# LLM Wrapper - Universal Large Language Model Library
A comprehensive, modular Python library for seamless integration with multiple Large Language Model providers. Built with enterprise-grade features including token tracking, usage analytics, and robust error handling.
## 🚀 Features
- **Multi-Provider Support**: Azure OpenAI, OpenAI, Anthropic Claude, and extensible for more
- **Unified API**: Single interface for all LLM providers
- **Token Tracking**: Comprehensive token usage logging with PostgreSQL backend
- **Usage Analytics**: Detailed statistics and monitoring capabilities
- **Enterprise Ready**: Connection pooling, error handling, and production-grade logging
- **Type Safety**: Full type hints and data validation
- **Modular Architecture**: Clean separation of concerns with factory pattern
- **Backward Compatible**: Legacy API support for existing integrations
## 📦 Installation
```bash
pip install hibiz-any-llm
```
## 🏗️ Architecture
```
llm_wrapper/
├── core/ # Core functionality and factory
├── providers/ # LLM provider implementations
├── models/ # Data models and schemas
├── database/ # Database management
└──utils/ # Token Calculation and validators
```
## 🛠️ Quick Start
### 1. Basic Setup
```python
from hibiz_any_llm import LLMWrapper, LLMProvider
# Configure your provider
azure_config = {
'service_url': 'https://your-resource.openai.azure.com',
'api_key': 'your-api-key',
'deployment_name': 'gpt-4',
'api_version': '2023-12-01-preview'
}
# Database configuration
db_config = {
'host': 'localhost',
'port': 5432,
'dbname': 'llm_usage',
'user': 'username',
'password': 'password'
}
# Initialize wrapper
wrapper = LLMWrapper(
provider_type=LLMProvider.AZURE_OPENAI,
provider_config=azure_config,
db_config=db_config,
enable_logging=True
)
```
### 2. Chat Completion
```python
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "What is machine learning?"}
]
response = wrapper.send_request(
prompt_payload=messages,
customer_id="customer_123",
organization_id="org_456",
app_name="chatbot",
module_name="education",
function_name="explain_concepts",
model="gpt-4",
temperature=0.7,
max_tokens=500
)
print(f"Response: {response['output_text']}")
print(f"Tokens used: {response['total_tokens']}")
```
### 3. Embeddings
```python
embedding_response = wrapper.create_embeddings(
input_texts=["Machine learning is amazing", "AI will change the world"],
customer_id="customer_123",
organization_id="org_456",
app_name="search_engine",
module_name="vectorization",
function_name="create_embeddings",
model="text-embedding-3-small"
)
print(f"Embeddings: {embedding_response['embeddings']}")
```
## 🔧 Provider Configurations
### Azure OpenAI
```python
azure_config = {
'service_url': 'https://your-resource.openai.azure.com',
'api_key': 'your-api-key',
'deployment_name': 'gpt-4',
'api_version': '2023-12-01-preview',
'timeout': 600
}
wrapper = LLMWrapper(LLMProvider.AZURE_OPENAI, azure_config, db_config)
```
### OpenAI
```python
openai_config = {
'api_key': 'sk-your-openai-api-key',
'organization_id': 'org-your-org-id', # Optional
'timeout': 600
}
wrapper = LLMWrapper(LLMProvider.OPENAI, openai_config, db_config)
```
### Anthropic Claude
```python
anthropic_config = {
'api_key': 'sk-ant-your-anthropic-api-key',
'default_model': 'claude-opus-4-20250514',
'timeout': 300
}
wrapper = LLMWrapper(LLMProvider.ANTHROPIC, anthropic_config, db_config)
```
### Google Gemini
```python
google_config = {
'api_key': 'your-gemini-api-key',
'default_model': 'gemini-2.0-flash',
'timeout': 300
}
wrapper = LLMWrapper(LLMProvider.GOOGLE, google_config, db_config)
```
### Twitter GROK
```python
