Code interpreter

AsyncSandbox

class AsyncSandbox(BaseAsyncSandbox)

E2B cloud sandbox is a secure and isolated cloud environment.

The sandbox allows you to:

• Access Linux OS
• Create, list, and delete files and directories
• Run commands
• Run isolated code
• Access the internet

Check docs here.

Use the AsyncSandbox.create() to create a new sandbox.

Example:

from e2b_code_interpreter import AsyncSandbox
sandbox = await AsyncSandbox.create()

run_code

@overload
async def run_code(code: str,
                   language: Union[Literal["python"], None] = None,
                   on_stdout: Optional[OutputHandler[OutputMessage]] = None,
                   on_stderr: Optional[OutputHandler[OutputMessage]] = None,
                   on_result: Optional[OutputHandler[Result]] = None,
                   on_error: Optional[OutputHandler[ExecutionError]] = None,
                   envs: Optional[Dict[str, str]] = None,
                   timeout: Optional[float] = None,
                   request_timeout: Optional[float] = None) -> Execution

Runs the code as Python.

Specify the language or context option to run the code as a different language or in a different Context.

You can reference previously defined variables, imports, and functions in the code.

Arguments:

• code: Code to execute
• language: Language to use for code execution. If not defined, the default Python context is used.
• on_stdout: Callback for stdout messages
• on_stderr: Callback for stderr messages
• on_result: Callback for the Result object
• on_error: Callback for the ExecutionError object
• envs: Custom environment variables
• timeout: Timeout for the code execution in seconds
• request_timeout: Timeout for the request in seconds

Returns:

Execution result object

run_code

@overload
async def run_code(code: str,
                   language: Optional[str] = None,
                   on_stdout: Optional[OutputHandler[OutputMessage]] = None,
                   on_stderr: Optional[OutputHandler[OutputMessage]] = None,
                   on_result: Optional[OutputHandler[Result]] = None,
                   on_error: Optional[OutputHandler[ExecutionError]] = None,
                   envs: Optional[Dict[str, str]] = None,
                   timeout: Optional[float] = None,
                   request_timeout: Optional[float] = None) -> Execution

Runs the code for the specified language.

Specify the language or context option to run the code as a different language or in a different Context. If no language is specified, Python is used.

You can reference previously defined variables, imports, and functions in the code.

Arguments:

• code: Code to execute
• language: Language to use for code execution. If not defined, the default Python context is used.
• on_stdout: Callback for stdout messages
• on_stderr: Callback for stderr messages
• on_result: Callback for the Result object
• on_error: Callback for the ExecutionError object
• envs: Custom environment variables
• timeout: Timeout for the code execution in seconds
• request_timeout: Timeout for the request in seconds

Returns:

Execution result object

run_code

@overload
async def run_code(code: str,
                   context: Optional[Context] = None,
                   on_stdout: Optional[OutputHandler[OutputMessage]] = None,
                   on_stderr: Optional[OutputHandler[OutputMessage]] = None,
                   on_result: Optional[OutputHandler[Result]] = None,
                   on_error: Optional[OutputHandler[ExecutionError]] = None,
                   envs: Optional[Dict[str, str]] = None,
                   timeout: Optional[float] = None,
                   request_timeout: Optional[float] = None) -> Execution

Runs the code in the specified context, if not specified, the default context is used.

Specify the language or context option to run the code as a different language or in a different Context.

You can reference previously defined variables, imports, and functions in the code.

Arguments:

• code: Code to execute
• context: Concrete context to run the code in. If not specified, the default context for the language is used. It’s mutually exclusive with the language.
• on_stdout: Callback for stdout messages
• on_stderr: Callback for stderr messages
• on_result: Callback for the Result object
• on_error: Callback for the ExecutionError object
• envs: Custom environment variables
• timeout: Timeout for the code execution in seconds
• request_timeout: Timeout for the request in seconds

Returns:

Execution result object

create_code_context

async def create_code_context(
        cwd: Optional[str] = None,
        language: Optional[str] = None,
        request_timeout: Optional[float] = None) -> Context

Creates a new context to run code in.

