phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity
5077 commits 1603 branches 645 tags 320 MiB
Commit graph

5077 commits

This branch
This branch
All branches
Author SHA1 Message Date
Krrish Dholakia
d0d08b4dce docs(routing.md): adding latency-based routing to docs 2024-01-01 08:36:40 +05:30
ishaan-jaff
d71f89aac3 bump: version 1.16.7 → 1.16.8 2023-12-30 20:25:52 +05:30
ishaan-jaff
c269c65371 (docs) langfuse log trace id, trace user id 2023-12-30 20:25:23 +05:30
ishaan-jaff
84fbc903aa (test) langfuse - set custom trace_id 2023-12-30 20:19:22 +05:30
ishaan-jaff
8ae4554a8a (feat) langfuse - set custom trace_id, trace_user_id 2023-12-30 20:19:03 +05:30
ishaan-jaff
cc7b964433 (docs) add litellm.cache docstring 2023-12-30 20:04:08 +05:30
ishaan-jaff
70cdc16d6f (feat) cache context manager - update cache 2023-12-30 19:50:53 +05:30
ishaan-jaff
bf4a9f40e8 (docs) cache context manager 2023-12-30 19:50:22 +05:30
ishaan-jaff
1c93642951 (docs) caching use context manager 2023-12-30 19:43:26 +05:30
ishaan-jaff
e35f17ca3c (test) caching - context managers 2023-12-30 19:33:47 +05:30
ishaan-jaff
ddddfe6602 (feat) add cache context manager 2023-12-30 19:32:51 +05:30
ishaan-jaff
231148ed73 (docs) caching 2023-12-30 19:04:36 +05:30
Krrish Dholakia
8ff3bbcfee fix(proxy_server.py): router model group alias routing 
check model alias group routing before specific deployment routing, to deal with an alias being the same as a deployment name (e.g. gpt-3.5-turbo)

n
 2023-12-30 17:55:24 +05:30
Krrish Dholakia
027218c3f0 test(test_lowest_latency_routing.py): add more tests 2023-12-30 17:41:42 +05:30
Krrish Dholakia
f2d0d5584a fix(router.py): fix latency based routing 2023-12-30 17:25:40 +05:30
Krrish Dholakia
c41b1418d4 test(test_router_init.py): fix test router init 2023-12-30 16:51:39 +05:30
Krrish Dholakia
3cb7acceaa test(test_least_busy_routing.py): fix test 2023-12-30 16:12:52 +05:30
Krrish Dholakia
3935f99083 test(test_router.py): add retries 2023-12-30 15:54:46 +05:30
Krrish Dholakia
69935db239 fix(router.py): periodically re-initialize azure/openai clients to solve max conn issue 2023-12-30 15:48:34 +05:30
Krrish Dholakia
d089157925 build(model_prices_and_context_window.json): fix text unicorn mapping 2023-12-30 13:38:24 +05:30
Krrish Dholakia
b66cf0aa43 fix(lowest_tpm_rpm_routing.py): broaden scope of get deployment logic 2023-12-30 13:27:50 +05:30
Krrish Dholakia
a6719caebd fix(aimage_generation): fix response type 2023-12-30 12:53:24 +05:30
Krrish Dholakia
750432457b fix(openai.py): fix async image gen call 2023-12-30 12:44:54 +05:30
Krrish Dholakia
2acd086596 test(test_least_busy_routing.py): fix test init 2023-12-30 12:39:13 +05:30
ishaan-jaff
535a547b66 (fix) use cloudflare optional params 2023-12-30 12:22:31 +05:30
Krrish Dholakia
c33c1d85bb fix: support dynamic timeouts for openai and azure 2023-12-30 12:14:02 +05:30
Krrish Dholakia
77be3e3114 fix(main.py): don't set timeout as an optional api param 2023-12-30 11:47:07 +05:30
ishaan-jaff
aee38d9329 (fix) batch_completions - set default timeout 2023-12-30 11:35:55 +05:30
Krrish Dholakia
38f55249e1 fix(router.py): support retry and fallbacks for atext_completion 2023-12-30 11:19:32 +05:30
ishaan-jaff
7ecd7b3e8d (docs) proxy - timeout per request 2023-12-30 11:18:03 +05:30
ishaan-jaff
6252987798 (docs) proxy - set timeout per request 2023-12-30 11:17:31 +05:30
ishaan-jaff
5d6954895f (fix) timeout optional param 2023-12-30 11:07:52 +05:30
ishaan-jaff
523415cb0c (test) dynamic timeout on router 2023-12-30 10:56:07 +05:30
ishaan-jaff
2f4cd3b569 (feat) proxy - support dynamic timeout per request 2023-12-30 10:55:42 +05:30
ishaan-jaff
459ba5b45e (feat) router, add ModelResponse type hints 2023-12-30 10:44:13 +05:30
ishaan-jaff
44fc20a0ff (feat) add cost tracking for voyage ai 2023-12-30 10:02:48 +05:30
ishaan-jaff
0a5f5812df (feat) cloudflare pricing + models 2023-12-30 09:50:57 +05:30
Krrish Dholakia
a34de56289 fix(router.py): handle initial scenario for tpm/rpm routing 2023-12-30 07:28:45 +05:30
Krish Dholakia
05795ead59
Merge pull request #1277 from AshGreh/patch-1 
Adds support for Vertex AI Unicorn
 2023-12-30 06:46:49 +05:30
Ash Greh
f23f227087
Update model_prices_and_context_window.json 
Corrected the math.
 2023-12-29 20:53:39 -04:00
Ash Greh
b0aea659bc
Update model_prices_and_context_window.json 
Adds simplified name for Unicorn.
 2023-12-29 20:47:12 -04:00
Ash Greh
4b8a1800c9
Update model_prices_and_context_window.json 
Adds support for unicorn
 2023-12-29 20:45:25 -04:00
Krish Dholakia
88a38d9c82
Merge pull request #1275 from marmikcfc/feature/add-response-format-for-mistral 
add support for mistral json mode via anyscale
 2023-12-29 23:10:52 +05:30
Marmik Pandya
1426594d3f add support for mistral json mode via anyscale 2023-12-29 22:26:22 +05:30
Krrish Dholakia
2fc264ca04 fix(router.py): fix int logic 2023-12-29 20:41:56 +05:30
Krrish Dholakia
cf91e49c87 refactor(lowest_tpm_rpm.py): move tpm/rpm based routing to a separate file for better testing 2023-12-29 18:33:43 +05:30
Krrish Dholakia
54d7bc2cc3 test(test_least_busy_router.py): add better testing for least busy routing 2023-12-29 17:16:00 +05:30
Krrish Dholakia
678bbfa9be fix(least_busy.py): support consistent use of model id instead of deployment name 2023-12-29 17:05:26 +05:30
ishaan-jaff
06e4b301b4 (test) gemini-pro-vision cost tracking 2023-12-29 16:31:28 +05:30
ishaan-jaff
739d9e7a78 (fix) vertex ai - use usage from response 2023-12-29 16:30:25 +05:30