server_root.py

from llama_cpp.server.app import create_app, Settings
from fastapi.middleware.cors import CORSMiddleware
from fastapi import Request
import os
import time

# Configuration from environment variables
model_path = os.environ.get("MODEL_FILE", "./model.gguf")
n_ctx = int(os.environ.get("N_CTX", 4096))
n_batch = int(os.environ.get("N_BATCH", 512))

settings = Settings(
    model=model_path,
    n_ctx=n_ctx,
    n_batch=n_batch
)

app = create_app(settings=settings)

# DEBUG MIDDLEWARE to catch 400s and see paths
@app.middleware("http")
async def log_requests(request: Request, call_next):
    start_time = time.time()
    path = request.url.path
    method = request.method
    print(f"DEBUG: Incoming {method} {path}")
    
    # Check if we are receiving the request correctly
    response = await call_next(request)
    
    process_time = time.time() - start_time
    print(f"DEBUG: {method} {path} - Status: {response.status_code} - Time: {process_time:.4f}s")
    return response

# Standard CORS Middleware
app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],
    allow_credentials=True,
    allow_methods=["*"],
    allow_headers=["*"],
)

if __name__ == "__main__":
    import uvicorn
    host = os.environ.get("HOST", "0.0.0.0")
    port = int(os.environ.get("PORT", 7860))
    print(f"Starting Intelligent Node with DEBUG LOGS & CORS on {host}:{port}")
    uvicorn.run(app, host=host, port=port)