nomyo-ai/nomyo
2
1
Fork 0
Code Issues Pull requests Projects Releases 8 Packages Wiki Activity Actions

feat: update project version and documentation link

Browse source 
- Bump version from 0.1.0 to 0.1.1
- Update documentation URL to point to GitHub repository
This commit is contained in:
Alpha Nerd 2026-02-03 18:40:51 +01:00
parent 77084737dd
commit 2c6677748a
8 changed files with 1104 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
.gitignore vendored
View file

@ -28,6 +28,7 @@ venv/
ENV/
env.bak/
venv.bak/
.claude/
# IDE
.idea/
@ -49,6 +50,7 @@ build/
dist/
*.egg-info/
*.egg
*.sh
# Virtual environments
venv/

57
doc/README.md Normal file
View file

@ -0,0 +1,57 @@
# NOMYO Secure Client Documentation
This documentation provides comprehensive information about using the NOMYO Secure Python Chat Client, a drop-in replacement for OpenAI's ChatCompletion API with end-to-end (E2E) encryption.
To use this client library you need a paid subscribtion on [NOMYO Inference](https://chat.nomyo.ai/).
## Overview
The NOMYO Secure Client provides:
- **End-to-end encryption** using hybrid encryption (AES-256-GCM + RSA-OAEP)
- **OpenAI API compatibility** - same interface as OpenAI's ChatCompletion
- **Secure memory protection** - prevents plaintext from being swapped to disk
- **Automatic key management** - handles key generation and loading automatically
- **HTTPS enforcement** - secure communication by default
## Quick Start
```python
import asyncio
from nomyo import SecureChatCompletion
async def main():
# Initialize client (defaults to https://api.nomyo.ai)
client = SecureChatCompletion(api_key="your-api-key-here")
# Simple chat completion
response = await client.create(
model="Qwen/Qwen3-0.6B",
messages=[
{"role": "user", "content": "Hello! How are you today?"}
],
security_tier="standard", # optional: standard, high or maximum
temperature=0.7
)
print(response['choices'][0]['message']['content'])
# Run the async function
asyncio.run(main())
```
## Documentation Structure
1. [Installation](installation.md) - How to install and set up the client
2. [Getting Started](getting-started.md) - Quick start guide with examples
3. [API Reference](api-reference.md) - Complete API documentation
4. [Security Guide](security-guide.md) - Security features and best practices
5. [Examples](examples.md) - Advanced usage scenarios
6. [Troubleshooting](troubleshooting.md) - Common issues and solutions
## Key Features
- **OpenAI Compatibility**: Use the same API as OpenAI's ChatCompletion
- **End-to-End Encryption**: All prompts and responses are automatically encrypted/decrypted
- **Secure Memory Protection**: Prevents sensitive data from being swapped to disk
- **Automatic Key Management**: Keys are generated and loaded automatically
- **Flexible Security Tiers**: Control security levels for different data types