grok_config = {
'api_key': 'your-grok-api-key',
'default_model': 'grok-4',
'timeout': 300
}
wrapper = LLMWrapper(LLMProvider.GROK, grok_config, db_config)
```
### Alibaba QWEN
```python
qwen_config = {
'api_key': 'your-qwen-api-key',
'default_model': 'qwen-plus',
'timeout': 300
}
wrapper = LLMWrapper(LLMProvider.QWEN, qwen_config, db_config)
```
### DeepSeek
```python
deepseek_config = {
'api_key': 'your-deepseek-api-key',
'default_model': 'deepseek-chat',
'timeout': 300
}
wrapper = LLMWrapper(LLMProvider.DEEP_SEEK, deepseek_config, db_config)
```
## 📊 Usage Analytics
### Get Usage Statistics
```python
stats = wrapper.get_usage_stats(
customer_id="customer_123",
start_date="2024-01-01T00:00:00",
end_date="2024-12-31T23:59:59",
app_name="chatbot"
)
print(f"Total requests: {stats['summary']['total_requests']}")
print(f"Total tokens: {stats['summary']['total_tokens']}")
print(f"Success rate: {stats['summary']['success_rate']}")
```
### Filter by Different Dimensions
```python
# By application
app_stats = wrapper.get_usage_stats(app_name="chatbot")
# By model
model_stats = wrapper.get_usage_stats(filters={"model_name": "gpt-4"})
# By request type
embedding_stats = wrapper.get_usage_stats(request_type="embedding")
```
## 🎯 Advanced Features
### JSON Response Format
```python
response = wrapper.send_request(
prompt_payload=[
{"role": "user", "content": "List 3 benefits of exercise in JSON format"}
],
customer_id="customer_789",
organization_id="org_456",
app_name="health_app",
module_name="exercise",
function_name="get_benefits",
response_type="json" # Automatically ensures JSON output
)
# Access parsed JSON
json_data = response['processed_output']
```
### Context Manager Support
```python
with LLMWrapper(LLMProvider.AZURE_OPENAI, azure_config, db_config) as wrapper:
response = wrapper.send_request(
prompt_payload=messages,
customer_id="customer_123",
organization_id="org_456",
app_name="temp_app",
module_name="test",
function_name="context_test"
)
# Automatic cleanup on exit
```
### Multi-Provider Switching
```python
providers = {
LLMProvider.AZURE_OPENAI: azure_config,
LLMProvider.OPENAI: openai_config,
LLMProvider.ANTHROPIC: anthropic_config
}
for provider_type, config in providers.items():
wrapper = LLMWrapper(provider_type, config, db_config)
response = wrapper.send_request(
prompt_payload=[{"role": "user", "content": "Hello!"}],
customer_id="multi_test",
organization_id="org_test",
app_name="provider_comparison",
module_name="testing",
function_name="hello_test"
)
print(f"{provider_type.value}: {response['output_text']}")
wrapper.close()
```
## 🗄️ Database Schema
The library automatically creates the following PostgreSQL table:
```sql
CREATE TABLE token_usage_log (
id SERIAL PRIMARY KEY,
customer_id VARCHAR(255) NOT NULL,
organization_id VARCHAR(255) NOT NULL,
provider VARCHAR(100) NOT NULL,
model_name VARCHAR(255) NOT NULL,
app_name VARCHAR(255),
module_name VARCHAR(255),
function_name VARCHAR(255),
request_type VARCHAR(50) NOT NULL,
request_params JSONB,
response_params JSONB,
input_tokens INTEGER DEFAULT 0,
output_tokens INTEGER DEFAULT 0,
total_tokens INTEGER DEFAULT 0,
request_timestamp TIMESTAMP DEFAULT NOW(),
response_time_ms INTEGER DEFAULT 0,
status VARCHAR(50) DEFAULT 'success',
request_id VARCHAR(255),
cost FLOAT
);
```
### Indexes for Performance
- `idx_customer_date` on (customer_id, request_timestamp)
- `idx_org_model` on (organization_id, model_name)
- `idx_app_module` on (app_name, module_name)
## 🧪 Error Handling
```python
from llm_wrapper import APIError, DatabaseError, ConfigurationError
try:
response = wrapper.send_request(...)
