lion-os 0.1.7

No project description provided

🦁 Lion Framework

A powerful Python framework for structured AI conversations and operations

🌟 Features

• 🎯 Dynamic structured output at runtime
• 🔄 Easy composition of multi-step processes
• 🤖 Support for any model via litellm
• 🏗️ Built-in conversation management
• 🧩 Extensible architecture
• 🔍 Type-safe with Pydantic models

🚀 Quick Install

pip install lion-os

Note

the operation API is experimental and may change in future versions. Use with caution.

💡 Usage Examples

1️⃣ Simple Communication

from lion import iModel, Branch

# Initialize model and branch
imodel = iModel(
    model="openai/gpt-4o",
    api_key="OPENAI_API_KEY",
    temperature=0.2,
)
branch = Branch(imodel=imodel)

# Basic communication
result = await branch.communicate(
    instruction="Give me ideas for FastAPI interview questions",
    context="We're hiring senior engineers"
)

2️⃣ Structured Output with Pydantic

from pydantic import BaseModel

class CodingQuestion(BaseModel):
    question: str
    evaluation_criteria: str

# Get structured responses
questions = await branch.operate(
    instruction="Generate FastAPI coding questions",
    context="Technical interview context",
    operative_model=CodingQuestion
)

3️⃣ Advanced Operations (Brainstorming)

from lion.operations import brainstorm

result = await brainstorm(
    instruct={
        "instruction": "Design API endpoints for a todo app",
        "context": "Building a modern task management system"
    },
    imodel=imodel,
    num_instruct=3,
    operative_model=CodingQuestion,
    auto_run=True
)

🎯 Key Components

Component	Description
Branch	Main conversation controller
MessageManager	Handles message flow and history
ToolManager	Manages function execution and tools
Operative	Structures operations and responses

Requirements

python 3.11+ required

⭐ Star History