ai-workspace-services/litellm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
30,881 Commits 9 Branches 7 Tags 935 MiB
12bc66aa5b
Commit Graph

30881 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Krrish Dholakia
dd663f80ce feat(ollama/chat): ensure content is str - even when input is list[str] 
Fixes https://github.com/BerriAI/litellm/issues/14217
 2025-09-12 17:41:25 -07:00
Arseny Boykov
f4318bccd3
[Performance] Use _PROXY_MaxParallelRequestsHandler_v3 by default again (#14450) 
* Use _PROXY_MaxParallelRequestsHandler_v3 by default (#14352)

(cherry picked from commit f3fa45cf8fbd5f5cce2f45a7312776d5005fb08e)
(cherry picked from commit 5b680bb4a3)

* Use random api_key for parallel requests test

* Fix off-by-one error in parallel request rate limit

The rate limiter was incorrectly rejecting requests when the limit was met, but not exceeded. The check in `is_cache_list_over_limit` was `int(counter_value) + 1 > current_limit`, which caused the first request to be rejected if the limit was 1.

This commit removes the `+ 1`, changing the logic to `int(counter_value) > current_limit`. The check now correctly allows requests up to the specified parallel limit.

* Test actual parallel requests

* Ensure rate limiting works correctly for multiple users

* Add sequential rate-limit test

* Revert random key usage
 2025-09-12 17:33:55 -07:00
Krrish Dholakia
82091de393 feat(hosted_vllm/): transcription endpoint support 
Closes https://github.com/BerriAI/litellm/issues/361#issuecomment-3244548055
 2025-09-12 17:15:14 -07:00
Krrish Dholakia
1bbbacea00 fix(key_management_endpoints.py): correctly raise an error when tags set on /key/update by non-premium user 
Closes https://github.com/BerriAI/litellm/issues/14366
 2025-09-12 15:50:29 -07:00
boopesh07
36299dbc73 Added user_email labels to the prometheus monitoring. 2025-09-12 15:38:23 -07:00
Ishaan Jaff
e87e50328e
[Feat] Bedrock Batches - Working e2e flow to upload file + create batch (#14518) 
* fix: bedrock batches transform

* fix: upload_url

* fixes for model name

* fix upload_url

* fix bedrock batch test

* test_mock_bedrock_file_url_mapping
 2025-09-12 15:37:09 -07:00
Yuta Saito
1de7f076ac feat: add tool-permission guardrail 2025-09-13 07:34:29 +09:00
Tim Elfrink
b84785b5b7 fix(lm_studio): resolve illegal Bearer header value issue 
- Change default API key from space ' ' to 'fake-api-key'
- Fixes httpcore.LocalProtocolError: Illegal header value b'Bearer  '
- Maintains compatibility with explicit API keys and environment variables
- Add comprehensive tests for provider info retrieval

Fixes #14502
 2025-09-12 22:41:30 +02:00
Ishaan Jaff
18372f9ebe
Revert "fix vertex ai file upload" (#14501) 2025-09-12 12:02:24 -07:00
Sameerlite
fa175e8d90
Fix gemini cli error (#14417) 
* Fix gemini cli error

* Added better handling

---------

Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
 2025-09-12 11:56:51 -07:00
Sameer Kankute
1a123b2cd5
Litellm gemini cli bug fix (#14451) 
* Fix gemini cli error

* Add reasoning request support

* Added better handling

* remove other PR code

* refactored code for better structure following

---------

Co-authored-by: sameer@berri.ai <sameer@berri.ai>
 2025-09-12 11:55:26 -07:00
Boopesh Shanmugam
8b338a4d8c
User Headers X LiteLLM Users Mapping feature (#14485) 
* Draft commit.

* user header mapping feature with backward compatibility with user_header_name field.

* user header mapping feature with backward compatibility with user_header_name field optimizations.

* Added unit tests.
 2025-09-12 11:49:37 -07:00
Luis Felipe Salazar Ucros
e15327ba96 add sambanova deepseek v3.1 and gpt-oss-120b 2025-09-12 18:31:17 +00:00
Fabrício Ceschin
dae5b0f0f3
Merge branch 'BerriAI:main' into LangfuseUsageDetails 2025-09-12 09:49:10 -04:00
Elias TOURNEUX
54f49b430d
fix: edit readme to add OVHCloud 2025-09-12 14:29:33 +02:00
Elias TOURNEUX
ef9d1ddc40
feat: Add OVHCloud AI Endpoints as a provider 2025-09-12 13:37:03 +02:00
rasmus.arpe@gmail.com
b8c362e443 add tests for the fix 2025-09-12 12:07:08 +02:00
rasmus.arpe@gmail.com
a1b339efb5 fix: fix soft budget crossed alert 2025-09-12 12:07:08 +02:00
Krish Dholakia
f8036a25a2
Merge pull request #14455 from lmnr-ai/fix/async-logging-tasks-context 
propagate execution context into logging tasks
 2025-09-12 00:36:08 -07:00
Krish Dholakia
113d2a8c5a
Merge pull request #14459 from holzman/fix-provider-budget 
Fix provider budgets
 2025-09-12 00:34:52 -07:00
Krish Dholakia
0413a701a2
Merge pull request #14460 from Sameerlite/litellm_vertex_gcs_bucket_issue 
fix vertex ai file upload
 2025-09-12 00:04:21 -07:00
Ishaan Jaff
f374103c46 UI new build 2025-09-11 20:20:52 -07:00
Krrish Dholakia
c802c472b5 docs(debugging.md): document new feature 
Closes https://github.com/BerriAI/litellm/issues/13814
 2025-09-11 20:17:39 -07:00
Ishaan Jaff
698a2dd382 fix: convert_anthropic_tool_to_databricks_tool 2025-09-11 20:12:01 -07:00
Ishaan Jaff
32d87c242b
[Fixes] Using Qwen API Tiered Pricing (#14479) 
* fix: use dashscope cost calc

