cua-agent 0.3.2__py3-none-any.whl → 0.4.0b1__py3-none-any.whl

agent/__init__.py

@@ -1,55 +1,19 @@
-"""CUA (Computer Use) Agent for AI-driven computer interaction."""
+"""
+agent - Decorator-based Computer Use Agent with liteLLM integration
+"""
 
-import sys
-import logging
+from .decorators import agent_loop
+from .agent import ComputerAgent
+from .types import Messages, AgentResponse
 
-__version__ = "0.1.0"
+# Import loops to register them
+from . import loops
 
-# Initialize logging
-logger = logging.getLogger("agent")
+__all__ = [
+    "agent_loop",
+    "ComputerAgent",
+    "Messages",
+    "AgentResponse"
+]
 
-# Initialize telemetry when the package is imported
-try:
-    # Import from core telemetry for basic functions
-    from core.telemetry import (
-        is_telemetry_enabled,
-        flush,
-        record_event,
-    )
-
-    # Import set_dimension from our own telemetry module
-    from .core.telemetry import set_dimension
-
-    # Check if telemetry is enabled
-    if is_telemetry_enabled():
-        logger.info("Telemetry is enabled")
-
-        # Record package initialization
-        record_event(
-            "module_init",
-            {
-                "module": "agent",
-                "version": __version__,
-                "python_version": sys.version,
-            },
-        )
-
-        # Set the package version as a dimension
-        set_dimension("agent_version", __version__)
-
-        # Flush events to ensure they're sent
-        flush()
-    else:
-        logger.info("Telemetry is disabled")
-except ImportError as e:
-    # Telemetry not available
-    logger.warning(f"Telemetry not available: {e}")
-except Exception as e:
-    # Other issues with telemetry
-    logger.warning(f"Error initializing telemetry: {e}")
-
-from .core.types import LLMProvider, LLM
-from .core.factory import AgentLoop
-from .core.agent import ComputerAgent
-
-__all__ = ["AgentLoop", "LLMProvider", "LLM", "ComputerAgent"]
+__version__ = "0.4.0b1"

agent/__main__.py

@@ -0,0 +1,21 @@
+"""
+Entry point for running agent CLI module.
+
+Usage:
+    python -m agent.cli <model_string>
+"""
+
+import sys
+import asyncio
+from .cli import main
+
+if __name__ == "__main__":
+    # Check if 'cli' is specified as the module
+    if len(sys.argv) > 1 and sys.argv[1] == "cli":
+        # Remove 'cli' from arguments and run CLI
+        sys.argv.pop(1)
+        asyncio.run(main())
+    else:
+        print("Usage: python -m agent.cli <model_string>")
+        print("Example: python -m agent.cli openai/computer-use-preview")
+        sys.exit(1)

agent/adapters/__init__.py

@@ -0,0 +1,9 @@
+"""
+Adapters package for agent - Custom LLM adapters for LiteLLM
+"""
+
+from .huggingfacelocal_adapter import HuggingFaceLocalAdapter
+
+__all__ = [
+    "HuggingFaceLocalAdapter",
+]

