Commit graph

146 commits

Author SHA1 Message Date
Krish Dholakia
036a6821d5
Merge pull request #5057 from BerriAI/litellm_rds_iam_auth
feat(proxy_cli.py): support iam-based auth to rds
2024-08-06 10:44:33 -07:00
Krrish Dholakia
1cc7c7fc59 feat(proxy_cli.py): support iam-based auth to rds
Initial pr for iam-based auth support for rds
2024-08-05 17:35:48 -07:00
Krrish Dholakia
936640948d fix: bump default allowed_fails + reduce default db pool limit
Fixes issues with running proxy server in production
2024-08-05 15:07:46 -07:00
Krrish Dholakia
fe62e4e1c4 fix(proxy_cli.py): bump default azure api version 2024-07-08 16:28:22 -07:00
Krrish Dholakia
b84d335624 fix(proxy_cli.py): run aws kms decrypt before starting proxy server 2024-06-28 16:03:56 -07:00
Ishaan Jaff
aa3c14fa46 make sure linting runs proxy_cli.py 2024-06-20 20:20:08 -07:00
Chris Van Pelt
306c2b425d
Update proxy_cli.py
Fixed indentation to so we don't get an `UnboundLocalError`.  Fixes #4324
2024-06-20 17:48:16 -07:00
Krrish Dholakia
248ee488f0 fix(proxy_cli.py): fix double counting json logs 2024-06-20 15:15:23 -07:00
Krrish Dholakia
e4dbb9b2db fix(proxy_cli.py): support passing the database url as an encrypted kms key 2024-06-10 15:48:27 -07:00
Krrish Dholakia
0d3e52373c fix(proxy/_logging.py): fix default logging level 2024-06-05 17:42:49 -07:00
Krrish Dholakia
3167bee25a fix(proxy_cli.py): enable json logging via litellm_settings param on config
allows user to enable json logs without needing to figure out env variables
2024-05-29 21:41:20 -07:00
Krrish Dholakia
058bfb101d feat(proxy_cli.py): support json logs on proxy
allow user to enable 'json logs' for proxy server
2024-05-20 09:18:12 -07:00
Krrish Dholakia
9eee2f3889 docs(prod.md): add 'disable load_dotenv' tutorial to docs 2024-05-14 19:13:22 -07:00
Krrish Dholakia
1ab4974773 fix: disable 'load_dotenv' for prod environments 2024-05-14 19:09:36 -07:00
Krrish Dholakia
6575143460 feat(proxy_server.py): return litellm version in response headers 2024-05-08 16:00:08 -07:00
Krrish Dholakia
b2741933dc fix(proxy_cli.py): don't double load the router config
was causing callbacks to be instantiated twice - double couting usage in cache
2024-04-10 13:23:56 -07:00
Krrish Dholakia
6d32323e3d fix(proxy_cli.py): revert db timeout change - user-controllable param
db timeout is a user controllable param, not necessary to change defaults
2024-04-03 09:37:57 -07:00
Krrish Dholakia
f07500c5ea fix(proxy_server.py): bump default db timeouts 2024-04-03 09:35:08 -07:00
Krrish Dholakia
1e856443e1 feat(proxy/utils.py): enable updating db in a separate server 2024-03-27 16:02:36 -07:00
Krrish Dholakia
b204f0c01c fix(proxy_cli.py): fix circular import issue 2024-03-26 21:16:41 -07:00
Krrish Dholakia
6d418a2920 fix(llm_guard.py): working llm-guard 'key-specific' mode 2024-03-26 17:47:20 -07:00
Krish Dholakia
9d7aceb06e
Merge pull request #2697 from antoniomdk/fix-database-credentials-leakage
(fix) Remove print statements from append_query_params
2024-03-26 16:07:33 -07:00
Ishaan Jaff
6b4b05b58f (fix) remove litellm.telemetry 2024-03-26 11:21:09 -07:00