except APIError as e:
print(f"API Error: {e}")
except DatabaseError as e:
print(f"Database Error: {e}")
except ConfigurationError as e:
print(f"Configuration Error: {e}")
```
## 🔒 Security Best Practices
1. **Environment Variables**: Store API keys in environment variables
```python
import os
config = {
'api_key': os.getenv('AZURE_OPENAI_API_KEY'),
'service_url': os.getenv('AZURE_OPENAI_SERVICE_URL'),
# ...
}
```
2. **Database Security**: Use connection pooling and proper credentials
```python
db_config = {
'host': os.getenv('DB_HOST'),
'user': os.getenv('DB_USER'),
'password': os.getenv('DB_PASSWORD'),
'pool_size': 10,
'max_overflow': 20
}
```
## 📈 Performance Optimization
### Connection Pooling
The library uses SQLAlchemy's connection pooling:
```python
db_config = {
'host': 'localhost',
'port': 5432,
'dbname': 'llm_usage',
'user': 'username',
'password': 'password',
'pool_size': 10, # Number of persistent connections
'max_overflow': 20, # Additional connections when needed
'pool_pre_ping': True # Validate connections before use
}
```
### Batch Processing
For multiple requests, use connection reuse:
```python
with LLMWrapper(provider_type, config, db_config) as wrapper:
for request_data in batch_requests:
response = wrapper.send_request(**request_data)
# Process response
```
## 📝 Logging
Configure logging for production:
```python
import logging
# Configure logging
logging.basicConfig(
level=logging.INFO,
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
handlers=[
logging.FileHandler('llm_wrapper.log'),
logging.StreamHandler()
]
)
```
## 🔄 Migration from Legacy Version
### Old API (v0.1.x)
```python
# Old way
wrapper = LLMWrapper(service_url, api_key, deployment_name, api_version, db_config)
response = wrapper.send_request(messages, customer_id, ...)
```
### New API (v0.2.x)
```python
# New way
wrapper = LLMWrapper(LLMProvider.AZURE_OPENAI, provider_config, db_config)
response = wrapper.send_request(messages, customer_id, ...)
```
The response format remains the same for backward compatibility.
## 🤝 Contributing
1. Fork the repository
2. Create a feature branch: `git checkout -b feature/new-provider`
3. Make your changes
4. Add tests for new functionality
5. Run tests: `pytest`
6. Submit a pull request
### Adding New Providers
1. Create a new provider class inheriting from `BaseLLMProvider`
2. Implement required methods: `send_chat_completion`, `create_embeddings`, `validate_config`
3. Add the provider to `LLMProviderFactory`
4. Add provider-specific configuration in constants
5. Write tests
## 📄 License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
## 🆘 Support
- **Email**: akilan@hibizsolutions.com
## 🏷️ Changelog
### v0.2.0 (Latest)
- ✅ Multi-provider support (Azure OpenAI, OpenAI, Anthropic)
- ✅ Modular architecture with factory pattern
- ✅ Enhanced token tracking and analytics
- ✅ Improved error handling and validation
- ✅ Type safety with full type hints
- ✅ Performance optimizations
- ✅ Backward compatibility
### v0.1.0
- ✅ Basic Azure OpenAI support
- ✅ Token tracking
- ✅ PostgreSQL logging
## 🎯 Roadmap
- [ ] Google PaLM/Gemini support
