Commit graph

3262 commits

Author SHA1 Message Date
ishaan-jaff
ee6b936377 (test) caching - get cache key for embedding 2023-12-14 14:08:58 +05:30
ishaan-jaff
80fc8050eb (feat) proxy - model group alias 2023-12-14 13:24:10 +05:30
ishaan-jaff
77bcaaae9e (fix) proxy cli --version 2023-12-14 13:22:39 +05:30
ishaan-jaff
b70bfbb06f (test) router - test_model_group_aliases 2023-12-14 13:16:44 +05:30
ishaan-jaff
841e941ecd (test) router - model_group_alias 2023-12-14 13:08:35 +05:30
ishaan-jaff
b7a5ab5ffa (feat) proxy - use model_group_alias 2023-12-14 13:08:14 +05:30
ishaan-jaff
1e48f58443 (fix) custom_callback_input test 2023-12-14 12:40:07 +05:30
ishaan-jaff
241add8b33 (feat) proxy add --version 2023-12-14 12:28:42 +05:30
Krrish Dholakia
73e5b96d8e fix(utils.py): support cache logging for async router calls 2023-12-13 19:11:43 -08:00
Krrish Dholakia
cffd190887 test(test_custom_callback_router.py): fix test 2023-12-13 19:06:02 -08:00
Krrish Dholakia
73ecc012a9 docs(embedding.md): add embedding docs to proxy 2023-12-13 18:58:46 -08:00
Krrish Dholakia
8d688b6217 fix(utils.py): support caching for embedding + log cache hits
n

n
2023-12-13 18:37:30 -08:00
Krrish Dholakia
0f29cda8d9 test(test_amazing_vertex_completion.py): fix testing 2023-12-13 16:41:26 -08:00
Krrish Dholakia
e678009695 fix(vertex_ai.py): add exception mapping for acompletion calls 2023-12-13 16:35:50 -08:00
Krrish Dholakia
effdddc1c8 fix(custom_logger.py): enable pre_call hooks to modify incoming data to proxy 2023-12-13 16:20:37 -08:00
Krrish Dholakia
88d09fc5a7 fix(vertex.md): adding gemini-pro support to docs 2023-12-13 14:38:55 -08:00
Krrish Dholakia
7b8851cce5 fix(ollama.py): fix async completion calls for ollama 2023-12-13 13:10:25 -08:00
Mariusz Woloszyn
1feb6317f6 Fix #1119, no content when streaming. 2023-12-13 21:42:35 +01:00
Krrish Dholakia
75bcb37cb2 fix(factory.py): fix tgai rendering template 2023-12-13 12:27:31 -08:00
Krrish Dholakia
69c29f8f86 fix(vertex_ai.py): add support for real async streaming + completion calls 2023-12-13 11:53:55 -08:00
Krrish Dholakia
07015843ac fix(vertex_ai.py): support optional params + enable async calls for gemini 2023-12-13 11:01:23 -08:00
Krrish Dholakia
ef7a6e3ae1 feat(vertex_ai.py): adds support for gemini-pro on vertex ai 2023-12-13 10:26:30 -08:00
ishaan-jaff
86e626edab (feat) pass vertex_ai/ as custom_llm_provider 2023-12-13 19:02:24 +03:00
Krrish Dholakia
d1aef59fbc fix(utils.py): fix stream chunk builder for sync/async success 2023-12-13 07:52:51 -08:00
Krrish Dholakia
a64bd2ca1e fix(sagemaker.py): filter out templated prompt if in model response 2023-12-13 07:43:33 -08:00
zeeland
79ea466cf5 refactor: add CustomStreamWrapper return type for completion 2023-12-13 22:57:19 +08:00
Krrish Dholakia
f9dfeb502a fix(langfuse.py): serialize message for logging 2023-12-12 21:41:05 -08:00
Krrish Dholakia
82d28a8825 fix(factory.py): safely fail prompt template get requests for together ai 2023-12-12 17:28:22 -08:00
Krrish Dholakia
693292a64c feat(proxy_server.py): add new /key/update endpoint 2023-12-12 17:18:51 -08:00
Krrish Dholakia
8e7116635f fix(ollama.py): add support for async streaming 2023-12-12 16:44:20 -08:00
Krrish Dholakia
dfdb17ae36 test: refactor testing 2023-12-12 16:21:41 -08:00
Krrish Dholakia
669862643b fix(utils.py): flush holding chunk for streaming, on stream end 2023-12-12 16:13:31 -08:00
Krrish Dholakia
a266ad0319 refactor(proxy_server.py): code cleanup 2023-12-12 15:49:41 -08:00
Krrish Dholakia
8b07a6c046 fix(main.py): pass user_id + encoding_format for logging + to openai/azure 2023-12-12 15:46:44 -08:00
Krrish Dholakia
35fa176c97 fix(utils.py): fix logging
n
2023-12-12 15:46:36 -08:00
Krrish Dholakia
1e970841a4 fix(utils.py): more logging 2023-12-12 15:46:27 -08:00
Krrish Dholakia
632d6e0bff fix(utils.py): add more logging 2023-12-12 15:46:12 -08:00
Krrish Dholakia
6e87d1ca18 fix(utils.py): safe fail complete streaming response 2023-12-12 15:46:12 -08:00
Krrish Dholakia
d6669fe9e3 fix(utils.py): add more logging 2023-12-12 15:46:00 -08:00
Krrish Dholakia
bdf29ca71f fix(sagemaker.py): debug streaming 2023-12-12 15:45:07 -08:00
ishaan-jaff
a251a52717 (chore) remove junk tkinter import 2023-12-12 13:54:50 -08:00
ishaan-jaff
6d76878382 (fix) pydantic: Field "model_list" has conflict with protected namespace "model_". 2023-12-12 12:38:11 -08:00
ishaan-jaff
b6b88370ca (fix) from re import T - junk import 2023-12-12 12:26:15 -08:00
ishaan-jaff
eefb2bbf09 (ci/cd) run again 2023-12-12 12:22:14 -08:00
ishaan-jaff
99b48eff17 (fix) tkinter import 2023-12-12 12:18:25 -08:00
Krrish Dholakia
902b68dcbd bump: version 1.12.5.dev1 → 1.12.5 2023-12-12 11:11:09 -08:00
Krrish Dholakia
edbf97adf2 test: testing fixes 2023-12-12 10:57:51 -08:00
Krrish Dholakia
9cf5ab468f fix(router.py): deepcopy initial model list, don't mutate it 2023-12-12 09:54:06 -08:00
ishaan-jaff
a5dd8b1d4a (fix) use deepcopy for model list 2023-12-12 09:53:52 -08:00
ishaan-jaff
f5d64a4992 (fix) test router 2023-12-12 09:50:44 -08:00