Open-source, secure environment with real-world tools for enterprise-grade agents.
Python agentaiai-agentai-agentscode-interpretercopilotdevelopmentdevtoolsgptgpt-4javascriptllmnextjsopenaipythonreactsoftwaretypescript
Update docs
Vasek Mlejnskyfe9a6b8538a1
diff --git a/.DS_Store b/.DS_Storenew file mode 100644index 000000000..5008ddfcfBinary files /dev/null and b/.DS_Store differdiff --git a/apps/web/src/app/(docs)/docs/code-interpreting/analyze-data/page.mdx b/apps/web/src/app/(docs)/docs/code-interpreting/analyze-data/page.mdxindex 2712c8c7c..b1ed77e50 100644--- a/apps/web/src/app/(docs)/docs/code-interpreting/analyze-data/page.mdx+++ b/apps/web/src/app/(docs)/docs/code-interpreting/analyze-data/page.mdx@@ -1,3 +1,6 @@+import Image from 'next/image'+import imgChart from '@/images/analyze-data-chart.png'+# Analyze data with AIYou can use E2B Sandbox to run AI-generated code to analyze data. Here's how the AI data analysis workflow usually looks like:@@ -5,3 +8,338 @@ You can use E2B Sandbox to run AI-generated code to analyze data. Here's how the2. You prompt the LLM to generate code (usually Python) based on the user's data.3. The sandbox runs the AU-generated code and returns the results.4. You display the results to the user.++---++## Example: Analyze CSV file with E2B and Claude 3.5 Sonnet+This short example will show you how to use E2B Sandbox to run AI-generated code to analyze CSV data.++### Table of Contents+1. [Install dependencies](#1-install-dependencies)+2. [Set your API keys](#2-set-your-api-keys)+3. [Download example CSV file](#3-download-example-csv-file)+4. [Initialize the sandbox and upload the dataset to the sandbox](#4-initialize-the-sandbox-and-upload-the-dataset-to-the-sandbox)+5. [Prepare the method for running AI-generated code](#5-prepare-the-method-for-running-ai-generated-code)+6. [Prepare the prompt and initialize Anthropic client](#6-prepare-the-prompt-and-initialize-anthropic-client)+7. [Connect the sandbox to the LLM with tool calling](#7-connect-the-sandbox-to-the-llm-with-tool-calling)+8. [Parse the response and run the AI-generated code in the sandbox](#8-parse-the-response-and-run-the-ai-generated-code-in-the-sandbox)+9. [Save the generated chart](#9-save-the-generated-chart)+10. [Run the full code](#10-run-the-full-code)++### 1. Install dependencies+Install the E2B SDK and Claude SDK to your project by running the following command in your terminal.++<CodeGroup isTerminalCommand>+```bash {{ language: 'js' }}+npm i @e2b/code-interpreter @anthropic-ai/sdk dotenv+```+```bash {{ language: 'python' }}+pip install e2b_code_interpreter anthropic python-dotenv+```+</CodeGroup>++### 2. Set your API keys+1. Get your E2B API key from [E2B Dashboard](/dashboard?tab=keys).+2. Get your Claude API key from [Claude API Dashboard](https://console.anthropic.com/settings/keys).+3. Paste the keys into your `.env` file.++<CodeGroup title=".env">+```bash+E2B_API_KEY=e2b_***+ANTHROPIC_API_KEY=sk-ant-***+```+</CodeGroup>++### 3. Download example CSV file+{/* We'll be using the publicly available [AirBnB NYC dataset](https://www.kaggle.com/datasets/dgomonov/new-york-city-airbnb-open-data). */}++We'll be using the publicly available [dataset of about 10,000 movies](https://www.kaggle.com/datasets/muqarrishzaib/tmdb-10000-movies-dataset).+1. Click the "Download" button at the top of the page.+2. Select "Download as zip (2 MB)".+3. Unzip the file and you should see `dataset.csv` file. Move it to the root of your project.+++### 4. Initialize the sandbox and upload the dataset to the sandbox+We'll upload the dataset from the third step to the sandbox and save it as `dataset.csv` file.