- [ ] Cost calculation and tracking
- [ ] Rate limiting and retry mechanisms
- [ ] Async support
- [ ] Streaming responses
- [ ] Fine-tuning integration
- [ ] Monitoring dashboard
---
**Made with ❤️ by [Hibiz Solutions](https://hibizsolutions.com)**
Raw data
{
"_id": null,
"home_page": null,
"name": "hibiz-any-llm",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": "Akilan R M <akilan@hibizsolutions.com>",
"keywords": "llm, language-model, openai, azure, gpt, ai, machine-learning, database, postgresql, mysql, mongodb, usage-tracking, api-wrapper",
"author": null,
"author_email": "Akilan R M <akilan@hibizsolutions.com>",
"download_url": "https://files.pythonhosted.org/packages/16/d3/c45714baacb390affd3690ccfdde4a210c7d0bfee14d29e6061eb7b5c49c/hibiz_any_llm-0.0.4.tar.gz",
"platform": null,
"description": "# LLM Wrapper - Universal Large Language Model Library\r\n\r\nA comprehensive, modular Python library for seamless integration with multiple Large Language Model providers. Built with enterprise-grade features including token tracking, usage analytics, and robust error handling.\r\n\r\n## \ud83d\ude80 Features\r\n\r\n- **Multi-Provider Support**: Azure OpenAI, OpenAI, Anthropic Claude, and extensible for more\r\n- **Unified API**: Single interface for all LLM providers\r\n- **Token Tracking**: Comprehensive token usage logging with PostgreSQL backend\r\n- **Usage Analytics**: Detailed statistics and monitoring capabilities\r\n- **Enterprise Ready**: Connection pooling, error handling, and production-grade logging\r\n- **Type Safety**: Full type hints and data validation\r\n- **Modular Architecture**: Clean separation of concerns with factory pattern\r\n- **Backward Compatible**: Legacy API support for existing integrations\r\n\r\n## \ud83d\udce6 Installation\r\n\r\n```bash\r\npip install hibiz-any-llm\r\n```\r\n\r\n## \ud83c\udfd7\ufe0f Architecture\r\n\r\n```\r\nllm_wrapper/\r\n\u251c\u2500\u2500 core/ # Core functionality and factory\r\n\u251c\u2500\u2500 providers/ # LLM provider implementations\r\n\u251c\u2500\u2500 models/ # Data models and schemas\r\n\u251c\u2500\u2500 database/ # Database management\r\n\u2514\u2500\u2500utils/ # Token Calculation and validators\r\n```\r\n\r\n## \ud83d\udee0\ufe0f Quick Start\r\n\r\n### 1. Basic Setup\r\n\r\n```python\r\nfrom hibiz_any_llm import LLMWrapper, LLMProvider\r\n\r\n# Configure your provider\r\nazure_config = {\r\n 'service_url': 'https://your-resource.openai.azure.com',\r\n 'api_key': 'your-api-key',\r\n 'deployment_name': 'gpt-4',\r\n 'api_version': '2023-12-01-preview'\r\n}\r\n\r\n# Database configuration\r\ndb_config = {\r\n 'host': 'localhost',\r\n 'port': 5432,\r\n 'dbname': 'llm_usage',\r\n 'user': 'username',\r\n 'password': 'password'\r\n}\r\n\r\n# Initialize wrapper\r\nwrapper = LLMWrapper(\r\n provider_type=LLMProvider.AZURE_OPENAI,\r\n provider_config=azure_config,\r\n db_config=db_config,\r\n enable_logging=True\r\n)\r\n```\r\n\r\n### 2. Chat Completion\r\n\r\n```python\r\nmessages = [\r\n {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\r\n {\"role\": \"user\", \"content\": \"What is machine learning?