Code Interpreter API

Introduction

IntelliAsk's Code Interpreter API provides a secure and hassle-free way to execute code and manage files through a simple API interface. Whether you're using it through IntelliAsk's Agents or integrating it directly into your applications, the API offers a powerful sandbox environment for running code in multiple programming languages.

Getting Started

Code Interpreter ships as part of the IntelliAsk stack (the codeapi service). Once it's running, there's nothing for end users to install or configure:

1. Deploy the codeapi service with the rest of the stack — see Deploy → Components → Code Interpreter
2. The app is already wired to it: INTELLIASK_CODE_BASEURL points at the in-stack codeapi-api service and the signing keys are auto-provisioned — there's no API key to set
3. Start executing code and generating files securely through IntelliAsk's Agents or the "Run Code" button

Key Features

Supported Languages

Execute code in multiple programming languages:

• Python, Node.js (JS/TS), Go, C/C++, Java, PHP, Rust, Fortran, Rscript

Seamless File Handling

• Upload files for processing
• Download generated outputs
• Secure file management
• Session-based file organization

Security & Convenience

• Secure sandboxed execution environment
• Strong sandbox isolation (NsJail user namespaces)
• No local setup required for end users
• Session-based, isolated file storage

Programmatic Tool Calling

Programmatic Tool Calling lets IntelliAsk Agents route selected MCP tools through the Code Interpreter sandbox. Instead of asking the model to call each tool directly, IntelliAsk provides a Code Interpreter-backed orchestration tool; generated sandbox code can call registered tool stubs, use loops and conditionals, process intermediate results, and return a final answer.

The sandbox still does not receive general network access. Tool calls are brokered through the Code Interpreter Tool Call Server and IntelliAsk's registered tool map, so only tools available to the agent can be called.

Using the API

In IntelliAsk

The API has first-class support in IntelliAsk through these main methods:

1. AI Agents: Enable Code Interpreter in your agent's configuration to allow it to execute code and process files automatically.

2. Manual Execution: Use the "Run Code" button in code blocks within the chat interface, as shown here:

3. Programmatic Tool Calling: Enable the programmatic_tools capability and mark selected MCP tools as Programmatic so agents can orchestrate those tools from sandboxed code.

Authentication

There is no API key to manage. The IntelliAsk app authenticates to the Code Interpreter with a short-lived Ed25519 JWT that it mints per request; the signing keys are auto-provisioned with the stack. See Services → Code Interpreter → Security for how request authentication and signed execution manifests work.

Core Functionality

Code Execution

• Run code snippets in supported languages
• Receive stdout/stderr output
• Get execution statistics (memory usage, CPU time)
• Handle program arguments
• Access execution status and results

File Operations

• Upload input files
• Download generated outputs
• Preview generated Office, CSV, text, and PDF-like artifacts inline when IntelliAsk can safely extract/render them
• List available files
• Delete unnecessary files
• Manage file sessions

Generated artifact previews are intentionally size-bounded. Set FILE_PREVIEW_MAX_EXTRACT_BYTES in IntelliAsk's .env to change the source-file size limit for inline preview extraction; larger files remain available for download.

Limitations

• Code cannot access the network
• Only 10 files can be generated per run
• Resource limits (RAM per execution, file upload size, and request quotas) depend on how you provision and configure your deployment

Use Cases

• Code Testing: Test code snippets in multiple languages
• File Processing: Transform and analyze files programmatically
• AI Applications: Execute AI-generated code securely
• Development Tools: Build interactive coding environments
• Objective Logic: Verify code logic and correctness, improving AI models

Separate, scalable service

Code execution runs as its own service (the codeapi stack) rather than inside the chat app, which keeps the core IntelliAsk application lightweight and lets the sandbox infrastructure scale independently. It runs as a set of components — an API gateway, sandboxed workers, an egress gateway, a tool-call broker, and a file server — with strong isolation (NsJail user namespaces) so untrusted code runs safely.

For the architecture, the full environment surface, and the security model, see Services → Code Interpreter.

---

Conclusion

The Code Interpreter API provides a secure, convenient way to execute code and manage files in an isolated sandbox. Used through IntelliAsk's Agents or the "Run Code" button, it offers a robust solution for code execution needs — with no setup required from end users.