197
doc/api-reference.md Normal file
View file

@ -0,0 +1,197 @@
# API Reference
## SecureChatCompletion Class
The `SecureChatCompletion` class is the main entry point for using the NOMYO secure client. It provides the same interface as OpenAI's ChatCompletion API with end-to-end encryption.
### Constructor
```python
SecureChatCompletion(
base_url: str = "https://api.nomyo.ai",
allow_http: bool = False,
api_key: Optional[str] = None,
secure_memory: bool = True
)
```
**Parameters:**
- `base_url` (str): Base URL of the NOMYO Router (must use HTTPS for production)
- `allow_http` (bool): Allow HTTP connections (ONLY for local development, never in production)
- `api_key` (Optional[str]): Optional API key for bearer authentication
- `secure_memory` (bool): Enable secure memory protection (default: True)
### Methods
#### create(model, messages, **kwargs)
Creates a new chat completion for the provided messages and parameters.
**Parameters:**
- `model` (str): The model to use for the chat completion
- `messages` (List[Dict]): A list of message objects. Each message has a role ("system", "user", or "assistant") and content
- `**kwargs`: Additional parameters that can be passed to the API
**Supported OpenAI Parameters:**
- `temperature` (float): Sampling temperature (0-2)
- `max_tokens` (int): Maximum tokens to generate
- `top_p` (float): Nucleus sampling
- `frequency_penalty` (float): Frequency penalty
- `presence_penalty` (float): Presence penalty
- `stop` (Union[str, List[str]]): Stop sequences
- `n` (int): Number of completions
- `stream` (bool): Streaming always = False to minimize de-/encryption overhead
- `tools` (List): Tool definitions
- `tool_choice` (str): Tool selection strategy
- `user` (str): User identifier
- `security_tier` (str): Security level ("standard", "high", or "maximum")
**Returns:**
A dictionary containing the chat completion response with the following structure:
```python
{
"id": str,
"object": "chat.completion",
"created": int,
"model": str,
"choices": [
{
"index": int,
"message": {
"role": str,
"content": str,
"tool_calls": List[Dict] # if tools were used
},
"finish_reason": str
}
],
"usage": {
"prompt_tokens": int,
"completion_tokens": int,
"total_tokens": int
}
}
```
#### acreate(model, messages, **kwargs)
Async alias for create() method.
**Parameters:** Same as create() method
**Returns:** Same as create() method
## SecureCompletionClient Class
The `SecureCompletionClient` class handles the underlying encryption, key management, and API communication.
### Constructor
```python
SecureCompletionClient(router_url: str = "https://api.nomyo.ai:12434", allow_http: bool = False)
```
**Parameters:**
- `router_url` (str): Base URL of the NOMYO Router (must use HTTPS for production)
- `allow_http` (bool): Allow HTTP connections (ONLY for local development, never in production)
### Methods
#### generate_keys(save_to_file: bool = False, key_dir: str = "client_keys", password: Optional[str] = None)
Generate RSA key pair for secure communication.
**Parameters:**
- `save_to_file` (bool): Whether to save keys to files
- `key_dir` (str): Directory to save keys (if save_to_file is True)
- `password` (Optional[str]): Optional password to encrypt private key
#### load_keys(private_key_path: str, public_key_path: Optional[str] = None, password: Optional[str] = None)
Load RSA keys from files.
**Parameters:**
- `private_key_path` (str): Path to private key file
- `public_key_path` (Optional[str]): Path to public key file (optional, derived from private key if not provided)
- `password` (Optional[str]): Optional password for encrypted private key
#### fetch_server_public_key()
Fetch the server's public key from the /pki/public_key endpoint.
**Returns:**
Server's public key as PEM string
#### encrypt_payload(payload: Dict[str, Any])
Encrypt a payload using hybrid encryption (AES-256-GCM + RSA-OAEP).
**Parameters:**
- `payload` (Dict[str, Any]): Dictionary containing the chat completion request
**Returns:**
Encrypted payload as bytes
#### decrypt_response(encrypted_response: bytes, payload_id: str)
Decrypt a response from the secure endpoint.
**Parameters:**
- `encrypted_response` (bytes): Encrypted response bytes
- `payload_id` (str): Payload ID for metadata verification
**Returns:**
Decrypted response dictionary
#### send_secure_request(payload: Dict[str, Any], payload_id: str, api_key: Optional[str] = None, security_tier: Optional[str] = None)
Send a secure chat completion request to the router.
**Parameters:**
- `payload` (Dict[str, Any]): Chat completion request payload
- `payload_id` (str): Unique identifier for this request
- `api_key` (Optional[str]): Optional API key for bearer authentication
- `security_tier` (Optional[str]): Optional security tier for routing
**Returns:**
Decrypted response from the LLM
## Exception Classes
### APIError
Base class for all API-related errors.
### AuthenticationError
Raised when authentication fails (e.g., invalid API key).
### InvalidRequestError
Raised when the request is invalid (HTTP 400).
### APIConnectionError
Raised when there's a connection error.
### RateLimitError
Raised when rate limit is exceeded (HTTP 429).
### ServerError
Raised when the server returns an error (HTTP 500).
### SecurityError
Raised when a security violation is detected.

