Commit graph

24591 commits

Author SHA1 Message Date
Philip Kiely
5fa4a18073 add testing and remove redundant function 2025-08-21 11:25:26 -07:00
Luiz Rennó Costa
f8711200d0 fix: fixing descriptor/response size difference when indexing descriptor 2025-08-21 13:43:23 -03:00
Michal Otmianowski
a6f052882b fix test 2025-08-21 12:10:29 +02:00
Michal Otmianowski
d53dd58c4d remove unnecessary comments 2025-08-21 11:39:08 +02:00
Michal Otmianowski
feae09da5d minor adjustments 2025-08-21 11:33:11 +02:00
Michal Otmianowski
5dd7e00127 formatting adjustments 2025-08-21 11:27:12 +02:00
Michal Otmianowski
08c942c306 refactor tests 2025-08-21 10:38:43 +02:00
Michal Otmianowski
744dca1dc3 init asyc implementation 2025-08-21 10:22:54 +02:00
Jan Kessler
3eecff44c6
fix permission access on prisma migrate in non-root image 2025-08-21 09:00:55 +02:00
Krish Dholakia
0e6e8af1c3
Merge pull request #13795 from TomeHirata/feat/predict/mlflow
Include predicted output in MLflow tracing
2025-08-20 22:40:33 -07:00
Krish Dholakia
1f84451925
Merge pull request #13803 from UlookEE/fix_bedrock_epc_acompletion
fix : Synchronize cache behavior between acompletion and completion
2025-08-20 22:38:30 -07:00
Krish Dholakia
ff267ab68e
Merge pull request #13820 from kankute-sameer/litellm_rerank_deepinfra_endpoint
Add rerank endpoint support for deepinfra
2025-08-20 22:33:25 -07:00
Krish Dholakia
609679ded4
Merge pull request #13835 from 0x-fang/fix_api_key_guardrail_proxy
Fix(bedrock): fix the api key support for bedrock guardrail in proxy
2025-08-20 22:31:17 -07:00
Krrish Dholakia
dba78046b9 fix(internal_user_endpoints.py): show remaining users when free SSO users is enabled 2025-08-20 22:26:01 -07:00
Krrish Dholakia
046a7ae906 feat(ui_sso.py): initial commit adding free SSO for up to 5 users
Fixes https://github.com/BerriAI/litellm/issues/13031
2025-08-20 21:46:34 -07:00
Ishaan Jaff
07f6235730
[Performance] Improve LiteLLM Python SDK RPS by +200 RPS (#13839)
* fix _proxy_from_env +100 RPS

* fix: global_braintrust_http_handler

* test_braintrust_logging
2025-08-20 21:46:33 -07:00
Krrish Dholakia
ebab77e7ce build(model_prices_and_context_window.json): remove retired dbrx model 2025-08-20 21:27:06 -07:00
Krrish Dholakia
ea39094658 build(model_prices_and_context_window.json): remove deprecated model from model cost map 2025-08-20 21:24:18 -07:00
Krish Dholakia
b9621c760d
Merge pull request #13836 from BerriAI/litellm_dev_08_16_2025_p1
Add OTEL tracing for actual LLM API call
2025-08-20 19:10:10 -07:00
Fang Gong
91040b6b56 fix the api key support for bedrock guardrail in proxy 2025-08-20 18:46:00 -07:00
Krrish Dholakia
34ad646101 fix(auth_checks.py): handle both flows + add unit tests 2025-08-20 16:42:08 -07:00
Krrish Dholakia
e5c3e006c2 fix(proxy_server.py): fix merge config + db router settings logic 2025-08-20 16:33:31 -07:00
Krrish Dholakia
52cbedf044 fix(auth_checks.py): ensure if key has access to aliased model, it still works 2025-08-20 15:36:32 -07:00
Krrish Dholakia
b0c98efd14 fix(__init__.py): remove redundant value 2025-08-20 15:10:58 -07:00
Krrish Dholakia
5c1b27af99 docs(quick_start.md): add back to navbar
useful for showing setup via cli
2025-08-20 15:09:19 -07:00
Krrish Dholakia
fb5b2d8d47 docs: remove old doc
prevent showing up on searches
2025-08-20 15:01:32 -07:00
Ishaan Jaff
55dcaded72
[Feat] Add VertexAI qwen API Service (#13828)
* add support for vertex AI QWEN API