Antonio Molner Domenech
c713648db1 Update print statements to use verbose logger and DEBUG level 2024-03-26 22:41:28 +07:00
Ishaan Jaff
3ad6e5ffc1 (feat) start proxy with default num_workers=1 2024-03-20 10:46:32 -07:00
ishaan-jaff
ea6f42216c (docs) use port 4000 2024-03-08 21:59:00 -08:00
ishaan-jaff
9ed51e791b (fix) default num workers 2024-03-08 15:24:08 -08:00
Krrish Dholakia
3303236305 test(test_proxy_server.py): add back bedrock embedding tests 2024-03-04 18:28:05 -08:00
Krrish Dholakia
045d84e167 fix(proxy_cli.py): allow user to control db connection pool + timeouts from config 2024-02-17 19:03:43 -08:00
ishaan-jaff
c7e4432597 (feat) inc default gunicorn timeout 2024-02-12 21:49:32 -08:00
ishaan-jaff
18e73ec03d (feat) litellm set ssl_certificates 2024-02-10 17:52:47 -08:00
Krrish Dholakia
ff93609453 build(schema.prisma): support direct url on prisma schema 2024-02-08 17:37:37 -08:00
Krrish Dholakia
0d803e1379 fix(proxy_cli.py): fix max connection limit issue on db 2024-02-07 22:57:44 -08:00
Krrish Dholakia
4a0df3cb4f fix(proxy_cli.py-&&-proxy_server.py): bump reset budget intervals and fix pool limits for prisma connections 2024-02-06 19:39:49 -08:00
Krish Dholakia
9ab59045a3
Merge branch 'main' into litellm_embedding_caching_updates 2024-02-03 18:08:47 -08:00
Krrish Dholakia
8e9197b5b4 build(proxy_cli.py): make running gunicorn an optional cli arg
when running proxy locally, running with uvicorn is much better for debugging
2024-01-29 15:32:34 -08:00
Krrish Dholakia
dda115fcb7 build(ui/litellm_dashboard_v_2): allow app owner to create keys and view their keys 2024-01-27 13:48:35 -08:00
Krrish Dholakia
1e5efdfa37 fix(proxy_server.py): support setting tpm/rpm limits per user / per key 2024-01-18 17:03:18 -08:00
Krrish Dholakia
73daee7e07 fix(proxy_cli.py): ensure proxy always retries if db push fails to connect to db 2024-01-17 17:37:59 -08:00
ishaan-jaff
893627cab4 (feat) use env variables to set host, port, num_workers 2024-01-16 08:36:29 -08:00
ishaan-jaff
6a09fcfa06 (feat) print num_workers when starting prox 2024-01-16 08:21:37 -08:00
ishaan-jaff
7b1c8471c5 v0 num_workers 2024-01-16 08:15:12 -08:00
ishaan-jaff
61dff3decb (fix) gunicorn - show request logs like uvicorn 2024-01-13 11:22:16 -08:00
Krrish Dholakia
3d7c169a58 fix(proxy_cli.py): only run prisma db push if prisma in environment 2024-01-13 19:44:12 +05:30
Krrish Dholakia
007870390d fix: support async redis caching 2024-01-12 21:46:41 +05:30
XD3000/高瑞雲
574d042655 #1424:gunicorn can't run in windows 2024-01-12 14:30:23 +08:00
Krrish Dholakia
43533812a7 fix(proxy_cli.py): read db url from config, not just environment 2024-01-11 19:19:29 +05:30
Krrish Dholakia
5bc44353e0 feat(proxy_cli.py): move print statements to show actually deployed port 2024-01-10 22:09:58 +05:30
Ishaan Jaff
58d0366447
Merge pull request #1399 from BerriAI/litellm_default_use_gunicorn
LiteLLM Proxy - Use Gunicorn with Uvicorn workers
2024-01-10 21:46:04 +05:30
Krrish Dholakia
b06d7f0cb6 build(config.yml): reintroduce mounting config.yaml 2024-01-10 18:03:57 +05:30