362
doc/examples.md Normal file
View file

@ -0,0 +1,362 @@
# Examples
## Basic Usage Examples
### Simple Chat Completion
```python
import asyncio
from nomyo import SecureChatCompletion
async def simple_chat():
client = SecureChatCompletion(api_key="your-api-key-here")
response = await client.create(
model="Qwen/Qwen3-0.6B",
messages=[
{"role": "user", "content": "Hello, how are you?"}
],
temperature=0.7
)
print(response['choices'][0]['message']['content'])
asyncio.run(simple_chat())
```
### Chat with System Message
```python
import asyncio
from nomyo import SecureChatCompletion
async def chat_with_system():
client = SecureChatCompletion(api_key="your-api-key-here")
response = await client.create(
model="Qwen/Qwen3-0.6B",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "What is the capital of France?"}
],
temperature=0.7
)
print(response['choices'][0]['message']['content'])
asyncio.run(chat_with_system())
```
## Advanced Usage Examples
### Using Different Security Tiers
```python
import asyncio
from nomyo import SecureChatCompletion
async def security_tiers():
client = SecureChatCompletion(api_key="your-api-key-here")
# Standard security
response1 = await client.create(
model="Qwen/Qwen3-0.6B",
messages=[{"role": "user", "content": "General query"}],
security_tier="standard"
)
# High security for sensitive data
response2 = await client.create(
model="Qwen/Qwen3-0.6B",
messages=[{"role": "user", "content": "Bank account info"}],
security_tier="high"
)
# Maximum security for classified data
response3 = await client.create(
model="Qwen/Qwen3-0.6B",
messages=[{"role": "user", "content": "Medical records"}],
security_tier="maximum"
)
asyncio.run(security_tiers())
```
### Using Tools
```python
import asyncio
from nomyo import SecureChatCompletion
async def chat_with_tools():
client = SecureChatCompletion(api_key="your-api-key-here")
response = await client.create(
model="Qwen/Qwen3-0.6B",
messages=[
{"role": "user", "content": "What's the weather in Paris?"}
],
tools=[
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get weather information",
"parameters": {
"type": "object",
"properties": {
"location": {"type": "string"}
},
"required": ["location"]
}
}
}
],
temperature=0.7
)
print(response['choices'][0]['message']['content'])
asyncio.run(chat_with_tools())
```
### Error Handling
```python
import asyncio
from nomyo import SecureChatCompletion, AuthenticationError, InvalidRequestError
async def error_handling():
client = SecureChatCompletion(api_key="your-api-key-here")
try:
response = await client.create(
model="Qwen/Qwen3-0.6B",
messages=[{"role": "user", "content": "Hello"}]
)
print(response['choices'][0]['message']['content'])
except AuthenticationError as e:
print(f"Authentication failed: {e}")
except InvalidRequestError as e:
print(f"Invalid request: {e}")
except Exception as e:
print(f"Other error: {e}")
asyncio.run(error_handling())
```
### Custom Base URL
```python
import asyncio
from nomyo import SecureChatCompletion
async def custom_base_url():
# For local development
client = SecureChatCompletion(
base_url="https://NOMYO-PRO-ROUTER:12435",
allow_http=True
)
response = await client.create(
model="Qwen/Qwen3-0.6B",
messages=[{"role": "user", "content": "Hello"}]
)
print(response['choices'][0]['message']['content'])
asyncio.run(custom_base_url())
```
### API Key Authentication
```python
import asyncio
from nomyo import SecureChatCompletion
async def api_key_auth():
# Initialize with API key
client = SecureChatCompletion(
api_key="your-api-key-here"
)
response = await client.create(
model="Qwen/Qwen3-0.6B",
messages=[{"role": "user", "content": "Hello"}]
)
print(response['choices'][0]['message']['content'])
asyncio.run(api_key_auth())
```
## Real-World Scenarios
### Chat Application with History
```python
import asyncio
from nomyo import SecureChatCompletion
class SecureChatApp:
def __init__(self):
self.client = SecureChatCompletion(api_key="your-api-key-here")
self.conversation_history = []
async def chat(self, message):
# Add user message to history
self.conversation_history.append({"role": "user", "content": message})
# Get response from the model
response = await self.client.create(
model="Qwen/Qwen3-0.6B",
messages=self.conversation_history,
temperature=0.7
)
# Add assistant response to history
assistant_message = response['choices'][0]['message']
self.conversation_history.append(assistant_message)
return assistant_message['content']
async def main():
app = SecureChatApp()
# First message
response1 = await app.chat("Hello, what's your name?")
print(f"Assistant: {response1}")
# Second message
response2 = await app.chat("Can you tell me about secure chat clients?")
print(f"Assistant: {response2}")
asyncio.run(main())
```
### Data Processing with Tools
```python
import asyncio
from nomyo import SecureChatCompletion
async def data_processing():
client = SecureChatCompletion(api_key="your-api-key-here")
# Process data with tool calling
response = await client.create(
model="Qwen/Qwen3-0.6B",
messages=[
{"role": "user", "content": "Process this data: 100, 200, 300, 400"}
],
tools=[
{
"type": "function",
"function": {
"name": "calculate_statistics",
"description": "Calculate statistical measures",
"parameters": {
"type": "object",
"properties": {
"data": {"type": "array", "items": {"type": "number"}}
},
"required": ["data"]
}
}
}
]
)
print(response['choices'][0]['message']['content'])
asyncio.run(data_processing())
```
### Batch Processing
```python
import asyncio
from nomyo import SecureChatCompletion
async def batch_processing():
client = SecureChatCompletion(api_key="your-api-key-here")
# Process multiple queries concurrently
tasks = []
queries = [
"What is the weather today?",
"Tell me about Python programming",
"How to learn machine learning?"
]
for query in queries:
task = client.create(
model="Qwen/Qwen3-0.6B",
messages=[{"role": "user", "content": query}],
temperature=0.7
)
tasks.append(task)
# Execute all queries in parallel
responses = await asyncio.gather(*tasks)
for i, response in enumerate(responses):
print(f"Query {i+1}: {response['choices'][0]['message']['content'][:100]}...")
asyncio.run(batch_processing())
```
## Configuration Examples
### Custom Client Configuration
```python
import asyncio
from nomyo import SecureChatCompletion
async def custom_config():
# Create a client with custom configuration
client = SecureChatCompletion(
allow_http=False, # Force HTTPS
api_key="your-api-key",
secure_memory=True # Explicitly enable secure memory protection (default)
)
response = await client.create(
model="Qwen/Qwen3-0.6B",
messages=[{"role": "user", "content": "Hello"}],
temperature=0.7
)
print(response['choices'][0]['message']['content'])
asyncio.run(custom_config())
```
### Environment-Based Configuration (strongly recommended)
```python
import asyncio
import os
from nomyo import SecureChatCompletion
async def env_config():
# Load configuration from environment variables
api_key = os.getenv('NOMYO_API_KEY')
client = SecureChatCompletion(
api_key=api_key
)
response = await client.create(
model="Qwen/Qwen3-0.6B",
messages=[{"role": "user", "content": "Hello"}]
)
print(response['choices'][0]['message']['content'])
asyncio.run(env_config())
```
##