\"}\r\n]\r\n\r\nresponse = wrapper.send_request(\r\n prompt_payload=messages,\r\n customer_id=\"customer_123\",\r\n organization_id=\"org_456\",\r\n app_name=\"chatbot\",\r\n module_name=\"education\",\r\n function_name=\"explain_concepts\",\r\n model=\"gpt-4\",\r\n temperature=0.7,\r\n max_tokens=500\r\n)\r\n\r\nprint(f\"Response: {response['output_text']}\")\r\nprint(f\"Tokens used: {response['total_tokens']}\")\r\n```\r\n\r\n### 3. Embeddings\r\n\r\n```python\r\nembedding_response = wrapper.create_embeddings(\r\n input_texts=[\"Machine learning is amazing\", \"AI will change the world\"],\r\n customer_id=\"customer_123\",\r\n organization_id=\"org_456\",\r\n app_name=\"search_engine\",\r\n module_name=\"vectorization\",\r\n function_name=\"create_embeddings\",\r\n model=\"text-embedding-3-small\"\r\n)\r\n\r\nprint(f\"Embeddings: {embedding_response['embeddings']}\")\r\n```\r\n\r\n## \ud83d\udd27 Provider Configurations\r\n\r\n### Azure OpenAI\r\n\r\n```python\r\nazure_config = {\r\n 'service_url': 'https://your-resource.openai.azure.com',\r\n 'api_key': 'your-api-key',\r\n 'deployment_name': 'gpt-4',\r\n 'api_version': '2023-12-01-preview',\r\n 'timeout': 600\r\n}\r\n\r\nwrapper = LLMWrapper(LLMProvider.AZURE_OPENAI, azure_config, db_config)\r\n```\r\n\r\n### OpenAI\r\n\r\n```python\r\nopenai_config = {\r\n 'api_key': 'sk-your-openai-api-key',\r\n 'organization_id': 'org-your-org-id', # Optional\r\n 'timeout': 600\r\n}\r\n\r\nwrapper = LLMWrapper(LLMProvider.OPENAI, openai_config, db_config)\r\n```\r\n\r\n### Anthropic Claude\r\n\r\n```python\r\nanthropic_config = {\r\n 'api_key': 'sk-ant-your-anthropic-api-key',\r\n 'default_model': 'claude-opus-4-20250514',\r\n 'timeout': 300\r\n}\r\n\r\nwrapper = LLMWrapper(LLMProvider.ANTHROPIC, anthropic_config, db_config)\r\n```\r\n### Google Gemini\r\n\r\n```python\r\ngoogle_config = {\r\n 'api_key': 'your-gemini-api-key',\r\n 'default_model': 'gemini-2.0-flash',\r\n 'timeout': 300\r\n}\r\n\r\nwrapper = LLMWrapper(LLMProvider.GOOGLE, google_config, db_config)\r\n```\r\n### Twitter GROK\r\n\r\n```python\r\ngrok_config = {\r\n 'api_key': 'your-grok-api-key',\r\n 'default_model': 'grok-4',\r\n 'timeout': 300\r\n}\r\n\r\nwrapper = LLMWrapper(LLMProvider.GROK, grok_config, db_config)\r\n```\r\n### Alibaba QWEN\r\n\r\n```python\r\nqwen_config = {\r\n 'api_key': 'your-qwen-api-key',\r\n 'default_model': 'qwen-plus',\r\n 'timeout': 300\r\n}\r\n\r\nwrapper = LLMWrapper(LLMProvider.QWEN, qwen_config, db_config)\r\n```\r\n### DeepSeek\r\n\r\n```python\r\ndeepseek_config = {\r\n 'api_key': 'your-deepseek-api-key',\r\n 'default_model': 'deepseek-chat',\r\n 'timeout': 300\r\n}\r\n\r\nwrapper = LLMWrapper(LLMProvider.DEEP_SEEK, deepseek_config, db_config)\r\n```\r\n\r\n## \ud83d\udcca Usage Analytics\r\n\r\n### Get Usage Statistics\r\n\r\n```python\r\nstats = wrapper.get_usage_stats(\r\n customer_id=\"customer_123\",\r\n start_date=\"2024-01-01T00:00:00\",\r\n end_date=\"2024-12-31T23:59:59\",\r\n app_name=\"chatbot\"\r\n)\r\n\r\nprint(f\"Total requests: {stats['summary']['total_requests']}\")\r\nprint(f\"Total tokens: {stats['summary']['total_tokens']}\")\r\nprint(f\"Success rate: {stats['summary']['success_rate']}\")\r\n```\r\n\r\n### Filter by Different Dimensions\r\n\r\n```python\r\n# By application\r\napp_stats = wrapper.get_usage_stats(app_name=\"chatbot\")\r\n\r\n# By model\r\nmodel_stats = wrapper.get_usage_stats(filters={\"model_name\": \"gpt-4\"})\r\n\r\n# By request type\r\nembedding_stats = wrapper.get_usage_stats(request_type=\"embedding\")\r\n```\r\n\r\n## \ud83c\udfaf Advanced Features\r\n\r\n### JSON Response Format\r\n\r\n```python\r\nresponse = wrapper.send_request(\r\n prompt_payload=[\r\n {\"role\": \"user\", \"content\": \"List 3 benefits of exercise in JSON format\"}\r\n ],\r\n customer_id=\"customer_789\",\r\n organization_id=\"org_456\",\r\n app_name=\"health_app\",\r\n module_name=\"exercise\",\r\n function_name=\"get_benefits\",\r\n response_type=\"json\" # Automatically ensures JSON output\r\n)\r\n\r\n# Access parsed JSON\r\njson_data = response['processed_output']\r\n```\r\n\r\n### Context Manager Support\r\n\r\n```python\r\nwith LLMWrapper(LLMProvider.AZURE_OPENAI, azure_config, db_config) as wrapper:\r\n response = wrapper.send_request(\r\n prompt_payload=messages,\r\n customer_id=\"customer_123\",\r\n organization_id=\"org_456\",\r\n app_name=\"temp_app\",\r\n module_name=\"test\",\r\n function_name=\"context_test\"\r\n )\r\n # Automatic cleanup on exit\r\n```\r\n\r\n### Multi-Provider Switching\r\n\r\n```python\r\nproviders = {\r\n LLMProvider.AZURE_OPENAI: azure_config,\r\n LLMProvider.OPENAI: openai_config,\r\n LLMProvider.ANTHROPIC: anthropic_config\r\n}\r\n\r\nfor provider_type, config in providers.items():\r\n wrapper = LLMWrapper(provider_type, config, db_config)\r\n response = wrapper.send_request(\r\n prompt_payload=[{\"role\": \"user\", \"content\": \"Hello!\"}],\r\n customer_id=\"multi_test\",\r\n organization_id=\"org_test\",\r\n app_name=\"provider_comparison\",\r\n module_name=\"testing\",\r\n function_name=\"hello_test\"\r\n )\r\n print(f\"{provider_type.value}: {response['output_text']}\")\r\n wrapper.close()\r\n```\r\n\r\n## \ud83d\uddc4\ufe0f Database Schema\r\n\r\nThe library automatically creates the following PostgreSQL table:\r\n\r\n```sql\r\nCREATE TABLE token_usage_log (\r\n id SERIAL PRIMARY KEY,\r\n customer_id VARCHAR(255) NOT NULL,\r\n organization_id VARCHAR(255) NOT NULL,\r\n provider VARCHAR(100) NOT NULL,\r\n model_name VARCHAR(255) NOT NULL,\r\n app_name VARCHAR(255),\r\n module_name VARCHAR(255),\r\n function_name VARCHAR(255),\r\n request_type VARCHAR(50) NOT NULL,\r\n request_params JSONB,\r\n response_params JSONB,\r\n input_tokens INTEGER DEFAULT 0,\r\n output_tokens INTEGER DEFAULT 0,\r\n total_tokens INTEGER DEFAULT 0,\r\n request_timestamp TIMESTAMP DEFAULT NOW(),\r\n response_time_ms INTEGER DEFAULT 0,\r\n status VARCHAR(50) DEFAULT 'success',\r\n request_id VARCHAR(255),\r\n cost FLOAT\r\n);\r\n```\r\n\r\n### Indexes for Performance\r\n\r\n- `idx_customer_date` on (customer_id, request_timestamp)\r\n- `idx_org_model` on (organization_id, model_name)\r\n- `idx_app_module` on (app_name, module_name)\r\n\r\n## \ud83e\uddea Error Handling\r\n\r\n```python\r\nfrom llm_wrapper import APIError, DatabaseError, ConfigurationError\r\n\r\ntry:\r\n response = wrapper.send_request(...)