* streaming QWEN API support

* test_partner_models_httpx

* test_partner_models_httpx_streaming

* add cost tracking for vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maa

* docs qwen models vertexAI
2025-08-20 15:00:33 -07:00
tanjiro
5299e9ad4a
fix key edit settings after regenerating key (#13815) 2025-08-20 14:34:38 -07:00
tanjiro
f7a3af5cde
new notifications (#13813) 2025-08-20 14:32:04 -07:00
Ishaan Jaff
6f6fd0de0d
add fireworks_ai/accounts/fireworks/models/deepseek-v3-0324 (#13821) 2025-08-20 14:31:24 -07:00
Sameer Kankute
5b5a2d12a8 remove test 2025-08-21 00:32:16 +05:30
Sameer Kankute
1d1d637ac0 fix automated checks 2025-08-21 00:09:17 +05:30
Sameer Kankute
37b84d1582 Add rerank endpoint support for deepinfra 2025-08-20 23:36:05 +05:30
Ishaan Jaff
12bae8fdda test_partner_models_httpx_streaming 2025-08-20 09:44:47 -07:00
Ishaan Jaff
e69a895884 test_apply_default_settings 2025-08-20 08:53:38 -07:00
Ishaan Jaff
45a9af8063 security fix 2025-08-20 08:40:49 -07:00
Ishaan Jaff
e229a6a796 security fix 2025-08-20 08:35:59 -07:00
Qingchuan Hao
f2a6be390b feat(utils.py): accept 'api_version' as param for validate_environment 2025-08-20 14:29:58 +00:00
hgyun.lee
036b358636 Synchronize cache behavior between acompletion and completion 2025-08-20 18:27:36 +09:00
Fang Gong
d2b943f391 fix application inference profile for pass-through endpoints for bedrock 2025-08-20 01:06:29 -07:00
Fang Gong
fe51647e3c fix application inference profile for pass-through endpoints for bedrock 2025-08-20 01:03:49 -07:00
Fang Gong
caad9b3ca7 fix application inference profile for pass-through endpoints for bedrock 2025-08-20 00:40:43 -07:00
Tomu Hirata
5879f6e930 comment 2025-08-20 15:46:53 +09:00
Tomu Hirata
c1dbd1c2c1 remove comment
Signed-off-by: Tomu Hirata <tomu.hirata@gmail.com>
2025-08-20 15:42:26 +09:00
Tomu Hirata
d64b579131 Include predicted output in tracing
Signed-off-by: Tomu Hirata <tomu.hirata@gmail.com>
2025-08-20 15:39:32 +09:00
Tim Elfrink
972d7f7133 Merge branch 'main' of https://github.com/BerriAI/litellm into feat/github-copilot-thinking-reasoning-support 2025-08-20 07:58:11 +02:00
Krish Dholakia
4df07a5060
Merge pull request #13622 from BerriAI/fix-passthrough-deletion-failure
Fix query passthrough deletion
2025-08-19 22:34:07 -07:00
Krish Dholakia
bfe814f981
Merge pull request #13637 from Tasmay-Tibrewal/main
Added Qwen3, Deepseek R1 0528 Throughput, GLM 4.5 and GPT-OSS models for Together AI
2025-08-19 22:33:17 -07:00
Krish Dholakia
749bafc550
Merge pull request #13660 from BerriAI/litellm_azure_gpt-t
[LLM Translation] Adjust max_input_tokens for azure/gpt-5-chat models in JSON configuration
2025-08-19 22:32:56 -07:00
Krish Dholakia
04feaf33c0
Merge pull request #13748 from hakasecurity/migrate-to-aim-new-firewall-api
Migrate to aim new firewall api
2025-08-19 22:32:22 -07:00