phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 11:14:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
16468 commits 2484 branches 894 tags 537 MiB
Commit graph

56 commits

Author SHA1 Message Date
Ishaan Jaff
e1839c8da2 allow index to not exist in sagemaker chunks 2024-08-15 19:45:59 -07:00
Ishaan Jaff
b93152e978 assume index is not always in stream chunk 2024-08-15 19:42:03 -07:00
Ishaan Jaff
fa569aaf6f feat add support for aws_region_name 2024-08-15 19:32:59 -07:00
Ishaan Jaff
0d374fb7c0 fix sagemaker test 2024-08-15 18:23:41 -07:00
Ishaan Jaff
df4ea8fba6 refactor sagemaker to be async 2024-08-15 18:18:02 -07:00
Krrish Dholakia
6e9f048618 fix: move to using pydantic obj for setting values 2024-07-11 13:18:36 -07:00
Peter Muller
d8fc8252fa
Revert imports changes, update tests to match 2024-07-02 19:09:22 -07:00
Peter Muller
d9e9a8645b
Add tests for SageMaker region selection 2024-07-02 15:30:39 -07:00
Peter Muller
c6be8326db
Allow calling SageMaker endpoints from different regions 2024-07-01 16:00:42 -07:00
Krrish Dholakia
6575143460 feat(proxy_server.py): return litellm version in response headers 2024-05-08 16:00:08 -07:00
Krrish Dholakia
48c2c3d78a fix(utils.py): fix streaming to not return usage dict 
Fixes https://github.com/BerriAI/litellm/issues/3237
 2024-04-24 08:06:07 -07:00
yishiyiyuan
5faa493d35 🐞 fix: djl vllm support 
support vllm response format on sagemaker, which only return one choice.
 2024-04-03 11:00:51 +08:00
Krrish Dholakia
109cd93a39 fix(sagemaker.py): support model_id consistently. support dynamic args for async calls 2024-03-29 09:05:00 -07:00
Krrish Dholakia
d547944556 fix(sagemaker.py): support 'model_id' param for sagemaker 
allow passing inference component param to sagemaker in the same format as we handle this for bedrock
 2024-03-29 08:43:17 -07:00
Krrish Dholakia
49c4aa5e75 fix(sagemaker.py): fix async sagemaker calls 
https://github.com/BerriAI/litellm/issues/2086
 2024-02-20 17:20:01 -08:00
Krrish Dholakia
074d93cc97 feat(llama_guard.py): allow user to define custom unsafe content categories 2024-02-17 17:42:47 -08:00
Krish Dholakia
57654f4533
Merge branch 'main' into litellm_aioboto3_sagemaker 2024-02-14 21:46:58 -08:00
Krrish Dholakia
3ef391800a fix(sagemaker.py): fix token iterator default flag 2024-02-13 21:41:09 -08:00
Krrish Dholakia
f09c09ace4 docs(pii_masking.md): fix presidio tutorial 2024-02-13 07:42:27 -08:00
Krrish Dholakia
2f815705ca fix(sagemaker.py): use __anext__ 2024-02-12 22:13:35 -08:00
Krrish Dholakia
b1bc30ee16 feat(sagemaker.py): aioboto3 streaming support 2024-02-12 21:18:34 -08:00
Krrish Dholakia
460b48914e feat(sagemaker.py): initial commit of working sagemaker with aioboto3 2024-02-12 17:25:57 -08:00
Krrish Dholakia
09ec6d6458 fix(utils.py): fix sagemaker async logging for sync streaming 
https://github.com/BerriAI/litellm/issues/1592
 2024-01-25 12:49:45 -08:00
ishaan-jaff
802fd6cebf v0 add TokenIterator, stream support 2024-01-22 21:49:44 -08:00
ishaan-jaff
0e26ef858b (feat) sagemaker - map status code and message 2024-01-15 21:43:16 -08:00
Krrish Dholakia
3577857ed1 fix(sagemaker.py): fix the post-call logging logic 2024-01-06 21:52:58 +05:30
Krrish Dholakia
cbcf406fd0 feat(admin_ui.py): support creating keys on admin ui 2023-12-28 16:59:11 +05:30
Krrish Dholakia
4905929de3 refactor: add black formatting 2023-12-25 14:11:20 +05:30
Krrish Dholakia
a64bd2ca1e fix(sagemaker.py): filter out templated prompt if in model response 2023-12-13 07:43:33 -08:00
Krrish Dholakia
102de97960 refactor: fix linting errors 2023-12-06 11:46:15 -08:00
Krrish Dholakia
94f065f83c feat(sagemaker.py): support huggingface embedding models 2023-12-06 11:41:38 -08:00
Krrish Dholakia
648d41c96f fix(sagemaker.py): prompt templating fixes 2023-12-05 17:47:44 -08:00
Krrish Dholakia
ff949490de docs(input.md): add hf_model_name to docs 2023-12-05 16:56:18 -08:00
Krrish Dholakia
88845dddb1 fix(sagemaker.py): bring back llama2 templating for sagemaker 2023-12-05 16:42:19 -08:00
Krrish Dholakia
54d8a9df3f fix(sagemaker.py): enable passing hf model name for prompt template 2023-12-05 16:31:59 -08:00
Krrish Dholakia
a38504ff1b fix(sagemaker.py): fix meta llama model name for sagemaker custom deployment 2023-12-05 16:23:03 -08:00
Krrish Dholakia
3c60682eb4 fix(sagemaker.py): accept all amazon neuron llama2 models 2023-12-05 16:19:28 -08:00
Krrish Dholakia
01fc7f1931 fix(sagemaker.py): add support for amazon neuron llama models 2023-12-05 16:18:20 -08:00
Krrish Dholakia
b4c78c7b9e fix(utils.py): support sagemaker llama2 custom endpoints 2023-12-05 16:05:15 -08:00
ishaan-jaff
9d259d08e7 (linting) fix 2023-11-27 10:27:51 -08:00
ishaan-jaff
f7ae01da8a (feat) completion:sagemaker - support chat models 2023-11-27 10:11:10 -08:00
ishaan-jaff
e407b185ee (feat) completion:sagemaker - better debugging 2023-11-27 09:08:20 -08:00
ishaan-jaff
50f883a2fb (fix) pydantic errors with response.time 2023-11-20 18:28:19 -08:00
Krrish Dholakia
45b6f8b853 refactor: fixing linting issues 2023-11-11 18:52:28 -08:00
Krrish Dholakia
4f42beb9d9 refactor(huggingface,-anthropic,-replicate,-sagemaker): making huggingface, anthropic, replicate, sagemaker compatible openai v1 sdk 2023-11-11 17:38:15 -08:00
ishaan-jaff
194f85e92f (feat) add model_response.usage.completion_tokens for bedrock, palm, petals, sagemaker 2023-10-27 09:51:50 -07:00
Krrish Dholakia
af2fd0e0de fix: fix value error if model returns empty completion 2023-10-10 10:11:40 -07:00
ishaan-jaff
acef90b923 (feat) sagemaker auth in completion 2023-10-07 15:27:58 -07:00
Krrish Dholakia
dd7e397650 style(test_completion.py): fix merge conflict 2023-10-05 22:09:38 -07:00
Krrish Dholakia
0daf2e3880 fixes to get optional params 2023-10-02 14:44:11 -07:00