ishaan-jaff
|
85b07f8165
|
(test) gemini is an unstable API
|
2024-02-28 18:52:28 -08:00 |
|
Krish Dholakia
|
7d2a9f9222
|
Merge pull request #2236 from BerriAI/litellm_faster_usage_logs_pg_db
fix(proxy_server.py): introduces a beta endpoint for admin to view global spend
|
2024-02-28 17:08:55 -08:00 |
|
Krrish Dholakia
|
cf3022f156
|
test: skip aws test - aws account suspended
|
2024-02-28 16:56:55 -08:00 |
|
Krrish Dholakia
|
129e84f0c5
|
test: removing aws tests - account suspended - pending their approval
|
2024-02-28 13:46:20 -08:00 |
|
ishaan-jaff
|
f21eed7c0c
|
(ci/cd) run again
|
2024-02-28 11:55:40 -08:00 |
|
ishaan-jaff
|
6021421135
|
(ci/cd) run again
|
2024-02-27 20:49:04 -08:00 |
|
ishaan-jaff
|
35b36aa53f
|
(ci/cd) run again
|
2024-02-27 20:35:06 -08:00 |
|
ishaan-jaff
|
f2f1d6becc
|
(ci/cd) run again
|
2024-02-26 18:54:21 -08:00 |
|
Krrish Dholakia
|
96f39265f6
|
test(test_completion.py): remove deprecated together ai model
|
2024-02-22 21:33:34 -08:00 |
|
ishaan-jaff
|
968bea03fd
|
(ci/cd) run again
|
2024-02-21 22:27:24 -08:00 |
|
Krrish Dholakia
|
75d30cd000
|
test: handle api errors for gemini/palm testing
|
2024-02-21 21:44:08 -08:00 |
|
Krrish Dholakia
|
0a1e32510d
|
test(test_completion.py): handle palm failing
|
2024-02-21 20:44:44 -08:00 |
|
Krrish Dholakia
|
11c12e7381
|
fix(gemini.py): fix async streaming + add native async completions
|
2024-02-19 22:41:36 -08:00 |
|
ishaan-jaff
|
e8b9eff72f
|
(ci/cd) run again
|
2024-02-17 19:23:40 -08:00 |
|
Krrish Dholakia
|
a7d0f19e6c
|
test(test_completion.py): handle azure gpt-4 vision internal error
|
2024-02-16 13:16:46 -08:00 |
|
Krrish Dholakia
|
79105b0996
|
fix: fix tests
|
2024-02-15 21:27:54 -08:00 |
|
Krrish Dholakia
|
f7c17f52d6
|
test(test_completion.py): skip flaky test
|
2024-02-15 16:38:22 -08:00 |
|
ishaan-jaff
|
afff73e38e
|
(fix) fix moderation test
|
2024-02-14 11:40:58 -08:00 |
|
Krrish Dholakia
|
d7459347ff
|
test(test_completion.py): fix test
|
2024-02-13 22:13:48 -08:00 |
|
ishaan-jaff
|
57aed8c7cd
|
(ci/cd) run again
|
2024-02-13 07:08:26 -08:00 |
|
ishaan-jaff
|
b4335dbad5
|
(ci/cd) run again
|
2024-02-12 22:20:42 -08:00 |
|
ishaan-jaff
|
09014e4b64
|
(ci/cd) run again
|
2024-02-12 21:58:13 -08:00 |
|
ishaan-jaff
|
d565b4cf6f
|
(ci/cd) run again
|
2024-02-12 21:46:48 -08:00 |
|
Krrish Dholakia
|
6b00bee6f4
|
test: api error handling
|
2024-02-12 09:11:46 -08:00 |
|
Krrish Dholakia
|
07aa05bf17
|
fix(test_parallel_request_limiter.py): use mock responses for streaming
|
2024-02-08 21:45:38 -08:00 |
|
Krrish Dholakia
|
6e2c8732c9
|
