Document Processing: Analyze Files with AI

npm install multer pdf-parse

import Anthropic from '@anthropic-ai/sdk';
import fs from 'fs/promises';
import path from 'path';
import * as dotenv from 'dotenv';
dotenv.config();

const client = new Anthropic();

async function analyzeDocument(filePath, instruction) { const ext = path.extname(filePath).toLowerCase(); let content; if (ext === '.txt' || ext === '.md' || ext === '.csv') { content = await fs.readFile(filePath, 'utf-8'); } else { throw new Error(`Unsupported file type: ${ext}`); } // Truncate if too long (Claude handles up to 200K tokens) const maxChars = 180000; if (content.length > maxChars) { content = content.slice(0, maxChars) + '

[Content truncated...]'; } const response = await client.messages.create({ model: 'claude-opus-4-5', max_tokens: 2048, messages: [{ role: 'user', content: `Here is the document content:

${content}

---

${instruction}` }] }); return response.content[0].text;
}

// Example usage
const summary = await analyzeDocument('./report.txt', 'Summarize this document in 5 bullet points.');
console.log(summary);

const extraction = await analyzeDocument('./data.csv', 'List all unique values in the "category" column.');

import multer from 'multer';
const upload = multer({ dest: 'uploads/', limits: { fileSize: 10 * 1024 * 1024 } });

app.post('/analyze', upload.single('document'), async (req, res) => { if (!req.file) return res.status(400).json({ error: 'No file uploaded' }); const { instruction = 'Summarize this document.' } = req.body; try { const content = await fs.readFile(req.file.path, 'utf-8'); const response = await client.messages.create({ model: 'claude-opus-4-5', max_tokens: 2048, messages: [{ role: 'user', content: `Document:

${content}

Task: ${instruction}` }] }); // Clean up temp file await fs.unlink(req.file.path); res.json({ result: response.content[0].text }); } catch (error) { res.status(500).json({ error: error.message }); }
});