Commit graph

7 commits

Author SHA1 Message Date
Krish Dholakia
350cfc36f7
Litellm merge pr (#7161)
* build: merge branch

* test: fix openai naming

* fix(main.py): fix openai renaming

* style: ignore function length for config factory

* fix(sagemaker/): fix routing logic

* fix: fix imports

* fix: fix override
2024-12-10 22:49:26 -08:00
Krish Dholakia
e903fe6038
refactor(sagemaker/): separate chat + completion routes + make them b… (#7151)
* refactor(sagemaker/): separate chat + completion routes + make them both use base llm config

Addresses https://github.com/andrewyng/aisuite/issues/113#issuecomment-2512369132

* fix(main.py): pass hf model name + custom prompt dict to litellm params
2024-12-10 19:40:05 -08:00
Krish Dholakia
311432ca17
refactor(fireworks_ai/): inherit from openai like base config (#7146)
* refactor(fireworks_ai/): inherit from openai like base config

refactors fireworks ai to use a common config

* test: fix import in test

* refactor(watsonx/): refactor watsonx to use llm base config

refactors chat + completion routes to base config path

* fix: fix linting error

* test: fix test

* fix: fix test
2024-12-10 16:15:19 -08:00
Ishaan Jaff
bd39e1ab5d
(Refactor) Code Quality improvement - Use Common base handler for cloudflare/ provider (#7127)
* add get_complete_url to base config

* cloudflare - refactor to following existing pattern

* migrate cloudflare chat completions to base llm http handler

* fix unused import

* fix fake stream in cloudflare

* fix cloudflare transformation

* fix naming for BaseModelResponseIterator

* add async cloudflare streaming test

* test cloudflare

* add handler.py

* add handler.py in cohere handler.py
2024-12-10 10:12:22 -08:00
Ishaan Jaff
1ef311343c
(Refactor) Code Quality improvement - Use Common base handler for clarifai/ (#7125)
All checks were successful
Read Version from pyproject.toml / read-version (push) Successful in 32s
* use base_llm_http_handler for clarifai

* fix clarifai completion

* handle faking streaming base llm http handler

* add fake streaming for clarifai

* add FakeStreamResponseIterator for base model iterator

* fix get_model_response_iterator

* fix base model iterator

* fix base model iterator

* add support for faking sync streams clarfiai

* add fake streaming for clarifai

* remove unused code

* fix import

* fix llm http handler

* test_async_completion_clarifai

* fix clarifai tests

* fix linting
2024-12-09 21:04:48 -08:00
Ishaan Jaff
ff7c95694d
(Refactor) Code Quality improvement - use Common base handler for Cohere (#7117)
* fix use new format for Cohere config

* fix base llm http handler

* Litellm code qa common config (#7116)

* feat(base_llm): initial commit for common base config class

Addresses code qa critique https://github.com/andrewyng/aisuite/issues/113#issuecomment-2512369132

* feat(base_llm/): add transform request/response abstract methods to base config class

---------

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

* use base transform helpers

* use base_llm_http_handler for cohere

* working cohere using base llm handler

* add async cohere chat completion support on base handler

* fix completion code

* working sync cohere stream

* add async support cohere_chat

* fix types get_model_response_iterator

* async / sync tests cohere

* feat  cohere using base llm class

* fix linting errors

* fix _abc error

* add cohere params to transformation

* remove old cohere file

* fix type error

* fix merge conflicts

* fix cohere merge conflicts

* fix linting error

* fix litellm.llms.custom_httpx.http_handler.HTTPHandler.post

* fix passing cohere specific params

---------

Co-authored-by: Krrish Dholakia <krrishdholakia@gmail.com>
2024-12-09 17:45:29 -08:00
Krish Dholakia
5bbf906c83
Litellm code qa common config (#7113)
All checks were successful
Read Version from pyproject.toml / read-version (push) Successful in 44s
* feat(base_llm): initial commit for common base config class

Addresses code qa critique https://github.com/andrewyng/aisuite/issues/113#issuecomment-2512369132

* feat(base_llm/): add transform request/response abstract methods to base config class

* feat(cohere-+-clarifai): refactor integrations to use common base config class

* fix: fix linting errors

* refactor(anthropic/): move anthropic + vertex anthropic to use base config

* test: fix xai test

* test: fix tests

* fix: fix linting errors

* test: comment out WIP test

* fix(transformation.py): fix is pdf used check

* fix: fix linting error
2024-12-09 15:58:25 -08:00