Krrish Dholakia
|
ba76929303
|
feat(proxy_server.py): dynamic reloading config.yaml with new models
|
2023-12-01 20:32:24 -08:00 |
|
Krrish Dholakia
|
fbdcde1a54
|
fix(proxy_server.py): fix linting errors
|
2023-12-01 19:45:09 -08:00 |
|
Krrish Dholakia
|
284fb64f4d
|
feat: support for azure key vault
|
2023-12-01 19:36:06 -08:00 |
|
Krrish Dholakia
|
e8efde5a83
|
fix(proxy_server.py): check if bearer token passed in
|
2023-12-01 17:06:29 -08:00 |
|
ishaan-jaff
|
c42d7e104c
|
(proxy) fix types
|
2023-12-01 16:05:29 -08:00 |
|
ishaan-jaff
|
ff8adeb991
|
(feat) proxy: use dict
|
2023-12-01 16:00:00 -08:00 |
|
Krrish Dholakia
|
923f90aed2
|
fix(proxy_server.py): accept max tokens as int
|
2023-12-01 15:19:34 -08:00 |
|
Krrish Dholakia
|
3d7fab6c0c
|
fix: linting errors
|
2023-12-01 15:02:22 -08:00 |
|
ishaan-jaff
|
d7597bb7ce
|
(fix) linting
|
2023-12-01 14:51:44 -08:00 |
|
ishaan-jaff
|
ad47788663
|
(linting) fix
|
2023-12-01 14:34:15 -08:00 |
|
ishaan-jaff
|
6178e81bad
|
(fix) proxy: pydantic
|
2023-12-01 13:58:28 -08:00 |
|
ishaan-jaff
|
42f9f35ac1
|
(feat) proxy-pydantic,swagger for chat/completion
|
2023-12-01 13:50:51 -08:00 |
|
ishaan-jaff
|
9750c6f2e1
|
(docs) proxy: add tags=chat/completions + add response type
|
2023-12-01 10:00:48 -08:00 |
|
ishaan-jaff
|
5b64d34b2f
|
(fix) proxy: raise exceptions
|
2023-12-01 09:21:06 -08:00 |
|
ishaan-jaff
|
9920678437
|
(fix) proxy: use orjson.loads()
|
2023-11-30 20:24:31 -08:00 |
|
ishaan-jaff
|
f57600a66f
|
(fix) formatting
|
2023-11-30 20:03:56 -08:00 |
|
ishaan-jaff
|
2101029d0d
|
(feat) proxy: /embedding -> use ORJSON responses
|
2023-11-30 20:00:35 -08:00 |
|
ishaan-jaff
|
c9e21d97cd
|
(feat) proxy: use orjson
|
2023-11-30 19:50:47 -08:00 |
|
Frank Colson
|
8d5fff2ec5
|
Add backwards compatability
|
2023-11-30 16:35:19 -07:00 |
|
Frank Colson
|
ccdac2d049
|
Use poetry extras for proxy
|
2023-11-30 16:23:34 -07:00 |
|
ishaan-jaff
|
f0d02c827e
|
(fix) proxy - don't overwrite metadata passed
|
2023-11-30 15:15:47 -08:00 |
|
Krrish Dholakia
|
8777ac35f0
|
refactor(proxy_server.py): fix linting issues
|
2023-11-30 09:24:59 -08:00 |
|
Krrish Dholakia
|
af56d8a759
|
fix(utils.py): fix azure completion cost calculation
|
2023-11-30 09:19:35 -08:00 |
|
Krrish Dholakia
|
2108b7b528
|
fix(proxy_server.py): provide an endpoint that gives model-specific info from proxy
|
2023-11-30 09:08:19 -08:00 |
|
ishaan-jaff
|
3155b2da3f
|
(fix) proxy: print cwd()
|
2023-11-30 08:52:06 -08:00 |
|
ishaan-jaff
|
370e78647b
|
(cleanup) proxy/health
|
2023-11-29 20:15:52 -08:00 |
|
Krrish Dholakia
|
d7b70d47de
|