212
doc/getting-started.md Normal file
View file

@ -0,0 +1,212 @@
# Getting Started
## Basic Usage
The NOMYO client provides end-to-end encryption (E2E) for all communications between your application and the NOMYO inference endpoints. This ensures that your prompts and responses are protected from unauthorized access or interception.
The NOMYO client provides the same interface as OpenAI's ChatCompletion API, making it easy to integrate into existing code.
The encryption and decryption process is causing overhead, thus inference speed will be lower compared to unencrypted inference. Using high and maximum security_tiers in the client request will add additional latency to the round-trip-time, but guarantees highest confidential use cases.
To minimize en-/decryption overhead the API is **none**-streaming. OpenAI API compatibily allows to set streaming=True in the request, but this will be ignored on the server side to allow maximum response token generation.
### Simple Chat Completion
```python
import asyncio
from nomyo import SecureChatCompletion
async def main():
# Initialize client
client = SecureChatCompletion(api_key="your-api-key-here")
# Simple chat completion
response = await client.create(
model="Qwen/Qwen3-0.6B",
messages=[
{"role": "user", "content": "Hello! How are you today?"}
],
temperature=0.7
)
print(response['choices'][0]['message']['content'])
asyncio.run(main())
```
### With System Messages
```python
import asyncio
from nomyo import SecureChatCompletion
async def main():
client = SecureChatCompletion(api_key="your-api-key-here")
response = await client.create(
model="Qwen/Qwen3-0.6B",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "What is the capital of France?"}
],
temperature=0.7
)
print(response['choices'][0]['message']['content'])
asyncio.run(main())
```
## API Key Authentication
```python
import asyncio
from nomyo import SecureChatCompletion
async def main():
# Initialize with API key (recommended for production)
client = SecureChatCompletion(
api_key="your-api-key-here"
)
# Or pass API key in the create() method
response = await client.create(
model="Qwen/Qwen3-0.6B",
messages=[
{"role": "user", "content": "Hello!"}
],
api_key="your-api-key-here" # Overrides instance API key
)
asyncio.run(main())
```
## Security Tiers
The client supports different security tiers for controlling data protection levels:
```python
import asyncio
from nomyo import SecureChatCompletion
async def main():
client = SecureChatCompletion(api_key="your-api-key-here")
# Standard security tier (default)
response = await client.create(
model="Qwen/Qwen3-0.6B",
messages=[
{"role": "user", "content": "Hello!"}
],
security_tier="standard"
)
# High security tier for sensitive data
response = await client.create(
model="Qwen/Qwen3-0.6B",
messages=[
{"role": "user", "content": "What's my bank account balance?"}
],
security_tier="high" #enforces secure tokenizer
)
# Maximum security tier for classified data
response = await client.create(
model="Qwen/Qwen3-0.6B",
messages=[
{"role": "user", "content": "Share my personal medical records"}
],
security_tier="maximum" #HIPAA PHI compliance or other confidential use cases
)
asyncio.run(main())
```
## Using Tools
```python
import asyncio
from nomyo import SecureChatCompletion
async def main():
client = SecureChatCompletion(api_key="your-api-key-here")
response = await client.create(
model="Qwen/Qwen3-0.6B",
messages=[
{"role": "user", "content": "What's the weather in Paris?"}
],
tools=[
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get weather information",
"parameters": {
"type": "object",
"properties": {
"location": {"type": "string"}
},
"required": ["location"]
}
}
}
],
temperature=0.7
)
print(response['choices'][0]['message']['content'])
asyncio.run(main())
```
## Async Alias
The client also provides an `acreate` async alias for convenience:
```python
import asyncio
from nomyo import SecureChatCompletion
async def main():
client = SecureChatCompletion(api_key="your-api-key-here")
response = await client.acreate(
model="Qwen/Qwen3-0.6B",
messages=[
{"role": "user", "content": "Hello!"}
],
temperature=0.7
)
print(response['choices'][0]['message']['content'])
asyncio.run(main())
```
## Error Handling
```python
import asyncio
from nomyo import SecureChatCompletion, AuthenticationError, InvalidRequestError
async def main():
client = SecureChatCompletion(base_url="https://api.nomyo.ai:12434")
try:
response = await client.create(
model="Qwen/Qwen3-0.6B",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response['choices'][0]['message']['content'])
except AuthenticationError as e:
print(f"Authentication failed: {e}")
except InvalidRequestError as e:
print(f"Invalid request: {e}")
except Exception as e:
print(f"Other error: {e}")
asyncio.run(main())
```

