Commit graph

26 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
Ishaan Jaff
1bac18a98c cleanup_azure_files 2025-02-15 15:32:42 -08:00
Ishaan Jaff
0ffd99afff test_avertex_batch_prediction
All checks were successful
Read Version from pyproject.toml / read-version (push) Successful in 36s
2025-02-14 22:03:24 -08:00
Ishaan Jaff
616233089e test_mock_openai_retrieve_fine_tune_job 2025-02-14 21:35:26 -08:00
Ishaan Jaff
946bc1e3fa fix use mock tests for fine tuning api requests to openai 2025-02-14 21:20:20 -08:00
Ishaan Jaff
0bdebe36d8 test fix openai batches and files 2025-02-14 19:03:30 -08:00
Ishaan Jaff
8a235e7d38
(Refactor / QA) - Use LoggingCallbackManager to append callbacks and ensure no duplicate callbacks are added (#8112)
* LoggingCallbackManager

* add logging_callback_manager

* use logging_callback_manager

* add add_litellm_failure_callback

* use add_litellm_callback

* use add_litellm_async_success_callback

* add_litellm_async_failure_callback

* linting fix

* fix logging callback manager

* test_duplicate_multiple_loggers_test

* use _reset_all_callbacks

* fix testing with dup callbacks

* test_basic_image_generation

* reset callbacks for tests

* fix check for _add_custom_logger_to_list

* fix test_amazing_sync_embedding

* fix _get_custom_logger_key

* fix batches testing

* fix _reset_all_callbacks

* fix _check_callback_list_size

* add callback_manager_test

* fix test gemini-2.0-flash-thinking-exp-01-21
2025-01-30 19:35:50 -08:00
Ishaan Jaff
46b44f3a7f ci/cd run again
All checks were successful
Read Version from pyproject.toml / read-version (push) Successful in 37s
2025-01-28 22:18:03 -08:00
Ishaan Jaff
5a7dc11432 test fix test_async_create_batch use only openai for testing, hitting azure limits 2025-01-28 22:17:49 -08:00
Ishaan Jaff
b60efd4646 fix test_async_create_batch 2025-01-22 22:15:49 -08:00
Ishaan Jaff
13f364682d
(Feat - Batches API) add support for retrieving vertex api batch jobs (#7661)
* add _async_retrieve_batch

* fix aretrieve_batch

* fix _get_batch_id_from_vertex_ai_batch_response

* fix batches docs
2025-01-09 18:35:03 -08:00
Ishaan Jaff
3110bb0723 use pathrise-convert-1606954137718 2025-01-05 14:14:43 -08:00
Ishaan Jaff
137879ffea vertex testing use pathrise-convert-1606954137718 2025-01-05 14:00:17 -08:00
Ishaan Jaff
2979b8301c
(feat) POST /fine_tuning/jobs support passing vertex specific hyper params (#7490)
All checks were successful
Read Version from pyproject.toml / read-version (push) Successful in 12s
* update convert_openai_request_to_vertex

* test_create_vertex_fine_tune_jobs_mocked

* fix order of methods

* update LiteLLMFineTuningJobCreate

* update OpenAIFineTuningHyperparameters

* update vertex hyper params in response

* _transform_openai_hyperparameters_to_vertex_hyperparameters

* supervised_tuning_spec["hyperParameters"] fix

* fix mapping for ft params testing

* docs fine tuning apis

* fix test_convert_basic_openai_request_to_vertex_request

* update hyperparams for create fine tuning

* fix linting

* test_create_vertex_fine_tune_jobs_mocked_with_hyperparameters

* run ci/cd again

* test_convert_basic_openai_request_to_vertex_request
2025-01-01 07:44:48 -08:00
Ishaan Jaff
859f6e1635
(fix) v1/fine_tuning/jobs with VertexAI (#7487)
* update convert_openai_request_to_vertex

* test_create_vertex_fine_tune_jobs_mocked
2024-12-31 15:09:56 -08:00
Ishaan Jaff
32e8bdef6f update clean up jobs 2024-12-28 19:45:19 -08:00
Ishaan Jaff
6409de6291 fix ft job test - add resource cleanup 2024-12-28 19:28:54 -08:00
Ishaan Jaff
f719743d4a cleanup_azure_ft_models 2024-12-28 19:10:23 -08:00
Ishaan Jaff
2ece919f01
(Feat) - new endpoint GET /v1/fine_tuning/jobs/{fine_tuning_job_id:path} (#7427)
* init commit ft jobs logging