fix(proxy_server.py): have /health and /routes be router endpoints
|
2023-11-29 19:59:56 -08:00 |
|
ishaan-jaff
|
681f2e6078
|
(fix) proxy: /health
|
2023-11-29 16:23:37 -08:00 |
|
ishaan-jaff
|
f29114dadc
|
(fix) proxy: /health works with router updates
|
2023-11-29 16:09:31 -08:00 |
|
ishaan-jaff
|
229f50394d
|
(fix) proxy: making receiving data print_verbose
|
2023-11-29 07:50:52 -08:00 |
|
Krrish Dholakia
|
6162d32b5a
|
fix(proxy_server.py): ensure /models returns unique model names
|
2023-11-28 17:32:20 -08:00 |
|
ishaan-jaff
|
062cf64c43
|
(feat) proxy: add logs on router performance
|
2023-11-28 15:44:56 -08:00 |
|
Krrish Dholakia
|
8fff23b944
|
fix(proxy_server.py): support reading master key from os environment
|
2023-11-28 14:05:17 -08:00 |
|
ishaan-jaff
|
42df7f9a08
|
(feat) proxy set num_retries=3
|
2023-11-27 19:33:59 -08:00 |
|
ishaan-jaff
|
a606d951c5
|
(fix) proxy set litellm attributes
|
2023-11-27 13:39:18 -08:00 |
|
ishaan-jaff
|
3fbd2a853f
|
(feat) --health for checking config models
|
2023-11-27 12:13:21 -08:00 |
|
Krrish Dholakia
|
fb680ce4a2
|
fix(acompletion): fix acompletion raise exception issue when custom llm provider is none
|
2023-11-27 11:34:48 -08:00 |
|
Krrish Dholakia
|
1b723d4694
|
fix(proxy_server.py): fix user model returned in /models
|
2023-11-27 08:04:49 -08:00 |
|
Krrish Dholakia
|
8884ceb606
|
fix(proxy_server.py): expose a /health endpoint
|
2023-11-25 18:28:47 -08:00 |
|
ishaan-jaff
|
b0552cad35
|
(feat) proxy: make chat/completions async
|
2023-11-25 12:54:03 -08:00 |
|
Krrish Dholakia
|
e421642ba8
|
fix: fix linting issues
|
2023-11-24 15:46:25 -08:00 |
|
Krrish Dholakia
|
bcf0595bd4
|
feat(proxy_server.py): new /key/info endpoint to access key information (master key only)
|
2023-11-24 15:24:50 -08:00 |
|
Krrish Dholakia
|
32cdd0a613
|
feat(proxy_server.py): tracking spend per api key
|
2023-11-24 15:14:06 -08:00 |
|
Krrish Dholakia
|
6f40fd8ee2
|
fix(proxy_server.py): fix linting issues
|
2023-11-24 11:39:01 -08:00 |
|
ishaan-jaff
|
b1db3a38d7
|
(fix) prisma using: secrets.compare_digest
|
2023-11-24 10:02:08 -08:00 |
|
David Manouchehri
|
a1a0af824a
|
Fix timing attack on master_key.
|
2023-11-24 12:12:29 -05:00 |
|
David Manouchehri
|
5165461c51
|
Fix master key check.
|
2023-11-24 12:03:30 -05:00 |
|
David Manouchehri
|
75dcb8ba2a
|
Fix OpenAPI auth spec.
|
2023-11-24 11:59:33 -05:00 |
|
ishaan-jaff
|
865e3959f3
|
(feat) proxy: cost tracking add track_cost_callback
|
2023-11-24 05:53:23 -08:00 |
|
Kumaran Rajendhiran
|
9fb31448a9
|
Fail gracefully if ollama is already being served
|
2023-11-24 16:52:55 +05:30 |
|