Ishaan Jaff 86cdb8382b [Feat] Use aiohttp transport by default - 97% lower median latency (#11097) ...

* fix: add flag for disabling use_aiohttp_transport

* feat: add _create_async_transport

* feat: fixes for transport

* add httpx-aiohttp

* feat: fixes for transport

* refactor: fixes for transport

* build: fix deps

* fixes: test fixes

* fix: ensure aiohttp does not auto set content type

* test: test fixes

* feat: add LiteLLMAiohttpTransport

* fix: fixes for responses API handling

* test: fixes for responses API handling

* test: fixes for responses API handling

* feat: fixes for transport

* fix: base embedding handler

* test: test_async_http_handler_force_ipv4

* test: fix failing deepeval test

* fix: add YARL for bedrock urls

* fix: issues with transport

* fix: comment out linting issues

* test fix

* test: XAI is unstable

* test: fixes for using respx

* test: XAI fixes

* test: XAI fixes

* test: infinity testing fixes

* docs(config_settings.md): document param

* test: test_openai_image_edit_litellm_sdk

* test: remove deprecated test

* bump respx==0.22.0

* test: test_xai_message_name_filtering

* test: fix anthropic test after bumping httpx

* use n 4 for mapped tests (#11109)

* fix: use 1 session per event loop

* test: test_client_session_helper

* fix: linting error

* fix: resolving GET requests on httpx 0.28.1

* test fixes proxy unit tests

* fix: add ssl verify settings

* fix: proxy unit tests

* fix: refactor

* tests: basic unit tests for aiohttp transports

* tests: fixes xai

---------

Co-authored-by: Krrish Dholakia <krrishdholakia@gmail.com>

2025-05-23 22:55:35 -07:00

..

gcs_pub_sub_body

[UI] - Add Guardrail Tracing to LiteLLM SpendLogs (#10893)

2025-05-16 12:20:20 -07:00

langfuse_expected_request_body

Revert "Revert "Support passing prompt_label to langfuse (#11018)""

2025-05-22 14:14:39 -07:00

base_test.py

Litellm dev 11 11 2024 (#6693)

2024-11-12 00:16:35 +05:30

conftest.py

(refactor) use helper function _assemble_complete_response_from_streaming_chunks to assemble complete responses in caching and logging callbacks (#6220)

2024-10-15 12:45:12 +05:30

create_mock_standard_logging_payload.py

(fixes) datadog logging - handle 1MB max log size on DD (#6996)

2024-12-02 23:01:42 -08:00

gettysburg.wav

(Testing) - Add e2e testing for langfuse logging with tags (#7922)

2025-01-22 09:09:25 -08:00

log.txt

test: update test

2025-04-10 14:04:57 -07:00

test_alerting.py

[Fix + Refactor] Trigger Soft Budget Webhooks When Key Crosses Threshold (#10491)

2025-05-02 07:06:07 -07:00

test_amazing_s3_logs.py

test: update tests to new deployment model (#10142)

2025-04-18 14:22:12 -07:00

test_assemble_streaming_responses.py

test(test_assemble_streaming_responses.py): update test to use correct type

2025-03-17 18:17:01 -07:00

test_azure_blob_storage.py

(feat) Add Azure Blob Storage Logging Integration (#7265)

2024-12-16 22:18:22 -08:00

test_bedrock_knowledgebase_hook.py

fix typo (#10535)

2025-05-03 11:39:40 -07:00

test_built_in_tools_cost_tracking.py

test_openai_responses_api_web_search_cost_tracking

2025-05-03 20:22:42 -07:00

test_datadog_llm_obs.py

Litellm dev bedrock anthropic 3 7 v2 (#8843)

2025-02-26 16:05:33 -08:00

test_datadog.py

(Feat) datadog_llm_observability callback - emit request_tags on logs (#7883)

2025-01-20 20:36:27 -08:00

test_gcs_pub_sub.py

[Feat] Responses API - Add session management support for non-openai models (#10321)

2025-04-25 23:24:24 -07:00

test_generic_api_callback.py

fix: pass application/json for GenericAPILogger (#10772)

2025-05-12 14:15:33 -07:00

test_humanloop_unit_tests.py

HumanLoop integration for Prompt Management (#7479)

2024-12-30 22:26:03 -08:00

test_langfuse_e2e_test.py

(Bug Fix - Langfuse) - fix for when model response has choices=[] (#8339)

2025-02-06 18:02:26 -08:00

test_langfuse_unit_tests.py

[Feat] Use aiohttp transport by default - 97% lower median latency (#11097)

2025-05-23 22:55:35 -07:00

test_langsmith_unit_test.py

(Bug fix) - don't log messages in model_parameters in StandardLoggingPayload (#8932)

2025-03-01 13:39:45 -08:00

test_log_db_redis_services.py

LiteLLM Minor Fixes & Improvements (12/05/2024) (#7037)

2024-12-05 00:02:31 -08:00

test_logging_redaction_e2e_test.py

Litellm dev 01 02 2025 p1 (#7516)

2025-01-03 14:40:57 -08:00

test_moderations_api_logging.py

[Feat] Add logging callback support for /moderations API (#10390)

2025-04-28 20:24:17 -07:00

test_opentelemetry_unit_tests.py

Fix otel - follow genai semantic conventions + support 'instructions' param for tts (#10608)

2025-05-06 21:57:01 -07:00

test_otel_logging.py

fix(litellm_logging.py): log custom headers in requester metadata (#10818)

2025-05-13 23:04:37 -07:00

test_pagerduty_alerting.py

[Refactor] Make Pagerduty a free feature (#10857)

2025-05-15 10:12:06 -07:00

test_prometheus_unit_tests.py

[Feat] Prometheus - Track route on proxy_* metrics (#10992)

2025-05-20 22:55:55 -07:00

test_spend_logs.py

[Feat] Responses API - Add session management support for non-openai models (#10321)

2025-04-25 23:24:24 -07:00

test_standard_logging_payload.py

[Feat] Responses API - Add session management support for non-openai models (#10321)

2025-04-25 23:24:24 -07:00

test_token_counting.py

[Feat] Use aiohttp transport by default - 97% lower median latency (#11097)

2025-05-23 22:55:35 -07:00

test_unit_test_litellm_logging.py

(performance improvement - litellm sdk + proxy) - ensure litellm does not create unnecessary threads when running async functions (#7680)

2025-01-10 17:57:22 -08:00

test_unit_tests_init_callbacks.py

Expose /list and /info endpoints for Audit Log events (#11102)

2025-05-23 22:54:59 -07:00

test_view_request_resp_logs.py

(Feat) - Allow viewing Request/Response Logs stored in GCS Bucket (#8449)

2025-02-10 20:38:55 -08:00