Commit graph

13364 commits

Author SHA1 Message Date
Krrish Dholakia
a93471a3c7 feat(team_endpoints.py): unfurl 'all-proxy-models' on team info endpoints 2025-03-14 16:54:24 -07:00
Krrish Dholakia
08abee1990 fix: fix linting error 2025-03-14 14:17:28 -07:00
Krrish Dholakia
f089b1e23f feat(endpoints.py): support adding credentials by model id
Allows user to reuse existing model credentials
2025-03-14 12:32:32 -07:00
Ishaan Jaff
d67fc03e20 fix endpoint 2025-03-14 12:26:17 -07:00
Krrish Dholakia
605a4d1121 feat(endpoints.py): enable retrieving existing credentials by model name
Enables reusing existing credentials
2025-03-14 12:02:50 -07:00
Ishaan Jaff
c84717c9e0 add health/test_connection 2025-03-14 11:30:24 -07:00
Ishaan Jaff
6742d3cb10 fix route llm request to allow non-router models 2025-03-14 11:10:10 -07:00
Brian Dev
12db28b0af Support 'system' role ollama 2025-03-15 00:55:18 +07:00
Krrish Dholakia
6629354329 fix(endpoints.py): update credentials should update before storing 2025-03-14 10:42:17 -07:00
Krrish Dholakia
fc0d21794d style: cleanup credential from leftnav - now in models tab 2025-03-14 10:14:21 -07:00
Ishaan Jaff
c36e5cae50 backend instant delete model 2025-03-14 10:12:50 -07:00
Lucas Raschek
56d3e75b33 Map total tokens to prompt_tokens too 2025-03-14 18:04:43 +01:00
Ishaan Jaff
c2d290785a ui new build 2025-03-13 21:44:32 -07:00
Ishaan Jaff
276a7089df
Merge pull request #9220 from BerriAI/litellm_qa_responses_api
[Fixes] Responses API - allow /responses and subpaths as LLM API route + Add exception mapping for responses API
2025-03-13 21:36:59 -07:00
Ishaan Jaff
241a36a74f
Merge pull request #9222 from BerriAI/litellm_snowflake_pr_mar_13
[Feat] Add Snowflake Cortex to LiteLLM
2025-03-13 21:35:39 -07:00
Krish Dholakia
f89dbb8ab3
Merge branch 'main' into litellm_dev_03_13_2025_p3 2025-03-13 20:12:16 -07:00
Ishaan Jaff
69b47cf738 fix code quality check 2025-03-13 20:10:41 -07:00
Ishaan Jaff
7827c275ba exception_type 2025-03-13 20:09:32 -07:00
Krish Dholakia
e8c67f25e3
Merge pull request #9221 from BerriAI/litellm_dev_03_13_2025_p2
Support bedrock converse cache token tracking
2025-03-13 20:08:33 -07:00
Krish Dholakia
fd8a5960ec
Merge pull request #9216 from BerriAI/litellm_dev_03_12_2025_contributor_prs_p2
Litellm dev 03 12 2025 contributor prs p2
2025-03-13 20:03:57 -07:00
Krrish Dholakia
58a7351a73 fix: fix linting errors 2025-03-13 19:40:18 -07:00
Krrish Dholakia
8a6e4715aa feat(converse_transformation.py): fix type for bedrock cache usage block 2025-03-13 19:33:22 -07:00
Krrish Dholakia
f2d0aaacbc fix: fix linting errors 2025-03-13 19:26:46 -07:00
Krrish Dholakia
dc3b02920f feat(model_management_endpoints.py): support audit logs on /model/add and /model/update endpoints
complete CUD endpoint audit logging on models + users
2025-03-13 19:17:40 -07:00
Krrish Dholakia
9145e8db77 feat: fix linting errors 2025-03-13 19:00:27 -07:00
Krrish Dholakia
37b30395c9 feat(model_management_endpoints.py): emit audit logs on model delete 2025-03-13 18:48:38 -07:00
Krrish Dholakia
e90b3d9c4c feat(internal_user_endpoints.py): add audit logs on /user/update 2025-03-13 18:17:05 -07:00
Ishaan Jaff
d3781dfe36 fix linting errors 2025-03-13 16:58:34 -07:00
Krrish Dholakia
5cfae0e98a feat(internal_user_endpoints.py): emit audit log on /user/new event 2025-03-13 16:47:58 -07:00
Ishaan Jaff
d7847feba9 Add stubbed routes to pass initial auth tests 2025-03-13 16:43:25 -07:00
Sunny Wan
c942f4cd86 Merge branch 'main' of https://github.com/SunnyWan59/litellm 2025-03-13 19:42:25 -04:00
Sunny Wan
70770b6aa4 Removed unnecessary code and refactored 2025-03-13 19:42:10 -04:00
Sunny Wan
f9a5109203
Merge branch 'BerriAI:main' into main 2025-03-13 19:37:22 -04:00
Krrish Dholakia
0af6cde994 fix(invoke_handler.py): support cache token tracking on converse streaming 2025-03-13 16:10:13 -07:00
Ishaan Jaff
15d618f5b1 Add exception mapping for responses API 2025-03-13 15:57:58 -07:00
Krrish Dholakia
f99b1937db feat(converse_transformation.py): translate converse usage block with cache creation values to openai format 2025-03-13 15:49:25 -07:00
Ishaan Jaff
1ee6b7852f fix exception_type 2025-03-13 15:33:17 -07:00
Krrish Dholakia
997f2f0b3e fix(aim.py): fix linting error 2025-03-13 15:32:42 -07:00
Krrish Dholakia
f17bc60593 test: patch test to avoid lakera changes to sensitivity 2025-03-13 15:18:08 -07:00
Ishaan Jaff
2543e3a902 fix auth add responses API to llm routes 2025-03-13 15:13:07 -07:00
Krrish Dholakia
5ffd3f56f8 fix(azure.py): track azure llm api latency metric 2025-03-13 14:47:35 -07:00
Krrish Dholakia
1cd57e95aa fix: fix linting error 2025-03-13 14:33:19 -07:00
Krrish Dholakia
86ed6be85e fix: fix learnlm test 2025-03-13 10:54:09 -07:00
Krish Dholakia
a2414d09c1
Merge pull request #8356 from hakasecurity/feature/aim-post-call
Aim Security post-call guardrails support
2025-03-13 10:48:42 -07:00
Krish Dholakia
2c011d9a93
Merge pull request #9123 from omrishiv/8911-fix-model-encoding
Fixes bedrock modelId encoding for Inference Profiles
2025-03-13 10:42:32 -07:00
Tomer Bin
6ebf11e4b3 ruff format 2025-03-13 08:58:29 +02:00
Tomer Bin
32dedbe551 CR 2025-03-13 08:54:00 +02:00
Tomer Bin
4a31b32a88 Support post-call guards for stream and non-stream responses 2025-03-13 08:53:54 +02:00
Krrish Dholakia
be35c9a663 docs(reasoning_content.md): clarify 'thinking' param support is from v1.63.0+
All checks were successful
Read Version from pyproject.toml / read-version (push) Successful in 13s
Helm unit test / unit-test (push) Successful in 22s
Fixes https://github.com/BerriAI/litellm/issues/9171
2025-03-12 22:30:57 -07:00
Krish Dholakia
58e5f3e0c9
Merge pull request #9193 from youngchannelforyou/feat/gemini_response_status_code
(gemini)Handle HTTP 201 status code in Vertex AI response
2025-03-12 22:24:01 -07:00