ishaan-jaff
|
1b9e992fef
|
(ci/cd) run again
|
2024-01-29 18:24:39 -08:00 |
|
ishaan-jaff
|
cbf6441732
|
(test) fix test_completion_invalid_param_cohere
|
2024-01-29 17:03:58 -08:00 |
|
ishaan-jaff
|
e2a7910113
|
(test) dynamoDB backwards compat
|
2024-01-29 16:53:27 -08:00 |
|
ishaan-jaff
|
ceeaa70349
|
(test) using default key generate params
|
2024-01-29 14:46:36 -08:00 |
|
ishaan-jaff
|
f263677459
|
(ci/cd) cohere api is flaky - run again
|
2024-01-29 12:08:23 -08:00 |
|
ishaan-jaff
|
c304117caa
|
(fix) cohere test
|
2024-01-29 11:36:00 -08:00 |
|
ishaan-jaff
|
3c44a54e7a
|
(ci/cd) run again
|
2024-01-29 11:29:32 -08:00 |
|
ishaan-jaff
|
2e64ca9057
|
(fix) dynamoDB + hashed tokens bug
|
2024-01-29 11:17:27 -08:00 |
|
ishaan-jaff
|
336c8af01e
|
(test) caching, swap out unstable model
|
2024-01-29 11:00:15 -08:00 |
|
ishaan-jaff
|
eb3cab85fb
|
(ci/cd) run again
|
2024-01-29 10:36:25 -08:00 |
|
ishaan-jaff
|
6de59a1744
|
(ci/cd) run again
|
2024-01-29 09:46:44 -08:00 |
|
ishaan-jaff
|
d858f4c027
|
(ci/cd) run again
|
2024-01-29 09:15:53 -08:00 |
|
Krrish Dholakia
|
8d4749b94a
|
test(test_caching.py): fix cache test if embedding call is fast
|
2024-01-26 23:00:59 -08:00 |
|
Krish Dholakia
|
ba4089824d
|
Merge pull request #1646 from BerriAI/litellm_image_gen_cost_tracking_proxy
Litellm image gen cost tracking proxy
|
2024-01-26 22:30:14 -08:00 |
|
Krish Dholakia
|
e1f1e4fefb
|
Merge pull request #1642 from BerriAI/litellm_key_aliases
feat(proxy_server.py): save abbreviated key name if `allow_user_auth` enabled
|
2024-01-26 22:07:17 -08:00 |
|
Krrish Dholakia
|
58052e5d36
|
test(test_key_generate_prisma.py): reset custom auth value
|
2024-01-26 21:12:38 -08:00 |
|
Krrish Dholakia
|
618d216c11
|
fix(openai.py): fix image gen logging
|
2024-01-26 21:04:06 -08:00 |
|
Krrish Dholakia
|
a299ac2328
|
fix(utils.py): enable cost tracking for image gen models on proxy
|
2024-01-26 20:51:13 -08:00 |
|
Krish Dholakia
|
b36f628fc8
|
Merge pull request #1641 from BerriAI/litellm_bedrock_region_based_pricing
feat(utils.py): support region based pricing for bedrock + use bedrock's token counts if given
|
2024-01-26 20:28:16 -08:00 |
|
Krrish Dholakia
|
7412463ebb
|
test: ensure test calls contain bearer token
|
2024-01-26 20:15:35 -08:00 |
|
Krrish Dholakia
|
5dfe54d20d
|
feat(proxy_server.py): save abbreviated key name if allow_user_auth enabled
|
2024-01-26 15:31:37 -08:00 |
|
Krrish Dholakia
|
f5da95685a
|
feat(utils.py): support region based pricing for bedrock + use bedrock's token counts if given
|
2024-01-26 14:53:58 -08:00 |
|
ishaan-jaff
|
8b5e397abe
|
(fix) dynamo - use hashed tokens budget tracking
|
2024-01-26 14:32:34 -08:00 |
|
ishaan-jaff
|
0ee8e8f081
|
(fix) test - prisma key budget tracking
|
2024-01-26 14:31:04 -08:00 |
|
ishaan-jaff
|
17370dc50f
