adaptive-memory-multi-model-router 2.15.4 → 2.16.0

package/adapters/a3m_adapter/adapter/llamaindex.py

@@ -1,162 +0,0 @@
-"""
-A3M Router Adapter for LlamaIndex.
-
-Drop-in replacement for LlamaIndex's BaseLLM that routes through A3M Router
-for intelligent, cost-optimized model selection.
-"""
-
-from __future__ import annotations
-
-import logging
-from typing import Any, Dict, List, Optional, Sequence
-
-logger = logging.getLogger(__name__)
-
-# Check availability
-LLAMAINDEX_AVAILABLE = False
-_llama_metadata_class = None
-try:
-    from llama_index.core.base.llms.base import BaseLLM, CompletionResponse
-    from llama_index.core.base.llms.types import ChatMessage
-    LLAMAINDEX_AVAILABLE = True
-    try:
-        from llama_index.core.base.llms.base import LLMMetadata
-        _llama_metadata_class = LLMMetadata
-    except ImportError:
-        pass
-except ImportError:
-    logger.warning("LlamaIndex not installed. Install with: pip install llama-index")
-
-A3M_AVAILABLE = False
-try:
-    from a3m.router import A3MRouter, RouteResponse
-    A3M_AVAILABLE = True
-except ImportError:
-    logger.warning("A3M Router not installed. Install with: pip install adaptive-memory-multi-model-router")
-
-
-class A3MLlamaIndexAdapter:
-    """
-    A3M Router adapter for LlamaIndex's BaseLLM interface.
-
-    Routes prompts through A3M Router to automatically select the cheapest
-    capable model across 47+ LLM providers.
-    """
-
-    def __init__(
-        self,
-        model: str = "auto",
-        temperature: float = 0.0,
-        max_tokens: Optional[int] = 4096,
-        parallel_ensemble: int = 1,
-        api_key: Optional[str] = None,
-        **kwargs: Any,
-    ) -> None:
-        """
-        Initialize A3M Router adapter.
-        """
-        self.model = model
-        self.temperature = temperature
-        self.max_tokens = max_tokens
-        self.parallel_ensemble = parallel_ensemble
-        self.api_key = api_key
-        self._a3m_router = None
-        self._initialized = False
-
-    def _ensure_router(self) -> None:
-        """Lazily initialize the A3M router."""
-        if self._initialized:
-            return
-        
-        if not A3M_AVAILABLE:
-            raise ImportError(
-                "A3M Router is not installed. "
-                "Install with: pip install adaptive-memory-multi-model-router"
-            )
-        
-        self._a3m_router = A3MRouter(
-            model=self.model,
-            temperature=self.temperature,
-            parallel_ensemble=self.parallel_ensemble,
-        )
-        self._initialized = True
-        logger.info(
-            "A3M Router initialized: model=%s, ensemble=%d",
-            self.model,
-            self.parallel_ensemble,
-        )
-
-    @property
-    def metadata(self) -> Dict[str, Any]:
-        """Return LLM metadata as a dict (framework-agnostic)."""
-        return {
-            "context_window": 128000,
-            "num_output": self.max_tokens or 4096,
-            "model_name": self.model,
-            "is_chat_model": True,
-        }
-
-    def complete(self, prompt: str, **kwargs: Any) -> CompletionResponse:
-        """Complete a prompt using A3M Router."""
-        self._ensure_router()
-        
-        messages = [{"role": "user", "content": prompt}]
-        
-        import asyncio
-        loop = asyncio.get_event_loop()
-        route_result = loop.run_in_executor(
-            None,
-            lambda: self._a3m_router.route(
-                messages=messages,
-                temperature=self.temperature,
-                max_tokens=self.max_tokens,
-                **kwargs,
-            ),
-        )
-        
-        return CompletionResponse(text=route_result.content, raw=route_result)
-
-    def chat(self, messages: Sequence[ChatMessage], **kwargs: Any) -> CompletionResponse:
-        """Chat completion using A3M Router."""
-        self._ensure_router()
-        
-        a3m_messages = self._convert_messages(messages)
-        
-        import asyncio
-        loop = asyncio.get_event_loop()
-        route_result = loop.run_in_executor(
-            None,
-            lambda: self._a3m_router.route(
-                messages=a3m_messages,
-                temperature=self.temperature,
-                max_tokens=self.max_tokens,
-                **kwargs,
-            ),
-        )
-        
-        return CompletionResponse(text=route_result.content, raw=route_result)
-
-    def _convert_messages(self, messages: Sequence[ChatMessage]) -> List[Dict[str, Any]]:
-        """Convert LlamaIndex ChatMessages to A3M format."""
-        a3m_messages = []
-        for msg in messages:
-            role = msg.role.value if hasattr(msg.role, 'value') else str(msg.role).lower()
-            role_map = {
-                "system": "system",
-                "user": "user", 
-                "assistant": "assistant",
-                "tool": "tool",
-                "function": "function",
-            }
-            a3m_role = role_map.get(role, "user")
-            a3m_messages.append({"role": a3m_role, "content": msg.content})
-        return a3m_messages
-
-    def __repr__(self) -> str:
-        return (
-            f"A3MLlamaIndexAdapter("
-            f"model={self.model!r}, "
-            f"temperature={self.temperature}, "
-            f"max_tokens={self.max_tokens}, "
-            f"ensemble={self.parallel_ensemble})"
-        )