\r\nexcept APIError as e:\r\n print(f\"API Error: {e}\")\r\nexcept DatabaseError as e:\r\n print(f\"Database Error: {e}\")\r\nexcept ConfigurationError as e:\r\n print(f\"Configuration Error: {e}\")\r\n```\r\n\r\n## \ud83d\udd12 Security Best Practices\r\n\r\n1. **Environment Variables**: Store API keys in environment variables\r\n```python\r\nimport os\r\n\r\nconfig = {\r\n 'api_key': os.getenv('AZURE_OPENAI_API_KEY'),\r\n 'service_url': os.getenv('AZURE_OPENAI_SERVICE_URL'),\r\n # ...\r\n}\r\n```\r\n\r\n2. **Database Security**: Use connection pooling and proper credentials\r\n```python\r\ndb_config = {\r\n 'host': os.getenv('DB_HOST'),\r\n 'user': os.getenv('DB_USER'),\r\n 'password': os.getenv('DB_PASSWORD'),\r\n 'pool_size': 10,\r\n 'max_overflow': 20\r\n}\r\n```\r\n\r\n## \ud83d\udcc8 Performance Optimization\r\n\r\n### Connection Pooling\r\n\r\nThe library uses SQLAlchemy's connection pooling:\r\n\r\n```python\r\ndb_config = {\r\n 'host': 'localhost',\r\n 'port': 5432,\r\n 'dbname': 'llm_usage',\r\n 'user': 'username',\r\n 'password': 'password',\r\n 'pool_size': 10, # Number of persistent connections\r\n 'max_overflow': 20, # Additional connections when needed\r\n 'pool_pre_ping': True # Validate connections before use\r\n}\r\n```\r\n\r\n### Batch Processing\r\n\r\nFor multiple requests, use connection reuse:\r\n\r\n```python\r\nwith LLMWrapper(provider_type, config, db_config) as wrapper:\r\n for request_data in batch_requests:\r\n response = wrapper.send_request(**request_data)\r\n # Process response\r\n```\r\n\r\n## \ud83d\udcdd Logging\r\n\r\nConfigure logging for production:\r\n\r\n```python\r\nimport logging\r\n\r\n# Configure logging\r\nlogging.basicConfig(\r\n level=logging.INFO,\r\n format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',\r\n handlers=[\r\n logging.FileHandler('llm_wrapper.log'),\r\n logging.StreamHandler()\r\n ]\r\n)\r\n```\r\n\r\n## \ud83d\udd04 Migration from Legacy Version\r\n\r\n### Old API (v0.1.x)\r\n\r\n```python\r\n# Old way\r\nwrapper = LLMWrapper(service_url, api_key, deployment_name, api_version, db_config)\r\nresponse = wrapper.send_request(messages, customer_id, ...)\r\n```\r\n\r\n### New API (v0.2.x)\r\n\r\n```python\r\n# New way\r\nwrapper = LLMWrapper(LLMProvider.AZURE_OPENAI, provider_config, db_config)\r\nresponse = wrapper.send_request(messages, customer_id, ...)\r\n```\r\n\r\nThe response format remains the same for backward compatibility.