Upload alpha_factory/run.py with huggingface_hub

alpha_factory/run.py

@@ -1,41 +1,73 @@
 """
 Alpha Factory — Entry Point
-Run: python -m alpha_factory.run [--dry-run] [--batch-size N]
+Run: python -m alpha_factory.run [--dry-run] [--batch-size N] [--interactive]
 """
 import asyncio
 import argparse
 from rich.console import Console
 from .config import load_config
+from .infra import ModelManager, interactive_model_select, LLMClient
 from .orchestration import AlphaPipeline
 
 console = Console()
 
 
+async def setup_models(interactive: bool = False, hf_token: str = None) -> ModelManager:
+    """Discover models and optionally let user pick interactively."""
+    manager = ModelManager(hf_token=hf_token)
+
+    console.print("\n[bold]🔍 Discovering available models...[/]")
+    await manager.discover_all()
+
+    if interactive:
+        # Let user pick models for each tier
+        selections = interactive_model_select(manager)
+        for tier, model in selections.items():
+            manager.select_model(tier, model)
+    else:
+        # Auto-assign best available
+        manager.auto_assign_defaults()
+
+    manager.print_status()
+    return manager
+
+
 def main():
     parser = argparse.ArgumentParser(description="Alpha Factory — LLM-Driven Alpha Generation Pipeline")
     parser.add_argument("--dry-run", action="store_true", help="Run without BRAIN submissions")
     parser.add_argument("--batch-size", type=int, default=10, help="Number of candidates per batch")
-    parser.add_argument("--config", type=str, default=None, help="Path to config override file")
+    parser.add_argument("--interactive", action="store_true", help="Interactively select models")
+    parser.add_argument("--hf-token", type=str, default=None, help="HuggingFace API token (or set HF_TOKEN env)")
+    parser.add_argument("--ollama-url", type=str, default="http://localhost:11434", help="Ollama server URL")
     args = parser.parse_args()
 
     config = load_config()
-    if args.batch_size:
-        config.batch_size = args.batch_size
+    config.batch_size = args.batch_size
 
     console.print(f"""
 [bold green]━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[/]
-[bold green]  ALPHA FACTORY v{config.__class__.__module__.split('.')[0]}[/]
+[bold green]  ALPHA FACTORY v0.1.0[/]
 [bold green]  Open-Source LLM-Driven Pipeline for WorldQuant BRAIN[/]
 [bold green]━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━[/]
 
   Mode:       {"DRY RUN (no BRAIN submissions)" if args.dry_run else "LIVE"}
   Batch size: {args.batch_size}
-  LLM:        {config.llm.base_url}
-  Model:      {config.llm.microfish_model} (generation)
-              {config.llm.mediumfish_model} (critique)
+  Ollama:     {args.ollama_url}
+  HF Token:   {"✓ Set" if args.hf_token or __import__('os').getenv('HF_TOKEN') else "✗ Not set (cloud models unavailable)"}
 """)
 
+    # Discover and select models
+    manager = asyncio.run(setup_models(
+        interactive=args.interactive,
+        hf_token=args.hf_token,
+    ))
+
+    # Update LLM config with Ollama URL
+    config.llm.base_url = f"{args.ollama_url}/v1"
+
+    # Create pipeline with model manager
     pipeline = AlphaPipeline(config)
+    pipeline.llm = LLMClient(config.llm, model_manager=manager)
 
     try:
         result = asyncio.run(pipeline.run_batch(args.batch_size))