# ResumeParser Pro 🚀
[](https://badge.fury.io/py/resumeparser-pro)
[](https://pypi.org/project/resumeparser-pro/)
[](https://opensource.org/licenses/MIT)
Production-ready AI-powered resume parser with parallel processing capabilities. Extract structured data from resumes in PDF, DOCX, and TXT formats using state-of-the-art language models.
## 🌟 Features
- **🤖 AI-Powered**: Uses advanced language models (GPT, Gemini, Claude, etc.)
- **⚡ Parallel Processing**: Process multiple resumes simultaneously
- **📊 Structured Output**: Returns clean, validated JSON data
- **🎯 High Accuracy**: Extracts 20+ fields with intelligent categorization
- **📈 Production Ready**: Robust error handling and logging
- **🔌 Easy Integration**: Simple API with just 3 lines of code
## 🚀 Quick Start
### Installation
```bash
pip install ai-resume-parser
```
For full functionality (recommended)
```bash
pip install ai-resume-parser[full]
```
### Basic Usage
```python
from resumeparser_pro import ResumeParserPro
#Initialize parser
parser = ResumeParserPro(
provider="google_genai",
model_name="gemini-2.0-flash",
api_key="your-api-key"
)
#Parse single resume
result = parser.parse_resume("resume.pdf")
print(f"Name: {result.resume_data.contact_info.full_name}")
print(f"Experience: {result.resume_data.total_experience_months} months")
```
### Example Parsed Resume data
```python
{'file_path': 'resume.pdf',
'success': True,
'resume_data': {'contact_info': {'full_name': 'Jason Miller',
'email': 'email@email.com',
'phone': '+1386862',
'location': 'Los Angeles, CA 90291, United States',
'linkedin': 'https://www.linkedin.com/in/jason-miller',
'github': None,
'portfolio': None,
'other_profiles': ['https://www.pinterest.com/jason-miller']},
'professional_summary': 'Experienced Amazon Associate with five years’ tenure in a shipping yard setting, maintaining an average picking/packing speed of 98%. Holds a zero error% score in adhering to packing specs and 97% error-free ratio on packing records. Completed a certificate in Warehouse Sanitation and has a valid commercial driver’s license.',
'skills': [{'category': 'Technical Skills',
'skills': ['Picking',
'Packing',
'Inventory Management',
'Shipping',
'Record Keeping',
'Kanban System',
'Kaizen',
'Gemba',
'5S'],
'proficiency_level': None},
{'category': 'Soft Skills',
'skills': ['Mathematics'],
'proficiency_level': None},
{'category': 'Other',
'skills': ['Cleaning Equipment', 'Deep Sanitation Practices'],
'proficiency_level': None}],
'work_experience': [{'job_title': 'Amazon Warehouse Associate',
'company': 'Amazon',
'location': 'Miami Gardens',
'employment_type': None,
'start_date': '2021-01',
'end_date': '2022-07',
'duration_months': 19,
'description': 'Performed all warehouse laborer duties such as packing, picking, counting, record keeping, and maintaining a clean area.',
'responsibilities': [],
'achievements': ['Consistently maintained picking/packing speeds in the 98th percentile.',
'Picked all orders with 100% accuracy despite high speeds.',
'Maintained a clean work area, meeting 97.5% of the inspection requirements.'],
'technologies': []},
{'job_title': 'Laboratory Inventory Assistant',
'company': 'Dunrea Laboratories',
'location': 'Orlando',
'employment_type': 'Full-time',
'start_date': '2019-01',
'end_date': '2020-12',
'duration_months': 24,
'description': 'Full-time lab assistant in a small, regional laboratory tasked with · participating in Kaizen Events, Gemba walks, and 5S to remove barriers and improve productivity.',
'responsibilities': ['Filled the warehouse helper job description, which involved picking, packing, shipping, inventory management, and cleaning equipment.'],
'achievements': ['Saved 12% on UPS orders by staying on top of special deals.',
