Krrish Dholakia
|
3955b058ed
|
fix(vertex_httpx.py): support streaming via httpx client
|
2024-06-12 19:55:14 -07:00 |
|
Krrish Dholakia
|
3b913443fe
|
feat(vertex_httpx.py): Moving to call vertex ai via httpx (instead of their sdk). Allows us to support all their api updates.
|
2024-06-12 16:47:00 -07:00 |
|
Krrish Dholakia
|
fb96f07ccb
|
docs(raw_request_prod.md): add seeing raw request / response for proxy on docs
|
2024-06-12 11:00:29 -07:00 |
|
Krrish Dholakia
|
2e0dae608a
|
docs(bedrock.md): add provider specific param info to bedrock docs
|
2024-06-12 10:57:40 -07:00 |
|
Krrish Dholakia
|
c059352908
|
docs(enterprise.md): add logging spend with custom metadata
|
2024-06-12 08:55:03 -07:00 |
|
Ishaan Jaff
|
2c0493f753
|
Merge pull request #4145 from BerriAI/litellm_add_embedding_004
[Feat] add VertexAI `vertex_ai/text-embedding-004` , `vertex_ai/text-multilingual-embedding-002 `
|
2024-06-12 08:51:07 -07:00 |
|
Krrish Dholakia
|
31cb1269f5
|
fix(proxy/_types.py): support logging k,v pairs to spend logs with spend_logs_metadata param
|
2024-06-12 08:42:35 -07:00 |
|
Ishaan Jaff
|
c23ab09779
|
docs - text-embedding-004
|
2024-06-12 08:39:26 -07:00 |
|
Ishaan Jaff
|
3af2d7846e
|
add text-embedding-004
|
2024-06-12 08:31:37 -07:00 |
|
Ishaan Jaff
|
f1c1dddb8b
|
ci/cd run again
|
2024-06-11 23:28:09 -07:00 |
|
Ishaan Jaff
|
1b21aa6157
|
(ci/cd) run again
|
2024-06-11 23:22:43 -07:00 |
|
Ishaan Jaff
|
5ebeb4d067
|
ci/cd fix predibase 500 errors
|
2024-06-11 23:15:48 -07:00 |
|
Ishaan Jaff
|
a9e61ef96d
|
(ci/cd) run again
|
2024-06-11 22:03:47 -07:00 |
|
Ishaan Jaff
|
b507c54385
|
fix new team test
|
2024-06-11 22:03:03 -07:00 |
|
Ishaan Jaff
|
6d2134ad2a
|
Merge pull request #4138 from BerriAI/litellm_log_management_endpoint_logs_otel
[FEAT] log management endpoint logs to otel
|
2024-06-11 19:00:13 -07:00 |
|
Krrish Dholakia
|
54f9faac79
|
fix(__init__.py): fix linting error
|
2024-06-11 18:42:01 -07:00 |
|
Krish Dholakia
|
029d32344f
|
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
|
75b0d7821b
|
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
|
ef6e920161
|
Added handling of unmapped provider, with test
|
2024-06-11 18:34:10 -07:00 |
|
Ishaan Jaff
|
995b1e7315
|
fix when user_api_key_dict is None
|
2024-06-11 18:33:15 -07:00 |
|
Krish Dholakia
|
7c23077a71
|
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
|
a53ba9b2fb
|
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
|
8be37bee04
|
Added simple test of get_supported_openai_params with no custom provider
|
2024-06-11 18:18:21 -07:00 |
|
James Braza
|
cb5456c9f5
|
Allowing inferring custom LLM provider from model inside get_supported_openai_params
|
2024-06-11 18:16:19 -07:00 |
|
Ishaan Jaff
|
b10ac0d1f3
|
fix linting error
|
2024-06-11 18:14:06 -07:00 |
|
Ishaan Jaff
|
f5b10a47e3
|
Merge pull request #4136 from jamesbraza/adding-mypy-dev-group
Added `mypy` to the Poetry `dev` group
|
2024-06-11 18:14:00 -07:00 |
|
Krrish Dholakia
|
b0daeba8e7
|
build(requirements.txt): make sure tiktoken v0.7.0 is provided
|
2024-06-11 18:11:08 -07:00 |
|
Ishaan Jaff
|
fba7d2e623
|
fix team endpoints
|
2024-06-11 18:10:20 -07:00 |
|
Krrish Dholakia
|
0ab0111d57
|
test(test_team.py): fix error string asserted
|
2024-06-11 18:05:20 -07:00 |
|
Ishaan Jaff
|
7ad981b85c
|
fix - log mgmt data to OTEL
|
2024-06-11 18:05:10 -07:00 |
|
Ishaan Jaff
|
51b78422df
|
fix http_request
|
2024-06-11 17:57:50 -07:00 |
|
Krrish Dholakia
|
a9cbf2209c
|
fix(utils.py): support dynamic api key for azure_ai route
|
2024-06-11 17:51:29 -07:00 |
|
Ishaan Jaff
|
479a39cebd
|
fix test new team
|
2024-06-11 17:48:11 -07:00 |
|
Krrish Dholakia
|
a1ca70a8a7
|
fix: more bug fixes
|
2024-06-11 17:41:59 -07:00 |
|
Krrish Dholakia
|
6305d2dbcf
|
fix(__init__.py): add 'log_raw_request_response' flag to init
|
2024-06-11 17:26:03 -07:00 |
|
Ishaan Jaff
|
30f74aa471
|
fix import error
|
2024-06-11 17:17:57 -07:00 |
|
Ishaan Jaff
|
427f2ee1fa
|
feat - otel log /team exceptions
|
2024-06-11 16:27:07 -07:00 |
|
Ishaan Jaff
|
f2abac748e
|
fix refactor management endpoint utils
|
2024-06-11 16:16:10 -07:00 |
|
Krrish Dholakia
|
c27ae34a39
|
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
|
13cb49688a
|
feat - log management endpoint logs to otel
|
2024-06-11 16:09:11 -07:00 |
|
Krrish Dholakia
|
9c7788ae48
|
fix(utils.py): fix formatting
|
2024-06-11 15:49:20 -07:00 |
|
Krrish Dholakia
|
2d8e4ddfa0
|
fix(main.py): trigger new build
|
2024-06-11 15:13:50 -07:00 |
|
James Braza
|
917e8678db
|
Added mypy to the dev Poetry group
|
2024-06-11 14:43:32 -07:00 |
|
Ishaan Jaff
|
5eb2822d31
|
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
|
d7f1445615
|
doc - OTEL trace propogation
|
2024-06-11 14:25:33 -07:00 |
|
Krrish Dholakia
|
61a450d0fc
|
docs(azure_ai.md): add updated azure ai routing docs
|
2024-06-11 14:18:34 -07:00 |
|
Krrish Dholakia
|
f40d47942f
|
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
|
88e567af2c
|
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
|
d829e6a297
|
test - propogate trace IDs across services
|
2024-06-11 14:00:25 -07:00 |
|
Ishaan Jaff
|
7ce1289548
|
feat - use traceparent to proporgate OTEL traces
|
2024-06-11 13:57:31 -07:00 |
|