Commit graph

2221 commits

Author SHA1 Message Date
Krrish Dholakia
fe24b9d90b feat(azure/gpt_transformation.py): add azure audio model support
Closes https://github.com/BerriAI/litellm/issues/6305
2025-03-19 22:57:49 -07:00
Ishaan Jaff
9203910ab6 fix import hashlib 2025-03-19 21:08:19 -07:00
Ishaan Jaff
247e4d09ee
Merge branch 'main' into litellm_fix_ssl_verify 2025-03-19 21:03:06 -07:00
James Guthrie
437dbe7246 fix: VertexAI outputDimensionality configuration
VertexAI's API documentation [1] is an absolute mess. In it, they
describe the parameter to configure output dimensionality as
`output_dimensionality`. In the API example, they switch to using snake
case `outputDimensionality`, which is the correct variant.

[1]: https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/text-embeddings-api#generative-ai-get-text-embedding-drest
2025-03-19 11:07:36 +01:00
Krish Dholakia
01c6cbd270
Merge pull request #9363 from BerriAI/litellm_dev_03_18_2025_p3
All checks were successful
Read Version from pyproject.toml / read-version (push) Successful in 18s
Helm unit test / unit-test (push) Successful in 21s
fix(common_utils.py): handle cris only model
2025-03-18 23:36:12 -07:00
Krrish Dholakia
9adad381b4 fix(common_utils.py): handle cris only model
Fixes https://github.com/BerriAI/litellm/issues/9161#issuecomment-2734905153
2025-03-18 23:35:43 -07:00
Ishaan Jaff
65083ca8da get_openai_client_cache_key 2025-03-18 18:35:50 -07:00
Ishaan Jaff
3daef0d740 fix common utils 2025-03-18 17:59:46 -07:00
Ishaan Jaff
a45830dac3 use common caching logic for openai/azure clients 2025-03-18 17:57:03 -07:00
Ishaan Jaff
f73e9047dc use common logic for re-using openai clients 2025-03-18 17:56:32 -07:00
Ishaan Jaff
55ea2370ba Union[TranscriptionResponse, Coroutine[Any, Any, TranscriptionResponse]]: 2025-03-18 14:23:14 -07:00
Ishaan Jaff
b20a69f9fc fix code quality 2025-03-18 12:58:59 -07:00
Ishaan Jaff
dc3d7b3afc test_azure_instruct 2025-03-18 12:56:11 -07:00
Ishaan Jaff
2cd49ef096 fix test_ensure_initialize_azure_sdk_client_always_used 2025-03-18 12:46:55 -07:00
Ishaan Jaff
b60178f534 fix azure chat logic 2025-03-18 12:42:24 -07:00
Ishaan Jaff
80a5cfa01d test_azure_embedding_max_retries_0 2025-03-18 12:35:34 -07:00
Ishaan Jaff
842625a6f0 :test_completion_azure_ad_toke 2025-03-18 12:25:32 -07:00
Ishaan Jaff
d4b3082ca2 fix azure embedding test 2025-03-18 12:19:12 -07:00
Ishaan Jaff
38e2dd00cc fix amebedding issue on ssl azure 2025-03-18 11:42:11 -07:00
Ishaan Jaff
dfd7a7d547 fix linting error 2025-03-18 11:38:31 -07:00
Ishaan Jaff
3458c69eb0 fix common utils 2025-03-18 11:04:02 -07:00
Ishaan Jaff
c1e0cb136e fix using azure openai clients 2025-03-18 10:47:29 -07:00
Ishaan Jaff
e34be5a3b6 use get_azure_openai_client 2025-03-18 10:28:39 -07:00
Ishaan Jaff
a0c5fb81b8 fix logic for intializing openai clients 2025-03-18 10:23:30 -07:00
Ishaan Jaff
0601768bb8 use ssl on initialize_azure_sdk_client 2025-03-18 10:14:51 -07:00
Ishaan Jaff
34142a1b62 _init_azure_client_for_cloudflare_ai_gateway 2025-03-18 10:11:54 -07:00
Ishaan Jaff
