Commit graph

1547 commits

Author SHA1 Message Date
ishaan-jaff
7ddc0dad24 (test) fix test_model_group_aliases 2023-12-06 21:25:30 -08:00
ishaan-jaff
fa70b1f85b (test) unset model_group_alias_map after test 2023-12-06 20:35:14 -08:00
ishaan-jaff
095aa94e71 (fix) linting 2023-12-06 20:26:57 -08:00
ishaan-jaff
ee70c4e822 (feat) router - add model_group_alias_map 2023-12-06 20:13:33 -08:00
Krrish Dholakia
d3e179e5ad test: fix testing 2023-12-06 19:35:12 -08:00
Krrish Dholakia
ac7d0a1632 fix(together_ai.py): improve together ai custom prompt templating 2023-12-06 19:34:49 -08:00
ishaan-jaff
04eecaa493 (test) custom logger on fail 2023-12-06 19:15:08 -08:00
ishaan-jaff
f3469fdef8 (test) aembedding on custom logger 2023-12-06 19:09:06 -08:00
Krrish Dholakia
fff0228c20 fix(factory.py): support togethercomputer codellama pt 2023-12-06 19:02:58 -08:00
Krrish Dholakia
d4c6cc3920 test: fix testing 2023-12-06 18:52:49 -08:00
Krrish Dholakia
c0eedf28fc test: fix proxy server testing 2023-12-06 18:38:53 -08:00
ishaan-jaff
1b43c7120c (test) custom logger - check kwargs passed all the way 2023-12-06 18:08:48 -08:00
Krrish Dholakia
0295509b3b fix(factory.py): fix claude 2.1 prompt template to handle system, assistant, user prompt 2023-12-06 18:02:06 -08:00
ishaan-jaff
c8c45ef9c4 (test) async custom logger 2023-12-06 17:53:06 -08:00
Krrish Dholakia
45b4140615 test: fix config import for proxy testing 2023-12-06 17:40:38 -08:00
Krrish Dholakia
d814184bc3 test: fix test imports 2023-12-06 17:21:47 -08:00
Krrish Dholakia
d2de7ffe27 test(test_proxy_server_langfuse.py): add langfuse proxy testing 2023-12-06 17:19:17 -08:00
Krrish Dholakia
51492125b5 test: skip flaky test 2023-12-06 16:50:02 -08:00
Krrish Dholakia
f1c1ec8523 fix(bedrock.py): fix embeddings call 2023-12-06 14:16:00 -08:00
Krrish Dholakia
346551da29 fix(proxy_server.py): allow worker config to just be the config filepath 2023-12-06 14:03:25 -08:00
Krrish Dholakia
d962d5d4c0 fix(bedrock.py): adding support for cohere embeddings 2023-12-06 13:25:18 -08:00
Krrish Dholakia
94f065f83c feat(sagemaker.py): support huggingface embedding models 2023-12-06 11:41:38 -08:00
Krrish Dholakia
f6546076b0 docs(quick_start.md): add docs on calling openai-compatible endpoint on proxy 2023-12-06 11:06:09 -08:00
ishaan-jaff
cc48b35a8d (test) router - read os.environ/ OpenAI 2023-12-06 10:56:27 -08:00
ishaan-jaff
8f47293ce8 (chore) linting fix 2023-12-06 10:48:01 -08:00
ishaan-jaff
01aa8941a5 (test) OTEL / traceloop - waiting for async support 2023-12-06 10:08:37 -08:00
ishaan-jaff
11a8713a50 (test) router - set sync stream client 2023-12-06 10:08:37 -08:00
ishaan-jaff
bd0579703c (test) router - reading os.environ/ with client 2023-12-06 09:26:21 -08:00
ishaan-jaff
527aadd1ab (test) router - reading os.environ/ variables 2023-12-06 09:19:51 -08:00
ishaan-jaff
5e065ebb8f (test) router - explcitly call one deployment 2023-12-05 21:57:00 -08:00
Krrish Dholakia
7b83238cb5 fix(router.py): log when a call is retried or fallback happens 2023-12-05 21:29:58 -08:00
Krrish Dholakia
648d41c96f fix(sagemaker.py): prompt templating fixes 2023-12-05 17:47:44 -08:00
ishaan-jaff
0eccc1b1f8 (test) router: call 1 deployment 2023-12-05 17:35:35 -08:00
ishaan-jaff
1fa9ddd739 (chore) linting fix 2023-12-05 17:29:09 -08:00
ishaan-jaff
703a575a5d (test) call 1 deployment on router 2023-12-05 16:56:38 -08:00
Krrish Dholakia
ff949490de docs(input.md): add hf_model_name to docs 2023-12-05 16:56:18 -08:00
Krrish Dholakia
54d8a9df3f fix(sagemaker.py): enable passing hf model name for prompt template 2023-12-05 16:31:59 -08:00
Krrish Dholakia
b4c78c7b9e fix(utils.py): support sagemaker llama2 custom endpoints 2023-12-05 16:05:15 -08:00
Krrish Dholakia
68ca2a28d4 docs: adds redis url to router + proxy docs 2023-12-05 15:08:00 -08:00
ishaan-jaff
c717ed4d05 (test) router: test async embedding + embedding 2023-12-05 14:28:23 -08:00
ishaan-jaff
3ff57493f4 (test) router: openai async, sync, stream, no stream 2023-12-05 14:21:37 -08:00
ishaan-jaff
bc70a6fba8 (test) router: add tests for azure completion, acompletion 2023-12-05 13:59:27 -08:00
ishaan-jaff
0d1b42eda5 (test) azure - test async + sync embedding 2023-12-05 13:35:05 -08:00
ishaan-jaff
1463cc6023 (test) router Azure regular chat completion call 2023-12-05 13:28:07 -08:00
ishaan-jaff
e579918dd9 (test) Router: Test Azure acompletion, stream 2023-12-05 13:22:27 -08:00
ishaan-jaff
5829227d86 (test) router streaming + azure 2023-12-05 12:54:00 -08:00
Krrish Dholakia
b46c73a46e fix: fix proxy testing 2023-12-05 11:13:09 -08:00
ishaan-jaff
3bdf61f02a (test) test bedrock on router 2023-12-05 09:35:08 -08:00
ishaan-jaff
9ba17657ad (feat) init redis cache with **kwargs 2023-12-04 20:50:08 -08:00
Krrish Dholakia
030bd22078 feat(proxy_server.py): allow user to override api key auth 2023-12-04 18:32:58 -08:00