'Cut down storage waste by 23% by switching to a Kanban system.'],
'technologies': []}],
'education': [{'degree': 'Associates Degree in Logistics and Supply Chain Fundamentals',
'field_of_study': None,
'institution': 'Atlanta Technical College',
'location': 'Atlanta',
'start_date': '2021-01',
'end_date': '2022-07',
'gpa': None,
'honors': [],
'relevant_coursework': ['Warehousing Operations',
'Logistics and Distribution Practices',
'Inventory Systems',
'Supply Chain Principles']}],
'projects': [],
'certifications': [],
'languages': [{'language': 'English', 'proficiency': None},
{'language': 'Spanish', 'proficiency': None}],
'publications': [],
'awards': [{'title': 'Employee of the month',
'issuer': 'Amazon',
'date': None,
'description': None}],
'volunteer_experience': [],
'interests': ['Action Cricket', 'Rugby', 'Athletics'],
'total_experience_months': 43,
'industry': 'Logistics & Supply Chain',
'seniority_level': 'Mid-level'},
'error_message': None,
'parsing_time_seconds': 3.71349,
'timestamp': '2025-07-25T15:19:50.614831'}
```
# Flexible approach (recommended)
```python
if result.success:
name = result.resume_data.contact_info.full_name
experience = result.resume_data.total_experience_months
# Quick overview (convenience method)
print(result.get_summary())
# Full data export
resume_dict = result.model_dump()
```
### Batch Processing
```python
#Process multiple resumes in parallel
file_paths = ["resume1.pdf", "resume2.docx", "resume3.pdf"]
results = parser.parse_batch(file_paths)
#returns list of parsed resumes
#Get successful results
successful_resumes = parser.get_successful_resumes(results)
print(f"Parsed {len(successful_resumes)} resumes successfully")
```
## 📊 Extracted Data
ResumeParser Pro extracts **20+ structured fields**:
### Contact Information
- Full name, email, phone number
- Location, LinkedIn, GitHub, portfolio
- Other social profiles
### Professional Data
- Work experience with **integer month durations**
- Education with GPA standardization
- Skills categorized by type
- Projects with technologies and outcomes
- Certifications with dates and organizations
### Metadata
- Total experience in months
- Industry classification
- Seniority level assessment
## 🎯 Supported AI Providers
Since `ai-resume-parser` uses LangChain's `init_chat_model`, it supports **all LangChain-compatible providers**:
### **Major Providers:**
| Provider | Example Models | Setup |
|----------|--------|-------|
| **Google** | Gemini 2.0 Flash, Gemini Pro, Gemini 1.5 | `provider="google_genai"` |
| **OpenAI** | GPT-4o, GPT-4o-mini, GPT-4 Turbo | `provider="openai"` |
| **Anthropic** | Claude 3.5 Sonnet, Claude 3 Opus | `provider="anthropic"` |
| **Azure OpenAI** | GPT-4, GPT-3.5-turbo | `provider="azure_openai"` |
| **AWS Bedrock** | Claude, Llama, Titan | `provider="bedrock"` |
| **Cohere** | Command, Command-R | `provider="cohere"` |
| **Mistral** | Mistral Large, Mixtral | `provider="mistral"` |
| **Ollama** | Local models (Llama, CodeLlama) | `provider="ollama"` |
| **Together** | Various open-source models | `provider="together"` |
### **Usage Examples:**
```python
#Google Gemini
!pip install langchain-google-genai
parser = ResumeParserPro(
provider="google_genai",
model_name="gemini-2.0-flash",
api_key="your-google-api-key"
)
#Azure OpenAI
parser = ResumeParserPro(
provider="azure_openai",
model_name="gpt-4",
api_key="your-azure-key"
)
#Local Ollama
parser = ResumeParserPro(
provider="ollama",
model_name="llama2:7b",
api_key="" # No API key needed for local
)
#AWS Bedrock
parser = ResumeParserPro(
provider="bedrock",
model_name="anthropic.claude-3-sonnet-20240229-v1:0",
api_key="your-aws-credentials"
)
```
**Full list**: See [LangChain Model Providers](https://python.langchain.com/docs/integrations/chat/) for complete provider support.
