Build with Mavaia

Installation

pip install mavaia-core

Python Client

from mavaia_core import MavaiaClient

client = MavaiaClient()

# Generate with cognitive orchestration
response = client.generate(
    query="Explain quantum entanglement",
    reasoning_strategy="tree_of_thought",
    memory_enabled=True
)

print(response["result"])

OpenAI-Compatible API

import openai

client = openai.OpenAI(
    base_url="http://localhost:8000/v1",
    api_key="not-needed"
)

response = client.chat.completions.create(
    model="mavaia-cognitive",
    messages=[{"role": "user", "content": "..."}]
)

print(response.choices[0].message.content)

Creating a Custom Module

from mavaia_core.brain.base_module import BaseBrainModule, ModuleMetadata
from typing import Any

class CustomAnalyzer(BaseBrainModule):
    """Custom module for domain-specific analysis"""
    
    @property
    def metadata(self) -> ModuleMetadata:
        return ModuleMetadata(
            name="custom_analyzer",
            version="1.0.0",
            description="Domain-specific analysis module",
            operations=["analyze", "classify", "extract"],
            dependencies=["numpy", "scikit-learn"],
            enabled=True,
            model_required=False
        )
    
    def execute(self, operation: str, params: dict[str, Any]) -> dict[str, Any]:
        """Execute the requested operation"""
        if operation == "analyze":
            return self._analyze(params)
        elif operation == "classify":
            return self._classify(params)
        elif operation == "extract":
            return self._extract(params)
        else:
            raise ValueError(f"Unknown operation: {operation}")
    
    def _analyze(self, params: dict[str, Any]) -> dict[str, Any]:
        text = params.get("text", "")
        # Your custom analysis logic
        return {
            "analysis": {...},
            "confidence": 0.95
        }

# Module is automatically discovered and available via:
# POST /v1/modules/custom_analyzer/execute