Commit graph

645 commits

Author SHA1 Message Date
Krrish Dholakia
497419a766 fix(router.py): add support for cooldowns with redis 2023-11-22 19:54:22 -08:00
Krrish Dholakia
a2207d462e feat(router.py): add server cooldown logic 2023-11-22 15:59:48 -08:00
Krrish Dholakia
73d70ef01c feat(router.py): adding latency-based routing strategy 2023-11-21 21:19:27 -08:00
ishaan-jaff
2b1fc64f36 (fix) using callbacks with router 2023-11-20 19:08:53 -08:00
Krrish Dholakia
2ac804a42f feat(proxy_server.py): enable model aliases 2023-11-20 16:51:04 -08:00
Krrish Dholakia
7472be1529 fix(routing.py): update token usage on streaming 2023-11-20 14:19:25 -08:00
Krrish Dholakia
5f4dca301b refactor(router.py): adding user support message 2023-11-18 19:05:45 -08:00
Krrish Dholakia
43c26f3382 docs(routing.md): updating docs for managing multiple deployments 2023-11-18 19:02:50 -08:00
Krrish Dholakia
cf0a9f591c fix(router.py): introducing usage-based-routing 2023-11-17 17:56:26 -08:00
Krrish Dholakia
452946b2f8 refactor(router.py): code cleanup 2023-11-17 17:05:46 -08:00
Krrish Dholakia
7d70bf84a7 test(test_langfuse.py): handle timeouts 2023-11-17 17:05:46 -08:00
Krrish Dholakia
02ed97d0b2 fix(acompletion): support client side timeouts + raise exceptions correctly for async calls 2023-11-17 15:39:47 -08:00
Krrish Dholakia
a753487d79 fix(router.py): check if async response is coroutine 2023-11-16 21:53:35 -08:00
Krrish Dholakia
d9123ea2e8 docs(routing.md): update tutorial on deploying router 2023-11-16 21:46:43 -08:00
Krrish Dholakia
c47ca6cc50 refactor(router.py): renaming variable 2023-11-15 12:31:29 -08:00
Krrish Dholakia
4676b3dabd feat(router.py): enable passing chat completion params for Router.chat.completion.create 2023-11-15 12:28:16 -08:00
Krrish Dholakia
0f6713993d fix(router.py): enabling retrying with expo backoff (without tenacity) for router 2023-11-14 20:57:51 -08:00
Krrish Dholakia
5d58bb9cd0 fix(main.py): misrouting ollama models to nlp cloud 2023-11-14 18:55:08 -08:00
Krrish Dholakia
1032b49f23 bump: version 1.0.0.dev1 → 1.0.0 2023-11-13 16:48:53 -08:00
Krrish Dholakia
4e233c915b fix(router.py): enable calling router with instructor 2023-11-13 15:16:57 -08:00
Krrish Dholakia
67e8b12a09 fix(utils.py): fix cached responses - translate dict to objects 2023-11-10 10:38:20 -08:00
Nathan Kim
ada2d40a43 first commit 2023-11-09 22:12:39 -08:00
Nathan Kim
672cd09e3f first commit 2023-11-09 22:07:19 -08:00
Krrish Dholakia
78fb8cf941 fix(router.py): fix linting issues 2023-11-06 18:50:09 -08:00
Krrish Dholakia
a7a0605b4f fix(router.py): adding health checks 2023-11-06 18:26:41 -08:00
Krrish Dholakia
632533f2e2 bump: version 0.13.6.dev3 → 0.13.6 2023-11-06 18:19:20 -08:00
Krish Dholakia
a157a3da8c Merge pull request #722 from karvetskiy/fix-router-caching
Fix caching for Router
2023-10-31 16:39:18 -07:00
mc-marcocheng
c7b6911c7b Handle empty input edge case 2023-10-31 14:38:04 +08:00
seva
f0a9f8c61e Router & Caching fixes:
- Add optional TTL to Cache parameters
- Fix tpm and rpm caching in Router
2023-10-30 13:29:35 +01:00
mc-marcocheng
f74c0f101f avoid overwriting litellm_params 2023-10-27 15:30:34 +08:00
mc-marcocheng
bd43b96d8d Feature: Router aembedding 2023-10-25 11:19:45 +08:00
Krrish Dholakia
3477486886 fix(router.py): adding support for async completion calls
https://github.com/BerriAI/litellm/issues/676
2023-10-24 17:20:31 -07:00
Krrish Dholakia
e6e9a595f8 refactor(router.py): spacing 2023-10-24 12:30:59 -07:00
Krrish Dholakia
98c25b08cd fix(vertex_ai.py): fix output parsing 2023-10-24 12:08:22 -07:00
Krrish Dholakia
c7e8bf3e80 test(test_router.py): fixing router testing 2023-10-24 10:21:10 -07:00
mc-marcocheng
fc3c32dde5 Fix data being overwritten 2023-10-24 16:02:15 +08:00
Krrish Dholakia
0aad58cf48 fix(router.py): enable additional params to be passe din 2023-10-23 20:41:18 -07:00
Krrish Dholakia
eb40ba8f2e docs(router.py): fix linting issue 2023-10-23 15:15:10 -07:00
Krrish Dholakia
cc760d783e fix(router.py): fix null model names error
https://github.com/BerriAI/litellm/issues/669#issuecomment-1775456245
2023-10-23 09:30:04 -07:00
ishaan-jaff
9347b25e37 (fix) litellm proxy with router 2023-10-20 09:38:22 -07:00
Krrish Dholakia
494b9bbc62 test: fix linting testing 2023-10-19 18:40:33 -07:00
Krrish Dholakia
0c083e7a5c feat(proxy_server.py): add model router to proxy 2023-10-18 17:40:08 -07:00
Krrish Dholakia
204218508d fix(router.py): completing redis support work for router 2023-10-18 12:13:00 -07:00
Krrish Dholakia
168b5a181c fix(test_proxy.py): fix tests 2023-10-17 22:34:12 -07:00
Krrish Dholakia
f23431fdc4 feat(router.py): add routing capabilities for multiple deployments 2023-10-17 22:28:31 -07:00