Commit graph

616 commits

Author SHA1 Message Date
Ased Mammad
c39c8f70eb
fix(proxy_server.py) Check when '_hidden_params' is None 2024-01-02 19:04:51 +03:30
Krrish Dholakia
940569703e feat(proxy_server.py): add slack alerting to proxy server
add alerting for calls hanging, failing and db read/writes failing

https://github.com/BerriAI/litellm/issues/1298
2024-01-02 17:45:18 +05:30
ishaan-jaff
c27b1fc5f8 (feat) proxy swagger - make admin link clickable 2024-01-02 17:04:32 +05:30
ishaan-jaff
6d2b9fd470 (feat) use - user router for aembedding 2024-01-02 12:27:08 +05:30
ishaan-jaff
0acaaf8f8f (test) sustained load test proxy 2024-01-02 12:10:34 +05:30
ishaan-jaff
ddc31c4810 (feat) proxy - use user_config for /chat/compeltions 2024-01-02 12:10:34 +05:30
Krrish Dholakia
e1e3721917 build(user.py): fix page param read issue 2024-01-01 17:25:52 +05:30
Krrish Dholakia
a41e56a730 fix(proxy_server.py): enabling user auth via ui
https://github.com/BerriAI/litellm/issues/1231
2024-01-01 17:14:24 +05:30
Krrish Dholakia
ca40a88987 fix(proxy_server.py): check if user email in user db 2024-01-01 14:19:59 +05:30
ishaan-jaff
7623c1a846 (feat) proxy - only use print_verbose 2024-01-01 13:52:11 +05:30
Krrish Dholakia
24e7dc359d feat(proxy_server.py): introduces new /user/auth endpoint for handling user email auth
decouples streamlit ui from proxy server. this then requires the proxy to handle user auth separately.
2024-01-01 13:44:47 +05:30
ishaan-jaff
52db2a6040 (feat) proxy - remove streamlit ui on startup 2024-01-01 12:54:23 +05:30
ishaan-jaff
c8f8bd9e57 (test) proxy - log metadata to langfuse 2024-01-01 11:54:16 +05:30
ishaan-jaff
694956b44e (test) proxy - pass metadata to openai client 2024-01-01 11:12:57 +05:30
ishaan-jaff
dacd86030b (fix) proxy - remove extra print statemet 2024-01-01 10:52:09 +05:30
ishaan-jaff
16fb83e007 (fix) proxy - remove errant print statement 2024-01-01 10:48:12 +05:30
Krrish Dholakia
8ff3bbcfee fix(proxy_server.py): router model group alias routing
check model alias group routing before specific deployment routing, to deal with an alias being the same as a deployment name (e.g. gpt-3.5-turbo)

