Documentation

E2B can work with any LLM and AI framework. The easiest way to connect an LLM to E2B is to use the tool use capabilities of the LLM (sometimes known as function calling). If the LLM doesn’t support tool use, you can, for example, prompt the LLM to output code snippets and then manually extract the code snippets with RegEx.

OpenAI
Anthropic
Mistral
Groq
Vercel AI SDK
CrewAI
LangChain
LlamaIndex
Ollama
Hugging Face

OpenAI

Simple

# pip install openai e2b-code-interpreter
from openai import OpenAI
from e2b_code_interpreter import Sandbox

# Create OpenAI client
client = OpenAI()
system = "You are a helpful assistant that can execute python code in a Jupyter notebook. Only respond with the code to be executed and nothing else. Strip backticks in code blocks."
prompt = "Calculate how many r's are in the word 'strawberry'"

# Send messages to OpenAI API
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": system},
        {"role": "user", "content": prompt}
    ]
)

# Extract the code from the response
code = response.choices[0].message.content

# Execute code in E2B Sandbox
if code:
    with Sandbox.create() as sandbox:
        execution = sandbox.run_code(code)
        result = execution.text

    print(result)

Function calling

# pip install openai e2b-code-interpreter
import json
from openai import OpenAI
from e2b_code_interpreter import Sandbox

# Create OpenAI client
client = OpenAI()
model = "gpt-4o"

# Define the messages
messages = [
    {
        "role": "user",
        "content": "Calculate how many r's are in the word 'strawberry'"
    }
]

# Define the tools
tools = [{
    "type": "function",
    "function": {
        "name": "execute_python",
        "description": "Execute python code in a Jupyter notebook cell and return result",
        "parameters": {
            "type": "object",
            "properties": {
                "code": {
                    "type": "string",
                    "description": "The python code to execute in a single cell"
                }
            },
            "required": ["code"]
        }
    }
}]

# Generate text with OpenAI
response = client.chat.completions.create(
    model=model,
    messages=messages,
    tools=tools,
)

# Append the response message to the messages list
response_message = response.choices[0].message
messages.append(response_message)

# Execute the tool if it's called by the model
if response_message.tool_calls:
    for tool_call in response_message.tool_calls:
        if tool_call.function.name == "execute_python":
            # Create a sandbox and execute the code
            with Sandbox.create() as sandbox:
                code = json.loads(tool_call.function.arguments)['code']
                execution = sandbox.run_code(code)
                result = execution.text

            # Send the result back to the model
            messages.append({
                "role": "tool",
                "name": "execute_python",
                "content": result,
                "tool_call_id": tool_call.id,
            })

# Generate the final response
final_response = client.chat.completions.create(
    model=model,
    messages=messages
)

print(final_response.choices[0].message.content)

Anthropic

Simple

# pip install anthropic e2b-code-interpreter
from anthropic import Anthropic
from e2b_code_interpreter import Sandbox

# Create Anthropic client
anthropic = Anthropic()
system_prompt = "You are a helpful assistant that can execute python code in a Jupyter notebook. Only respond with the code to be executed and nothing else. Strip backticks in code blocks."
prompt = "Calculate how many r's are in the word 'strawberry'"

# Send messages to Anthropic API
response = anthropic.messages.create(
    model="claude-3-5-sonnet-20240620",
    max_tokens=1024,
    messages=[
        {"role": "assistant", "content": system_prompt},
        {"role": "user", "content": prompt}
    ]
)

# Extract code from response
code = response.content[0].text

# Execute code in E2B Sandbox
with Sandbox.create() as sandbox:
    execution = sandbox.run_code(code)
    result = execution.logs.stdout

print(result)

Function calling

# pip install anthropic e2b-code-interpreter
from anthropic import Anthropic
from e2b_code_interpreter import Sandbox

# Create Anthropic client
client = Anthropic()
model = "claude-3-5-sonnet-20240620"

# Define the messages
messages = [
    {
        "role": "user",
        "content": "Calculate how many r's are in the word 'strawberry'"
    }
]