74
doc/installation.md Normal file
View file

@ -0,0 +1,74 @@
# Installation Guide
## Prerequisites
- Python 3.7 or higher
- pip (Python package installer)
## Installation
### Install from PyPI (recommended)
```bash
pip install nomyo
```
### Install from source
```bash
# Clone the repository
git clone https://github.com/nomyo-ai/nomyo.git
cd nomyo
# Install dependencies
pip install -r requirements.txt
# Install the package
pip install -e .
```
## Dependencies
The NOMYO client requires the following dependencies:
- `cryptography` - Cryptographic primitives (RSA, AES, etc.)
- `httpx` - Async HTTP client
- `anyio` - Async compatibility layer
These are automatically installed when you install the package via pip.
## Virtual Environment (Recommended)
It's recommended to use a virtual environment to avoid conflicts with other Python packages:
```bash
# Create virtual environment
python -m venv nomyo_env
# Activate virtual environment
source nomyo_env/bin/activate # On Linux/Mac
# or
nomyo_env\Scripts\activate # On Windows
# Install nomyo
pip install nomyo
```
## Verify Installation
To verify the installation worked correctly:
```python
import nomyo
print("NOMYO client installed successfully!")
```
## Development Installation
For development purposes, you can install the package in development mode:
```bash
pip install -e .[dev]
```
This will install additional development dependencies.

