ishaan-jaff
|
be1bbb2dcd
|
(test) test exceptions
|
2024-01-15 22:01:33 -08:00 |
|
ishaan-jaff
|
00ac18e8b7
|
(feat) improve bedrock, sagemaker exception mapping
|
2024-01-15 21:22:22 -08:00 |
|
ishaan-jaff
|
60586fc37f
|
(test) proxy rules
|
2024-01-15 21:11:50 -08:00 |
|
ishaan-jaff
|
a8f2550c25
|
(ci/cd) openrouter unstable - use other model
|
2024-01-15 17:43:56 -08:00 |
|
ishaan-jaff
|
c50d8afc86
|
(test) test_post_call_rule
|
2024-01-15 17:17:43 -08:00 |
|
ishaan-jaff
|
4e6a238820
|
(test) hf currently loading error
|
2024-01-15 17:07:49 -08:00 |
|
ishaan-jaff
|
63e80056e5
|
(test) proxy exception mapping
|
2024-01-15 10:43:54 -08:00 |
|
ishaan-jaff
|
f0d001658a
|
(test) proxy exception mapping - exactly like OpenAI
|
2024-01-15 10:43:26 -08:00 |
|
Ishaan Jaff
|
ad06b08a5e
|
Merge pull request #1442 from BerriAI/litellm_bedrock_provisioned_throughput
[Feat] Support Bedrock provisioned throughput LLMs
|
2024-01-14 10:51:28 +05:30 |
|
ishaan-jaff
|
719b051b3d
|
(test) provisioned throughput model
|
2024-01-13 15:56:24 -08:00 |
|
ishaan-jaff
|
0307ba7def
|
(test) bedrock provisioned througput
|
2024-01-13 15:40:30 -08:00 |
|
ishaan-jaff
|
fffb077cf6
|
(test) get optional_params Azure
|
2024-01-13 14:32:41 -08:00 |
|
ishaan-jaff
|
f62dbd0e08
|
(test) litellm.completion_cost mistral, anyscale
|
2024-01-13 12:35:09 -08:00 |
|
ishaan-jaff
|
4b3e9c6b38
|
(ci/cd) run testing again
|
2024-01-13 11:50:43 -08:00 |
|
ishaan-jaff
|
f3d25d2c27
|
(test) hidden params in stream_chunk builder
|
2024-01-13 11:10:23 -08:00 |
|
ishaan-jaff
|
99dcce1e0f
|
(test) aembedding includes custom_llm_provider
|
2024-01-12 17:52:14 -08:00 |
|
ishaan-jaff
|
c1686b264f
|
(test) embedding hidden params
|
2024-01-12 17:35:33 -08:00 |
|
ishaan-jaff
|
f85b64b85c
|
(test) custom_llm_provider in streaming response
|
2024-01-12 17:15:15 -08:00 |
|
ishaan-jaff
|
70899521ae
|
(test) custom_llm_provider in hidden params
|
2024-01-12 17:09:59 -08:00 |
|
Krrish Dholakia
|
51110bfb62
|
fix(main.py): support text completion routing
|
2024-01-12 11:24:31 +05:30 |
|
Krrish Dholakia
|
d895979065
|
test(test_health_check.py): fix test
|
2024-01-12 00:21:11 +05:30 |
|
ishaan-jaff
|
b7567865de
|
(test) caching for bedrock/embedding str inputs
|
2024-01-11 23:12:57 +05:30 |
|
ishaan-jaff
|
276d11946e
|
(test) bedrock - embedding with strings
|
2024-01-11 23:04:41 +05:30 |
|
ishaan-jaff
|
a876748bf5
|
v0
|
2024-01-11 22:56:18 +05:30 |
|
ishaan-jaff
|
bb8eac0597
|
(test) improve s3 logging test
|
2024-01-11 16:57:51 +05:30 |
|
Ishaan Jaff
|
e5b491b39f
|
Merge pull request #1413 from BerriAI/litellm_log_cache_hits
[Feat] Proxy - Log Cache Hits on success callbacks + Testing
|
2024-01-11 16:39:22 +05:30 |
|
ishaan-jaff
|
4a1541c485
|
(fix) retry gemini-pro-vision 3 times
|
2024-01-11 14:39:08 +05:30 |
|
ishaan-jaff
|
cc78e003bf
|
(test) s3 log cache hits
|
2024-01-11 11:44:48 +05:30 |
|
ishaan-jaff
|
cf86af46a8
|
(fix) litellm.acompletion with type hints
|
2024-01-11 10:47:12 +05:30 |
|
Ishaan Jaff
|
2433d6c613
|
Merge pull request #1200 from MateoCamara/explicit-args-acomplete
feat: added explicit args to acomplete
|
2024-01-11 10:39:05 +05:30 |
|
ishaan-jaff
|
0b20ab7d2b
|
(feat) proxy - support s3_callback_params
|
2024-01-11 09:57:47 +05:30 |
|
ishaan-jaff
|
f263cf51ea
|
(test) s3 logs for /chat/completions
|
2024-01-11 09:16:06 +05:30 |
|
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 |
|