* add qwen logo
 2025-09-11 20:07:41 -07:00
Krrish Dholakia
48619f2b7b fix(litellm_logging.py): support emitting raw response on self.litellm_request_debug is true 
Addresses https://github.com/BerriAI/litellm/issues/13814
 2025-09-11 20:07:26 -07:00
Ishaan Jaff
1e230e87e3 fixes for mypy 2025-09-11 20:05:29 -07:00
Krrish Dholakia
d89152bb2c feat(litellm_logging.py): support new litellm debug parameter - litellm_request_debug on requests 
enables printing raw request when flag is set to true on requests
 2025-09-11 20:04:24 -07:00
Ishaan Jaff
94038108ad fix dashscope api base 2025-09-11 20:00:54 -07:00
Ishaan Jaff
69ef062f55 fix tiered_pricing test 2025-09-11 19:56:44 -07:00
Ishaan Jaff
51d5255452
[Bug]: Azure OpenAI & AI Foundry Reject Image Generation Payload Due to extra_body Injection in LiteLLM v1.76.3 (#14475) 
* add request body azure img gen

* fix test_get_optional_params_image_gen_filters_empty_values

* test_azure_image_generation_request_body

* test_azure_image_generation_request_body
 2025-09-11 19:39:06 -07:00
Krrish Dholakia
0c8b311155 test: add unit testing for both flows on key unblock 2025-09-11 19:15:15 -07:00
Krrish Dholakia
0f6898ad0a fix(key_management_endpoints.py): check if key is a hashed token or sk key before lookup 
Fixes https://github.com/BerriAI/litellm/issues/13887
 2025-09-11 19:10:00 -07:00
Krrish Dholakia
805069c287 fix(adapters/streaming_iterator.py): Don't send content block after message delta block is sent 
Fixes https://github.com/BerriAI/litellm/issues/14315
 2025-09-11 18:52:02 -07:00
Ishaan Jaff
dda115cc6d
[Feat] Cost Tracking - Add support for Tiered Cost Tracking for Qwen API (Dashscope) (#14471) 
* add dashscope logo

* docs fix

* docs fix

* fix supports_batch_calling

* fix naming

* fix input_cost_per_audio_token

* use output_cost_per_reasoning_token

* add tiered_pricing in get_model_info

* test fixes

* fix cost calc

* ruff fix
 2025-09-11 18:14:39 -07:00
Krrish Dholakia
54e71bd077 fix(common_utils.py): add helpful message 2025-09-11 16:10:13 -07:00
Krrish Dholakia
d0732f55b3 test(test_get_azure_ad_token_provider.py): add unit test to ensure default azure credentials used in the right context 2025-09-11 16:07:32 -07:00
Krrish Dholakia
84a7329dba fix(secret_managers/get_azure_Ad_token_providers.py): infer credential type from env var 
don't default to ClientSecretCredential unless present in env var
 2025-09-11 16:04:06 -07:00
Krrish Dholakia
3f3efea301 test(test_gemini.py): add additional testing for additionalproperties case 2025-09-11 15:12:21 -07:00
Krish Dholakia
b1025b54fb
Merge pull request #14466 from BerriAI/revert-14252-main 
Revert "Add additionalProperties to vertex ai Schema definition"
 2025-09-11 14:38:57 -07:00
Krish Dholakia
5c3d407b7a
Revert "Add additionalProperties to vertex ai Schema definition" 2025-09-11 14:38:25 -07:00
Sashanken
c6626559a2 Fixed Log Tab Key Alias filtering inaccurately for failed logs 2025-09-11 13:05:48 -07:00
Burt Holzman
e9e548d797 Fix provider budgets 2025-09-11 12:08:43 -05:00
Sameer Kankute
090e0fddf4 fix vertex ai file upload 2025-09-11 22:20:54 +05:30
Din
ee5a9d0aa0 propagate execution context into logging tasks 2025-09-11 15:54:40 +01:00
Fabrício Ceschin
5cb5268e43
Merge branch 'BerriAI:main' into LangfuseUsageDetails 2025-09-11 10:15:22 -04:00
Vedran Vidović
e6a6300b70 Describing the labels field use in the Vertex AI 2025-09-11 15:28:55 +02:00
Tom Alon
b83b497d38 PR fixes 2025-09-11 13:38:06 +03:00
Tom Alon
b473344f70 Implement anonymization logic 2025-09-11 11:47:19 +03:00
drorbaron
2ee8c0c6d7 rename aim headers + tests 2025-09-11 11:19:58 +03:00