API Documentation

CV Parser & OCR Services

CV Parser API Reference

Use this API endpoint to integrate CV parsing into your applications

CV Parser API Endpoint

POST

Request Format

Method: POST

Content-Type: multipart/form-data

Parameters:

• file (required) - PDF file to parse
• model (required) - LLM model name (e.g., "llama3.1:latest")

Example Usage

cv-parser.js

const formData = new FormData();formData.append('file', pdfFile);formData.append('model', 'llama3.1:latest');const response = await fetch('', {  method: 'POST',  body: formData});const result = await response.json();console.log(result);

Response Format

cv-response.json

{  "success": true,  "data": {    "cv": {      "personalInfo": {        "firstName": "John",        "lastName": "Doe",        "fullName": "John Doe",        "email": "john.doe@example.com",        "phone": "+1-234-567-8900",        "location": "San Francisco, CA",        "linkedin": "https://linkedin.com/in/johndoe",        "github": "https://github.com/johndoe"      },      "summary": "Experienced software engineer with 5+ years...",      "experience": [        {          "company": "Tech Corp",          "position": "Senior Software Engineer",          "startDate": "2020-01",          "endDate": "2023-12",          "current": false,          "location": "San Francisco, CA",          "description": "Led development of...",          "achievements": ["Improved performance by 40%", "Led team of 5"]        }      ],      "education": [        {          "institution": "University of Technology",          "degree": "Bachelor of Computer Science",          "field": "Computer Science",          "startDate": "2016-09",          "endDate": "2020-05",          "gpa": "3.8"        }      ],      "skills": {        "technical": ["JavaScript", "Python", "React", "Node.js"],        "languages": ["English", "Spanish"],        "certifications": ["AWS Certified Developer"]      },      "projects": [        {          "name": "E-commerce Platform",          "description": "Full-stack e-commerce solution",          "technologies": ["React", "Node.js", "MongoDB"],          "url": "https://github.com/johndoe/ecommerce"        }      ]    },    "document": {      "filename": "john_doe_cv.pdf",      "pageCount": 2,      "processingMethod": "text-extraction",      "processingTime": 2500,      "confidence": 95.5    },    "rawText": "John Doe\nSoftware Engineer\n...",    "processingInfo": {      "ocrService": "http://localhost:8080",      "documentType": "CV",      "confidence": 95.5,      "cvRelevanceScore": 0.92,      "cvCompleteness": {        "completeness": 0.88,        "missingSections": ["volunteer"],        "suggestions": ["Add volunteer experience"]      }    }  }}

C# Model Classes

public class CVParserResult
{
    public string Name { get; set; }
    public string Email { get; set; }
    public string Phone { get; set; }
    public List<Experience> Experience { get; set; }
    public List<Education> Education { get; set; }
    public List<string> Skills { get; set; }
}

public class Experience
{
    public string Company { get; set; }
    public string Position { get; set; }
    public string Duration { get; set; }
}

public class Education
{
    public string Institution { get; set; }
    public string Degree { get; set; }
    public string Year { get; set; }
}

Important Notes:

• The API requires a valid Ollama server connection
• The specified model must be installed on your Ollama server
• Only PDF files are supported
• Response format may vary based on CV content and model used

OCR Service API Reference

Standalone PDF text extraction and OCR processing service

OCR Service API Endpoint