File size: 717 Bytes
106db30
 
fb5554d
25a22d9
106db30
 
ad8faaf
 
106db30
 
883ba9d
ad8faaf
ab7097f
 
106db30
 
fb5554d
 
 
 
 
 
 
25a22d9
 
 
 
106db30
 
 
25a22d9
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
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

model_path = "/home/user/model/gguf-model.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)