# Define the tools
tools = [{
    "name": "execute_python",
    "description": "Execute python code in a Jupyter notebook cell and return (not print) the result",
    "input_schema": {
        "type": "object",
        "properties": {
            "code": {
                "type": "string",
                "description": "The python code to execute in a single cell"
            }
        },
        "required": ["code"]
    }
}]

# Generate text with Anthropic
message = client.messages.create(
    model=model,
    max_tokens=1024,
    messages=messages,
    tools=tools
)

# Append the response message to the messages list
messages.append({
    "role": "assistant",
    "content": message.content
})

# Execute the tool if it's called by the model
if message.stop_reason == "tool_use":
    tool_use = next(block for block in message.content if block.type == "tool_use")
    tool_name = tool_use.name
    tool_input = tool_use.input

    if tool_name == "execute_python":
        with Sandbox.create() as sandbox:
            code = tool_input['code']
            execution = sandbox.run_code(code)
            result = execution.text

        # Append the tool result to the messages list
        messages.append({
            "role": "user",
            "content": [
                {
                    "type": "tool_result",
                    "tool_use_id": tool_use.id,
                    "content": result,
                }
            ],
        })

# Generate the final response
final_response = client.messages.create(
    model=model,
    max_tokens=1024,
    messages=messages,
    tools=tools
)

print(final_response.content[0].text)

Mistral

Simple

# pip install mistralai e2b-code-interpreter
import os
from mistralai import Mistral
from e2b_code_interpreter import Sandbox

# Create Mistral client
client = Mistral(api_key=os.environ["MISTRAL_API_KEY"])
system_prompt = "You are a helpful assistant that can execute python code in a Jupyter notebook. Only respond with the code to be executed and nothing else. Strip backticks in code blocks."
prompt = "Calculate how many r's are in the word 'strawberry'"

# Send the prompt to the model
response = client.chat.complete(
    model="codestral-latest",
    messages=[
        {"role": "system", "content": system_prompt},
        {"role": "user", "content": prompt}
    ]
)

# Extract the code from the response
code = response.choices[0].message.content

# Execute code in E2B Sandbox
with Sandbox.create() as sandbox:
    execution = sandbox.run_code(code)
    result = execution.text

print(result)

Function calling

# pip install mistralai e2b-code-interpreter
import os
import json
from mistralai import Mistral
from e2b_code_interpreter import Sandbox

# Create Mistral client
client = Mistral(api_key=os.environ["MISTRAL_API_KEY"])
model = "mistral-large-latest"
messages = [
    {
        "role": "user",
        "content": "Calculate how many r's are in the word 'strawberry'"
    }
]

# Define the tools
tools = [{
    "type": "function",
    "function": {
        "name": "execute_python",
        "description": "Execute python code in a Jupyter notebook cell and return result",
        "parameters": {
            "type": "object",
            "properties": {
                "code": {
                    "type": "string",
                    "description": "The python code to execute in a single cell"
                }
            },
            "required": ["code"]
        }
    }
}]

# Send the prompt to the model
response = client.chat.complete(
    model=model,
    messages=messages,
    tools=tools
)

# Append the response message to the messages list
response_message = response.choices[0].message
messages.append(response_message)

# Execute the tool if it's called by the model
if response_message.tool_calls:
    for tool_call in response_message.tool_calls:
        if tool_call.function.name == "execute_python":
            # Create a sandbox and execute the code
            with Sandbox.create() as sandbox:
                code = json.loads(tool_call.function.arguments)['code']
                execution = sandbox.run_code(code)
                result = execution.text

            # Send the result back to the model
            messages.append({
                "role": "tool",
                "name": "execute_python",
                "content": result,
                "tool_call_id": tool_call.id,
            })

# Generate the final response
final_response = client.chat.complete(
    model=model,
    messages=messages,
)

print(final_response.choices[0].message.content)

Groq

# pip install groq e2b-code-interpreter
import os
from groq import Groq
from e2b_code_interpreter import Sandbox

api_key = os.environ["GROQ_API_KEY"]

# Create Groq client
client = Groq(api_key=api_key)
system_prompt = "You are a helpful assistant that can execute python code in a Jupyter notebook. Only respond with the code to be executed and nothing else. Strip backticks in code blocks."
prompt = "Calculate how many r's are in the word 'strawberry.'"