++<CodeGroup>+```js {{ language: 'js', description: 'index.ts' }}+import 'dotenv/config'+import fs from 'fs'+import { Sandbox } from '@e2b/code-interpreter'++// Create sandbox+const sbx = await Sandbox.create()++// Upload the dataset to the sandbox+const content = fs.readFileSync('dataset.csv')+const datasetPathInSandbox = await sbx.files.write('dataset.csv', content)+```+```python {{ language: 'python', description: 'main.py' }}+from dotenv import load_dotenv+load_dotenv()+from e2b_code_interpreter import Sandbox++# Create sandbox+sbx = Sandbox()++# Upload the dataset to the sandbox+dataset_path_in_sandbox = ""+with open("dataset.csv", "rb") as f:+ dataset_path_in_sandbox = sbx.files.write("dataset.csv", f)++```+</CodeGroup>++### 5. Prepare the method for running AI-generated code+Add the following code to the file. Here we're adding the method for code execution.++<CodeGroup>+```js {{ language: 'js', description: 'index.ts' }}+// ... code from the previous step++async function runAIGeneratedCode(aiGeneratedCode: string) {+ console.log('Running the code in the sandbox....')+ const execution = await sbx.runCode(aiGeneratedCode)+ console.log('Code execution finished!')+ console.log(execution)+}+```+```python {{ language: 'python', description: 'main.py' }}+# ... code from the previous step++def run_ai_generated_code(ai_generated_code: str):+ print('Running the code in the sandbox....')+ execution = sbx.run_code(ai_generated_code)+ print('Code execution finished!')+ print(execution)+```+</CodeGroup>++### 6. Prepare the prompt and initialize Anthropic client+The prompt we'll be using describes the dataset and the analysis we want to perform like this:+ 1. Describe the columns in the CSV dataset.+ 2. Ask the LLM what we want to analyze - here we want to analyze the vote average over time. We're asking for a chart as the output.+ 3. Instruct the LLM to generate Python code for the data analysis.++<CodeGroup>+```js {{ language: 'js', description: 'index.ts' }}+import Anthropic from '@anthropic-ai/sdk'++const prompt = `+I have a CSV file about movies. It has about 10k rows. It's saved in the sandbox at ${datasetPathInSandbox.path}.+These are the columns:+- 'id': number, id of the movie+- 'original_language': string like "eng", "es", "ko", etc+- 'original_title': string that's name of the movie in the original language+- 'overview': string about the movie+- 'popularity': float, from 0 to 9137.939. It's not normalized at all and there are outliers+- 'release_date': date in the format yyyy-mm-dd+- 'title': string that's the name of the movie in english+- 'vote_average': float number between 0 and 10 that's representing viewers voting average+- 'vote_count': int for how many viewers voted++I want to better understand how the vote average has changed over the years. Write Python code that analyzes the dataset based on my request and produces right chart accordingly`++const anthropic = new Anthropic()+const msg = await anthropic.messages.create({+ model: 'claude-3-5-sonnet-20240620',+ max_tokens: 1024,+ messages: [{ role: 'user', content: prompt }],+})+```++```python {{ language: 'python', description: 'main.py' }}+from dotenv import load_dotenv+load_dotenv()+from anthropic import Anthropic++prompt = '''+I have a CSV file about movies. It has about 10k rows. It's saved in the sandbox at {datasetPathInSandbox.path}.