gordonchan commited on
Commit
020aaa1
1 Parent(s): ca56e6a

Upload server.py

Browse files
Files changed (1) hide show
  1. server.py +40 -0
server.py ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from api.config import SETTINGS
2
+ from api.models import app, EMBEDDED_MODEL, GENERATE_ENGINE
3
+
4
+
5
+ prefix = SETTINGS.api_prefix
6
+
7
+ if EMBEDDED_MODEL is not None:
8
+ from api.routes.embedding import embedding_router
9
+
10
+ app.include_router(embedding_router, prefix=prefix, tags=["Embedding"])
11
+
12
+
13
+ if GENERATE_ENGINE is not None:
14
+ from api.routes import model_router
15
+
16
+ app.include_router(model_router, prefix=prefix, tags=["Model"])
17
+
18
+ if SETTINGS.engine == "vllm":
19
+ from api.vllm_routes import chat_router as chat_router
20
+ from api.vllm_routes import completion_router as completion_router
21
+
22
+ elif SETTINGS.engine == "llama.cpp":
23
+ from api.llama_cpp_routes import chat_router as chat_router
24
+ from api.llama_cpp_routes import completion_router as completion_router
25
+
26
+ elif SETTINGS.engine == "tgi":
27
+ from api.tgi_routes import chat_router as chat_router
28
+ from api.tgi_routes.completion import completion_router as completion_router
29
+
30
+ else:
31
+ from api.routes.chat import chat_router as chat_router
32
+ from api.routes.completion import completion_router as completion_router
33
+
34
+ app.include_router(chat_router, prefix=prefix, tags=["Chat Completion"])
35
+ app.include_router(completion_router, prefix=prefix, tags=["Completion"])
36
+
37
+
38
+ if __name__ == '__main__':
39
+ import uvicorn
40
+ uvicorn.run(app, host=SETTINGS.host, port=SETTINGS.port, log_level="info")