Krrish Dholakia
|
a858cc4d0c
|
docs(main.py): clarify 'num_retries' usage
|
2024-08-09 16:57:06 -07:00 |
|
Krrish Dholakia
|
ba7b070883
|
fix(utils.py): set max_retries = num_retries, if given
|
2024-08-09 16:54:54 -07:00 |
|
Krrish Dholakia
|
9f0a05d406
|
fix(utils.py): only return non-null default values
|
2024-08-09 16:34:59 -07:00 |
|
Ishaan Jaff
|
3548a55277
|
Merge pull request #5139 from BerriAI/litellm_log_vertex_metadata_as_spans
[Feat-Langfuse] log VertexAI Grounding Metadata as Spans
|
2024-08-09 14:52:59 -07:00 |
|
Ishaan Jaff
|
2fa73acf32
|
Merge pull request #5138 from BerriAI/litellm_bedrock_tool_calling
Feat - Translate openai function names to bedrock converse schema
|
2024-08-09 14:52:40 -07:00 |
|
Ishaan Jaff
|
3e2a1fe0aa
|
log provider specific metadata as a span
|
2024-08-09 14:32:02 -07:00 |
|
Ishaan Jaff
|
6dc9b39095
|
test invalid tool namehandling
|
2024-08-09 13:26:21 -07:00 |
|
Ishaan Jaff
|
8b98193a51
|
bedrock make_valid_bedrock_tool_name
|
2024-08-09 13:16:38 -07:00 |
|
Krrish Dholakia
|
177f670c7d
|
build(test_completion.py): ci/cd run again
|
2024-08-09 12:28:26 -07:00 |
|
Ishaan Jaff
|
2f8db40cab
|
ui new build
|
2024-08-09 12:26:24 -07:00 |
|
Krrish Dholakia
|
6180c52cfe
|
fix(router.py): fix types
|
2024-08-09 12:24:48 -07:00 |
|
Ishaan Jaff
|
db7897dcc0
|
Merge pull request #5136 from BerriAI/litellm_add_cohere_embedding_models
ui allow adding cohere models
|
2024-08-09 12:19:19 -07:00 |
|
Ishaan Jaff
|
f260c1a043
|
Merge pull request #5134 from BerriAI/litellm_refactor_promt
[Feat] v2 prometheus deployment outage, healthy, partial outage alerting
|
2024-08-09 12:18:40 -07:00 |
|
Krrish Dholakia
|
7b6db63d30
|
fix(router.py): fallback on 400-status code requests
|
2024-08-09 12:16:49 -07:00 |
|
Ishaan Jaff
|
05a4555fe7
|
ui add cohere embedding models
|
2024-08-09 12:11:02 -07:00 |
|
Ishaan Jaff
|
e734568b5a
|
fix cohere / cohere_chat when timeout is None
|
2024-08-09 12:10:02 -07:00 |
|
Ishaan Jaff
|
df024fbbbc
|
add testing for cohere embeddings
|
2024-08-09 12:08:25 -07:00 |
|
Ishaan Jaff
|
f8b0118ecd
|
Merge pull request #5137 from BerriAI/litellm_add_cohere_embedding_model_pricing
[Feat] Add pricing for cohere embedding models
|
2024-08-09 11:32:40 -07:00 |
|
Ishaan Jaff
|
9b5693a5a2
|
ui allow adding cohere models
|
2024-08-09 11:30:34 -07:00 |
|
Ishaan Jaff
|
c8997e3986
|
add cohere embed-multilingual-v2.0
|
2024-08-09 11:30:07 -07:00 |
|
Krrish Dholakia
|
0cf81eba62
|
fix(huggingface_restapi.py): support passing 'wait_for_model' param on completion calls
|
2024-08-09 09:25:19 -07:00 |
|
Krrish Dholakia
|
466dc9f32a
|
fix(huggingface_restapi.py): fix hf embeddings optional param processing
|
2024-08-09 09:10:56 -07:00 |
|
Ishaan Jaff
|
fc9086759d
|
docs prometheus metrics
|
2024-08-09 09:07:31 -07:00 |
|
Ishaan Jaff
|
0b9ad45790
|
refactor prom metrics
|