Arguments:

• cwd: Set the current working directory for the context, defaults to /home/user
• language: Language of the context. If not specified, defaults to Python
• request_timeout: Timeout for the request in milliseconds

Returns:

Context object

OutputMessage

@dataclass
class OutputMessage()

Represents an output message from the sandbox code execution.

line

The output line.

timestamp

Unix epoch in nanoseconds

error

Whether the output is an error.

ExecutionError

@dataclass
class ExecutionError()

Represents an error that occurred during the execution of a cell. The error contains the name of the error, the value of the error, and the traceback.

name

Name of the error.

value

Value of the error.

traceback

The raw traceback of the error.

to_json

def to_json() -> str

Returns the JSON representation of the Error object.

MIMEType

class MIMEType(str)

Represents a MIME type.

Result

@dataclass
class Result()

Represents the data to be displayed as a result of executing a cell in a Jupyter notebook. The result is similar to the structure returned by ipython kernel: https://ipython.readthedocs.io/en/stable/development/execution.html#execution-semantics

The result can contain multiple types of data, such as text, images, plots, etc. Each type of data is represented as a string, and the result can contain multiple types of data. The display calls don’t have to have text representation, for the actual result the representation is always present for the result, the other representations are always optional.

is_main_result

Whether this data is the result of the cell. Data can be produced by display calls of which can be multiple in a cell.

extra

Extra data that can be included. Not part of the standard types.

formats

def formats() -> Iterable[str]

Returns all available formats of the result.

Returns:

All available formats of the result in MIME types.

__str__

def __str__() -> Optional[str]

Returns the text representation of the data.

Returns:

The text representation of the data.

_repr_html_

def _repr_html_() -> Optional[str]

Returns the HTML representation of the data.

Returns:

The HTML representation of the data.

_repr_markdown_

def _repr_markdown_() -> Optional[str]

Returns the Markdown representation of the data.

Returns:

The Markdown representation of the data.

_repr_svg_

def _repr_svg_() -> Optional[str]

Returns the SVG representation of the data.

Returns:

The SVG representation of the data.

_repr_png_

def _repr_png_() -> Optional[str]

Returns the base64 representation of the PNG data.

Returns:

The base64 representation of the PNG data.

_repr_jpeg_

def _repr_jpeg_() -> Optional[str]

Returns the base64 representation of the JPEG data.

Returns:

The base64 representation of the JPEG data.

_repr_pdf_

def _repr_pdf_() -> Optional[str]

Returns the PDF representation of the data.

Returns:

The PDF representation of the data.

_repr_latex_

def _repr_latex_() -> Optional[str]

Returns the LaTeX representation of the data.

Returns:

The LaTeX representation of the data.

_repr_json_

def _repr_json_() -> Optional[dict]

Returns the JSON representation of the data.

Returns:

The JSON representation of the data.

_repr_javascript_

def _repr_javascript_() -> Optional[str]

Returns the JavaScript representation of the data.

Returns:

The JavaScript representation of the data.

Logs

@dataclass(repr=False)
class Logs()

Data printed to stdout and stderr during execution, usually by print statements, logs, warnings, subprocesses, etc.

stdout

List of strings printed to stdout by prints, subprocesses, etc.

stderr

List of strings printed to stderr by prints, subprocesses, etc.

to_json

def to_json() -> str

Returns the JSON representation of the Logs object.

serialize_results

def serialize_results(results: List[Result]) -> List[Dict[str, str]]

Serializes the results to JSON.

Execution

@dataclass(repr=False)
class Execution()

Represents the result of a cell execution.

results

List of the result of the cell (interactively interpreted last line), display calls (e.g. matplotlib plots).

logs

Logs printed to stdout and stderr during execution.

error

Error object if an error occurred, None otherwise.

execution_count

Execution count of the cell.

text

@property
def text() -> Optional[str]

Returns the text representation of the result.

Returns:

The text representation of the result.

to_json

def to_json() -> str

Returns the JSON representation of the Execution object.

Context

@dataclass
class Context()

Represents a context for code execution.

id

The ID of the context.

language

The language of the context.

cwd

The working directory of the context.

ChartType

class ChartType(str, enum.Enum)

Chart types

ScaleType

class ScaleType(str, enum.Enum)

Ax scale types

Chart

class Chart()

Extracted data from a chart. It’s useful for building an interactive charts or custom visualizations.