## 📈 Performance
- **Speed**: ~3-5 seconds per resume (based on th llm used)
- **Parallel Processing**: 5-10x faster for batch operations
- **Accuracy**: 95%+ field extraction accuracy
- **File Support**: PDF, DOCX, TXT formats
## 🛠️ Advanced Features
### Custom Configuration
```python
parser = ResumeParserPro(
provider="openai",
model_name="gpt-4o-mini",
api_key="your-api-key",
max_workers=10, # Parallel processing workers
temperature=0.1 # Model consistency
)
```
### Error Handling
```python
results = parser.parse_batch(file_paths, include_failed=True)
Get processing summary
summary = parser.get_summary(results)
print(f"Success rate: {summary['success_rate']:.1f}%")
print(f"Failed files: {len(summary['failed_files'])}")
```
## 📋 Requirements
- Python 3.8+
- API key from supported provider
- Optional: PyMuPDF, python-docx for enhanced file support
## 🤝 Contributing
Contributions welcome! Please read our contributing guidelines.
## 📄 License
MIT License - see LICENSE file for details.
## 🆘 Support
- 📖 [Documentation](https://github.com/Ruthikr/ai-resume-parser/docs)
- 🐛 [Issue Tracker](https://github.com/Ruthikr/ai-resume-parser/issues)
- 💬 [Discussions](https://github.com/Ruthikr/ai-resume-parser/discussions)
---
**Built with ❤️ for the recruitment and HR community**
Raw data
{
"_id": null,
"home_page": null,
"name": "ai-resume-parser",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "resume parsing, AI, NLP, parallel processing, recruitment, HR, LLM, resume, parser, Gemini, Google GenAI, OpenAI, job",
"author": null,
"author_email": "Ruthik Reddy <ruthikr369@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/e6/0d/a75344e6a24a886003194aaa460bbe5e828e218bf1ce7b295af144e1b93a/ai_resume_parser-1.0.3.tar.gz",
"platform": null,
"description": "# ResumeParser Pro \ud83d\ude80\n\n[](https://badge.fury.io/py/resumeparser-pro)\n[](https://pypi.org/project/resumeparser-pro/)\n[](https://opensource.org/licenses/MIT)\n\nProduction-ready AI-powered resume parser with parallel processing capabilities. Extract structured data from resumes in PDF, DOCX, and TXT formats using state-of-the-art language models.\n\n## \ud83c\udf1f Features\n\n- **\ud83e\udd16 AI-Powered**: Uses advanced language models (GPT, Gemini, Claude, etc.)\n- **\u26a1 Parallel Processing**: Process multiple resumes simultaneously\n- **\ud83d\udcca Structured Output**: Returns clean, validated JSON data\n- **\ud83c\udfaf High Accuracy**: Extracts 20+ fields with intelligent categorization\n- **\ud83d\udcc8 Production Ready**: Robust error handling and logging\n- **\ud83d\udd0c Easy Integration**: Simple API with just 3 lines of code\n\n## \ud83d\ude80 Quick Start\n\n### Installation\n```bash\npip install ai-resume-parser\n```\nFor full functionality (recommended)\n```bash\npip install ai-resume-parser[full]\n```\n\n\n### Basic Usage\n```python\nfrom resumeparser_pro import ResumeParserPro\n\n#Initialize parser\nparser = ResumeParserPro(\nprovider=\"google_genai\",\nmodel_name=\"gemini-2.0-flash\",\napi_key=\"your-api-key\"\n)\n\n#Parse single resume\nresult = parser.parse_resume(\"resume.pdf\")\nprint(f\"Name: {result.resume_data.contact_info.full_name}\")\nprint(f\"Experience: {result.resume_data.total_experience_months} months\")\n```\n### Example Parsed Resume data\n\n```python\n{'file_path': 'resume.pdf',\n 'success': True,\n 'resume_data': {'contact_info': {'full_name': 'Jason Miller',\n 'email': 'email@email.com',\n 'phone': '+1386862',\n 'location': 