198
doc/security-guide.md Normal file
View file

@ -0,0 +1,198 @@
# Security Guide
## Overview
The NOMYO client provides end-to-end encryption for all communications between your application and the NOMYO inference endpoints. This ensures that your prompts and responses are protected from unauthorized access or interception.
## Encryption Mechanism
### Hybrid Encryption
The client uses a hybrid encryption approach combining:
1. **AES-256-GCM** for payload encryption (authenticated encryption)
2. **RSA-OAEP** for key exchange (4096-bit keys)
This provides both performance (AES for data) and security (RSA for key exchange).
### Key Management
#### Automatic Key Generation
Keys are automatically generated in memory on first use/session init. The client handles all key management internally.
#### Key Persistence (optional)
Keys *can* be saved to the `client_keys/` directory for reuse (i.e. in dev scenarios) across sessions [not recommend]:
```python
# Generate keys and save to file
await client.generate_keys(save_to_file=True, password="your-password")
```
#### Password Protection
Saved private keys should be password-protected in all environments:
```python
await client.generate_keys(save_to_file=True, password="your-strong-password")
```
## Secure Memory Protection
### Ephemeral AES Keys
- **Per-request encryption keys**: A unique AES-256 key is generated for each request
- **Automatic rotation**: AES keys are never reused - a fresh key is created for every encryption operation
- **Forward secrecy**: Compromise of one AES key only affects that single request
- **Secure generation**: AES keys are generated using cryptographically secure random number generation (`secrets.token_bytes`)
- **Automatic cleanup**: AES keys are zeroed from memory immediately after use
### Memory Protection
The client can use secure memory protection to:
- Prevent plaintext payloads from being swapped to disk
- Guarantee memory is zeroed after encryption
- Prevent sensitive data from being stored in memory dumps
## Security Best Practices
### For Production Use
1. **Always use password protection** for private keys
2. **Keep private keys secure** (permissions set to 600 - owner-only access)
3. **Never share your private key**
4. **Verify server's public key fingerprint** before first use
5. **Use HTTPS connections** (never allow HTTP in production)
### Key Management
```python
# Generate keys with password protection
await client.generate_keys(
save_to_file=True,
key_dir="client_keys",
password="strong-password-here"
)
# Load existing keys with password
await client.load_keys(
"client_keys/private_key.pem",
"client_keys/public_key.pem",
password="strong-password-here"
)
```
### Security Tiers
The client supports three security tiers:
- **Standard**: General secure inference
- **High**: Sensitive business data
- **Maximum**: Maximum isolation (HIPAA PHI, classified data)
```python
# Use different security tiers
response = await client.create(
model="Qwen/Qwen3-0.6B",
messages=[{"role": "user", "content": "My sensitive data"}],
security_tier="high"
)
```
## Security Features
### End-to-End Encryption
All prompts and responses are automatically encrypted and decrypted, ensuring:
- No plaintext data is sent over the network
- No plaintext data is stored in memory
- No plaintext data is stored on disk
### Forward Secrecy
Each request uses a unique AES key, ensuring that:
- Compromise of one request's key only affects that request
- Previous requests remain secure even if current key is compromised
### Key Exchange Security
RSA-OAEP key exchange with 4096-bit keys provides:
- Strong encryption for key exchange
- Protection against known attacks
- Forward secrecy for key material
### Memory Protection
Secure memory features:
- Prevents plaintext from being swapped to disk
- Guarantees zeroing of sensitive memory
- Prevents memory dumps from containing sensitive data
## Compliance Considerations
### HIPAA Compliance
The client can be used for HIPAA-compliant applications when:
- Keys are password-protected
- HTTPS is used for all connections
- Private keys are stored securely
- Appropriate security measures are in place
### Data Classification
- **Standard**: General data
- **High**: Sensitive business data
- **Maximum**: Classified data (PHI, PII, etc.)
## Security Testing
The client includes comprehensive security testing:
- All encryption/decryption operations are tested
- Key management is verified
- Memory protection is validated
- Error handling is tested
Run the test suite to verify security:
```bash
python3 test.py
```
## Troubleshooting Security Issues
### Common Issues
1. **Key loading failures**: Ensure private key file permissions are correct (600)
2. **Connection errors**: Verify HTTPS is used for production
3. **Decryption failures**: Check that the correct API key is used
4. **Memory protection errors**: SecureMemory module may not be available on all systems
### Debugging
The client adds metadata to responses that can help with debugging:
```python
response = await client.create(
model="Qwen/Qwen3-0.6B",
messages=[{"role": "user", "content": "Hello"}]
)
print(response["_metadata"]) # Contains security-related information
```
### Logging
Enable logging to see security operations:
```python
import logging
logging.basicConfig(level=logging.DEBUG)
```

4
pyproject.toml
View file

@ -4,7 +4,7 @@ build-backend = "hatchling.build"
[project]
name = "nomyo"
version = "0.1.0"
version = "0.1.1"
description = "OpenAI-compatible secure chat client with end-to-end encryption for NOMYO Inference Endpoints"
authors = [
{name = "NOMYO.AI", email = "ichi@nomyo.ai"},
@ -44,7 +44,7 @@ dependencies = [
[project.urls]
Homepage = "https://nomyo.ai"
Documentation = "https://nomyo.ai/nomyo-docs"
Documentation = "https://github.com/nomyo-ai/nomyo/doc"
Repository = "https://github.com/nomyo-ai/nomyo"
Issues = "https://github.com/nomyo-ai/nomyo/issues"