Krish Dholakia
|
77332ced58
|
Merge pull request #4137 from jamesbraza/custom-llm-provider
Allowing inference of LLM provider in `get_supported_openai_params`
|
2024-06-11 18:38:42 -07:00 |
|
Krish Dholakia
|
30d269f93a
|
Merge pull request #4139 from BerriAI/litellm_fix_budget_exceeded_error_code
fix(proxy_server.py): use consistent 400-status code error code for exceeded budget errors
|
2024-06-11 18:36:58 -07:00 |
|
James Braza
|
cab0e0e703
|
Added handling of unmapped provider, with test
|
2024-06-11 18:34:10 -07:00 |
|
Ishaan Jaff
|
c4bed6dfff
|
fix when user_api_key_dict is None
|
2024-06-11 18:33:15 -07:00 |
|
Krish Dholakia
|
83114ef714
|
Merge pull request #4119 from BerriAI/litellm_tiktoken_bump
feat(utils.py): bump tiktoken dependency to 0.7.0 (gpt-4o token counting support)
|
2024-06-11 18:24:58 -07:00 |
|
Krish Dholakia
|
bb9653eedb
|
Merge pull request #4134 from BerriAI/litellm_azure_ai_route
Azure AI support all models
|
2024-06-11 18:24:05 -07:00 |
|
James Braza
|
85b8724484
|
Added simple test of get_supported_openai_params with no custom provider
|
2024-06-11 18:18:21 -07:00 |
|
James Braza
|
f33cb2fbaa
|
Allowing inferring custom LLM provider from model inside get_supported_openai_params
|
2024-06-11 18:16:19 -07:00 |
|
Ishaan Jaff
|
8c63e6e493
|
fix linting error
|
2024-06-11 18:14:06 -07:00 |
|
Ishaan Jaff
|
f9fd962191
|
fix team endpoints
|
2024-06-11 18:10:20 -07:00 |
|
Krrish Dholakia
|
fb1dc7d86b
|
test(test_team.py): fix error string asserted
|
2024-06-11 18:05:20 -07:00 |
|
Ishaan Jaff
|
5d5d02156a
|
fix - log mgmt data to OTEL
|
2024-06-11 18:05:10 -07:00 |
|
Ishaan Jaff
|
5f078edc13
|
fix http_request
|
2024-06-11 17:57:50 -07:00 |
|
Krrish Dholakia
|
a0ee9ba78e
|
fix(utils.py): support dynamic api key for azure_ai route
|
2024-06-11 17:51:29 -07:00 |
|
Ishaan Jaff
|
714b4ee59d
|
fix test new team
|
2024-06-11 17:48:11 -07:00 |
|
Krrish Dholakia
|
85c9ff6783
|
fix: more bug fixes
|
2024-06-11 17:41:59 -07:00 |
|
Krrish Dholakia
|
a545615054
|
fix(__init__.py): add 'log_raw_request_response' flag to init
|
2024-06-11 17:26:03 -07:00 |
|
Ishaan Jaff
|
252aeaf4fe
|
fix import error
|
2024-06-11 17:17:57 -07:00 |
|
Ishaan Jaff
|
4859244e67
|
feat - otel log /team exceptions
|
2024-06-11 16:27:07 -07:00 |
|
Ishaan Jaff
|
1b73da1b21
|
fix refactor management endpoint utils
|
2024-06-11 16:16:10 -07:00 |
|
Krrish Dholakia
|
2a5a30fa7a
|
fix(proxy_server.py): use consistent 400-status code error code for exceeded budget errors
standardizes error code for budget exceeded errors to status code 400
|
2024-06-11 16:10:58 -07:00 |
|
Ishaan Jaff
|
9d78e1bd5f
|
feat - log management endpoint logs to otel
|
2024-06-11 16:09:11 -07:00 |
|
Krrish Dholakia
|
caae69c18f
|
fix(utils.py): fix formatting
|
2024-06-11 15:49:20 -07:00 |
|
Krrish Dholakia
|
0f1c40d698
|
fix(main.py): trigger new build
|
2024-06-11 15:13:50 -07:00 |
|
Ishaan Jaff
|
5994ca572c
|
Merge pull request #4133 from BerriAI/litellm_work_with_traceparents
[Feat] OTEL - allow propagating traceparent in headers
|
2024-06-11 14:27:08 -07:00 |
|
Ishaan Jaff
|
8d3bda27eb
|
doc - OTEL trace propogation
|
2024-06-11 14:25:33 -07:00 |
