tdpeuter/open-webui
tdpeuter/open-webui
1
Fork 0
forked from open-webui/open-webui
Code Issues Pull requests 1 Releases 2 Packages Activity Actions

refac: comment

Browse source
This commit is contained in:
Timothy J. Baek 2024-03-05 01:21:50 -08:00
parent 8fd7bc342d
commit b2dd2f191d
1 changed files with 6 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
backend/apps/ollama/main.py
View file

@ -37,6 +37,11 @@ app.state.MODELS = {}
REQUEST_POOL = [] REQUEST_POOL = []
# TODO: Implement a more intelligent load balancing mechanism for distributing requests among multiple backend instances.
# Current implementation uses a simple round-robin approach (random.choice). Consider incorporating algorithms like weighted round-robin,
# least connections, or least response time for better resource utilization and performance optimization.
@app.middleware("http") @app.middleware("http")
async def check_url(request: Request, call_next): async def check_url(request: Request, call_next):
if len(app.state.MODELS) == 0: if len(app.state.MODELS) == 0:
@ -761,7 +766,7 @@ async def generate_completion(
@app.api_route("/{path:path}", methods=["GET", "POST", "PUT", "DELETE"]) @app.api_route("/{path:path}", methods=["GET", "POST", "PUT", "DELETE"])
async def proxy(path: str, request: Request, user=Depends(get_current_user)): async def deprecated_proxy(path: str, request: Request, user=Depends(get_current_user)):
url = app.state.OLLAMA_BASE_URLS[0] url = app.state.OLLAMA_BASE_URLS[0]
target_url = f"{url}/{path}" target_url = f"{url}/{path}"