File size: 1,333 Bytes
6851411
 
a750766
772dd21
6851411
772dd21
 
 
6851411
9c71bb7
6851411
 
 
 
 
 
 
772dd21
 
ee07ed2
 
a750766
ee07ed2
 
 
afd6869
9c71bb7
ee07ed2
 
 
 
 
6851411
 
 
772dd21
 
cc88da6
772dd21
cc88da6
9c71bb7
772dd21
 
 
 
a750766
6851411
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
from fastapi import FastAPI
from app.middleware import api_key_guard
from app.routers import openai_api
import logging

# Configure logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

app = FastAPI(title="LLM Pro Finance API (Transformers)")

# Mount routers
app.include_router(openai_api.router, prefix="/v1")

# Optional API key middleware
app.middleware("http")(api_key_guard)

@app.on_event("startup")
async def startup_event():
    """Startup event - initialize model in background"""
    import threading
    logger.info("Starting LLM Pro Finance API...")
    logger.info("Initializing model in background thread...")
    
    def load_model():
        from app.providers.transformers_provider import initialize_model
        initialize_model()
    
    # Start model loading in background thread
    thread = threading.Thread(target=load_model, daemon=True)
    thread.start()
    logger.info("Model initialization started in background")

@app.get("/")
async def root():
    return {
        "status": "ok", 
        "service": "Qwen Open Finance R 8B Inference", 
        "version": "1.0.0",
        "model": "DragonLLM/qwen3-8b-fin-v1.0",
        "backend": "Transformers"
    }

@app.get("/health")
async def health():
    return {"status": "healthy", "service": "LLM Pro Finance API"}