File size: 774 Bytes
a1420d4
 
 
 
 
 
 
 
 
 
 
8d1666a
a1420d4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from llama_cpp.server.app import create_app, Settings
from fastapi.responses import HTMLResponse
from fastapi.middleware.cors import CORSMiddleware
from fastapi.responses import RedirectResponse
import os

try:
    print(os.system('ls'))
except:
    print('could Not print')

model_path = "qwen2-0.5b.Q2_K.gguf"

app = create_app(
    Settings(
        n_threads=4,
        model=model_path,
        embedding=True,
        n_gpu_layers=33
    )
)
app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],
    allow_credentials=True,
    allow_methods=["*"],
    allow_headers=["*"],
)

@app.get("/")
async def redirect_root_to_docs():
    return RedirectResponse("/docs")

if __name__ == "__main__":
    import uvicorn
    uvicorn.run(app, host="0.0.0.0", port=7860)