e2b-code-interpreter 1.0.0

E2B Code Interpreter - Stateful code execution

Code interpreter extension for Python

The repository contains a template and modules for the code interpreter sandbox. It is based on the Jupyter server and implements the Jupyter Kernel messaging protocol. This allows for sharing context between code executions and improves support for plotting charts and other display-able data.

Key Features

• Stateful Execution: Unlike traditional sandboxes that treat each code execution independently, this package maintains context across executions.
• Displaying Charts & Data: Implements parts of the Jupyter Kernel messaging protocol, which support for interactive features like plotting charts, rendering DataFrames, etc.

Installation

pip install e2b-code-interpreter

Examples

Minimal example with the sharing context

from e2b_code_interpreter import Sandbox

with Sandbox() as sandbox:
    sandbox.run_code()("x = 1")

    execution = sandbox.run_code()("x+=1; x")
    print(execution.text)  # outputs 2

Get charts and any display-able data

import base64
import io

from matplotlib import image as mpimg, pyplot as plt

from e2b_code_interpreter import Sandbox

code = """
import matplotlib.pyplot as plt
import numpy as np

x = np.linspace(0, 20, 100)
y = np.sin(x)

plt.plot(x, y)
plt.show()
"""

with Sandbox() as sandbox:
    # you can install dependencies in "jupyter notebook style"
    sandbox.run_code("!pip install matplotlib")

    # plot random chart
    execution = sandbox.run_code(code)

# there's your image
image = execution.results[0].png

# example how to show the image / prove it works
i = base64.b64decode(image)
i = io.BytesIO(i)
i = mpimg.imread(i, format='PNG')

plt.imshow(i, interpolation='nearest')
plt.show()

Streaming code output

from e2b_code_interpreter import Sandbox

code = """
import time
import pandas as pd

print("hello")
time.sleep(3)
data = pd.DataFrame(data=[[1, 2], [3, 4]], columns=["A", "B"])
display(data.head(10))
time.sleep(3)
print("world")
"""

with Sandbox() as sandbox:
    sandbox.run_code(code, on_stdout=print, on_stderr=print, on_result=(lambda result: print(result.text)))

More resources

• Check out the JavaScript/TypeScript and Python "Hello World" guides to learn how to use our SDK.

• See E2B documentation to get started.

• Visit our Cookbook to get inspired by examples with different LLMs and AI frameworks.

---