agent/adapters/huggingfacelocal_adapter.py

@@ -0,0 +1,216 @@
+import asyncio
+import warnings
+from typing import Iterator, AsyncIterator, Dict, List, Any, Optional
+import torch
+from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
+from litellm.types.utils import GenericStreamingChunk, ModelResponse
+from litellm import CustomLLM, completion, acompletion
+
+
+class HuggingFaceLocalAdapter(CustomLLM):
+    """HuggingFace Local Adapter for running vision-language models locally."""
+    
+    def __init__(self, device: str = "auto", **kwargs):
+        """Initialize the adapter.
+        
+        Args:
+            device: Device to load model on ("auto", "cuda", "cpu", etc.)
+            **kwargs: Additional arguments
+        """
+        super().__init__()
+        self.device = device
+        self.models = {}  # Cache for loaded models
+        self.processors = {}  # Cache for loaded processors
+        
+    def _load_model_and_processor(self, model_name: str):
+        """Load model and processor if not already cached.
+        
+        Args:
+            model_name: Name of the model to load
+            
+        Returns:
+            Tuple of (model, processor)
+        """
+        if model_name not in self.models:
+            # Load model
+            model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
+                model_name,
+                torch_dtype=torch.float16,
+                device_map=self.device,
+                attn_implementation="sdpa"
+            )
+            
+            # Load processor
+            processor = AutoProcessor.from_pretrained(model_name)
+            
+            # Cache them
+            self.models[model_name] = model
+            self.processors[model_name] = processor
+            
+        return self.models[model_name], self.processors[model_name]
+    
+    def _convert_messages(self, messages: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
+        """Convert OpenAI format messages to HuggingFace format.
+        
+        Args:
+            messages: Messages in OpenAI format
+            
+        Returns:
+            Messages in HuggingFace format
+        """
+        converted_messages = []
+        
+        for message in messages:
+            converted_message = {
+                "role": message["role"],
+                "content": []
+            }
+            
+            content = message.get("content", [])
+            if isinstance(content, str):
+                # Simple text content
+                converted_message["content"].append({
+                    "type": "text",
+                    "text": content
+                })
+            elif isinstance(content, list):
+                # Multi-modal content
+                for item in content:
+                    if item.get("type") == "text":
+                        converted_message["content"].append({
+                            "type": "text",
+                            "text": item.get("text", "")
+                        })
+                    elif item.get("type") == "image_url":
+                        # Convert image_url format to image format
+                        image_url = item.get("image_url", {}).get("url", "")
+                        converted_message["content"].append({
+                            "type": "image",
+                            "image": image_url
+                        })
+            
+            converted_messages.append(converted_message)
+            
+        return converted_messages
+    
+    def _generate(self, **kwargs) -> str:
+        """Generate response using the local HuggingFace model.
+        
+        Args:
+            **kwargs: Keyword arguments containing messages and model info
+            
+        Returns:
+            Generated text response
+        """
+        # Extract messages and model from kwargs
+        messages = kwargs.get('messages', [])
+        model_name = kwargs.get('model', 'ByteDance-Seed/UI-TARS-1.5-7B')
+        max_new_tokens = kwargs.get('max_tokens', 128)
+        
+        # Warn about ignored kwargs
+        ignored_kwargs = set(kwargs.keys()) - {'messages', 'model', 'max_tokens'}
+        if ignored_kwargs:
+            warnings.warn(f"Ignoring unsupported kwargs: {ignored_kwargs}")
+        
+        # Load model and processor
+        model, processor = self._load_model_and_processor(model_name)
+        
+        # Convert messages to HuggingFace format
+        hf_messages = self._convert_messages(messages)
+        
+        # Apply chat template and tokenize
+        inputs = processor.apply_chat_template(
+            hf_messages,
+            add_generation_prompt=True,
+            tokenize=True,
+            return_dict=True,
+            return_tensors="pt"
+        )
+        
+        # Move inputs to the same device as model
+        if torch.cuda.is_available() and self.device != "cpu":
+            inputs = inputs.to("cuda")
+        
+        # Generate response
+        with torch.no_grad():
+            generated_ids = model.generate(**inputs, max_new_tokens=max_new_tokens)
+            
+        # Trim input tokens from output
+        generated_ids_trimmed = [
+            out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+        ]
+        
+        # Decode output
+        output_text = processor.batch_decode(
+            generated_ids_trimmed, 
+            skip_special_tokens=True, 
+            clean_up_tokenization_spaces=False
+        )
+        
+        return output_text[0] if output_text else ""
+    
+    def completion(self, *args, **kwargs) -> ModelResponse:
+        """Synchronous completion method.
+        
+        Returns:
+            ModelResponse with generated text
+        """
+        generated_text = self._generate(**kwargs)
+        
+        return completion(
+            model=f"huggingface-local/{kwargs['model']}",
+            mock_response=generated_text,
+        )
+    
+    async def acompletion(self, *args, **kwargs) -> ModelResponse:
+        """Asynchronous completion method.
+        
+        Returns:
+            ModelResponse with generated text
+        """
+        # Run _generate in thread pool to avoid blocking
+        generated_text = await asyncio.to_thread(self._generate, **kwargs)
+        
+        return await acompletion(
+            model=f"huggingface-local/{kwargs['model']}",
+            mock_response=generated_text,
+        )
+    
+    def streaming(self, *args, **kwargs) -> Iterator[GenericStreamingChunk]:
+        """Synchronous streaming method.
+        
+        Returns:
+            Iterator of GenericStreamingChunk
+        """
+        generated_text = self._generate(**kwargs)
+        
+        generic_streaming_chunk: GenericStreamingChunk = {
+            "finish_reason": "stop",
+            "index": 0,
+            "is_finished": True,
+            "text": generated_text,
+            "tool_use": None,
+            "usage": {"completion_tokens": 0, "prompt_tokens": 0, "total_tokens": 0},
+        }
+        
+        yield generic_streaming_chunk
+    
+    async def astreaming(self, *args, **kwargs) -> AsyncIterator[GenericStreamingChunk]:
+        """Asynchronous streaming method.
+        
+        Returns:
+            AsyncIterator of GenericStreamingChunk
+        """
+        # Run _generate in thread pool to avoid blocking
+        generated_text = await asyncio.to_thread(self._generate, **kwargs)
+        
+        generic_streaming_chunk: GenericStreamingChunk = {
+            "finish_reason": "stop",
+            "index": 0,
+            "is_finished": True,
+            "text": generated_text,
+            "tool_use": None,
+            "usage": {"completion_tokens": 0, "prompt_tokens": 0, "total_tokens": 0},
+        }
+        
+        yield generic_streaming_chunk