
What am I doing wrong?
-
Can you make sure the example is same for both JS and Python?
-
I see that the examples are using
gpt-3.5-turbo- can you use a more recent model, as not a lot of people would be starting with GPT-3.5 today
Improved the JavaScript and Python AIML API example scripts for clarity, modularity, and robustness. Updated documentation for both examples, clarified model usage, and added a sample data.csv file for reproducible data science tasks. The JS and Python scripts now better extract and execute code from LLM responses, handle datasets, and save generated images.
|
Hey @mishushakov, thanks for the feedback 🙌 I’ve fixed the issues: Everything works now and the examples are identical across both languages 🚀 |
|
@mishushakov @tizkovatereza hi guys! a reminder to check on the PR :) |
mishushakov
left a comment
There was a problem hiding this comment.
left some comments regarding getting the stdout of the sandbox
Refactored JS and Python examples to streamline code execution in sandboxes, removing manual stdout/stderr collation and using the first result's text and image directly. Updated .env.example to include AIML_API_KEY and fixed README to link to the TypeScript example for AIML API.
|
@mishushakov thanks for the review 🙌 |
|
@mishushakov let us know if there is any other changes that need to be implemented |
🔄 Summary
This PR adds support for AI/ML API, an OpenAI-compatible provider offering 300+ models (e.g., DeepSeek, Gemini, ChatGPT), to the E2B Code Interpreter examples.
✅ What's Included
examples/aimlapi-js/: TypeScript example using E2B sandbox + AI/ML API via OpenAI SDKexamples/aimlapi-python/: Python version usingopenaiande2b-code-interpreter.env.template,README.md, and dependency setup for each variantREADME.mdwith proper UTM trackingLet me know if you'd like the examples styled/formatted differently — happy to iterate!