* add ft logging

* add logging for FineTuningJob

* simple FT Job create test

* simplify Azure fine tuning to use all methods in OAI ft

* update doc string

* add aretrieve_fine_tuning_job

* re use from litellm.proxy.utils import handle_exception_on_proxy

* fix naming

* add /fine_tuning/jobs/{fine_tuning_job_id:path}

* remove unused imports

* update func signature

* run ci/cd again

* ci/cd run again

* fix code qulity

* ci/cd run again
2024-12-27 17:01:14 -08:00
Ishaan Jaff
d36152f9eb fix ft testing 2024-12-27 14:33:16 -08:00
Ishaan Jaff
f7316f517a
(Feat) Add logging for POST v1/fine_tuning/jobs (#7426)
* init commit ft jobs logging

* add ft logging

* add logging for FineTuningJob

* simple FT Job create test
2024-12-26 08:58:47 -08:00
Krish Dholakia
760328b6ad
Litellm dev 12 25 2025 p2 (#7420)
* test: add new test image embedding to base llm unit tests

Addresses https://github.com/BerriAI/litellm/issues/6515

* fix(bedrock/embed/multimodal-embeddings): strip data prefix from image urls for bedrock multimodal embeddings

Fix https://github.com/BerriAI/litellm/issues/6515

* feat: initial commit for fireworks ai audio transcription support

Relevant issue: https://github.com/BerriAI/litellm/issues/7134

* test: initial fireworks ai test

* feat(fireworks_ai/): implemented fireworks ai audio transcription config

* fix(utils.py): register fireworks ai audio transcription config, in config manager

* fix(utils.py): add fireworks ai param translation to 'get_optional_params_transcription'

* refactor(fireworks_ai/): define text completion route with model name handling

moves model name handling to specific fireworks routes, as required by their api

* refactor(fireworks_ai/chat): define transform_Request - allows fixing model if accounts/ is missing

* fix: fix linting errors

* fix: fix linting errors

* fix: fix linting errors

* fix: fix linting errors

* fix(handler.py): fix linting errors

* fix(main.py): fix tgai text completion route

* refactor(together_ai/completion): refactors together ai text completion route to just use provider transform request

* refactor: move test_fine_tuning_api out of local_testing

reduces local testing ci/cd time
2024-12-25 18:35:34 -08:00
Ishaan Jaff
81be0b4090
(Feat) add `"/v1/batches/{batch_id:path}/cancel" endpoint (#7406)
* use 1 file for azure batches handling

* add cancel_batch endpoint

* add a cancel batch on open ai

* add cancel_batch endpoint

* add cancel batches to test

* remove unused imports

* test_batches_operations

* update test_batches_operations
2024-12-24 20:23:50 -08:00
Ishaan Jaff
08a4c72692
(feat) /batches - track user_api_key_alias, user_api_key_team_alias etc for /batch requests (#7401)
* run azure testing on ci/cd

* update docs on azure batches endpoints

* add input azure.jsonl

* refactor - use separate file for batches endpoints

* fixes for passing custom llm provider to /batch endpoints

* pass custom llm provider to files endpoints

* update azure batches doc

* add info for azure batches api

* update batches endpoints

* use simple helper for raising proxy exception

* update config.yml

* fix imports

* add type hints to get_litellm_params

* update get_litellm_params

* update get_litellm_params

* update get slp

* QOL - stop double logging a create batch operations on custom loggers

* re use slp from og event

* _create_standard_logging_object_for_completed_batch

* fix linting errors

* reduce num changes in PR

* update BATCH_STATUS_POLL_MAX_ATTEMPTS
2024-12-24 17:44:28 -08:00
Ishaan Jaff
47e12802df
(feat) /batches Add support for using /batches endpoints in OAI format (#7402)
* run azure testing on ci/cd

* update docs on azure batches endpoints

* add input azure.jsonl

* refactor - use separate file for batches endpoints

* fixes for passing custom llm provider to /batch endpoints

* pass custom llm provider to files endpoints

* update azure batches doc

* add info for azure batches api

* update batches endpoints

* use simple helper for raising proxy exception

* update config.yml

* fix imports

* update tests

* use existing settings

* update env var used

* update configs

* update config.yml

* update ft testing
2024-12-24 16:58:05 -08:00
Ishaan Jaff
05b0d2026f
(feat) Add cost tracking for /batches requests OpenAI (#7384)
* add basic logging for create`batch`

* add create_batch as a call type

* add basic dd logging for batches

* basic batch creation logging on DD

* batch endpoints add cost calc

* fix batches_async_logging

* separate folder for batches testing

* new job for batches tests

* test batches logging

* fix validation logic

* add vertex_batch_completions.jsonl

* test test_async_create_batch

* test_async_create_batch

* update tests

* test_completion_with_no_model

* remove dead code

* update load_vertex_ai_credentials

* test_avertex_batch_prediction

* update get async httpx client

* fix get_async_httpx_client

* update test_avertex_batch_prediction

* fix batches testing config.yaml

* add google deps

* fix vertex files handler
2024-12-23 17:47:26 -08:00