ishaan-jaff
|
df0f689027
|
(test) s3 logging
|
2024-01-11 08:58:03 +05:30 |
|
Krrish Dholakia
|
65928cd5f2
|
test(test_tpm_rpm_routing.py): add more logging for the test
|
2024-01-11 00:43:14 +05:30 |
|
Krrish Dholakia
|
969594a4b1
|
test(test_router.py): handle rate limiting error
|
2024-01-11 00:00:17 +05:30 |
|
Krrish Dholakia
|
61f2fe5837
|
fix(main.py): fix streaming completion token counting error
|
2024-01-10 23:44:35 +05:30 |
|
Krrish Dholakia
|
3080f27b54
|
fix(utils.py): raise correct error for azure content blocked error
|
2024-01-10 23:31:51 +05:30 |
|
Krrish Dholakia
|
6a8d518e44
|
test(test_lowest_latency_routing.py): use the correct cache key
|
2024-01-10 22:15:01 +05:30 |
|
ishaan-jaff
|
1ff9785c6b
|
(fix) test - moved to circe ci dockerfile
|
2024-01-10 21:54:13 +05:30 |
|
Krrish Dholakia
|
954d1b071c
|
test: remove invalid arg
|
2024-01-10 21:53:29 +05:30 |
|
Krrish Dholakia
|
9a829ff956
|
refactor: cleanup duplicates
|
2024-01-10 21:42:20 +05:30 |
|
Krish Dholakia
|
298e937586
|
Merge branch 'main' into litellm_latency_routing_updates
|
2024-01-10 21:33:54 +05:30 |
|
Krrish Dholakia
|
7f269e92c5
|
test(test_completion_with_retries.py): remove duplicate test
|
2024-01-10 21:17:30 +05:30 |
|
Krrish Dholakia
|
14a65eb730
|
test(test_proxy_server_keys.py): removing as this is now tested via the docker build job
|
2024-01-10 21:05:12 +05:30 |
|
Krrish Dholakia
|
162f6f1ed3
|
refactor: refactor key tests
|
2024-01-10 20:58:29 +05:30 |
|
Krrish Dholakia
|
0d86c4ce5b
|
refactor: move proxy server key testing
|
2024-01-10 20:56:52 +05:30 |
|
Krrish Dholakia
|
990c32a5d6
|
test(test_router.py): handle image gen timeouts
|
2024-01-10 20:56:52 +05:30 |
|
Krrish Dholakia
|
fe632c08a4
|
fix(router.py): allow user to control the latency routing time window
|
2024-01-10 20:56:52 +05:30 |
|
Krrish Dholakia
|
bb04a340a5
|
fix(lowest_latency.py): add back tpm/rpm checks, configurable time window
|
2024-01-10 20:52:01 +05:30 |
|
ishaan-jaff
|
f6012124b7
|
(fix) test for captured caplog
|
2024-01-10 13:17:34 +05:30 |
|
ishaan-jaff
|
a064786f3d
|
(ci/cd) retry deployed proxy test 3 times
|
2024-01-10 13:10:16 +05:30 |
|
Mateo Cámara
|
203089e6c7
|
Merge branch 'main' into explicit-args-acomplete
|
2024-01-09 13:07:37 +01:00 |
|
Mateo Cámara
|
9aedd4e794
|
Moved test to a new file
|
2024-01-09 13:02:12 +01:00 |
|
Ishaan Jaff
|
4cfa010dbd
|
Merge pull request #1381 from BerriAI/litellm_content_policy_violation_exception
[Feat] Add litellm.ContentPolicyViolationError
|
2024-01-09 17:18:29 +05:30 |
|
ishaan-jaff
|
248e5f3d92
|
(chore) remove deprecated completion_with_config() tests
|
2024-01-09 17:13:06 +05:30 |
|
ishaan-jaff
|
c0b56b6575
|
(test) catch litellm.ContentPolicyViolationError
|
2024-01-09 17:04:04 +05:30 |
|
ishaan-jaff
|
f0c10377cf
|
(test) ContentPolicyViolationError
|
2024-01-09 16:53:57 +05:30 |
|
Mateo Cámara
|
bb06c51ede
|
Added test to check if acompletion is using the same parameters as CompletionRequest attributes. Added functools to client decorator to expose acompletion parameters from outside.
