Krish Dholakia
1aa567f3b5
Merge pull request #3571 from BerriAI/litellm_hf_classifier_support
...
Huggingface classifier support
2024-05-10 17:54:27 -07:00
Krish Dholakia
69068f9577
Merge pull request #3572 from powerhouseofthecell/feature/enforce-unique-key-and-team-aliases
...
enforce unique key and team aliases in the ui
2024-05-10 17:53:26 -07:00
Ishaan Jaff
2c0c9e1fa4
Merge pull request #3573 from BerriAI/litellm_team_based_failure_callback
...
[Feat] Use Team based callbacks with litellm.failure_callbacks
2024-05-10 17:53:15 -07:00
Ishaan Jaff
1d25be0ca8
fix langfuse logger re-initialized on all failure callbacks
2024-05-10 17:48:44 -07:00
Ishaan Jaff
a4695c3010
test - using langfuse as a failure callback
2024-05-10 17:37:32 -07:00
Ishaan Jaff
4584989a31
fix - langfuse copy metadata
2024-05-10 17:33:29 -07:00
Ishaan Jaff
ce8523808b
fix langfuse failure logging
2024-05-10 17:02:38 -07:00
Krrish Dholakia
9e9f5d41d9
fix(proxy_server.py): check + get end-user obj even for master key calls
...
fixes issue where region-based routing wasn't working for end-users if master key was given
2024-05-10 16:54:51 -07:00
Ishaan Jaff
db0db5c62c
Merge pull request #3570 from BerriAI/litellm_test_model_openai_client
...
[Test] Proxy - uses the same OpenAI Client after 1 min
2024-05-10 16:54:45 -07:00
Ishaan Jaff
e3848abdfe
Merge pull request #3569 from BerriAI/litellm_fix_bug_upsert_deployments
...
[Fix] Upsert deployment bug
2024-05-10 16:53:59 -07:00
Ishaan Jaff
92b86056cf
fix langfuse team based logging tests
2024-05-10 16:39:49 -07:00
Ishaan Jaff
53f9d8280f
fix - support dynamic failure callbacks
2024-05-10 16:37:01 -07:00
Ishaan Jaff
1a8e853817
(ci/cd) run again
2024-05-10 16:19:03 -07:00
Ishaan Jaff
b6e0f00ed8
fix - using failure callbacks with team based logging
2024-05-10 16:18:13 -07:00
Ishaan Jaff
7d96272d52
fix auto inferring region
2024-05-10 16:08:05 -07:00
Krrish Dholakia
30d2df8940
docs(enterprise.md): add aws marketplace notice on docs
2024-05-10 15:54:29 -07:00
Krrish Dholakia
6a400a6200
test: fix test
2024-05-10 15:49:20 -07:00
Nick Wong
759ff3f750
added code to enforce unique key and team aliases in the ui
2024-05-10 15:42:07 -07:00
Krrish Dholakia
500995696a
test: fix linting
2024-05-10 14:42:06 -07:00
Krrish Dholakia
d4d175030f
docs(huggingface.md): add text-classification to huggingface docs
2024-05-10 14:39:14 -07:00
Krrish Dholakia
50be25d11a
test(test_optional_params.py): fix optional params
2024-05-10 14:08:47 -07:00
Ishaan Jaff
c744851d13
fix AUTO_INFER_REGION
2024-05-10 14:08:38 -07:00
Krrish Dholakia
c17f221b89
test(test_completion.py): reintegrate testing for huggingface tgi + non-tgi
2024-05-10 14:07:01 -07:00
Ishaan Jaff
9bbb13c373
fix bug upsert_deployment
2024-05-10 13:54:52 -07:00
Ishaan Jaff
933f8ed16b
fix - proxy_server.py
2024-05-10 13:47:35 -07:00
Ishaan Jaff
414af64343
test - OpenAI client is re-used for Azure, OpenAI
2024-05-10 13:43:19 -07:00
Ishaan Jaff
5c69515a13
fix - upsert_deployment logic
2024-05-10 13:41:51 -07:00
Ishaan Jaff
547976448f
fix feature flag logic
2024-05-10 12:50:46 -07:00
Ishaan Jaff
75d6658bbc
fix - explain why behind feature flag
2024-05-10 12:39:19 -07:00
Ishaan Jaff
6fd6490d63
fix hide - _auto_infer_region behind a feature flag
2024-05-10 12:38:06 -07:00
Ishaan Jaff
9d3f01c6ae
fix - router add model logic
2024-05-10 12:32:16 -07:00
Krrish Dholakia
781d5888c3
docs(predibase.md): add support for predibase to docs
2024-05-10 10:58:35 -07:00
Krish Dholakia
8a35354dd6
Merge pull request #3378 from duckboy81/patch-1
...
Expand access for other jwt algorithms
2024-05-10 10:07:36 -07:00
Krrish Dholakia
cdec7a414f
test(test_router_fallbacks.py): fix test
2024-05-10 09:58:40 -07:00
Krrish Dholakia
40e19a838c
bump: version 1.37.1 → 1.37.2
2024-05-10 08:40:31 -07:00
Krrish Dholakia
f9a0364bff
bump: version 1.37.0 → 1.37.1
2024-05-10 08:34:01 -07:00
Krrish Dholakia
9a31f3d3d9
fix(main.py): support env var 'VERTEX_PROJECT' and 'VERTEX_LOCATION'
2024-05-10 07:57:56 -07:00
Rajan Paneru
65b07bcb8c
Preserving the Pydantic Message Object
...
Following statement replaces the Pydantic Message Object and initialize it with the dict
model_response["choices"][0]["message"] = response_json["message"]
We need to make sure message is always litellm.Message object
As a fix, based on the code of ollama.py file, i am updating just the content intead of entire object for both sync and async functions
2024-05-10 22:12:32 +09:30
Rajan Paneru
8eb842dcf5
revered the patch so that the fix can be applied in the main place
2024-05-10 22:04:44 +09:30
Antonio Loison
c0c244006f
deps: remove diskcache from dependencies and add install in docs
2024-05-10 12:34:05 +02:00
Antonio Loison
9c1d312fdd
docs: add disk cache doc and update cache arguments
2024-05-10 12:17:03 +02:00
Simon Sanchez Viloria
e1372de9ee
Merge branch 'main' into feature/watsonx-integration
2024-05-10 12:09:09 +02:00
Antonio Loison
79c3d39d67
build(caching.py): move diskcache import inside class and add cache_dir argument to Cache
2024-05-10 12:04:54 +02:00
Simon Sanchez Viloria
d3d82827ed
(test) Add tests for WatsonX completion/acompletion streaming
2024-05-10 11:55:58 +02:00
Simon Sanchez Viloria
170fd11c82
(fix) watsonx.py: Fixed linting errors and make sure stream chunk always return usage
2024-05-10 11:53:33 +02:00
Antonio Loison
c1ba4ec078
chore: add diskcache as extra dependency
2024-05-10 11:19:14 +02:00
Antonio Loison
7ee07cd961
test(test_caching.py): use mock_response in disk cache test
2024-05-10 11:00:18 +02:00
Antonio Loison
9b2dcb2807
chore(pyproject.toml): add diskcache as extra
2024-05-10 10:56:36 +02:00
Antonio Loison
004877c7e5
build(caching.py): add disk option for cache
2024-05-10 10:03:38 +02:00
Antonio Loison
ac27f431a4
test(test_caching.py): add disk cache test when using completion
2024-05-10 10:03:38 +02:00
