Commit graph

408 commits

Author SHA1 Message Date
Krrish Dholakia
add4dfc528 fix(proxy_server.py): support model info augmenting for azure models 2023-12-02 21:33:54 -08:00
ishaan-jaff
ecddb852a2 (fix) proxy: pydantic error / warning message 2023-12-02 21:30:35 -08:00
Krrish Dholakia
47c1aa27c7 fix(proxy_server.py): add litellm model cost map info to /model/info 2023-12-02 21:24:28 -08:00
Krrish Dholakia
f0d8a87c48 fix(proxy_server.py): fix user param name sent to litellm.completion 2023-12-02 19:56:22 -08:00
Krrish Dholakia
5200818af1 fix(proxy_server.py): Passing user IDs to OpenAI to identify abusive virtual keys 2023-12-02 19:55:11 -08:00
Krrish Dholakia
492c9043f6 fix: fix linting issues 2023-12-02 19:30:03 -08:00
Krrish Dholakia
6b1b1b82cf fix(proxy_server.py): hash keys 2023-12-02 19:30:03 -08:00
Krrish Dholakia
722c325503 fix(proxy_server.py): update db with master key if set, and fix tracking cost for azure models 2023-12-02 15:58:08 -08:00
Krrish Dholakia
5a4c054eef fix(proxy_server.py): add testing for model info being added to /model/new 2023-12-02 14:15:45 -08:00
ishaan-jaff
da78fd617c (docs) proxy: OTEL 2023-12-02 11:56:02 -08:00
ishaan-jaff
6866895a27 (fix) proxy: config reading error 2023-12-02 11:09:38 -08:00
ishaan-jaff
54c5736f81 (fix) otel - make it optional 2023-12-02 11:02:03 -08:00
ishaan-jaff
5edb529891 (feat) proxy: embedding add OTEL collector 2023-12-02 09:41:29 -08:00
ishaan-jaff
4830aa08ee (fix) linting error 2023-12-02 09:39:26 -08:00
ishaan-jaff
dd8c1b0458 (feat) allow users to set OTEL_ENDPOINT as env 2023-12-01 21:29:26 -08:00
ishaan-jaff
2a25d9c15d (feat) proxy: name OTEL logger 2023-12-01 21:08:25 -08:00
ishaan-jaff
3e62f90b43 (feat) proxy: add OTEL logging input/output 2023-12-01 21:04:07 -08:00
Krrish Dholakia
60af976aac fix(proxy_server.py): expose model_info as part of pydantic model params object 2023-12-01 20:55:26 -08:00
Krrish Dholakia
bb687cb96f fix(proxy_server.py): redact api keys from proxy load 2023-12-01 20:47:13 -08:00
Krrish Dholakia
47730da262 fix(proxy_server.py): fix linting errors 2023-12-01 20:40:49 -08:00
Krrish Dholakia
72381c3cc2 feat(proxy_server.py): dynamic reloading config.yaml with new models 2023-12-01 20:32:24 -08:00
Krrish Dholakia
328113a28e fix(proxy_server.py): fix linting errors 2023-12-01 19:45:09 -08:00
Krrish Dholakia
368fee224e feat: support for azure key vault 2023-12-01 19:36:06 -08:00
Krrish Dholakia
cac7ecf840 fix(proxy_server.py): check if bearer token passed in 2023-12-01 17:06:29 -08:00
ishaan-jaff
61f902347f (proxy) fix types 2023-12-01 16:05:29 -08:00
ishaan-jaff
80e2ffbfa6 (feat) proxy: use dict 2023-12-01 16:00:00 -08:00
Krrish Dholakia
4da20ac0b9 fix(proxy_server.py): accept max tokens as int 2023-12-01 15:19:34 -08:00
Krrish Dholakia
8c1439e910 fix: linting errors 2023-12-01 15:02:22 -08:00
ishaan-jaff
fc40e83783 (fix) linting 2023-12-01 14:51:44 -08:00
ishaan-jaff
455c915b70 (linting) fix 2023-12-01 14:34:15 -08:00
ishaan-jaff
24386c05aa (fix) proxy: pydantic 2023-12-01 13:58:28 -08:00
ishaan-jaff
e8ae347681 (feat) proxy-pydantic,swagger for chat/completion 2023-12-01 13:50:51 -08:00
ishaan-jaff
e77b7e5a50 (docs) proxy: add tags=chat/completions + add response type 2023-12-01 10:00:48 -08:00
ishaan-jaff
2977d04f56 (fix) proxy: raise exceptions 2023-12-01 09:21:06 -08:00
ishaan-jaff
1e9aa69268 (fix) proxy: use orjson.loads() 2023-11-30 20:24:31 -08:00
ishaan-jaff
06805c7f47 (fix) formatting 2023-11-30 20:03:56 -08:00
ishaan-jaff
10d5ab8643 (feat) proxy: /embedding -> use ORJSON responses 2023-11-30 20:00:35 -08:00
ishaan-jaff
2d55cc753e (feat) proxy: use orjson 2023-11-30 19:50:47 -08:00
Frank Colson
7ddfeb75bc Add backwards compatability 2023-11-30 16:35:19 -07:00
Frank Colson
5e6913dff2 Use poetry extras for proxy 2023-11-30 16:23:34 -07:00
ishaan-jaff
bc2299184b (fix) proxy - don't overwrite metadata passed 2023-11-30 15:15:47 -08:00
Krrish Dholakia
062ede96e3 refactor(proxy_server.py): fix linting issues 2023-11-30 09:24:59 -08:00
Krrish Dholakia
b4b7acdb72 fix(utils.py): fix azure completion cost calculation 2023-11-30 09:19:35 -08:00
Krrish Dholakia
7ee089b5ca fix(proxy_server.py): provide an endpoint that gives model-specific info from proxy 2023-11-30 09:08:19 -08:00
ishaan-jaff
a56d4a1e83 (fix) proxy: print cwd() 2023-11-30 08:52:06 -08:00
ishaan-jaff
e5ce45dc2c (cleanup) proxy/health 2023-11-29 20:15:52 -08:00
Krrish Dholakia
50cc4a8595 fix(proxy_server.py): have /health and /routes be router endpoints 2023-11-29 19:59:56 -08:00
ishaan-jaff
3cc8305ec6 (fix) proxy: /health 2023-11-29 16:23:37 -08:00
ishaan-jaff
66bc0fc343 (fix) proxy: /health works with router updates 2023-11-29 16:09:31 -08:00
ishaan-jaff
f307e82a41 (fix) proxy: making receiving data print_verbose 2023-11-29 07:50:52 -08:00