Krrish Dholakia
8fbc34e7e9
docs(routing.md): add dynamic cooldowns to docs
2024-06-25 17:01:58 -07:00
Krrish Dholakia
d98e00d1e0
fix(router.py): set cooldown_time: per model
2024-06-25 16:51:55 -07:00
Krrish Dholakia
e813e984f7
fix(predibase.py): support json schema on predibase
2024-06-25 16:03:47 -07:00
Krrish Dholakia
6889a4c0dd
fix(utils.py): predibase exception mapping - map 424 as a badrequest error
2024-06-25 13:47:38 -07:00
Krrish Dholakia
6e02ac0056
fix(utils.py): add coverage for anthropic content policy error - vertex ai
2024-06-25 11:47:39 -07:00
Krrish Dholakia
cccc55213b
fix(router.py): improve error message returned for fallbacks
2024-06-25 11:27:20 -07:00
Ishaan Jaff and GitHub
2bd993039b
Merge pull request #4405 from BerriAI/litellm_update_mock_completion
...
[Fix] - use `n` in mock completion responses
2024-06-25 11:20:30 -07:00
Ishaan Jaff
ccf1bbc5d7
fix using mock completion
2024-06-25 11:14:40 -07:00
Krrish Dholakia
71b7c2886b
docs(reliability.md): add doc on mock testing fallbacks
2024-06-25 11:07:07 -07:00
Krrish Dholakia
0396d484fb
feat(router.py): support mock testing content policy + context window fallbacks
2024-06-25 10:58:19 -07:00
Ishaan Jaff
343e3f3e90
test - test_mock_request_n_greater_than_1
2024-06-25 10:54:18 -07:00
Ishaan Jaff
a230f5f6c5
feat - use n in mock completion
2024-06-25 10:50:47 -07:00
Ishaan Jaff and GitHub
6f51da4e78
Merge pull request #4403 from BerriAI/litellm_add_nvidia_nim
...
[Feat-New Provider] Add Nvidia NIM
2024-06-25 10:36:28 -07:00
Ishaan Jaff and GitHub
b9f83f48ba
Merge pull request #4364 from BerriAI/litellm_use_tracemalloc_mem_usage
...
[Feat] add endpoint to debug memory util
2024-06-25 10:32:52 -07:00
Ishaan Jaff
b4497acfc2
ci/cd run again
2024-06-25 09:48:49 -07:00
Ishaan Jaff
100f245fef
docs nvidia_nim
2024-06-25 09:46:42 -07:00
Ishaan Jaff
bac5dfb30b
docs - add nvidia nim
2024-06-25 09:38:34 -07:00
Krish Dholakia and GitHub
e2a50b66f2
Update README.md
2024-06-25 09:24:00 -07:00
Krish Dholakia and GitHub
e354840f90
Update README.md
2024-06-25 09:23:19 -07:00
Ishaan Jaff
e5f281074f
test - nvidia nim
2024-06-25 09:16:31 -07:00
Ishaan Jaff
07829514d1
feat - add param mapping for nvidia nim
2024-06-25 09:13:08 -07:00
Ishaan Jaff
d829d6393d
feat - add nvidia nim to main.py
2024-06-25 08:57:11 -07:00
Ishaan Jaff and GitHub
39a2b41e16
Merge pull request #4401 from kiriloman/main
...
Fix Groq Prices
2024-06-25 08:56:07 -07:00
Ishaan Jaff
abf919eef2
add nvidia nim to __init__
2024-06-25 08:53:06 -07:00
Kyrylo Yefimenko
8765e120f0
Fix Groq prices
2024-06-25 16:36:40 +01:00
Krish Dholakia and GitHub
75c8f77d9a
Merge pull request #4373 from CorrM/main
...
[Fix-Improve] Improve Ollama prompt input and fix Ollama function calling key error
2024-06-25 06:27:43 -07:00
corrm
5b720137fd
Improve ollama prompt: this formula give good result with AutoGen
2024-06-25 13:53:27 +03:00
corrm
b69a092f56
Rename ollama prompt:
...
