Alexsander Hamir 56328e6535 [Refactor#2] litellm/init – Lazy-load utils to reduce memory + import time (#17171) ... * fix: lazy load utils.py imports Lazy-load most functions and response types from utils.py to avoid loading tiktoken and other heavy dependencies at import time. This significantly reduces memory usage when importing completion from litellm.		2025-12-03 11:40:16 -08:00
..
anthropic_interface	[Feat] Allow using litellm.completion with /v1/messages API Spec (use gpt-4, gemini etc with claude code) (#11502)	2025-06-06 20:35:53 -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	(code quality) run ruff rule to ban unused imports (#7313)	2024-12-19 12:33:42 -08:00
batches	Guardrails API - add streaming support (#17400)	2025-12-02 22:52:09 -08:00
caching	fix redis event loop closed at first call (#16913)	2025-11-21 19:15:56 -08:00
completion_extras	Refactor Noma guardrail to use shared Responses transformation and include system instructions (#17315)	2025-12-01 19:56:14 -08:00
containers	Add E2E Container API Support (#16136)	2025-11-01 14:03:51 -07:00
endpoints/speech/speech_to_completion_bridge	fix: fix import errors	2025-09-14 09:32:21 -07:00
experimental_mcp_client	[Feat] mcp resources support (#16800)	2025-11-20 14:53:44 -08:00
files	[Feat] Add vllm batch+files API support (#15823)	2025-12-02 08:41:50 -08:00
fine_tuning	Litellm managed file updates combined (#11040)	2025-05-22 17:20:41 -07:00
google_genai	fix test /generateContent route	2025-10-04 10:49:46 -07:00
images	[Refactor#2] litellm/init – Lazy-load utils to reduce memory + import time (#17171)	2025-12-03 11:40:16 -08:00
integrations	Guardrails API - add streaming support (#17400)	2025-12-02 22:52:09 -08:00
litellm_core_utils	Merge pull request #17350 from BerriAI/litellm_rag_chat_completion_api	2025-12-03 13:29:32 +05:30
llms	[Refactor#2] litellm/init – Lazy-load utils to reduce memory + import time (#17171)	2025-12-03 11:40:16 -08:00
ocr	[Feat] /ocr - Add VertexAI OCR provider support + cost tracking (#16216)	2025-11-03 15:56:49 -08:00
passthrough	fix bedrock passthrough auth issue (#16879)	2025-11-24 18:44:59 -08:00
proxy	Merge pull request #17379 from BerriAI/litellm_login_route_refactor	2025-12-03 11:32:16 -08:00
rag	[Feat] RAG API - QA - allow internal user keys to access api, allow using litellm credentials with API, raise clear exception when RAG API fails (#17169)	2025-11-26 17:07:30 -08:00
realtime_api	fix: tested e2e implementation and added sample config.	2025-11-26 12:37:13 +00:00
rerank_api	[Feat] Add Nvidia NIM Rerank Support (#15152)	2025-10-02 18:58:52 -07:00
responses	Fix: litellm user auth not passing issue	2025-12-02 11:25:32 +05:30
router_strategy	fix: add None check for litellm_params (#16754)	2025-11-17 19:44:29 -08:00
router_utils	fix fallback handlers	2025-11-26 12:39:17 -08:00
search	[Bug Fix] Exa Search API - ensure request params are sent to Exa AI (#15855)	2025-10-23 11:56:30 -07:00
secret_managers	[Feat] Adds IAM role assumption support for AWS Secret Manager (#16887)	2025-11-20 12:38:48 -08:00
skills	[Feat] New API - Claude Skills API (Anthropic) (#17042)	2025-11-24 15:01:40 -08:00
types	fixing optional parameter default value (#17434)	2025-12-03 11:24:32 -08:00
vector_store_files	Vector store files Stable Release (#16643)	2025-11-15 13:00:33 -08:00
vector_stores	Add method for extracting vector store ids from path params (#16566)	2025-11-26 14:19:30 -08:00
videos	Add Vertex and Gemini Videos API with Cost Tracking + UI support (#16323)	2025-11-08 16:03:51 -08:00
__init__.py	[Refactor#2] litellm/init – Lazy-load utils to reduce memory + import time (#17171)	2025-12-03 11:40:16 -08:00
_lazy_imports.py	[Refactor#2] litellm/init – Lazy-load utils to reduce memory + import time (#17171)	2025-12-03 11:40:16 -08:00
_logging.py	[Feat] Add support for returning images with gemini/gemini-2.5-flash-image-preview with /chat/completions (#13983)	2025-08-27 16:16:19 -07:00
_redis.py	fix: Apply max_connections configuration to Redis async client (#15797)	2025-10-22 09:19:08 -07:00
_service_logger.py	[⚡️ Python SDK import] - reduce python sdk import time by .3s (#12140)	2025-06-28 14:57:10 -07:00
_uuid.py	Fix: revert fastuuid optional dependency, always use fastuuid in .__uid helper (#14941)	2025-09-26 09:14:20 -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	fix: prevent memory leak in aiohttp connection pooling (#17388)	2025-12-03 10:43:27 -08:00
cost.json
cost_calculator.py	Add cost tracking and logging support	2025-11-25 17:14:59 +05:30
exceptions.py	Adds support for returning Azure Content Policy error information when exceptions from Azure OpenAI occur (#16231)	2025-11-08 16:04:36 -08:00
main.py	[Refactor#2] litellm/init – Lazy-load utils to reduce memory + import time (#17171)	2025-12-03 11:40:16 -08:00
model_prices_and_context_window_backup.json	Fix bedrock models in model map	2025-12-03 17:31:20 +05:30
mypy.ini	fix mypy	2025-09-27 12:21:32 -07:00
py.typed
router.py	[Feat] New API - Claude Skills API (Anthropic) (#17042)	2025-11-24 15:01:40 -08:00
scheduler.py	Squashed commit of the following: (#9709)	2025-04-02 21:24:54 -07:00
timeout.py	Litellm ruff linting enforcement (#5992)	2024-10-01 19:44:20 -04:00
utils.py	Add vector store support for ragflow	2025-12-03 15:29:47 +05:30