\r\n\r\n## \ud83e\udd1d Contributing\r\n\r\n1. Fork the repository\r\n2. Create a feature branch: `git checkout -b feature/new-provider`\r\n3. Make your changes\r\n4. Add tests for new functionality\r\n5. Run tests: `pytest`\r\n6. Submit a pull request\r\n\r\n### Adding New Providers\r\n\r\n1. Create a new provider class inheriting from `BaseLLMProvider`\r\n2. Implement required methods: `send_chat_completion`, `create_embeddings`, `validate_config`\r\n3. Add the provider to `LLMProviderFactory`\r\n4. Add provider-specific configuration in constants\r\n5. Write tests\r\n\r\n\r\n## \ud83d\udcc4 License\r\n\r\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\r\n\r\n## \ud83c\udd98 Support\r\n\r\n- **Email**: akilan@hibizsolutions.com\r\n\r\n## \ud83c\udff7\ufe0f Changelog\r\n\r\n### v0.2.0 (Latest)\r\n- \u2705 Multi-provider support (Azure OpenAI, OpenAI, Anthropic)\r\n- \u2705 Modular architecture with factory pattern\r\n- \u2705 Enhanced token tracking and analytics\r\n- \u2705 Improved error handling and validation\r\n- \u2705 Type safety with full type hints\r\n- \u2705 Performance optimizations\r\n- \u2705 Backward compatibility\r\n\r\n### v0.1.0\r\n- \u2705 Basic Azure OpenAI support\r\n- \u2705 Token tracking\r\n- \u2705 PostgreSQL logging\r\n\r\n## \ud83c\udfaf Roadmap\r\n\r\n- [ ] Google PaLM/Gemini support\r\n- [ ] Cost calculation and tracking\r\n- [ ] Rate limiting and retry mechanisms\r\n- [ ] Async support\r\n- [ ] Streaming responses\r\n- [ ] Fine-tuning integration\r\n- [ ] Monitoring dashboard\r\n\r\n---\r\n\r\n**Made with \u2764\ufe0f by [Hibiz Solutions](https://hibizsolutions.com)**\r\n",
"bugtrack_url": null,
"license": null,
"summary": "A comprehensive Python wrapper for Large Language Models with database integration and usage tracking",
"version": "0.0.4",
"project_urls": null,
"split_keywords": [
"llm",
" language-model",
" openai",
" azure",
" gpt",
" ai",
" machine-learning",
" database",
" postgresql",
" mysql",
" mongodb",
" usage-tracking",
" api-wrapper"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "729897fd601f0aa01567534b495b0854dd7d967535d4e27d3dba19e273b53a7c",
"md5": "b57ccd92a2139e28498a4b3340653f59",
"sha256": "3590a580092309cb883e2b897406a030d215d68abd3a7ddf2267eb3bd6dcfa48"
},
"downloads": -1,
"filename": "hibiz_any_llm-0.0.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "b57ccd92a2139e28498a4b3340653f59",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 36635,
"upload_time": "2025-08-01T13:43:37",
"upload_time_iso_8601": "2025-08-01T13:43:37.795926Z",
"url": "https://files.pythonhosted.org/packages/72/98/97fd601f0aa01567534b495b0854dd7d967535d4e27d3dba19e273b53a7c/hibiz_any_llm-0.0.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "16d3c45714baacb390affd3690ccfdde4a210c7d0bfee14d29e6061eb7b5c49c",
"md5": "07acda36c769b79f701ad5e6caf81288",
"sha256": "688bcb2d4a897c875730f00b6662eceac5026ee5fe17a272e92b359336feaacf"
},
"downloads": -1,
"filename": "hibiz_any_llm-0.0.4.tar.gz",
"has_sig": false,
"md5_digest": "07acda36c769b79f701ad5e6caf81288",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 30927,
"upload_time": "2025-08-01T13:43:38",
"upload_time_iso_8601": "2025-08-01T13:43:38.872948Z",
"url": "https://files.pythonhosted.org/packages/16/d3/c45714baacb390affd3690ccfdde4a210c7d0bfee14d29e6061eb7b5c49c/hibiz_any_llm-0.0.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-01 13:43:38",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "hibiz-any-llm"
}
JSON