package/adapters/a3m_adapter/tests/__init__.py

@@ -1 +0,0 @@
-"""Tests for A3M adapters."""

package/adapters/a3m_adapter/tests/test_adapters.py

@@ -1,120 +0,0 @@
-"""
-Test script for A3M Router adapters.
-
-Tests the LangChain and LlamaIndex adapters to ensure they:
-1. Initialize correctly
-2. Route requests properly
-3. Return expected response types
-4. Handle errors gracefully
-"""
-
-import sys
-import os
-import logging
-
-# Add current directory to path
-sys.path.insert(0, '.')
-
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
-
-def test_langchain_adapter():
-    """Test LangChain adapter."""
-    print("Testing LangChain adapter...")
-    
-    try:
-        from a3m_llm_adapter import A3MChatModel
-        
-        # Initialize
-        llm = A3MChatModel(model="auto", temperature=0.7)
-        print(f"��✅ Initialized: {llm}")
-        
-        # Test simple generation
-        # Note: This would make actual API calls - we'll skip for now
-        # In a real test, we'd mock the A3M router
-        print("��✅ LangChain adapter structure OK")
-        return True
-        
-    except Exception as e:
-        print(f"��❌ LangChain adapter failed: {e}")
-        return False
-
-def test_llamaindex_adapter():
-    """Test LlamaIndex adapter."""
-    print("Testing LlamaIndex adapter...")
-    
-    try:
-        from a3m_llama_index_adapter import A3MLlamaIndexLLM
-        
-        # Initialize
-        llm = A3MLlamaIndexLLM(model="auto", temperature=0.5)
-        print(f"��✅ Initialized: {llm}")
-        
-        # Check metadata
-        metadata = llm.metadata
-        print(f"��✅ Metadata: {metadata.model_name}, tokens: {metadata.num_output}")
-        return True
-        
-    except Exception as e:
-        print(f"��❌ LlamaIndex adapter failed: {e}")
-        return False
-
-def test_config():
-    """Test configuration."""
-    print("Testing configuration...")
-    
-    try:
-        from a3m_adapter_config import A3MConfig
-        
-        # Test defaults
-        config = A3MConfig()
-        print(f"��✅ Default config: model={config.model}")
-        
-        # Test to_dict
-        data = config.to_dict()
-        assert 'model' in data
-        print("��✅ Config to_dict works")
-        
-        # Test JSON serialization
-        json_str = config.to_json()
-        assert '"model"' in json_str
-        print("��✅ Config JSON serialization works")
-        
-        return True
-        
-    except Exception as e:
-        print(f"��❌ Config test failed: {e}")
-        return False
-
-def main():
-    """Run all tests."""
-    print("=" * 50)
-    print("A3M Router Adapter Tests")
-    print("=" * 50)
-    
-    tests = [
-        test_config,
-        test_langchain_adapter,
-        test_llamaindex_adapter,
-    ]
-    
-    passed = 0
-    total = len(tests)
-    
-    for test in tests:
-        if test():
-            passed += 1
-        print()
-    
-    print("=" * 50)
-    print(f"Results: {passed}/{total} tests passed")
-    
-    if passed == total:
-        print("���🎉 All tests passed!")
-        return 0
-    else:
-        print("��❌ Some tests failed")
-        return 1
-
-if __name__ == "__main__":
-    sys.exit(main())

package/adapters/setup.py

@@ -1,23 +0,0 @@
-from setuptools import setup, find_packages
-import os
-
-setup(
-    name="a3m_adapter",
-    version="1.0.0",
-    description="A3M Router adapters for LangChain, LlamaIndex, and other LLM frameworks",
-    long_description=open("README.md").read() if os.path.exists("README.md") else "",
-    long_description_content_type="text/markdown",
-    author="A3M Team",
-    author_email="hello@a3m.ai",
-    packages=find_packages(),
-    install_requires=[
-        "requests>=2.25.1",
-        "pydantic>=1.9.0",
-    ],
-    extras_require={
-        "langchain": ["langchain>=0.0.365", "langchain-core>=0.0.365"],
-        "llamaindex": ["llama-index>=0.8.0"],
-        "dev": ["pytest>=6.0"],
-    },
-    python_requires=">=3.8",
-)