Commit graph

4555 commits

Author SHA1 Message Date
ishaan-jaff
9a35f347ab (test) - caching - override when caching = False 2023-12-14 16:20:29 +05:30
ishaan-jaff
008df34ddc (feat) use async_cache for acompletion/aembedding 2023-12-14 16:04:45 +05:30
ishaan-jaff
a8e12661c2 (fix) caching - get_cache_key - dont use set 2023-12-14 14:09:24 +05:30
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
b6b371b051 bump: version 1.14.0 → 1.14.1 2023-12-13 16:20:37 -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
Krish Dholakia
03d6dcefbb
Merge pull request #1123 from nirga/patch-1
fix: traceloop links
2023-12-13 14:52:11 -08:00
Krrish Dholakia
88d09fc5a7 fix(vertex.md): adding gemini-pro support to docs 2023-12-13 14:38:55 -08:00
Nir Gazit
590f0173bc
fix: traceloop links 2023-12-13 22:23:29 +01:00
Krrish Dholakia
7b8851cce5 fix(ollama.py): fix async completion calls for ollama 2023-12-13 13:10:25 -08:00
Krrish Dholakia
52375e0377 bump: version 1.14.0.dev1 → 1.14.0 2023-12-13 12:36:29 -08:00
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
625df3c256 bump: version 1.13.2 → 1.14.0.dev1 2023-12-13 10:26:55 -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
Krish Dholakia
7e1a355b77
Adding gemini-pro to model cost map 2023-12-13 09:51:49 -08:00
ishaan-jaff
86e626edab (feat) pass vertex_ai/ as custom_llm_provider 2023-12-13 19:02:24 +03:00
ishaan-jaff
6846f656e6 add chat-bison@002 2023-12-13 18:58:42 +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
Krrish Dholakia
c9b83ff853 bump: version 1.13.1 → 1.13.2 2023-12-12 22:02:17 -08:00
Krrish Dholakia
f9dfeb502a fix(langfuse.py): serialize message for logging 2023-12-12 21:41:05 -08:00
ishaan-jaff
7856d65d44 (docs) proxy dockerfile 2023-12-12 19:44:55 -08:00
ishaan-jaff
03edba5ff5 (docs) router on config 2023-12-12 19:41:11 -08:00
ishaan-jaff
c294d2c506 (docs) proxy - how to set router_settings 2023-12-12 19:35:21 -08:00
Krish Dholakia
1b94256889
Merge pull request #995 from wallies/patch-1
multistage docker build
2023-12-12 17:32:46 -08:00
Krrish Dholakia
9d008396b3 bump: version 1.13.0 → 1.13.1 2023-12-12 17:28:32 -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
2ebaaf1ea2 bump: version 1.12.9 → 1.13.0 2023-12-12 17:21:47 -08:00
Krrish Dholakia
693292a64c feat(proxy_server.py): add new /key/update endpoint 2023-12-12 17:18:51 -08:00
Krrish Dholakia
23a4ac724b bump: version 1.12.8 → 1.12.9 2023-12-12 16:46:31 -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
7efcc550e2 bump: version 1.12.7 → 1.12.8 2023-12-12 15:49:53 -08:00
Krrish Dholakia
a266ad0319 refactor(proxy_server.py): code cleanup 2023-12-12 15:49:41 -08:00