ishaan-jaff
|
4e8e3ff33a
|
(fix) async custom logger - trigger when stream completed
|
2023-12-08 17:25:05 -08:00 |
|
Krrish Dholakia
|
5fa2b6e5ad
|
fix(proxy_server.py): enable pre+post-call hooks and max parallel request limits
|
2023-12-08 17:11:30 -08:00 |
|
ishaan-jaff
|
76d0c50523
|
(ci/cd) comment beta test
|
2023-12-08 14:27:53 -08:00 |
|
ishaan-jaff
|
73984504e9
|
(test) proxy: access model_info and request_obj
|
2023-12-08 14:26:18 -08:00 |
|
ishaan-jaff
|
14d57ec7de
|
(feat) proxy: log model_info + proxy_server request
|
2023-12-08 14:26:18 -08:00 |
|
ishaan-jaff
|
93b1df1c79
|
(feat) embedding - pass model_info, proxy_server request
|
2023-12-08 14:26:18 -08:00 |
|
ishaan-jaff
|
9805269bd7
|
(feat) proxy: pass model_info as kwargs
|
2023-12-08 14:26:18 -08:00 |
|
ishaan-jaff
|
be94a8c478
|
(feat) pass model_info, proxy_server_request to callback
|
2023-12-08 14:26:18 -08:00 |
|
ishaan-jaff
|
72cca2e5a7
|
(feat) pass model_info, proxy_server_request callback
|
2023-12-08 14:26:18 -08:00 |
|
Krrish Dholakia
|
bab958561e
|
fix(proxy/utils.py): correctly raise exceptions on db call fail
|
2023-12-08 13:35:42 -08:00 |
|
Krrish Dholakia
|
9f0b83248a
|
fix(proxy/utils.py): add backoff/retry logic to db read/writes
|
2023-12-08 13:34:31 -08:00 |
|
ishaan-jaff
|
b8e9e1edc9
|
(fix) test caching
|
2023-12-08 13:15:00 -08:00 |
|
Krrish Dholakia
|
f06c3e0f08
|
fix(proxy_server.py): initializing sentry in proxy logging before db init
|
2023-12-08 11:58:16 -08:00 |
|
ishaan-jaff
|
fa8ba9dd4e
|
(test) cache + streaming
|
2023-12-08 11:50:37 -08:00 |
|
ishaan-jaff
|
6e8ad10991
|
(feat) caching - streaming caching support
|
2023-12-08 11:50:37 -08:00 |
|
ishaan-jaff
|
9b0afbe2cb
|
(fix) bug - caching: gen cache key in order
|
2023-12-08 11:50:37 -08:00 |
|
Krrish Dholakia
|
7aec95ed7c
|
feat(proxy_server.py): add sentry logging for db read/writes
|
2023-12-08 11:40:19 -08:00 |
|
Krrish Dholakia
|
4e6a8d09d0
|
fix(proxy/utils.py): tracking db failed writes
|
2023-12-08 10:40:02 -08:00 |
|
Krrish Dholakia
|
1b35736797
|
fix(utils.py): fix cost calculation to handle tool input
|
2023-12-08 09:53:46 -08:00 |
|
Krrish Dholakia
|
9494c2cd9e
|
fix(requirements.txt): add ollama async_generator in requirements.txt
|
2023-12-08 09:20:04 -08:00 |
|
Krrish Dholakia
|
2f1c5aa0c7
|
fix: setting cache responses on proxy
|
2023-12-07 20:39:40 -08:00 |
|
Krrish Dholakia
|
f5afc429b3
|
fix(proxy_server.py): add call hooks pre+post completion and embedding calls
|
2023-12-07 20:35:32 -08:00 |
|
Krrish Dholakia
|
dfba305508
|
test: test_router.py
fix router testing
n
|
2023-12-07 20:10:36 -08:00 |
|
Krrish Dholakia
|
9cf3051ea2
|