n
2023-12-30 17:55:24 +05:30
Krrish Dholakia
38f55249e1 fix(router.py): support retry and fallbacks for atext_completion 2023-12-30 11:19:32 +05:30
Krrish Dholakia
cbcf406fd0 feat(admin_ui.py): support creating keys on admin ui 2023-12-28 16:59:11 +05:30
Krrish Dholakia
71a8b95710 refactor(proxy_server.py): make print statements into print_verbose 2023-12-28 15:08:23 +05:30
Krrish Dholakia
e5a287379a refactor(proxy_server.py): move admin ui to be locally hosted within proxy 2023-12-28 15:06:32 +05:30
ishaan-jaff
3919710823 (docs) proxy - swagger docs, add tags for model/info 2023-12-28 13:13:04 +05:30
ishaan-jaff
ab90b547d8 (fix) proxy - raise error when user missing litellm[proxy] 2023-12-28 13:07:44 +05:30
Krrish Dholakia
bf4c4426e5 fix(proxy_server.py): return [DONE] end of stream chunk 2023-12-28 11:30:49 +05:30
Krrish Dholakia
3b1685e7c6 feat(health_check.py): more detailed health check calls 2023-12-28 09:12:57 +05:30
ishaan-jaff
c1a8e30b01 (feat) proxy - remove appdirs 2023-12-27 17:40:05 +05:30
ishaan-jaff
07ea2e26f4 (fix) proxy - remove bloat - deprecated log_input_output 2023-12-27 17:36:53 +05:30
ishaan-jaff
74ea0832ca (feat) proxy remove appdirs as a dep 2023-12-27 17:33:47 +05:30
ishaan-jaff
af15e49948 (feat) proxy - remove subprocess install 2023-12-27 17:28:03 +05:30
Krrish Dholakia
9ba520cc8b fix(google_kms.py): support enums for key management system 2023-12-27 13:19:33 +05:30
Krrish Dholakia
235526625d feat(proxy_server.py): support maxage cache control 2023-12-26 17:50:27 +05:30
Krrish Dholakia
167a6ba319 refactor(google_kms.py): fix linting issue 2023-12-26 16:21:35 +05:30
Krrish Dholakia
2070a785a4 feat(utils.py): support google kms for secret management
https://github.com/BerriAI/litellm/issues/1235
2023-12-26 15:39:40 +05:30
Krrish Dholakia
871f207124 docs(user_keys.md): docs on passing user keys to litellm proxy 2023-12-26 13:55:28 +05:30
ishaan-jaff
d273d19bd9 (feat) proxy, use --model with --test 2023-12-26 09:40:58 +05:30
Krrish Dholakia
4905929de3 refactor: add black formatting 2023-12-25 14:11:20 +05:30
Krrish Dholakia
b3a98d8400 fix(proxy_server.py): accept keys with none duration 2023-12-25 13:46:24 +05:30
Krrish Dholakia
9f79f75635 fix(proxy/utils.py): return different exceptions if key is invalid vs. expired
https://github.com/BerriAI/litellm/issues/1230
2023-12-25 10:29:44 +05:30
Krrish Dholakia
402b2e5733 build(test_streaming.py): fix linting issues 2023-12-25 07:34:54 +05:30
Krrish Dholakia
343a06fd84 fix(proxy_server.py): raise streaming exceptions 2023-12-25 07:18:09 +05:30
Krrish Dholakia
b4b4a7d43a Revert "test(test_azure_perf.py): add perf testing for router streaming"
This reverts commit 4fa7f19888.
2023-12-23 13:19:07 +05:30
Krrish Dholakia
4fa7f19888 test(test_azure_perf.py): add perf testing for router streaming 2023-12-23 13:16:49 +05:30
Krish Dholakia
8afdc12918
Merge pull request #1211 from sihyeonn/fix/sh-success-callback
fix: success_callback logic for cost_tracking
2023-12-23 11:41:30 +05:30
Krrish Dholakia
89ee9fe400 fix(proxy_server.py): manage budget at user-level not key-level
https://github.com/BerriAI/litellm/issues/1220
2023-12-22 15:10:38 +05:30
Krrish Dholakia
979575a2a6 fix(proxy_server.py): handle misformatted json body in chat completion request 2023-12-22 12:30:36 +05:30
Krrish Dholakia
278f61f3ed fix(utils.py): handle 'os.environ/' being passed in as kwargs 2023-12-22 11:08:44 +05:30
Krrish Dholakia
1a32228da5 feat(proxy_server.py): support max budget on proxy 2023-12-21 16:07:20 +05:30
Krrish Dholakia
14115d0d60 feat(proxy_server.py): add new images/generation endpoint 2023-12-21 15:39:09 +05:30
Krrish Dholakia
81078c4004 fix(proxy/utils.py): jsonify object before db writes 2023-12-21 13:03:14 +05:30
Sihyeon Jang
4f41c3c513 fix: success_callback logic for cost_tracking
Signed-off-by: Sihyeon Jang <uneedsihyeon@gmail.com>
2023-12-21 16:09:59 +09:00