scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-09 03:18:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 109
17246 commits 3347 branches 1448 tags 5 GiB
Commit graph

17246 commits

This branch
This branch
All branches
Author SHA1 Message Date
Ishaan Jaff
cbef0c0a0d add key_state created at to token 2024-08-26 16:52:33 -07:00
Ishaan Jaff
fb150f7ce5 update schema 2024-08-26 16:52:19 -07:00
Ishaan Jaff
4f8026f44d fix refactor cohere 2024-08-26 16:33:04 -07:00
Krrish Dholakia
0a15d3b3c3 fix(utils.py): fix message replace 2024-08-26 15:43:30 -07:00
Krrish Dholakia
8e9acd117b fix(sagemaker.py): support streaming for messages api 
Fixes https://github.com/BerriAI/litellm/issues/5372
 2024-08-26 15:08:08 -07:00
Ishaan Jaff
71bf5b31b2
Merge pull request #5371 from BerriAI/litellm_vertex_ft_models 
[Feat] Add support for fine tuned vertexai models
 2024-08-26 15:01:23 -07:00
John HU
9a18106745
Add pricing for imagen-3 and imagen-3-fast 2024-08-26 14:41:47 -07:00
Ishaan Jaff
da63775371 use common folder for cohere 2024-08-26 14:28:50 -07:00
Ishaan Jaff
f9ea0d8fa9 refactor cohere to be in a folder 2024-08-26 14:16:25 -07:00
Krrish Dholakia
174b1c43e3 fix(utils.py): support 'PERPLEXITY_API_KEY' in env 2024-08-26 13:59:57 -07:00
Ishaan Jaff
8d9f94ede7 vertex add finetuned models 2024-08-26 13:39:20 -07:00
Krrish Dholakia
8233a20db0 docs: fix dead links 2024-08-26 13:28:25 -07:00
Ishaan Jaff
07a45fc844 add test for test_completion_fine_tuned_model 2024-08-26 13:26:56 -07:00
Ishaan Jaff
3d11b21726 add fine tuned vertex model support 2024-08-26 13:10:04 -07:00
Krrish Dholakia
bea6fb2375 fix(vertex_httpx.py): use special param 2024-08-26 13:08:28 -07:00
Krrish Dholakia
2b40f2eaed test(test_function_calling.py): fix test 2024-08-26 12:18:50 -07:00
Krrish Dholakia
1cbf851ac2 fix(utils.py): fix value check 2024-08-26 12:04:56 -07:00
Krrish Dholakia
8695cf186d fix(main.py): fix linting errors 2024-08-26 11:44:37 -07:00
Krrish Dholakia
b9d1296319 feat(utils.py): support gemini/vertex ai streaming function param usage 2024-08-26 11:23:45 -07:00
Ishaan Jaff
b2bac2bc34 fix link on getting started 2024-08-26 11:06:46 -07:00
Ishaan Jaff
ea4fc4dbf4
Merge pull request #5367 from BerriAI/docs_use_litellm_proxy 
[Docs] use litellm sdk with litellm proxy server
 2024-08-26 11:03:51 -07:00
Ishaan Jaff
6d61c396b3 docs using litellm sdk with litellm proxy 2024-08-26 11:03:33 -07:00
Krrish Dholakia
d13d2e8a62 feat(vertex_httpx.py): support functions param for gemini google ai studio + vertex ai 
Closes https://github.com/BerriAI/litellm/issues/5344
 2024-08-26 10:59:01 -07:00
Ishaan Jaff
68bb735b3b docs use litellm proxy with litellm python sdk 2024-08-26 10:50:24 -07:00
Ishaan Jaff
71739e942a fix qdrant semantic cache 2024-08-26 09:25:59 -07:00
Krrish Dholakia
4e9f66bc7e fix(vertex_httpx.py): return project id, if given 2024-08-26 09:14:04 -07:00
Ishaan Jaff
98c1fb0fbd docs - explain how custom guardrail is mounted 2024-08-26 08:47:01 -07:00
Ishaan Jaff
735eb041b9 ci/cd run again 2024-08-26 08:36:58 -07:00
Krrish Dholakia
4d29c1fb69 fix(vertex_httpx.py): use dynamic project id 2024-08-24 23:34:20 -07:00
Krish Dholakia
87dbdced06
Merge pull request #4582 from BerriAI/litellm_vertex_migration 
refactor(main.py): migrate vertex gemini calls to vertex_httpx
 2024-08-24 19:33:21 -07:00
Krrish Dholakia
64952ab044 fix: fix tests 2024-08-24 19:32:22 -07:00
Krish Dholakia
f27abe0462
Merge branch 'main' into litellm_vertex_migration 2024-08-24 18:24:19 -07:00
Krrish Dholakia
5019e0322f fix(utils.py): fix linting errors 2024-08-24 17:51:59 -07:00
Ishaan Jaff
b2388e3409 test test_cooldown_same_model_name 2024-08-24 17:16:25 -07:00
Krrish Dholakia
5572ad7241 fix(cooldown_cache.py): fix linting errors 2024-08-24 17:11:32 -07:00
Krrish Dholakia
33972cc79c fix(router.py): enable dynamic retry after in exception string 
Updates cooldown logic to cooldown individual models

 Closes https://github.com/BerriAI/litellm/issues/1339
 2024-08-24 16:59:30 -07:00
Ishaan Jaff
366b78f2a5 bump: version 1.44.5 → 1.44.6 2024-08-24 16:46:55 -07:00
Ishaan Jaff
d9769c393e ui new build 2024-08-24 16:45:53 -07:00
Ishaan Jaff
20840eaad3 fix linting errors when adding a new team member 2024-08-24 16:38:43 -07:00
Ishaan Jaff
0ad5f58930
Merge pull request #5357 from BerriAI/ui_allow_setting_tpm_rpm_per_model 
[Feat] Admin UI - allow setting tpm / rpm per model
 2024-08-24 16:28:08 -07:00
Ishaan Jaff
c99914d18e
Merge pull request #5356 from BerriAI/ui_allow_setting_rpm_tpm_on_ui 
Feat - ui allow setting tpm / rpm limits on keys on ui
 2024-08-24 16:27:58 -07:00
Ishaan Jaff
11187920ec
Merge pull request #5352 from BerriAI/litellm_allow_setting_caching_mode 
[Feat-Caching] allow setting caching mode to default off
 2024-08-24 16:27:45 -07:00
Ishaan Jaff
35740da03d
Merge pull request #5354 from BerriAI/vertex_allow_auth 
[Feat-Vertex] Support using  workload identity federation
 2024-08-24 16:27:29 -07:00
Ishaan Jaff
e8b9fbf9f9 fix allow setting per model tpm rpm limits 2024-08-24 15:34:25 -07:00
Krrish Dholakia
76834c6c59 test(test_router.py): add test to ensure retry-after matches received value 2024-08-24 15:21:04 -07:00
Krrish Dholakia
7beb0910c6 test(test_router.py): skip test - create separate pr to match retry after 2024-08-24 15:19:27 -07:00
Krrish Dholakia
756a828c15 fix(azure.py): add response header coverage for azure models 2024-08-24 15:12:51 -07:00
Krrish Dholakia
87549a2391 fix(main.py): cover openai /v1/completions endpoint 2024-08-24 13:25:17 -07:00
Krrish Dholakia
de2373d52b fix(openai.py): coverage for correctly re-raising exception headers on openai chat completion + embedding endpoints 2024-08-24 12:55:15 -07:00
Ishaan Jaff
98d1113e89 ui allow setting tpm / rpm limits on ui 2024-08-24 12:42:39 -07:00