+These are the columns:+- 'id': number, id of the movie+- 'original_language': string like "eng", "es", "ko", etc+- 'original_title': string that's name of the movie in the original language+- 'overview': string about the movie+- 'popularity': float, from 0 to 9137.939. It's not normalized at all and there are outliers+- 'release_date': date in the format yyyy-mm-dd+- 'title': string that's the name of the movie in english+- 'vote_average': float number between 0 and 10 that's representing viewers voting average+- 'vote_count': int for how many viewers voted++I want to better understand how the vote average has changed over the years. Write Python code that analyzes the dataset based on my request and produces right chart accordingly'''++anthropic = Anthropic()+msg = anthropic.messages.create(+ model='claude-3-5-sonnet-20240620',+ max_tokens=1024,+ messages=[+ {"role": "user", "content": prompt}+ ]+)+```+</CodeGroup>++### 7. Connect the sandbox to the LLM with tool calling+We'll use Claude's ability to [use tools (function calling)](https://docs.anthropic.com/en/docs/build-with-claude/tool-use) to run the code in the sandbox.++The way we'll do it is by connecting the method for running AI-generated code we created in the previous step to the Claude model.++Update the initialization of the Anthropic client to include the tool use like this:+<CodeGroup>+```js {{ language: 'js', description: 'index.ts' }}+const msg = await anthropic.messages.create({+ model: 'claude-3-5-sonnet-20240620',+ max_tokens: 1024,+ messages: [{ role: 'user', content: prompt }],+ tools: [ // $HighlightLine+ { // $HighlightLine+ name: 'run_python_code', // $HighlightLine+ description: 'Run Python code', // $HighlightLine+ input_schema: { // $HighlightLine+ type: 'object', // $HighlightLine+ properties: { // $HighlightLine+ code: { // $HighlightLine+ type: 'string', // $HighlightLine+ description: 'The Python code to run', // $HighlightLine+ }, // $HighlightLine+ }, // $HighlightLine+ required: ['code'], // $HighlightLine+ }, // $HighlightLine+ }, // $HighlightLine+ ], // $HighlightLine+})+```+```python {{ language: 'python', description: 'main.py' }}+msg = anthropic.messages.create(+ model='claude-3-5-sonnet-20240620',+ max_tokens=1024,+ messages=[+ {"role": "user", "content": prompt}+ ],+ tools=[ # $HighlightLine+ { # $HighlightLine+ "name": "run_python_code", # $HighlightLine+ "description": "Run Python code", # $HighlightLine+ "input_schema": { # $HighlightLine+ "type": "object", # $HighlightLine+ "properties": { # $HighlightLine+ "code": { "type": "string", "description": "The Python code to run" }, # $HighlightLine+ }, # $HighlightLine+ "required": ["code"], # $HighlightLine+ }, # $HighlightLine+ }, # $HighlightLine+ ], # $HighlightLine+)+```+</CodeGroup>++### 8. Parse the LLM's response and run the AI-generated code in the sandbox+Now we'll parse the `msg` object to get the code from the LLM's response based on the tool we created in the previous step.+Once we have the code, we'll pass it to the `runAIGeneratedCode` method in JavaScript or `run_ai_generated_code` method in Python we created in the previous step to run the code in the sandbox.++<CodeGroup>+```js {{ language: 'js', description: 'index.ts' }}+// ... code from the previous steps++interface CodeRunToolInput {+ code: string+}++for (const contentBlock of msg.content) {+ if (contentBlock.type === 'tool_use') {+ if (contentBlock.name === 'run_python_code') {+ const code = (contentBlock.input as CodeRunToolInput).code+ console.log('Will run following code in the sandbox', code)+ // Execute the code in the sandbox+ await runAIGeneratedCode(code)+ }+ }+}+```+```python {{ language: 'python', description: 'main.py' }}+for content_block in msg.content:+ if content_block.type == 'tool_use':+ if content_block.name == 'run_python_code':+ code = content_block.input['code']+ print('Will run following code in the sandbox', code)+ # Execute the code in the sandbox+ run_ai_generated_code(code)+```+</CodeGroup>++### 9. Save the generated chart+When running code in the sandbox for data analysis, you can get different types of results.+Including stdout, stderr, charts, tables, text, runtime errors, and more.++In this example we're specifically asking for a chart so we'll be looking for the chart in the results.