|
(test) dimension param - openai
|
2024-01-26 10:37:01 -08:00 |
|
ishaan-jaff
|
652f4f89d0
|
(test) s3 + r2 logger
|
2024-01-25 21:16:28 -08:00 |
|
ishaan-jaff
|
fa1bbbebf1
|
(fix) r2 s3 logging test
|
2024-01-25 20:49:55 -08:00 |
|
ishaan-jaff
|
4fd2bd230f
|
(fix) test_view_spend_per_user
|
2024-01-25 20:41:31 -08:00 |
|
ishaan-jaff
|
8ed010c428
|
(test) s3 logs - works locally
|
2024-01-25 20:16:33 -08:00 |
|
ishaan-jaff
|
c069acc72e
|
(test) s3 logs
|
2024-01-25 20:13:22 -08:00 |
|
Krish Dholakia
|
612f74a426
|
Merge pull request #1618 from BerriAI/litellm_sagemaker_cost_tracking_fixes
fix(utils.py): fix sagemaker cost tracking for streaming
|
2024-01-25 19:01:57 -08:00 |
|
ishaan-jaff
|
863ff8ba26
|
(test) s3 logging on r2 using env vars
|
2024-01-25 18:36:20 -08:00 |
|
Krrish Dholakia
|
e948b39e3a
|
test(test_streaming.py): fix test to handle none chunk
|
2024-01-25 18:34:13 -08:00 |
|
Krrish Dholakia
|
39aec43b86
|
test(main.py): adding more logging
|
2024-01-25 18:15:24 -08:00 |
|
Krrish Dholakia
|
ac131b3824
|
fix(utils.py): completion_cost support for image gen models
|
2024-01-25 18:08:18 -08:00 |
|
Krrish Dholakia
|
014f83c847
|
fix(main.py): allow vertex ai project and location to be set in completion() call
|
2024-01-25 16:40:23 -08:00 |
|
ishaan-jaff
|
e00f46a6e9
|
(test) gpt-4-0125-preview
|
2024-01-25 16:40:23 -08:00 |
|
ishaan-jaff
|
c10bda3d30
|
(chore) cleanup testing file
|
2024-01-25 16:40:23 -08:00 |
|
ishaan-jaff
|
7e1b9158fe
|
(test) embedding models
|
2024-01-25 16:40:23 -08:00 |
|
Krrish Dholakia
|
fbab810189
|
fix(main.py): allow vertex ai project and location to be set in completion() call
|
2024-01-25 15:00:51 -08:00 |
|
Krrish Dholakia
|
bbe6a92eb9
|
fix(main.py): fix order of assembly for streaming chunks
|
2024-01-25 14:51:08 -08:00 |
|
ishaan-jaff
|
e2d9e40886
|
(test) gpt-4-0125-preview
|
2024-01-25 14:42:10 -08:00 |
|
ishaan-jaff
|
72790f44da
|
(chore) cleanup testing file
|
2024-01-25 14:36:11 -08:00 |
|
ishaan-jaff
|
6cbde02cab
|
(test) embedding models
|
2024-01-25 14:30:49 -08:00 |
|
Krrish Dholakia
|
09ec6d6458
|
fix(utils.py): fix sagemaker async logging for sync streaming
https://github.com/BerriAI/litellm/issues/1592
|
2024-01-25 12:49:45 -08:00 |
|
Krrish Dholakia
|
7e06944d80
|
test(test_dynamodb_logs.py): skip flaky test
|
2024-01-24 23:18:45 -08:00 |
|
Krrish Dholakia
|
12b2ad9ed1
|
fix(proxy_server.py): fix handling none value for existing spend object
|
2024-01-24 20:37:56 -08:00 |
|
Krish Dholakia
|
6501fdb76e
|
Merge branch 'main' into litellm_global_spend_updates
|
2024-01-24 20:20:15 -08:00 |
|
ishaan-jaff
|
3e59a02dfb
|
(test) test /key/gen with max_budget=None
|
2024-01-24 19:27:53 -08:00 |
|
ishaan-jaff
|
6bc715cf85
|
(test) logging cache_key in spendLogs
|
2024-01-24 18:54:23 -08:00 |
|