'Los Angeles, CA 90291, United States',\n 'linkedin': 'https://www.linkedin.com/in/jason-miller',\n 'github': None,\n 'portfolio': None,\n 'other_profiles': ['https://www.pinterest.com/jason-miller']},\n 'professional_summary': 'Experienced Amazon Associate with five years\u2019 tenure in a shipping yard setting, maintaining an average picking/packing speed of 98%. Holds a zero error% score in adhering to packing specs and 97% error-free ratio on packing records. Completed a certificate in Warehouse Sanitation and has a valid commercial driver\u2019s license.',\n 'skills': [{'category': 'Technical Skills',\n 'skills': ['Picking',\n 'Packing',\n 'Inventory Management',\n 'Shipping',\n 'Record Keeping',\n 'Kanban System',\n 'Kaizen',\n 'Gemba',\n '5S'],\n 'proficiency_level': None},\n {'category': 'Soft Skills',\n 'skills': ['Mathematics'],\n 'proficiency_level': None},\n {'category': 'Other',\n 'skills': ['Cleaning Equipment', 'Deep Sanitation Practices'],\n 'proficiency_level': None}],\n 'work_experience': [{'job_title': 'Amazon Warehouse Associate',\n 'company': 'Amazon',\n 'location': 'Miami Gardens',\n 'employment_type': None,\n 'start_date': '2021-01',\n 'end_date': '2022-07',\n 'duration_months': 19,\n 'description': 'Performed all warehouse laborer duties such as packing, picking, counting, record keeping, and maintaining a clean area.',\n 'responsibilities': [],\n 'achievements': ['Consistently maintained picking/packing speeds in the 98th percentile.',\n 'Picked all orders with 100% accuracy despite high speeds.',\n 'Maintained a clean work area, meeting 97.5% of the inspection requirements.'],\n 'technologies': []},\n {'job_title': 'Laboratory Inventory Assistant',\n 'company': 'Dunrea Laboratories',\n 'location': 'Orlando',\n 'employment_type': 'Full-time',\n 'start_date': '2019-01',\n 'end_date': '2020-12',\n 'duration_months': 24,\n 'description': 'Full-time lab assistant in a small, regional laboratory tasked with \u00b7 participating in Kaizen Events, Gemba walks, and 5S to remove barriers and improve productivity.',\n 'responsibilities': ['Filled the warehouse helper job description, which involved picking, packing, shipping, inventory management, and cleaning equipment.'],\n 'achievements': ['Saved 12% on UPS orders by staying on top of special deals.',\n 'Cut down storage waste by 23% by switching to a Kanban system.'],\n 'technologies': []}],\n 'education': [{'degree': 'Associates Degree in Logistics and Supply Chain Fundamentals',\n 'field_of_study': None,\n 'institution': 'Atlanta Technical College',\n 'location': 'Atlanta',\n 'start_date': '2021-01',\n 'end_date': '2022-07',\n 'gpa': None,\n 'honors': [],\n 'relevant_coursework': ['Warehousing Operations',\n 'Logistics and Distribution Practices',\n 'Inventory Systems',\n 'Supply Chain Principles']}],\n 'projects': [],\n 'certifications': [],\n 'languages': [{'language': 'English', 'proficiency': None},\n {'language': 'Spanish', 'proficiency': None}],\n 'publications': [],\n 'awards': [{'title': 'Employee of the month',\n 'issuer': 'Amazon',\n 'date': None,\n 'description': None}],\n 'volunteer_experience': [],\n 'interests': ['Action Cricket', 'Rugby', 'Athletics'],\n 'total_experience_months': 43,\n 'industry': 'Logistics & Supply Chain',\n 'seniority_level': 'Mid-level'},\n 'error_message': None,\n 'parsing_time_seconds': 3.71349,\n 'timestamp': '2025-07-25T15:19:50.614831'}\n```\n\n# Flexible approach (recommended)\n```python\nif