|
2024-01-09 12:06:49 +01:00 |
|
ishaan-jaff
|
cf98343eb5
|
(test) content policy violation error
|
2024-01-09 16:34:20 +05:30 |
|
ishaan-jaff
|
47f56f0d19
|
(test) deployed proxy key/gen
|
2024-01-09 16:07:33 +05:30 |
|
Ishaan Jaff
|
cdeb864e28
|
Merge pull request #1376 from BerriAI/litellm_deployed_proxy_prisma
[Test+Fix] Use deployed proxy with Prisma
|
2024-01-09 16:02:27 +05:30 |
|
ishaan-jaff
|
b5f9f05491
|
(test) fix - skip HF is currently loading exception
|
2024-01-09 15:53:19 +05:30 |
|
ishaan-jaff
|
bf65306ec3
|
(chore) undo extra space
|
2024-01-09 15:38:14 +05:30 |
|
ishaan-jaff
|
0434ee4f02
|
(ci/cd) run again
|
2024-01-09 15:32:10 +05:30 |
|
ishaan-jaff
|
916e93f398
|
(ci/cd) user DATABASE_URL to control prisma generate
|
2024-01-09 15:28:37 +05:30 |
|
ishaan-jaff
|
d24d9cb673
|
(ci/cd) run again
|
2024-01-09 15:22:28 +05:30 |
|
ishaan-jaff
|
7e15802388
|
(ci/cd) run again
|
2024-01-09 15:14:51 +05:30 |
|
ishaan-jaff
|
ba4646dbb6
|
(ci/cd) trigger again
|
2024-01-09 15:06:55 +05:30 |
|
ishaan-jaff
|
8f8237a1a0
|
(fix) echo DB URL
|
2024-01-09 13:30:49 +05:30 |
|
ishaan-jaff
|
46bd99ad98
|
(test) test deployed proxy keygen
|
2024-01-09 13:03:22 +05:30 |
|
Krrish Dholakia
|
cd350ab8d8
|
fix(proxy_server.py): don't reconnect prisma if already connected
|
2024-01-09 11:38:42 +05:30 |
|
Krrish Dholakia
|
e97eff4243
|
test(test_router.py): fix router test
|
2024-01-09 11:08:35 +05:30 |
|
ishaan-jaff
|
f46fa2b8a8
|
(fix) test - deprecated textdavinci003
|
2024-01-09 10:55:35 +05:30 |
|
ishaan-jaff
|
9c7a4fde87
|
(test) hosted - ollama catch timeouts
|
2024-01-09 10:35:29 +05:30 |
|
ishaan-jaff
|
5f2cbfc711
|
(feat) litellm.completion - support ollama timeout
|
2024-01-09 10:34:41 +05:30 |
|
Krrish Dholakia
|
e99a41307a
|
test: testing fixes
|
2024-01-09 10:23:34 +05:30 |
|
ishaan-jaff
|
08525ce200
|
(ci/cd) use 3 retries for image generation
|
2024-01-09 10:07:09 +05:30 |
|
ishaan-jaff
|
9be7e34cb0
|
(ci/cd) pytest skip slow replicate test
|
2024-01-09 09:57:06 +05:30 |
|
Krrish Dholakia
|
88d498a54a
|
fix(ollama.py): use tiktoken as backup for prompt token counting
|
2024-01-09 09:47:18 +05:30 |
|
Krrish Dholakia
|
a5147f9e06
|
feat(lowest_latency.py): support expanded time window for latency based routing
uses a 1hr avg. of latency for deployments, to determine which to route to
https://github.com/BerriAI/litellm/issues/1361
|
2024-01-09 09:38:04 +05:30 |
|
ishaan-jaff
|
6263103680
|
(ci/cd) run again
|
2024-01-08 22:42:31 +05:30 |
|
Krrish Dholakia
|
8edd3fe651
|
test(test_proxy_startup.py): fix gunicorn test
|
2024-01-08 19:55:18 +05:30 |
|