Commit graph

7 commits

Author SHA1 Message Date
Krrish Dholakia
f41cc5691d refactor: update method signature 2025-03-12 15:23:38 -07:00
Krish Dholakia
8ee79dd5d9 [BETA] Add OpenAI /images/variations + Topaz API support (#7700)
* feat(main.py): initial commit for `/image/variations` endpoint support

* refactor(base_llm/): introduce new base llm base config for image variation endpoints

* refactor(openai/image_variations/transformation.py): implement openai image variation transformation handler

* fix: test

* feat(openai/): working openai `/image/variation` endpoint calls via sdk

* feat(topaz/): topaz sync image variation call support

Addresses https://github.com/BerriAI/litellm/issues/7593

'

* fix(topaz/transformation.py): fix linting errors

* fix(openai/image_variations/handler.py): fix passing json data

* fix(main.py): image_variation/

support async image variation route - `aimage_variation`

* fix(test_get_model_info.py): fix test

* fix: cleanup unused imports

* feat(openai/): add async `/image/variations` endpoint support

* feat(topaz/): support async `/image/variations` calls

* fix: test

* fix(utils.py): fix get_model_info_helper for no model info w/ provider config

handles situation where model info is not known but provider config exists

* test(test_router_fallbacks.py): mark flaky test

* fix: fix unused imports

* test: bump otel load test perf threshold - accounts for current load tests hitting same server
2025-01-11 23:27:46 -08:00
Ishaan Jaff
5d3ae6da62 aiohttp_openai/ fixes - allow using aiohttp_openai/gpt-4o (#7598)
* fixes for get_complete_url

* update aiohttp tests

* fix event loop for aiohtto

* ci/cd run again

* test_aiohttp_openai
2025-01-06 21:39:11 -08:00
Ishaan Jaff
7ac1c0c1b2 (perf) - fixes for aiohttp handler to hit 1K RPS (#7590)
* fix getting aiohttp sesson

* fix _get_async_client_session
2025-01-06 15:41:39 -08:00
Ishaan Jaff
dc10cebde7 fix _make_common_async_call 2025-01-03 15:15:38 -08:00
Ishaan Jaff
6e2f712b06 (fix) aiohttp_openai/ route - get to 1K RPS on single instance (#7539)
* ClientSession

* re use client_session

* _init_client_session

* fix aiohttp
2025-01-03 15:12:17 -08:00
Ishaan Jaff
3a454ee2ce (perf) use aiohttp for custom_openai (#7514)
* use aiohttp handler

* BaseLLMAIOHTTPHandler

* use CustomOpenAIChatConfig

* CustomOpenAIChatConfig

* CustomOpenAIChatConfig

* fix linting

* AiohttpOpenAIChatConfig

* fix order

* aiohttp_openai
2025-01-02 22:15:17 -08:00