# Send the prompt to the model
response = client.chat.completions.create(
    model="llama3-70b-8192",
    messages=[
        {"role": "system", "content": system_prompt},
        {"role": "user", "content": prompt},
    ]
)

# Extract the code from the response
code = response.choices[0].message.content

# Execute code in E2B Sandbox
with Sandbox.create() as sandbox:
    execution = sandbox.run_code(code)
    result = execution.text

print(result)

Vercel AI SDK

Vercel’s AI SDK offers support for multiple different LLM providers through a unified JavaScript interface that’s easy to use.

Simple

// npm install ai @ai-sdk/openai @e2b/code-interpreter
import { openai } from '@ai-sdk/openai'
import { generateText } from 'ai'
import { Sandbox } from '@e2b/code-interpreter'

// Create OpenAI client
const model = openai('gpt-4o')
const system = "You are a helpful assistant that can execute python code in a Jupyter notebook. Only respond with the code to be executed and nothing else. Strip backticks in code blocks."
const prompt = "Calculate how many r's are in the word 'strawberry'"

// Generate code with OpenAI
const { text: code } = await generateText({
  model,
  system,
  prompt
})

// Run the code in E2B Sandbox
const sandbox = await Sandbox.create()
const { text, results, logs, error } = await sandbox.runCode(code)

console.log(text)

Function calling

// npm install ai @ai-sdk/openai zod @e2b/code-interpreter
import { openai } from '@ai-sdk/openai'
import { generateText } from 'ai'
import z from 'zod'
import { Sandbox } from '@e2b/code-interpreter'

// Create OpenAI client
const model = openai('gpt-4o')

const prompt = "Calculate how many r's are in the word 'strawberry'"

// Generate text with OpenAI
const { text } = await generateText({
  model,
  prompt,
  tools: {
    // Define a tool that runs code in a sandbox
    execute_python: {
      description: 'Execute python code in a Jupyter notebook cell and return result',
      parameters: z.object({
        code: z.string().describe('The python code to execute in a single cell'),
      }),
      execute: async ({ code }) => {
        // Create a sandbox, execute LLM-generated code, and return the result
        const sandbox = await Sandbox.create()
        const { text, results, logs, error } = await sandbox.runCode(code)
        return results
      },
    },
  },
  // This is required to feed the tool call result back to the LLM
  maxSteps: 2
})

console.log(text)

CrewAI

CrewAI is a platform for building AI agents.

# pip install crewai e2b-code-interpreter
from crewai.tools import tool
from crewai import Agent, Task, Crew, LLM
from e2b_code_interpreter import Sandbox

# Update tool definition using the decorator
@tool("Python Interpreter")
def execute_python(code: str) -> str:
    """
    Execute Python code and return the results.
    """
    with Sandbox.create() as sandbox:
        execution = sandbox.run_code(code)
        return execution.text

# Define the agent
python_executor = Agent(
    role='Python Executor',
    goal='Execute Python code and return the results',
    backstory='You are an expert Python programmer capable of executing code and returning results.',
    tools=[execute_python],
    llm=LLM(model="gpt-4o")
)

# Define the task
execute_task = Task(
    description="Calculate how many r's are in the word 'strawberry'",
    agent=python_executor,
    expected_output="The number of r's in the word 'strawberry'"
)

# Create the crew
code_execution_crew = Crew(
    agents=[python_executor],
    tasks=[execute_task],
    verbose=True,
)

# Run the crew
result = code_execution_crew.kickoff()
print(result)

LangChain

LangChain offers support multiple different LLM providers.