result.success:\n name = result.resume_data.contact_info.full_name\n experience = result.resume_data.total_experience_months\n \n# Quick overview (convenience method)\nprint(result.get_summary())\n\n# Full data export\nresume_dict = result.model_dump()\n```\n\n### Batch Processing\n```python\n#Process multiple resumes in parallel\nfile_paths = [\"resume1.pdf\", \"resume2.docx\", \"resume3.pdf\"]\nresults = parser.parse_batch(file_paths)\n#returns list of parsed resumes\n\n#Get successful results\nsuccessful_resumes = parser.get_successful_resumes(results)\nprint(f\"Parsed {len(successful_resumes)} resumes successfully\")\n```\n\n## \ud83d\udcca Extracted Data\n\nResumeParser Pro extracts **20+ structured fields**:\n\n### Contact Information\n- Full name, email, phone number\n- Location, LinkedIn, GitHub, portfolio\n- Other social profiles\n\n### Professional Data\n- Work experience with **integer month durations**\n- Education with GPA standardization\n- Skills categorized by type\n- Projects with technologies and outcomes\n- Certifications with dates and organizations\n\n### Metadata\n- Total experience in months\n- Industry classification\n- Seniority level assessment\n\n## \ud83c\udfaf Supported AI Providers\n\nSince `ai-resume-parser` uses LangChain's `init_chat_model`, it supports **all LangChain-compatible providers**:\n\n### **Major Providers:**\n| Provider | Example Models | Setup |\n|----------|--------|-------|\n| **Google** | Gemini 2.0 Flash, Gemini Pro, Gemini 1.5 | `provider=\"google_genai\"` |\n| **OpenAI** | GPT-4o, GPT-4o-mini, GPT-4 Turbo | `provider=\"openai\"` |\n| **Anthropic** | Claude 3.5 Sonnet, Claude 3 Opus | `provider=\"anthropic\"` |\n| **Azure OpenAI** | GPT-4, GPT-3.5-turbo | `provider=\"azure_openai\"` |\n| **AWS Bedrock** | Claude, Llama, Titan | `provider=\"bedrock\"` |\n| **Cohere** | Command, Command-R | `provider=\"cohere\"` |\n| **Mistral** | Mistral Large, Mixtral | `provider=\"mistral\"` |\n| **Ollama** | Local models (Llama, CodeLlama) | `provider=\"ollama\"` |\n| **Together** | Various open-source models | `provider=\"together\"` |\n\n### **Usage Examples:**\n```python\n#Google Gemini\n!pip install langchain-google-genai\n\nparser = ResumeParserPro(\nprovider=\"google_genai\",\nmodel_name=\"gemini-2.0-flash\",\napi_key=\"your-google-api-key\"\n)\n\n#Azure OpenAI\nparser = ResumeParserPro(\nprovider=\"azure_openai\",\nmodel_name=\"gpt-4\",\napi_key=\"your-azure-key\"\n)\n\n#Local Ollama\nparser = ResumeParserPro(\nprovider=\"ollama\",\nmodel_name=\"llama2:7b\",\napi_key=\"\" # No API key needed for local\n)\n\n#AWS Bedrock\nparser = ResumeParserPro(\nprovider=\"bedrock\",\nmodel_name=\"anthropic.claude-3-sonnet-20240229-v1:0\",\napi_key=\"your-aws-credentials\"\n)\n```\n\n**Full list**: See [LangChain Model Providers](https://python.langchain.com/docs/integrations/chat/) for complete provider support.\n\n\n## \ud83d\udcc8 Performance\n\n- **Speed**: ~3-5 seconds per resume (based on th llm used)\n- **Parallel Processing**: 5-10x faster for batch operations\n- **Accuracy**: 95%+ field extraction accuracy\n- **File Support**: PDF, DOCX, TXT formats\n\n## \ud83d\udee0\ufe0f Advanced Features\n\n### Custom Configuration\n```python\nparser = ResumeParserPro(\nprovider=\"openai\",\nmodel_name=\"gpt-4o-mini\",\napi_key=\"your-api-key\",\nmax_workers=10, # Parallel processing workers\ntemperature=0.1 # Model consistency\n)\n```\n\n### Error Handling\n```python\nresults = parser.parse_batch(file_paths, include_failed=True)\n\nGet processing summary\nsummary = parser.get_summary(results)\nprint(f\"Success rate: {summary['success_rate']:.1f}%\")\nprint(f\"Failed files: {len(summary['failed_files'])}\")\n```\n\n## \ud83d\udccb Requirements\n\n- Python 3.8+\n- API key from supported provider\n- Optional: PyMuPDF, python-docx for enhanced file support\n\n## \ud83e\udd1d Contributing\n\nContributions welcome! Please read our contributing guidelines.