This project is a web application built with Next.js that allows users to upload CV files in PDF format, parse them, and convert the content into structured JSON using OpenAI's language model. It streamlines the process of extracting relevant information from CVs for easier data management and analysist.
-
Clone the repository
git clone https://github.com/Mochrks/cv-parser-ai.git cd cv-parser-ai -
Install dependencies
npm install
-
Configure Environment Variables Create a
.envfile in the root directory and add:OPENAI_API_KEY=your_openai_api_key -
Run the development server
npm run dev
-
Open http://localhost:3000 with your browser to see the result.
- PDF Upload: Users can upload CV files in PDF format.
- PDF Parsing: Extracts text content from uploaded PDF files.
- AI-Powered Conversion: Utilizes OpenAI's model to convert parsed text into structured JSON.
- File Upload: User uploads a CV in PDF format.
- PDF Parsing: The application uses PDF.js to extract text content from the PDF.
- AI Processing: The extracted text is sent to OpenAI's model with a custom prompt to structure the data.
- JSON Generation: The AI model returns a structured JSON representation of the CV data.
POST api/process-pdf: Handles PDF file upload and parsing.POST api/generate-json: Sends parsed text to OpenAI for conversion to JSON.
- Pdf-parser
- Lucide-react icon
- TailwindCSS
A simple API endpoint to convert PDF files to text using Next.js.
-
Receive Request
- Endpoint only accepts POST method
- Receives PDF file in base64 format
-
Main Process
- Converts base64 to buffer
- Extracts text from PDF using pdf-parse
- Returns result in JSON format
// Required imports
import type { NextApiRequest, NextApiResponse } from 'next';
import pdfParse from 'pdf-parse';
export default async function handler(req: NextApiRequest, res: NextApiResponse) {
// Check for POST method
if (req.method !== 'POST') {
return res.status(405).json({ error: 'Method not allowed' });
}
try {
// Get file content from request body
const { fileContent } = req.body;
// Convert base64 to buffer
const pdfBuffer = Buffer.from(fileContent.split(',')[1], 'base64');
// Parse PDF to text
const pdfData = await pdfParse(pdfBuffer);
const text = pdfData.text;
// Send success response
return res.status(200).json({ text });
} catch (error) {
// Handle error
console.error('Error processing PDF:', error);
return res.status(500).json({ error: 'Failed to process PDF' });
}
}A Next.js API endpoint that converts CV/Resume text into structured JSON format using OpenAI's GPT model.
-
Receive Request
- Endpoint only accepts POST method
- Receives CV text in request body
-
Main Process
- Sends text to OpenAI API with specific CV structure instructions
- Processes response and converts to structured JSON
- Returns JSON result using format by props
// Required imports
import type { NextApiRequest, NextApiResponse } from 'next';
import { CV_STRUCTURE_INSTRUCTIONS } from '@/utils/cvStructure';
export default async function handler(req: NextApiRequest, res: NextApiResponse) {
// Check for POST method
if (req.method !== 'POST') {
return res.status(405).json({ error: 'Method not allowed' });
}
try {
// Get CV text from request body
const { text } = req.body;
// Make request to OpenAI API
const response = await fetch("https://api.openai.com/v1/chat/completions", {
method: "POST",
headers: {
"Content-Type": "application/json",
"Authorization": `Bearer ${process.env.OPENAI_API_KEY}`,
},
body: JSON.stringify({
model: "gpt-4o-mini",
messages: [
{
role: "system",
content: CV_STRUCTURE_INSTRUCTIONS
},
{
role: "user",
content: `Convert the following CV/Resume text into JSON:\n\n${text}`
}
],
temperature: 0.7,
max_tokens: 2000
}),
});
if (!response.ok) {
throw new Error('OpenAI API request failed');
}
// Process and return JSON response
const data = await response.json();
return res.status(200).json(JSON.parse(data.choices[0].message.content));
} catch (error) {
// Handle error
console.error('Error generating JSON:', error);
return res.status(500).json({ error: 'Failed to generate JSON' });
}
}