Simple

# pip install langchain langchain-openai e2b-code-interpreter
from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
from e2b_code_interpreter import Sandbox

system_prompt = "You are a helpful assistant that can execute python code in a Jupyter notebook. Only respond with the code to be executed and nothing else. Strip backticks in code blocks."
prompt = "Calculate how many r's are in the word 'strawberry'"

# Create LangChain components
llm = ChatOpenAI(model="gpt-4o")
prompt_template = ChatPromptTemplate.from_messages([
    ("system", system_prompt),
    ("human", "{input}")
])

output_parser = StrOutputParser()

# Create the chain
chain = prompt_template | llm | output_parser

# Run the chain
code = chain.invoke({"input": prompt})

# Execute code in E2B Sandbox
with Sandbox.create() as sandbox:
    execution = sandbox.run_code(code)
    result = execution.text

print(result)

Agent

# pip install langchain langchain-openai e2b-code-interpreter
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.tools import tool
from langchain.agents import create_tool_calling_agent, AgentExecutor
from langchain_openai import ChatOpenAI
from e2b_code_interpreter import Sandbox

system_prompt = "You are a helpful assistant that can execute python code in a Jupyter notebook. Only respond with the code to be executed and nothing else. Strip backticks in code blocks."
prompt = "Calculate how many r's are in the word 'strawberry'"

# Define the tool
@tool
def execute_python(code: str):
    """
    Execute python code in a Jupyter notebook.
    """
    with Sandbox.create() as sandbox:
        execution = sandbox.run_code(code)
        return execution.text

# Define LangChain components
prompt_template = ChatPromptTemplate.from_messages([
    ("system", system_prompt),
    ("human", "{input}"),
    ("placeholder", "{agent_scratchpad}"),
])

tools = [execute_python]
llm = ChatOpenAI(model="gpt-4o", temperature=0)

agent = create_tool_calling_agent(llm, tools, prompt_template)
agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)

# Run the agent
agent_executor.invoke({"input": prompt})

Function calling

# pip install langchain langchain-openai e2b-code-interpreter
from langchain_openai import ChatOpenAI
from langchain.tools import Tool
from langchain.schema import HumanMessage, AIMessage, FunctionMessage
from e2b_code_interpreter import Sandbox

def execute_python(code: str):
    with Sandbox.create() as sandbox:
        execution = sandbox.run_code(code)
        return execution.text

# Define a tool that uses the E2B Sandbox
e2b_sandbox_tool = Tool(
    name="execute_python",
    func=execute_python,
    description="Execute python code in a Jupyter notebook cell and return result"
)

# Initialize the language model and bind the tool
llm = ChatOpenAI(model="gpt-4o").bind_tools([e2b_sandbox_tool])

# Define the messages
messages = [
    HumanMessage(content="Calculate how many 'r's are in the word 'strawberry'.")
]

# Run the model with a prompt
result = llm.invoke(messages)
messages.append(AIMessage(content=result.content))

# Check if the model called the tool
if result.additional_kwargs.get('tool_calls'):
    tool_call = result.additional_kwargs['tool_calls'][0]
    if tool_call['function']['name'] == "execute_python":
        code = tool_call['function']['arguments']
        execution_result = execute_python(code)

        # Send the result back to the model
        messages.append(
            FunctionMessage(name="execute_python", content=execution_result)
        )

final_result = llm.invoke(messages)
print(final_result.content)

LlamaIndex

LlamaIndex offers support multiple different LLM providers.