feat(proxy_server.py): enable background health checks
|
2023-12-07 19:40:06 -08:00 |
|
ishaan-jaff
|
b8b15435b7
|
(test) undo fd04b48
|
2023-12-07 18:38:51 -08:00 |
|
ishaan-jaff
|
f99e3a3818
|
(fix) undo commit fd04b48
|
2023-12-07 18:37:06 -08:00 |
|
ishaan-jaff
|
3f4fe668a8
|
(ci/cd) vertex ai test
|
2023-12-07 18:20:58 -08:00 |
|
ishaan-jaff
|
fd04b48764
|
(feat) async callbacks with litellm.completion()
|
2023-12-07 18:09:57 -08:00 |
|
ishaan-jaff
|
762f28e4d7
|
(fix) make print_verbose non blocking
|
2023-12-07 17:31:32 -08:00 |
|
ishaan-jaff
|
2da50087b0
|
(fix) logging - better prints for async logger
|
2023-12-07 17:31:32 -08:00 |
|
Krrish Dholakia
|
4c0e95aec9
|
test: fix proxy custom logger test
|
2023-12-07 15:19:11 -08:00 |
|
Krrish Dholakia
|
91ce50338a
|
fix(_redis.py): check if string before checking os.environ
|
2023-12-07 15:08:11 -08:00 |
|
Krrish Dholakia
|
b92f1af301
|
test: cleaning up local testing
|
2023-12-07 14:20:14 -08:00 |
|
Krrish Dholakia
|
3846ec6124
|
fix(utils.py): fix get_llm_provider to handle the ':' in anthropic/bedrock calls
|
2023-12-07 14:19:11 -08:00 |
|
Krrish Dholakia
|
2b04dc310a
|
test: skip local proxy test in circle ci
|
2023-12-07 13:56:23 -08:00 |
|
ishaan-jaff
|
f236dae79d
|
(test) async logger + proxy
|
2023-12-07 13:54:27 -08:00 |
|
ishaan-jaff
|
5ddfaa33f3
|
(feat) proxy - async logger class + embeddings
|
2023-12-07 13:54:08 -08:00 |
|
Krrish Dholakia
|
e5638e2c5d
|
fix(router.py): fix default caching response value
|
2023-12-07 13:44:31 -08:00 |
|
ishaan-jaff
|
418099085c
|
(test) proxy - async logger, strict check async_success
|
2023-12-07 13:44:17 -08:00 |
|
ishaan-jaff
|
2bc583c2a6
|
(test) proxy - async custom logger
|
2023-12-07 13:19:17 -08:00 |
|
ishaan-jaff
|
0354d6d48f
|
(ci/cd) vertex test
|
2023-12-07 12:41:39 -08:00 |
|
ishaan-jaff
|
19f1035f5a
|
(ci/cd) vertex ai testing
|
2023-12-07 11:36:20 -08:00 |
|
Krrish Dholakia
|
d77e0cc716
|
docs(config.md): adding docs on parallel request rate limiting
|
2023-12-07 11:27:48 -08:00 |
|
ishaan-jaff
|
077f6b1298
|
(ci/cd) vertex ai
|
2023-12-07 11:19:29 -08:00 |
|
James4Ever0
|
69fc2694bb
|
Update factory.py
Fixing issue when calling from write-the -> langchain -> litellm served ollama
|
2023-12-08 02:58:28 +08:00 |
|
ishaan-jaff
|
90d474ff21
|
(ci/cd) vertex ai
|
2023-12-07 10:50:58 -08:00 |
|
ishaan-jaff
|
85668ff415
|
(ci/cd) vertex ai
|
2023-12-07 10:44:45 -08:00 |
|
ishaan-jaff
|
8dd6786123
|
(ci/cd) vertex ai
|
2023-12-07 10:39:24 -08:00 |
|
ishaan-jaff
|
0f8225c3eb
|
(ci/cd) use relative path for vertex
|
2023-12-07 10:38:06 -08:00 |
|
ishaan-jaff
|
378f211a29
|
(ci/cd) debugging
|
2023-12-07 10:36:58 -08:00 |
|