- 'Function' word to 'FunctionName'
- 'Tool Call' to `FunctionCall`
- 'Tool Call Result' to 'FunctionCall Result'
_I found that changes make some models better_
2024-06-25 12:40:07 +03:00
Krrish Dholakia
86cb5aa031
docs(routing.md): add quickstart
2024-06-24 22:25:39 -07:00
Krrish Dholakia
f8b390d421
fix(langfuse.py): cleanup
2024-06-24 21:43:40 -07:00
Ishaan Jaff
93dbdf6d92
bump: version 1.40.25 → 1.40.26
2024-06-24 21:15:36 -07:00
Ishaan Jaff and GitHub
a9d1be71ff
Merge pull request #4395 from BerriAI/litelm_use_spend_calc_aliases
...
Fix /spend/calculate use model_group_alias when set
2024-06-24 21:15:05 -07:00
Ishaan Jaff
9e7d8ba910
/spend/calculate use model aliases on this endpoint
2024-06-24 21:14:00 -07:00
Krish Dholakia and GitHub
9902947521
Merge pull request #4390 from BerriAI/litellm_langfuse_router_logging
...
Log rejected router requests to langfuse
2024-06-24 21:13:45 -07:00
Ishaan Jaff
a64d1de80f
test - aliases on /spend/calculate
2024-06-24 21:13:01 -07:00
Ishaan Jaff and GitHub
7e5f200c6d
Merge pull request #4394 from BerriAI/docs_enterprise_control_routes
...
docs control available public routes
2024-06-24 20:57:00 -07:00
Ishaan Jaff
7f8c502a44
docs control available public routes
2024-06-24 20:54:43 -07:00
Ishaan Jaff and GitHub
37f2712bba
Merge pull request #4389 from BerriAI/litellm_allow_user_to_define_public_routes
...
[Feat-Enterprise] - Allow setting custom public routes
2024-06-24 20:23:35 -07:00
Krish Dholakia and GitHub
5d570e7c6c
Merge pull request #4392 from BerriAI/litellm_gemini_content_policy_errors
...
fix(vertex_httpx.py): cover gemini content violation (on prompt)
2024-06-24 20:00:06 -07:00
Ishaan Jaff
2aa0ce50b5
fix importing litellm
2024-06-24 19:58:53 -07:00
Ishaan Jaff
bd2298eba4
example cofnig with public routes
2024-06-24 19:51:23 -07:00
Ishaan Jaff
5e1403cd0a
add helper to check route_in_additonal_public_routes
2024-06-24 19:50:35 -07:00
Krrish Dholakia
d182ea0f77
fix(utils.py): catch 422-status errors
2024-06-24 19:41:48 -07:00
Ishaan Jaff
11117665e1
test - spend/calculate endpoints
2024-06-24 19:32:52 -07:00
Krish Dholakia and GitHub
95f972ee9f
Merge pull request #4388 from BerriAI/litellm_custom_model_info
...
Support custom model info for router logic (e.g. `max_input_tokens`)
2024-06-24 19:31:37 -07:00
Krrish Dholakia
8e6e5a6d37
fix(vertex_httpx.py): Return empty model response for content filter violations
2024-06-24 19:22:20 -07:00
Krrish Dholakia
1ff0129a94
fix(vertex_httpx.py): cover gemini content violation (on prompt)
2024-06-24 19:13:56 -07:00
Ishaan Jaff
02ffed2545
feat - refactor /spend/calculate
2024-06-24 19:05:34 -07:00
Krrish Dholakia
a4bea47a2d
fix(router.py): log rejected router requests to langfuse
...
Fixes issue where rejected requests weren't being logged
2024-06-24 17:52:01 -07:00
Ishaan Jaff
5309be2456
example config with public routes
2024-06-24 17:46:38 -07:00
Krrish Dholakia