2024-08-09 09:02:23 -07:00 |
|
Krrish Dholakia
|
d471f7e840
|
feat(vertex_httpx.py): return vertex grounding, citation, and safety results
|
2024-08-09 08:54:55 -07:00 |
|
Krrish Dholakia
|
51ccfa9e77
|
fix(huggingface_restapi.py): fixes issue where 'wait_for_model' was not being passed as expected
|
2024-08-09 08:36:35 -07:00 |
|
Ishaan Jaff
|
a1c3167853
|
doc Grounding vertex ai
|
2024-08-09 08:31:38 -07:00 |
|
Ishaan Jaff
|
baaa444c8f
|
docs fix typo
|
2024-08-09 08:17:36 -07:00 |
|
Krrish Dholakia
|
dde477494f
|
docs(self_serve.md): add internal_user_budget_duration to docs
|
2024-08-08 23:54:26 -07:00 |
|
Krrish Dholakia
|
f0f19a9457
|
bump: version 1.43.4 → 1.43.5
|
2024-08-08 23:47:01 -07:00 |
|
Krish Dholakia
|
a41e892967
|
Merge pull request #5129 from BerriAI/litellm_sso_team_member_add
Litellm sso team member add
|
2024-08-08 23:34:14 -07:00 |
|
Krish Dholakia
|
3d259f1883
|
Merge branch 'main' into litellm_sso_team_member_add
|
2024-08-08 23:34:06 -07:00 |
|
Ishaan Jaff
|
30ab7191d6
|
ui new build
|
2024-08-08 23:30:51 -07:00 |
|
Ishaan Jaff
|
8f585f4234
|
sort providers alphabetical order
|
2024-08-08 23:29:08 -07:00 |
|
Ishaan Jaff
|
032a2e31a3
|
ui add mistral ai
|
2024-08-08 23:29:08 -07:00 |
|
Ishaan Jaff
|
2245711e69
|
ui new build
|
2024-08-08 23:29:08 -07:00 |
|
Ishaan Jaff
|
ad2acb1f6a
|
add groq through admin ui
|
2024-08-08 23:27:52 -07:00 |
|
Ishaan Jaff
|
a6d9789bc0
|
ui show litellm model name
|
2024-08-08 23:27:26 -07:00 |
|
Ishaan Jaff
|
8df074719a
|
docs vertex context caching
|
2024-08-08 23:27:02 -07:00 |
|
Ishaan Jaff
|
7135a0a60e
|
docs vertex
|
2024-08-08 23:27:02 -07:00 |
|
Ishaan Jaff
|
309ed056bf
|
docs cachedContent endpoint
|
2024-08-08 23:27:02 -07:00 |
|
Ishaan Jaff
|
b8b7644154
|
auto update the model in cachedContents request
|
2024-08-08 23:27:02 -07:00 |
|
Ishaan Jaff
|
780f574e4f
|
add native cachedContents endpoint
|
2024-08-08 23:27:02 -07:00 |
|
Ishaan Jaff
|
b5be4a2ea0
|
doc on using litellm proxy with vertex ai content caching
|
2024-08-08 23:26:47 -07:00 |
|
Ishaan Jaff
|
27e50d0344
|
add example using litellm proxy with gemini context caching
|
2024-08-08 23:26:25 -07:00 |
|
Krrish Dholakia
|
42ce03466d
|
fix(anthropic.py): fix translation from /v1/messages format to openai format
|
2024-08-08 23:26:14 -07:00 |
|
Krrish Dholakia
|
81a0a8ab22
|
fix(internal_user_endpoints.py): expose new 'internal_user_budget_duration' flag
Relevant to - https://github.com/BerriAI/litellm/issues/5106
|
2024-08-08 23:26:01 -07:00 |
|
Krrish Dholakia
|
a4e9512e98
|
test: skip flaky langsmith tests
|
2024-08-08 23:25:42 -07:00 |
|
Krrish Dholakia
|
f6097d54ff
|
test(test_langsmith.py): fix test
|
2024-08-08 23:25:42 -07:00 |
|
Krrish Dholakia
|
e56ece6ee1
|
fix(user_api_key_auth.py): Fixes https://github.com/BerriAI/litellm/issues/5111
|
2024-08-08 23:25:42 -07:00 |
|