\n\n## \ud83d\udcc4 License\n\nMIT License - see LICENSE file for details.\n\n## \ud83c\udd98 Support\n\n- \ud83d\udcd6 [Documentation](https://github.com/Ruthikr/ai-resume-parser/docs)\n- \ud83d\udc1b [Issue Tracker](https://github.com/Ruthikr/ai-resume-parser/issues)\n- \ud83d\udcac [Discussions](https://github.com/Ruthikr/ai-resume-parser/discussions)\n\n---\n\n**Built with \u2764\ufe0f for the recruitment and HR community**\n",
"bugtrack_url": null,
"license": null,
"summary": "AI-powered resume parser with parallel processing capabilities",
"version": "1.0.3",
"project_urls": {
"Documentation": "https://github.com/Ruthikr/ai-resume-parser/tree/main/docs",
"Homepage": "https://github.com/Ruthikr",
"Issues": "https://github.com/Ruthikr/ai-resume-parser/issues",
"Repository": "https://github.com/Ruthikr/ai-resume-parser"
},
"split_keywords": [
"resume parsing",
" ai",
" nlp",
" parallel processing",
" recruitment",
" hr",
" llm",
" resume",
" parser",
" gemini",
" google genai",
" openai",
" job"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "f38e9c28d35f21f3bebf9f404ff07769bf7d18f4a4508f0663a309be6bafd90c",
"md5": "8d1024bffb38d55b0e1f477d666239e7",
"sha256": "362a09f178e5295ff893cca3e4fe4270c04c4f6b64ee7d6b283a9da4294fc9ec"
},
"downloads": -1,
"filename": "ai_resume_parser-1.0.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "8d1024bffb38d55b0e1f477d666239e7",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 15526,
"upload_time": "2025-07-25T16:16:52",
"upload_time_iso_8601": "2025-07-25T16:16:52.677913Z",
"url": "https://files.pythonhosted.org/packages/f3/8e/9c28d35f21f3bebf9f404ff07769bf7d18f4a4508f0663a309be6bafd90c/ai_resume_parser-1.0.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "e60da75344e6a24a886003194aaa460bbe5e828e218bf1ce7b295af144e1b93a",
"md5": "73df355594673b2312948f1e0c3ac435",
"sha256": "450ac54894c73da3d0ac5aa456c11e2487fbc9375b8945c9b83850b2d66b26a7"
},
"downloads": -1,
"filename": "ai_resume_parser-1.0.3.tar.gz",
"has_sig": false,
"md5_digest": "73df355594673b2312948f1e0c3ac435",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 14131,
"upload_time": "2025-07-25T16:16:54",
"upload_time_iso_8601": "2025-07-25T16:16:54.892513Z",
"url": "https://files.pythonhosted.org/packages/e6/0d/a75344e6a24a886003194aaa460bbe5e828e218bf1ce7b295af144e1b93a/ai_resume_parser-1.0.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-25 16:16:54",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "Ruthikr",
"github_project": "ai-resume-parser",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "pydantic",
"specs": [
[
">=",
"2.0.0"
]
]
},
{
"name": "langchain-core",
"specs": [
[
">=",
"0.1.0"
]
]
},
{
"name": "python-dateutil",
"specs": [
[
">=",
"2.8.0"
]
]
},
{
"name": "pdfminer.six",
"specs": [
[
">=",
"20221105"
]
]
},
{
"name": "PyMuPDF",
"specs": [
[
">=",
"1.23.0"
]
]
},
{
"name": "python-docx",
"specs": [
[
">=",
"0.8.11"
]
]
},
{
"name": "phonenumbers",
"specs": [
[
">=",
"8.13.0"
]
]
}
],
"lcname": "ai-resume-parser"
}
JSON