|
Krrish Dholakia
|
2f13052017
|
test(test_completion.py): add testing to make sure tool calling works as expected for 'azure_ai/' route
|
2024-06-11 14:11:02 -07:00 |
|
Krrish Dholakia
|
4a27a50f9b
|
fix(utils.py): add new 'azure_ai/' route
supports azure's openai compatible api endpoint
|
2024-06-11 14:06:56 -07:00 |
|
Ishaan Jaff
|
8ce9c3a2b6
|
test - propogate trace IDs across services
|
2024-06-11 14:00:25 -07:00 |
|
Ishaan Jaff
|
2d5904c9a5
|
feat - use traceparent to proporgate OTEL traces
|
2024-06-11 13:57:31 -07:00 |
|
Krrish Dholakia
|
e7967eb763
|
fix(utils.py): allow user to opt in to raw request logging to langfuse
|
2024-06-11 13:35:22 -07:00 |
|
Krrish Dholakia
|
c7da20af3f
|
docs(ui.md): add okta sso support to docs
|
2024-06-11 13:17:41 -07:00 |
|
Ishaan Jaff
|
6c19b76edc
|
fix OTEL semantic conventions does not exist
|
2024-06-11 12:28:38 -07:00 |
|
David Manouchehri
|
0a07b26b74
|
fix(bedrock_httpx.py): Add IAM caching for converse flow.
|
2024-06-11 17:00:18 +00:00 |
|
David Manouchehri
|
de5b85f309
|
fix(bedrock_httpx.py): Fix STS region endpoint for converse flow.
|
2024-06-11 16:35:03 +00:00 |
|
David Manouchehri
|
52dd823d22
|
feat(azure.py): Add Azure AD cred caching for OIDC flow.
|
2024-06-11 15:54:44 +00:00 |
|
David Manouchehri
|
41b6c58ddc
|
feat(util.py/azure.py): Add OIDC support when running in Azure Kubernetes Service (AKS).
|
2024-06-11 15:54:34 +00:00 |
|
David Manouchehri
|
20e8df66bd
|
fix(bedrock_httpx.py): Fix STS region endpoint.
|
2024-06-11 15:43:33 +00:00 |
|
David Manouchehri
|
6fa14f9ff2
|
feat(bedrock_httpx.py): Add AWS IAM cred caching for OIDC flow.
|
2024-06-11 15:43:15 +00:00 |
|
David Manouchehri
|
b0c3bd4748
|
Merge remote-tracking branch 'upstream/main' into oidc-bedrock-httpx-caching-part-1
|
2024-06-11 15:42:31 +00:00 |
|
David Manouchehri
|
2ebf51886e
|
Revert "feat(bedrock_httpx.py): Add AWS IAM cred caching for OIDC flow."
This reverts commit 240a0da271 .
|
2024-06-11 15:42:18 +00:00 |
|
David Manouchehri
|
89bfff2f21
|
Revert "fix(bedrock_httpx.py): Fix STS region endpoint."
This reverts commit fd16937ad8 .
|
2024-06-11 15:42:09 +00:00 |
|
Ishaan Jaff
|
5e411a45d5
|
fix azure falbacks test
|
2024-06-10 21:50:54 -07:00 |
|
Krrish Dholakia
|
b75414362b
|
fix(utils.py): exception map vertex ai 500 internal server errors
|
2024-06-10 21:37:54 -07:00 |
|
Krrish Dholakia
|
74a27df9ba
|
feat(utils.py): bump tiktoken dependency to 0.7.0
adds support for gpt-4o token counting
|
2024-06-10 21:21:23 -07:00 |
|
Ishaan Jaff
|
a852b13e2c
|
ui - new build
|
2024-06-10 21:11:33 -07:00 |
|
Ishaan Jaff
|
90e297d745
|
fix azure cost tracking
|
2024-06-10 21:09:55 -07:00 |
|
Ishaan Jaff
|
fefccdcbea
|
Merge pull request #4116 from BerriAI/litellm_show_model_group_in_exceptions
fix - show `model group` in Azure ContentPolicy exceptions
|
2024-06-10 20:53:53 -07:00 |
|
Ishaan Jaff
|
baafe32ba7
|
fix - show model group in exceptions
|
2024-06-10 20:30:31 -07:00 |
|
Krish Dholakia
|
b2cc37c971
|
Merge pull request #4084 from BerriAI/litellm_batch_add_team_members
fix(proxy_server.py): allow passing in a list of team members
|
2024-06-10 20:26:35 -07:00 |
|