litellm/litellm
Ishaan Jaff b8e404dd95
[Feat] Backend Router - Add Auto-Router powered by semantic-router (#12955)
* add router.json

* test_router_auto_router

* async_pre_routing_hook

* fixes for auto router

* add async_pre_routing_hook

* add LiteLLMRouterEncoder

* update test auto_router_embedding_model

* add auto_router_embedding_model

* add AutoRouter

* fix async_pre_routing_hook

* update async_pre_routing_hook

* fix auto router

* fix router.json

* working router init

* working embedding encoder

* working auto router

* test_router_auto_router

* test auto router

* add semantic-router as optional for litellm

* add extras

* semantic_router==0.1.10

* ruff fix

* use aiohttp==3.10.11

* python-dotenv==1.0.1

* test auto router

* test_router_auto_router

* semantic_router

* test_is_auto_router_deployment

* fix check

* fix docker build step

* add semantic_router

* Revert "add semantic_router"

This reverts commit 537b67288798731a119d811f643b682086377ee9.
2025-07-24 18:32:56 -07:00
..
anthropic_interface
assistants
batch_completion
batches UI - Support 'batch' model health checks + make 'team-only' model concept clearer (#12770) 2025-07-19 14:30:38 -07:00
caching [LLM Translation - Redis] fix: redis caching for embedding response models (#12750) 2025-07-18 16:31:10 -07:00
completion_extras fix: remove unused imports in completion_extras transformation (#12655) 2025-07-16 10:23:13 -07:00
endpoints/speech/speech_to_completion_bridge
experimental_mcp_client [Feat] MCP Gateway - allow using MCPs with all LLM APIs when using /responses with LiteLLM (#12546) 2025-07-15 14:06:31 -07:00
files
fine_tuning
google_genai /streamGenerateContent - non-gemini model support (#12647) 2025-07-18 10:56:29 -07:00
images [Feat] Add Recraft Image Generation API Support - New LLM Provider (#12832) 2025-07-21 22:19:58 -07:00
integrations [Feat] Backend Router - Add Auto-Router powered by semantic-router (#12955) 2025-07-24 18:32:56 -07:00
litellm_core_utils [Feat] - Track cost + add tags for health checks done by LiteLLM Proxy (#12880) 2025-07-22 18:45:57 -07:00
llms fix morph api tests 2025-07-22 18:44:44 -07:00
passthrough
proxy fix(internal_user_endpoints.py): delete member from team table on /user/delete (#12926) 2025-07-24 16:42:28 -07:00
realtime_api
rerank_api Add Hosted VLLM rerank provider integration (#12738) 2025-07-18 10:55:50 -07:00
responses [Feat] MCP Gateway - allow using MCPs with all LLM APIs when using /responses with LiteLLM (#12546) 2025-07-15 14:06:31 -07:00
router_strategy [Feat] Backend Router - Add Auto-Router powered by semantic-router (#12955) 2025-07-24 18:32:56 -07:00
router_utils Fix async retryer on .acompletion() + forward clientside headers - filter out content-type from clientside request (causes llm api call to hang) (#12886) 2025-07-22 19:50:05 -07:00
secret_managers Revert "Litellm dev 07 21 2025 p1 (#12848)" 2025-07-22 18:28:36 -07:00
types [Feat] Backend Router - Add Auto-Router powered by semantic-router (#12955) 2025-07-24 18:32:56 -07:00
vector_stores [Feat] LLM API Endpoint - Expose OpenAI Compatible /vector_stores/{vector_store_id}/search endpoint (#12749) 2025-07-18 18:18:53 -07:00
__init__.py ci/cd new release 2025-07-23 13:50:36 -07:00
_logging.py
_redis.py
_service_logger.py
_version.py
budget_manager.py
constants.py [Feat] - Track cost + add tags for health checks done by LiteLLM Proxy (#12880) 2025-07-22 18:45:57 -07:00
cost_calculator.py fix recraft cost calc 2025-07-22 18:12:12 -07:00
cost.json
exceptions.py
main.py Fix async retryer on .acompletion() + forward clientside headers - filter out content-type from clientside request (causes llm api call to hang) (#12886) 2025-07-22 19:50:05 -07:00
model_prices_and_context_window_backup.json [UI] Allow setting up CloudZero Usage through LiteLLM UI (#12923) 2025-07-23 21:17:12 -07:00
mypy.ini
py.typed
router.py [Feat] Backend Router - Add Auto-Router powered by semantic-router (#12955) 2025-07-24 18:32:56 -07:00
scheduler.py
timeout.py
utils.py Revert "Litellm dev 07 21 2025 p1 (#12848)" 2025-07-22 18:28:36 -07:00