Commit graph

12 commits

Author SHA1 Message Date
9fc0593d3a
Add files via upload
final touches
2025-09-05 12:11:31 +02:00
caca498f49
Add files via upload
switching to custom cache logic for faster cache invalidation in faulty cache scenarios
removing aiocache dependency
2025-09-01 13:38:49 +02:00
0c6387f5af
Add files via upload
adding persistent connections for endpoints
adding cache to available models routine
2025-09-01 11:07:07 +02:00
9f19350f55
Add files via upload
improving high load endpoint selection by moving from rr to lc algorithm for connections > max_concurrent_connections
2025-09-01 09:30:23 +02:00
64549b4e1c
Add files via upload
Increasing timeout for heavy load situatuions
2025-09-01 09:01:41 +02:00
295ace0401
Add files via upload
fixing a result type bug in exception handleer
2025-08-31 11:40:13 +02:00
cb7224c030
Add files via upload
Adding:
- health endpoint
- extended /api/config
- frontend extension of backend server viz
2025-08-30 12:43:35 +02:00
9e0b53bba3
Additions
- Frontend
- Internal Monitoring Endpoints
- External OpenAI compatible backends
2025-08-30 00:12:56 +02:00
1403c08a81
enhance routing logic
add a pre-routing model check:
allows for different configs on the ollama backend servers
2025-08-29 13:13:25 +02:00
516ec8b102
Adding OpenAI compatibility
New Endpoints
New Requirements
2025-08-28 09:40:33 +02:00
cdb4485334
Update router.py
added t.b.d. OpenAI API compatible endpoints
2025-08-27 09:23:59 +02:00
5f1f3f7b57
Initial commit 2025-08-26 18:19:43 +02:00