Commit graph

4 commits

Author SHA1 Message Date
Krish Dholakia
6ba3c4a4f8
VertexAI non-jsonl file storage support (#9781)
* test: add initial e2e test

* fix(vertex_ai/files): initial commit adding sync file create support

* refactor: initial commit of vertex ai non-jsonl files reaching gcp endpoint

* fix(vertex_ai/files/transformation.py): initial working commit of non-jsonl file call reaching backend endpoint

* fix(vertex_ai/files/transformation.py): working e2e non-jsonl file upload

* test: working e2e jsonl call

* test: unit testing for jsonl file creation

* fix(vertex_ai/transformation.py): reset file pointer after read

allow multiple reads on same file object

* fix: fix linting errors

* fix: fix ruff linting errors

* fix: fix import

* fix: fix linting error

* fix: fix linting error

* fix(vertex_ai/files/transformation.py): fix linting error

* test: update test

* test: update tests

* fix: fix linting errors

* fix: fix test

* fix: fix linting error
2025-04-09 14:01:48 -07:00
Krish Dholakia
0120176541
Litellm dev 12 30 2024 p2 (#7495)
* test(azure_openai_o1.py): initial commit with testing for azure openai o1 preview model

* fix(base_llm_unit_tests.py): handle azure o1 preview response format tests

skip as o1 on azure doesn't support tool calling yet

* fix: initial commit of azure o1 handler using openai caller

simplifies calling + allows fake streaming logic alr. implemented for openai to just work

* feat(azure/o1_handler.py): fake o1 streaming for azure o1 models

azure does not currently support streaming for o1

* feat(o1_transformation.py): support overriding 'should_fake_stream' on azure/o1 via 'supports_native_streaming' param on model info

enables user to toggle on when azure allows o1 streaming without needing to bump versions

* style(router.py): remove 'give feedback/get help' messaging when router is used

Prevents noisy messaging

Closes https://github.com/BerriAI/litellm/issues/5942

* fix(types/utils.py): handle none logprobs

Fixes https://github.com/BerriAI/litellm/issues/328

* fix(exception_mapping_utils.py): fix error str unbound error

* refactor(azure_ai/): move to openai_like chat completion handler

allows for easy swapping of api base url's (e.g. ai.services.com)

Fixes https://github.com/BerriAI/litellm/issues/7275

* refactor(azure_ai/): move to base llm http handler

* fix(azure_ai/): handle differing api endpoints

* fix(azure_ai/): make sure all unit tests are passing

* fix: fix linting errors

* fix: fix linting errors

* fix: fix linting error

* fix: fix linting errors

* fix(azure_ai/transformation.py): handle extra body param

* fix(azure_ai/transformation.py): fix max retries param handling

* fix: fix test

* test(test_azure_o1.py): fix test

* fix(llm_http_handler.py): support handling azure ai unprocessable entity error

* fix(llm_http_handler.py): handle sync invalid param error for azure ai

* fix(azure_ai/): streaming support with base_llm_http_handler

* fix(llm_http_handler.py): working sync stream calls with unprocessable entity handling for azure ai

* fix: fix linting errors

* fix(llm_http_handler.py): fix linting error

* fix(azure_ai/): handle cohere tool call invalid index param error
2025-01-01 18:57:29 -08:00
Krish Dholakia
3671829e39
Complete 'requests' library removal (#7350)
All checks were successful
Read Version from pyproject.toml / read-version (push) Successful in 12s
* refactor: initial commit moving watsonx_text to base_llm_http_handler + clarifying new provider directory structure

* refactor(watsonx/completion/handler.py): move to using base llm http handler

removes 'requests' library usage

* fix(watsonx_text/transformation.py): fix result transformation

migrates to transformation.py, for usage with base llm http handler

* fix(streaming_handler.py): migrate watsonx streaming to transformation.py

ensures streaming works with base llm http handler

* fix(streaming_handler.py): fix streaming linting errors and remove watsonx conditional logic

* fix(watsonx/): fix chat route post completion route refactor

* refactor(watsonx/embed): refactor watsonx to use base llm http handler for embedding calls as well

* refactor(base.py): remove requests library usage from litellm

* build(pyproject.toml): remove requests library usage

* fix: fix linting errors

* fix: fix linting errors

* fix(types/utils.py): fix validation errors for modelresponsestream

* fix(replicate/handler.py): fix linting errors

* fix(litellm_logging.py): handle modelresponsestream object

* fix(streaming_handler.py): fix modelresponsestream args

* fix: remove unused imports

* test: fix test

* fix: fix test

* test: fix test

* test: fix tests

* test: fix test

* test: fix patch target

* test: fix test
2024-12-22 07:21:25 -08:00
Ishaan Jaff
6107f9f3f3
[Bug fix ]: Triton /infer handler incompatible with batch responses (#7337)
* migrate triton to base llm http handler

* clean up triton handler.py

* use transform functions for triton

* add TritonConfig

* get openai params for triton

* use triton embedding config

* test_completion_triton_generate_api

* test_completion_triton_infer_api

* fix TritonConfig doc string

* use TritonResponseIterator

* fix triton embeddings

* docs triton chat usage
2024-12-20 20:59:40 -08:00