++Let's update the `runAIGeneratedCode` method in JavaScript and `run_ai_generated_code` method in Python to check for the chart in the results and save it to the file.+<CodeGroup>+```js {{ language: 'js', description: 'index.ts' }}+async function runAIGeneratedCode(aiGeneratedCode: string) {+ console.log('Running the code in the sandbox....')+ const execution = await sbx.runCode(aiGeneratedCode)+ console.log('Code execution finished!')++ // First let's check if the code ran successfully.+ if (execution.error) { // $HighlightLine+ console.error('AI-generated code had an error. Try prompting the LLM differently.', execution.error) // $HighlightLine+ process.exit(1) // $HighlightLine+ } // $HighlightLine++ // Iterate over all the results and specifically check for png files that will represent the chart.+ let resultIdx = 0 // $HighlightLine+ for (const result of execution.results) { // $HighlightLine+ if (result.png) { // $HighlightLine+ // Save the png to a file+ // The png is in base64 format.+ fs.writeFileSync(`chart-${resultIdx}.png`, result.png, { encoding: 'base64' }) // $HighlightLine+ resultIdx++ // $HighlightLine+ } // $HighlightLine+ } // $HighlightLine+}+```+```python {{ language: 'python', description: 'main.py' }}+def run_ai_generated_code(ai_generated_code: str):+ print('Running the code in the sandbox....')+ execution = sbx.run_code(ai_generated_code)+ print('Code execution finished!')++ # First let's check if the code ran successfully.+ if execution.error: # $HighlightLine+ print('AI-generated code had an error. Try prompting the LLM differently.', execution.error) # $HighlightLine+ sys.exit(1) # $HighlightLine++ # Iterate over all the results and specifically check for png files that will represent the chart.+ result_idx = 0 # $HighlightLine+ for result in execution.results: # $HighlightLine+ if result.png: # $HighlightLine+ # Save the png to a file+ # The png is in base64 format.+ with open(f'chart-{result_idx}.png', 'wb') as f: # $HighlightLine+ f.write(base64.b64decode(result.png)) # $HighlightLine+ result_idx += 1 # $HighlightLine+```+</CodeGroup>++### 10. Run the full code+Now you can run the whole code to see the results.++<CodeGroup isTerminalCommand>+```bash {{ language: 'js' }}+npx tsx index.ts+```+```bash {{ language: 'python' }}+python main.py+```+</CodeGroup>++You should see the chart in the root of your project that will look similar to this:++<Image+ src={imgChart}+ className="rounded w-full"+ alt="Chart visualizing voting average of our dataset over time"+ unoptimized+/>\ No newline at end of filediff --git a/apps/web/src/components/Navigation/routes.tsx b/apps/web/src/components/Navigation/routes.tsxindex c7e465a13..d3b9cbafd 100644--- a/apps/web/src/components/Navigation/routes.tsx+++ b/apps/web/src/components/Navigation/routes.tsx@@ -156,12 +156,12 @@ export const routes: NavGroup[] = [title: 'Pre-installed libraries',href: '/docs/code-interpreting/analyze-data/pre-installed-libraries',},- {- title: '* Example',- href: '/docs/code-interpreting/analyze-data/example',- },],},+ {+ title: '* Connect your data',+ href: '/docs/code-interpreting/connect-your-data',+ },{title: 'Supported languages',links: [@@ -188,12 +188,8 @@ export const routes: NavGroup[] = []},{- title: '* Create charts & visualizations',- href: '/docs/code-interpreting/create-charts',- },- {- title: '* Connect your data',- href: '/docs/code-interpreting/connect-your-data',+ title: '* Code interpreting results',+ href: '/docs/code-interpreting/todo',},]},diff --git a/apps/web/src/images/analyze-data-chart.png b/apps/web/src/images/analyze-data-chart.pngnew file mode 100644index 000000000..ea9f89246Binary files /dev/null and b/apps/web/src/images/analyze-data-chart.png differ