edfbf21c39 fix re-using azure openai client 2025-03-18 10:06:56 -07:00
Ishaan Jaff
f2026ef907 fix - correctly re-use azure openai client 2025-03-18 09:51:28 -07:00
Ishaan Jaff
b74f3cb76c _get_azure_openai_client 2025-03-18 09:38:27 -07:00
Ishaan Jaff
26be805ad3 rename to _get_azure_openai_client 2025-03-18 09:25:26 -07:00
Ishaan Jaff
6e351136d7 handle _get_async_http_client for OpenAI 2025-03-18 08:56:08 -07:00
Krish Dholakia
bcbb88d802
Merge pull request #9326 from andjsmi/main
Modify completion handler for SageMaker to use payload from `prepared_request`
2025-03-17 22:16:43 -07:00
Krish Dholakia
cd5024f3b1
Merge pull request #9333 from BerriAI/litellm_dev_03_17_2025_p2
fix(ollama/completions/transformation.py): pass prompt, untemplated o…
2025-03-17 21:48:30 -07:00
Krrish Dholakia
22faf7d232 fix(ollama/completions/transformation.py): pass prompt, untemplated on /completions request
Fixes https://github.com/BerriAI/litellm/issues/6900
2025-03-17 18:35:44 -07:00
Andrew Smith
81a7cf0f44
Update handler.py to use prepared_request.body for input 2025-03-18 11:07:38 +11:00
Krrish Dholakia
057c774c14 fix(http_handler.py): fix typing error 2025-03-17 16:42:32 -07:00
Andrew Smith
a92e99e946
Update handler.py to use prepared_request.body 2025-03-18 10:23:32 +11:00
Krrish Dholakia
8e27b2026a fix(http_handler.py): support reading ssl security level from env var
Allows user to specify lower security settings
2025-03-17 15:48:31 -07:00
Krish Dholakia
d0d8ec2c40
Merge branch 'main' into litellm_dev_03_16_2025_p1 2025-03-17 10:02:53 -07:00
Krrish Dholakia
b093157369 fix(converse_transformation.py): fix linting error 2025-03-15 19:33:17 -07:00
Krrish Dholakia
5dc46f0cf7 fix(converse_transformation.py): fix encoding model 2025-03-15 14:03:37 -07:00
Krrish Dholakia
dd2c980d5b fix(utils.py): Prevents final chunk w/ usage from being ignored
Fixes https://github.com/BerriAI/litellm/issues/7112
2025-03-15 09:12:14 -07:00
Krish Dholakia
d4caaae1be
Merge pull request #9274 from BerriAI/litellm_contributor_rebase_branch
All checks were successful
Read Version from pyproject.toml / read-version (push) Successful in 43s
Helm unit test / unit-test (push) Successful in 50s
Litellm contributor rebase branch
2025-03-14 21:57:49 -07:00
Lucas Raschek
56d3e75b33 Map total tokens to prompt_tokens too 2025-03-14 18:04:43 +01:00
Ishaan Jaff
241a36a74f
Merge pull request #9222 from BerriAI/litellm_snowflake_pr_mar_13
[Feat] Add Snowflake Cortex to LiteLLM
2025-03-13 21:35:39 -07:00
Ishaan Jaff
69b47cf738 fix code quality check 2025-03-13 20:10:41 -07:00
Krish Dholakia
e8c67f25e3
Merge pull request #9221 from BerriAI/litellm_dev_03_13_2025_p2
Support bedrock converse cache token tracking
2025-03-13 20:08:33 -07:00
Krish Dholakia
fd8a5960ec
Merge pull request #9216 from BerriAI/litellm_dev_03_12_2025_contributor_prs_p2
Litellm dev 03 12 2025 contributor prs p2
2025-03-13 20:03:57 -07:00
Krrish Dholakia
8a6e4715aa feat(converse_transformation.py): fix type for bedrock cache usage block 2025-03-13 19:33:22 -07:00
Ishaan Jaff
d3781dfe36 fix linting errors 2025-03-13 16:58:34 -07:00