Code Interpreter Tool

Enable agents to write and execute Python code in sandboxed environments for data analysis, calculations, and visualizations.

Code Interpreter Tool

Code Interpreter allows agents to write and run Python code in a sandboxed execution environment. Agents can iteratively solve complex problems involving code, math, data analysis, or create graphs and charts.

Key Features

• Iterative execution: Agents can modify and retry code until it works
• Data analysis: Process CSV files and perform calculations
• Visualizations: Generate charts and graphs
• File support: Upload and download files
• Automatic retry: Failed code is automatically revised

Code Interpreter has additional charges beyond token-based fees. Each concurrent session is billed separately (active for 1 hour by default, 30-minute idle timeout).

Quick Start

Python

from azure.ai.projects.models import CodeInterpreterTool

code_interpreter = CodeInterpreterTool()

agent = project.agents.create_agent(
    model="gpt-4o",
    name="data-analyst",
    instructions="You can analyze data and create visualizations",
    tools=code_interpreter.definitions,
    tool_resources=code_interpreter.resources,
)

Attaching Files

Python

# Upload file
file = project.agents.files.upload_and_poll(
    file_path="data.csv",
    purpose=FilePurpose.AGENTS
)

# Create tool with file
code_interpreter = CodeInterpreterTool(file_ids=[file.id])

Supported File Types

• Code: .py, .js, .java, .cpp, .c
• Data: .csv, .json, .xml, .xlsx
• Documents: .pdf, .docx, .txt, .md
• Images: .jpg, .png, .gif

See File Search Tool for document retrieval.