Open-source, secure environment with real-world tools for enterprise-grade agents.
Python agentaiai-agentai-agentscode-interpretercopilotdevelopmentdevtoolsgptgpt-4javascriptllmnextjsopenaipythonreactsoftwaretypescript
Update docs
Vasek Mlejnsky425bd5b6b751
diff --git a/apps/docs/src/app/llm-platforms/openai/page.mdx b/apps/docs/src/app/llm-platforms/openai/page.mdxindex 281ff376f..8e1f54cd5 100644--- a/apps/docs/src/app/llm-platforms/openai/page.mdx+++ b/apps/docs/src/app/llm-platforms/openai/page.mdx@@ -8,7 +8,7 @@ The Assistants API allows you to build AI assistants within your own applicationThe specific feature of the OpenAI's Assistants API that we'll take advantage of is the [Function calling](https://platform.openai.com/docs/assistants/tools/function-calling).-Follow our simple guides to let the OpenAI's assistant use the E2B sandbox to download files, use a custom cloud browser, use a terminal, write, run, and debug code, and more.+Follow our guides to let the OpenAI's assistant use the E2B sandbox to download files, use a custom cloud browser, use a terminal, write, run, and debug code, and more.- [Python](#python)- [JavaScript](#java-script)@@ -23,10 +23,6 @@ In Python, we will use the `sandbox.add_action()` method to register a Python fuThe Python function you register will always receive the `sandbox` instance as the first argument.This allows you to define your actions in separate files.-<Note title="Source Code">-See the full Python code in our [cookbook](https://github.com/e2b-dev/e2b-cookbook/tree/main/guides/openai-assistant-py).-</Note>-### 1. Import E2B and create a sandbox<CodeGroup isFileName title="main.py" isRunnable={false}>```py@@ -39,8 +35,8 @@ sandbox = Sandbox() # $HighlightLine</CodeGroup>### 2. Define the assistant's actions-An assistant action is a regular Python function that takes the sandbox object as the first argument and a dictionary with arguments as the second. The assistant will be able to call this function to complete its task when it runs.-The action can do pretty much anything you want - running code, downloading files, analyzing data, for example running a terminal command.+An assistant action is a regular Python function that takes the sandbox object as the first argument and a dictionary with function arguments as the second. The assistant will be able to call this function to complete its task when it runs.+The action can do pretty much anything you want - running code, downloading files, analyzing data, or running a terminal command.We define three actions:- `save_code_to_file`@@ -183,7 +179,6 @@ sandbox.close()</CodeGroup>-See the full code [here](https://github.com/e2b-dev/e2b-cookbook/blob/main/guides/openai-assistant-py/openai_assistant/main.py).---@@ -199,10 +194,6 @@ In JavaScript, we will use the `sandbox.addAction()` method to register a JavaScThe JavaScript function you register will always receive the `sandbox` instance as the first argument.This allows you to define your actions in separate files.-<Note title="Source Code">-See the full JavaScript code in our [cookbook](https://github.com/e2b-dev/e2b-cookbook/tree/main/guides/openai-assistant-js).-</Note>-### 1. Import E2B and create a sandbox<CodeGroup isFileName title="index.ts" isRunnable={false}>