fix(bedrock.py): raise exception for amazon titan null response
|
2024-02-08 21:12:25 -08:00 |
|
ishaan-jaff
|
7e13750710
|
(ci/cd) runn again
|
2024-02-07 17:13:13 -08:00 |
|
ishaan-jaff
|
14637573a3
|
(ci/cd) run again
|
2024-02-07 16:55:38 -08:00 |
|
ishaan-jaff
|
54ace0933e
|
(fix) model_prices_and_context_window.json error
|
2024-02-07 15:42:37 -08:00 |
|
ishaan-jaff
|
fc50abe6d1
|
(ci/cd) run again
|
2024-02-06 18:25:15 -08:00 |
|
ishaan-jaff
|
3017377740
|
(ci/cd) run again
|
2024-02-06 16:08:25 -08:00 |
|
ishaan-jaff
|
ad4b6be3ee
|
(ci/cd) run again
|
2024-02-06 14:00:27 -08:00 |
|
Krrish Dholakia
|
84a60c7957
|
test(test_completion.py): fix test
|
2024-02-06 13:29:47 -08:00 |
|
Krrish Dholakia
|
dccd72fea1
|
fix(utils.py): round max tokens to be int always
|
2024-02-06 13:10:52 -08:00 |
|
ishaan-jaff
|
1e0f7fe167
|
(ci/cd) run again
|
2024-02-06 13:02:36 -08:00 |
|
ishaan-jaff
|
5c71590b84
|
(ci/cd) run again
|
2024-02-06 12:53:47 -08:00 |
|
ishaan-jaff
|
04a2e1f610
|
(ci/cd) run again
|
2024-02-06 12:22:24 -08:00 |
|
ishaan-jaff
|
e008f67637
|
(ci/cd) run in verbose mode
|
2024-02-06 10:57:20 -08:00 |
|
Krish Dholakia
|
92d50616c2
|
Merge pull request #1805 from BerriAI/litellm_cost_tracking_image_gen
feat(utils.py): support cost tracking for openai/azure image gen models
|
2024-02-03 22:23:22 -08:00 |
|
Krrish Dholakia
|
bd9c1764cb
|
test(test_completion.py): fix test
|
2024-02-03 21:44:57 -08:00 |
|
Krrish Dholakia
|
64dfb0a7cb
|
test(test_completion.py): fix test
|
2024-02-03 21:30:45 -08:00 |
|
Krish Dholakia
|
bf79d265d8
|
Merge pull request #1809 from BerriAI/litellm_embedding_caching_updates
Support caching individual items in embedding list (Async embedding only)
|
2024-02-03 21:04:23 -08:00 |
|
ishaan-jaff
|
26178104c2
|
(ci/cd) run again
|
2024-02-03 20:36:35 -08:00 |
|
ishaan-jaff
|
3dfe23de86
|
(test) tgai is unstable
|
2024-02-03 20:00:40 -08:00 |
|
Krrish Dholakia
|
740eda84ee
|
fix(utils.py): support get_secret("TOGETHER_AI_TOKEN")
|
2024-02-03 19:35:09 -08:00 |
|
Krrish Dholakia
|
85a3515d83
|
fix(utils.py): route together ai calls to openai client
together ai is now openai-compatible
n
|
2024-02-03 19:22:48 -08:00 |
|
Krrish Dholakia
|
20eff6839a
|
test(test_completion.py): skip flaky test
|
2024-02-02 18:44:17 -08:00 |
|
Krrish Dholakia
|
df815042de
|
fix(main.py): for health checks, don't use cached responses
|
2024-02-02 16:51:42 -08:00 |
|
Krrish Dholakia
|
71ee4524c5
|
fix(utils.py): fix azure exception mapping
|
2024-02-01 19:05:20 -08:00 |
|
ishaan-jaff
|
6167eb159c
|
(ci/cd) run again
|
2024-01-31 21:04:03 -08:00 |
|