The official Python library for the Hanzo API
Project description
Hanzo Python SDK
The official Python SDK for the Hanzo AI platform, providing unified access to 100+ LLM providers through a single OpenAI-compatible API interface.
๐ Features
- Unified API: Single interface for 100+ LLM providers (OpenAI, Anthropic, Google, Meta, etc.)
- OpenAI Compatible: Drop-in replacement for OpenAI SDK
- Enterprise Features: Cost tracking, rate limiting, observability
- Local AI Support: Run models locally with node infrastructure
- Model Context Protocol (MCP): Advanced tool use and context management
- Agent Framework: Build and orchestrate AI agents
- Memory Management: Persistent memory and RAG capabilities
- Network Orchestration: Distributed AI compute capabilities
๐ฆ Installation
Basic Installation
pip install hanzoai
Full Installation (All Features)
pip install "hanzoai[all]"
Development Installation
git clone https://github.com/hanzoai/python-sdk.git
cd python-sdk
make setup
๐ฏ Quick Start
Basic Usage
from hanzoai import Hanzo
# Initialize client
client = Hanzo(api_key="your-api-key")
# Chat completion
response = client.chat.completions.create(
model="gpt-4",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)
Using Different Providers
# Use Claude
response = client.chat.completions.create(
model="claude-3-opus-20240229",
messages=[{"role": "user", "content": "Hello!"}]
)
# Use local models
response = client.chat.completions.create(
model="llama2:7b",
messages=[{"role": "user", "content": "Hello!"}]
)
๐๏ธ Architecture
Package Structure
python-sdk/
โโโ pkg/
โ โโโ hanzo/ # CLI and orchestration tools
โ โโโ hanzo-mcp/ # Model Context Protocol implementation
โ โโโ hanzo-agents/ # Agent framework
โ โโโ hanzo-network/ # Distributed network capabilities
โ โโโ hanzo-memory/ # Memory and RAG
โ โโโ hanzo-aci/ # AI code intelligence
โ โโโ hanzo-repl/ # Interactive REPL
โ โโโ hanzoai/ # Core SDK
Core Components
1. Hanzo CLI (hanzo)
Command-line interface for AI operations:
# Chat with AI
hanzo chat
# Start local node
hanzo node start
# Manage router
hanzo router start
# Interactive REPL
hanzo repl
2. Model Context Protocol (hanzo-mcp)
Advanced tool use and context management:
from hanzo_mcp import create_mcp_server
server = create_mcp_server()
server.register_tool(my_tool)
server.start()
3. Agent Framework (hanzo-agents)
Build and orchestrate AI agents:
from hanzo_agents import Agent, Swarm
agent = Agent(
name="researcher",
model="gpt-4",
instructions="You are a research assistant"
)
swarm = Swarm([agent])
result = await swarm.run("Research quantum computing")
4. Network Orchestration (hanzo-network)
Distributed AI compute:
from hanzo_network import LocalComputeNode, DistributedNetwork
node = LocalComputeNode(node_id="node-001")
network = DistributedNetwork()
network.register_node(node)
5. Memory Management (hanzo-memory)
Persistent memory and RAG:
from hanzo_memory import MemoryService
memory = MemoryService()
await memory.store("key", "value")
result = await memory.retrieve("key")
๐ ๏ธ Development
Setup Development Environment
# Install Python 3.10+
make install-python
# Setup virtual environment
make setup
# Install development dependencies
make dev
Running Tests
# Run all tests
make test
# Run specific package tests
make test-hanzo
make test-mcp
make test-agents
# Run with coverage
make test-coverage
Code Quality
# Format code
make format
# Run linting
make lint
# Type checking
make type-check
Building Packages
# Build all packages
make build
# Build specific package
cd pkg/hanzo && uv build
๐ Documentation
Package Documentation
- Hanzo CLI Documentation
- MCP Documentation
- Agents Documentation
- Network Documentation
- Memory Documentation
API Reference
See the API documentation for detailed API reference.
๐ง Configuration
Environment Variables
# API Configuration
HANZO_API_KEY=your-api-key
HANZO_BASE_URL=https://api.hanzo.ai
# Router Configuration
HANZO_ROUTER_URL=http://localhost:4000/v1
# Node Configuration
HANZO_NODE_URL=http://localhost:8000/v1
# Logging
HANZO_LOG_LEVEL=INFO
Configuration File
Create ~/.hanzo/config.yaml:
api:
key: your-api-key
base_url: https://api.hanzo.ai
router:
url: http://localhost:4000/v1
node:
url: http://localhost:8000/v1
workers: 4
logging:
level: INFO
๐ข Deployment
Docker
# Build image
docker build -t hanzo-sdk .
# Run container
docker run -p 8000:8000 hanzo-sdk
Docker Compose
# Start all services
docker-compose up
# Start specific service
docker-compose up router
๐ค Contributing
We welcome contributions! Please see our Contributing Guide for details.
Development Workflow
- Fork the repository
- Create feature branch (
git checkout -b feature/amazing-feature) - Make changes and test
- Commit changes (
git commit -m 'Add amazing feature') - Push to branch (
git push origin feature/amazing-feature) - Open Pull Request
Code Standards
- Follow PEP 8
- Use type hints
- Write tests for new features
- Update documentation
- Run
make lintbefore committing
๐ Performance
Benchmarks
| Operation | Latency | Throughput |
|---|---|---|
| Chat Completion | 50ms | 20 req/s |
| Embedding | 10ms | 100 req/s |
| Local Inference | 200ms | 5 req/s |
Optimization Tips
- Use streaming for long responses
- Enable caching for repeated queries
- Use batch operations when possible
- Configure appropriate timeouts
๐ Security
- API keys are encrypted at rest
- All communications use TLS 1.3+
- Regular security audits
- SOC 2 Type II certified
Report security issues to security@hanzo.ai
๐ License
This project is licensed under the Apache License 2.0 - see the LICENSE file for details.
๐ Acknowledgments
- OpenAI for the API specification
- Anthropic for Claude integration
- The open-source community
๐ Support
- Documentation: https://docs.hanzo.ai
- Discord: https://discord.gg/hanzo
- Email: support@hanzo.ai
- GitHub Issues: https://github.com/hanzoai/python-sdk/issues
๐บ๏ธ Roadmap
- Multi-modal support (images, audio, video)
- Enhanced caching strategies
- WebSocket streaming
- Browser SDK
- Mobile SDKs (iOS, Android)
Built with โค๏ธ by the Hanzo team
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file hanzoai-2.1.2.tar.gz.
File metadata
- Download URL: hanzoai-2.1.2.tar.gz
- Upload date:
- Size: 464.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
7afce7ac7eba44f4e3afacedbbd98db8ba72b16bb1c8eaeefb0542fd4eb8d614
|
|
| MD5 |
218d23f9abc6b11f34c2a498c0508c82
|
|
| BLAKE2b-256 |
66dd705e537428e4bdfcd325f42824c4db7e545328bafa24b7cdec62e9606e11
|
File details
Details for the file hanzoai-2.1.2-py3-none-any.whl.
File metadata
- Download URL: hanzoai-2.1.2-py3-none-any.whl
- Upload date:
- Size: 386.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
0d0e4d1b458e9d94daec5a9475c405748067b6023297f8d7143a9d5278cc0055
|
|
| MD5 |
403a06fc4fa8438b5955be5d2ede5589
|
|
| BLAKE2b-256 |
420f4baa3dbd424686f348d204114498ab2b7c11f7eb5acebe5c864ec83c289b
|