litellm/litellm
2025-06-04 18:38:02 -07:00
..
anthropic_interface [Refactor] Anthropic /v1/messages endpoint - Refactor to use base llm http handler and transformations (#10677) 2025-05-08 17:56:50 -07:00
assistants Contributor PR - Support OPENAI_BASE_URL in addition to OPENAI_API_BASE (#9995) (#10423) 2025-04-29 21:27:37 -07:00
batch_completion
batches fix(router.py): write file to all deployments (#10708) 2025-05-10 00:08:30 -07:00
caching [Feat] Performance - Don't create 1 task for every hanging request alert (#11385) 2025-06-03 21:12:54 -07:00
experimental_mcp_client
files Litellm Unified File ID output file id support (#10713) 2025-05-10 11:02:09 -07:00
fine_tuning Litellm managed file updates combined (#11040) 2025-05-22 17:20:41 -07:00
images test: update tests 2025-05-24 12:26:31 -07:00
integrations update GCSBucketBase to handle GSM project ID if passed (#11409) 2025-06-04 10:02:26 -07:00
litellm_core_utils Anthropic - pass file url's as Document content type + Gemini - cache token tracking on streaming calls (#11387) 2025-06-03 21:36:49 -07:00
llms Add User ID validation to ensure it is not an email or phone number (#10102) 2025-06-04 18:38:02 -07:00
passthrough build(VLLM-Passthrough-with-loadbalancing-support-(enables-using-model-list-for-VLLM-/classify-endpoint)): Closes #11205 2025-05-31 09:00:04 -07:00
proxy Litellm dev 06 03 2025 p3 (#11388) 2025-06-03 22:35:51 -07:00
realtime_api Gemini Multimodal Live API support (#10841) 2025-05-15 22:39:09 -07:00
rerank_api
responses [Fix] Responses API - Session management (#11254) 2025-05-29 20:36:02 -07:00
router_strategy Rate Limiting: Check all slots on redis, Reduce number of cache writes (#11299) 2025-05-31 18:32:13 -07:00
router_utils Codestral - return litellm latency overhead on /v1/completions + Add '__contains__' support for ChatCompletionDeltaToolCall (#10879) 2025-05-27 16:13:44 -07:00
secret_managers fix(secret-managers): Break AzureCredentialType restriction on AZURE_CREDENTIAL (#11272) 2025-05-31 01:03:08 -07:00
types Anthropic - pass file url's as Document content type + Gemini - cache token tracking on streaming calls (#11387) 2025-06-03 21:36:49 -07:00
vector_stores [Fix] QA Fixes - Vector Store Object Permissions (#11291) 2025-05-31 09:41:05 -07:00
__init__.py fixes: expose flag to disable token counter (#11344) 2025-06-02 21:53:08 -07:00
_logging.py fix debug logs 2025-05-06 14:28:20 -07:00
_redis.py Squashed commit of the following: (#9709) 2025-04-02 21:24:54 -07:00
_service_logger.py [Feat] - Add Support for Showing Passthrough endpoint Error Logs on LiteLLM UI (#10990) 2025-05-20 18:29:39 -07:00
_version.py Virtual key based policies in Aim Guardrails (#9499) 2025-04-01 21:57:23 -07:00
budget_manager.py Squashed commit of the following: (#9709) 2025-04-02 21:24:54 -07:00
constants.py Support returning virtual key in custom auth + Handle provider-specific optional params for embedding calls (#11346) 2025-06-03 07:24:13 -07:00
cost_calculator.py Litellm dev 06 03 2025 p3 (#11388) 2025-06-03 22:35:51 -07:00
cost.json
exceptions.py [Feat] Add Lakera v2 Guardrail Support (#10880) 2025-05-16 17:08:21 -07:00
main.py [Feat] DD Trace - Add instrumentation for streaming chunks (#11338) 2025-06-02 16:48:39 -07:00
model_prices_and_context_window_backup.json build: cascade budget changes 2025-06-03 21:02:19 -07:00
mypy.ini fix linting errors from ryptography.hazmat.bindings._rust 2025-05-17 16:31:30 -07:00
py.typed
router.py build(VLLM-Passthrough-with-loadbalancing-support-(enables-using-model-list-for-VLLM-/classify-endpoint)): Closes #11205 2025-05-31 09:00:04 -07:00
scheduler.py Squashed commit of the following: (#9709) 2025-04-02 21:24:54 -07:00
timeout.py
utils.py Support returning virtual key in custom auth + Handle provider-specific optional params for embedding calls (#11346) 2025-06-03 07:24:13 -07:00