Sandbox

class Sandbox(BaseSandbox)

E2B cloud sandbox is a secure and isolated cloud environment.

The sandbox allows you to:

• Access Linux OS
• Create, list, and delete files and directories
• Run commands
• Run isolated code
• Access the internet

Check docs here.

Use the Sandbox() to create a new sandbox.

Example:

from e2b_code_interpreter import Sandbox

sandbox = Sandbox()

run_code

@overload
def run_code(code: str,
             language: Union[Literal["python"], None] = None,
             on_stdout: Optional[OutputHandler[OutputMessage]] = None,
             on_stderr: Optional[OutputHandler[OutputMessage]] = None,
             on_result: Optional[OutputHandler[Result]] = None,
             on_error: Optional[OutputHandler[ExecutionError]] = None,
             envs: Optional[Dict[str, str]] = None,
             timeout: Optional[float] = None,
             request_timeout: Optional[float] = None) -> Execution

Runs the code as Python.

Specify the language or context option to run the code as a different language or in a different Context.

You can reference previously defined variables, imports, and functions in the code.

Arguments:

• code: Code to execute
• language: Language to use for code execution. If not defined, the default Python context is used.
• on_stdout: Callback for stdout messages
• on_stderr: Callback for stderr messages
• on_result: Callback for the Result object
• on_error: Callback for the ExecutionError object
• envs: Custom environment variables
• timeout: Timeout for the code execution in seconds
• request_timeout: Timeout for the request in seconds

Returns:

Execution result object

run_code

@overload
def run_code(code: str,
             language: Optional[str] = None,
             on_stdout: Optional[OutputHandler[OutputMessage]] = None,
             on_stderr: Optional[OutputHandler[OutputMessage]] = None,
             on_result: Optional[OutputHandler[Result]] = None,
             on_error: Optional[OutputHandler[ExecutionError]] = None,
             envs: Optional[Dict[str, str]] = None,
             timeout: Optional[float] = None,
             request_timeout: Optional[float] = None) -> Execution

Runs the code for the specified language.

Specify the language or context option to run the code as a different language or in a different Context. If no language is specified, Python is used.

You can reference previously defined variables, imports, and functions in the code.

Arguments:

• code: Code to execute
• language: Language to use for code execution. If not defined, the default Python context is used.
• on_stdout: Callback for stdout messages
• on_stderr: Callback for stderr messages
• on_result: Callback for the Result object
• on_error: Callback for the ExecutionError object
• envs: Custom environment variables
• timeout: Timeout for the code execution in seconds
• request_timeout: Timeout for the request in seconds

Returns:

Execution result object

run_code

@overload
def run_code(code: str,
             context: Optional[Context] = None,
             on_stdout: Optional[OutputHandler[OutputMessage]] = None,
             on_stderr: Optional[OutputHandler[OutputMessage]] = None,
             on_result: Optional[OutputHandler[Result]] = None,
             on_error: Optional[OutputHandler[ExecutionError]] = None,
             envs: Optional[Dict[str, str]] = None,
             timeout: Optional[float] = None,
             request_timeout: Optional[float] = None) -> Execution

Runs the code in the specified context, if not specified, the default context is used.

Specify the language or context option to run the code as a different language or in a different Context.

You can reference previously defined variables, imports, and functions in the code.

Arguments:

• code: Code to execute
• context: Concrete context to run the code in. If not specified, the default context for the language is used. It’s mutually exclusive with the language.
• on_stdout: Callback for stdout messages
• on_stderr: Callback for stderr messages
• on_result: Callback for the Result object
• on_error: Callback for the ExecutionError object
• envs: Custom environment variables
• timeout: Timeout for the code execution in seconds
• request_timeout: Timeout for the request in seconds

Returns:

Execution result object

create_code_context

def create_code_context(cwd: Optional[str] = None,
                        language: Optional[str] = None,
                        request_timeout: Optional[float] = None) -> Context

Creates a new context to run code in.

Arguments:

• cwd: Set the current working directory for the context, defaults to /home/user
• language: Language of the context. If not specified, defaults to Python
• request_timeout: Timeout for the request in milliseconds

Returns:

Context object