# pip install llama-index e2b-code-interpreter
from llama_index.core.tools import FunctionTool
from llama_index.llms.openai import OpenAI
from llama_index.core.agent import ReActAgent
from e2b_code_interpreter import Sandbox

# Define the tool
def execute_python(code: str):
    with Sandbox.create() as sandbox:
        execution = sandbox.run_code(code)
        return execution.text

e2b_sandbox_tool = FunctionTool.from_defaults(
    name="execute_python",
    description="Execute python code in a Jupyter notebook cell and return result",
    fn=execute_python
)

# Initialize LLM
llm = OpenAI(model="gpt-4o")

# Initialize ReAct agent
agent = ReActAgent.from_tools([e2b_sandbox_tool], llm=llm, verbose=True)
agent.chat("Calculate how many r's are in the word 'strawberry'")

Ollama

# pip install ollama
import ollama
from e2b_code_interpreter import Sandbox

# Send the prompt to the model
response = ollama.chat(
    model="llama3.2",
    messages=[{
        "role": "system",
        "content": "You are a helpful assistant that can execute python code in a Jupyter notebook. Only respond with the code to be executed and nothing else. Strip backticks in code blocks."
    },
    {
        "role": "user",
        "content": "Calculate how many r's are in the word 'strawberry'"
    }
])

# Extract the code from the response
code = response['message']['content']

# Execute code in E2B Sandbox
with Sandbox.create() as sandbox:
    execution = sandbox.run_code(code)
    result = execution.logs.stdout

print(result)

Hugging Face

Hugging Face offers support for serverless inference for models on their model hub with Hugging Face’s Inference API.

Note that not every model on Hugging Face has native support for tool use and function calling.

from huggingface_hub import InferenceClient
from e2b_code_interpreter import Sandbox
import re

# Not all models are capable of direct tools use - we need to extract the code block manually and prompting the LLM to generate the code.
def match_code_block(llm_response):
  pattern = re.compile(r'```python Python\n(.*?)\n```', re.DOTALL) # Match everything in between ```python and ```
  match = pattern.search(llm_response)
  if match:
    code = match.group(1)
    print(code)
    return code
  return ""


system_prompt = """You are a helpful coding assistant that can execute python code in a Jupyter notebook. You are given tasks to complete and you run Python code to solve them.
Generally, you follow these rules:
- ALWAYS FORMAT YOUR RESPONSE IN MARKDOWN
- ALWAYS RESPOND ONLY WITH CODE IN CODE BLOCK LIKE THIS:
\`\`\`python
{code}
\`\`\`
"""
prompt = "Calculate how many r's are in the word 'strawberry.'"

# Initialize the client
client = InferenceClient(
    provider="hf-inference",
    api_key="HF_INFERENCE_API_KEY"
)

completion = client.chat.completions.create(
    model="Qwen/Qwen3-235B-A22B", # Or use any other model from Hugging Face
    messages=[
        {"role": "system", "content": system_prompt},
        {"role": "user", "content": prompt},
    ]
)

content = completion.choices[0].message.content
code = match_code_block(content)

with Sandbox.create() as sandbox:
    execution = sandbox.run_code(code)
    print(execution)

Connect LLMs to E2B

Contents

OpenAI

Simple

Function calling

Anthropic

Simple

Function calling

Mistral

Simple

Function calling

Groq

Vercel AI SDK

Simple

Function calling

CrewAI

LangChain

Simple

Agent

Function calling

LlamaIndex

Ollama

Hugging Face

​Contents

​OpenAI

​Simple

​Function calling

​Anthropic

​Simple

​Function calling

​Mistral

​Simple

​Function calling

​Groq

​Vercel AI SDK

​Simple

​Function calling

​CrewAI

​LangChain

​Simple

​Agent

​Function calling

​LlamaIndex

​Ollama

​Hugging Face

Contents

OpenAI

Simple

Function calling

Anthropic

Simple

Function calling

Mistral

Simple

Function calling

Groq

Vercel AI SDK

Simple

Function calling

CrewAI

LangChain

Simple

Agent

Function calling

LlamaIndex

Ollama

Hugging Face