Krrish Dholakia
94c5d9f82f
fix(proxy_server.py): use consistent naming schema - move to /team/block
2024-03-26 16:59:36 -07:00
Krrish Dholakia
ce44645000
feat(proxy_server.py): enable new /team/disable endpoint
...
reject all requests from this team id, without deleting it.
2024-03-26 15:40:50 -07:00
Krrish Dholakia
5ab34345e9
fix(proxy_server.py): rename proxy roles param to litellm_jwtauth
2024-03-26 15:04:30 -07:00
Krrish Dholakia
a0f55b92e6
fix(handle_jwt.py): support public key caching ttl param
2024-03-26 14:32:55 -07:00
Krrish Dholakia
d69ae350b4
fix(proxy_server.py): check if team scope in jwt
2024-03-26 14:01:02 -07:00
Krrish Dholakia
b9180a8c72
fix(handle_jwt.py): enable team-based jwt-auth access
...
Move auth to check on ‘client_id’ not ‘sub
2024-03-26 12:25:38 -07:00
Ishaan Jaff
04eca9de84
Merge pull request #2702 from BerriAI/litellm_cache_flush
...
[Feat] Proxy - /cache/flushall - delete all elements from cache
2024-03-26 09:34:39 -07:00
Ishaan Jaff
1a2ec398a8
(fix) doc string
2024-03-26 09:25:44 -07:00
Ishaan Jaff
f1ebbd32b8
(feat) /cache/flushall
2024-03-26 09:18:58 -07:00
Ishaan Jaff
237440cf13
(feat) support cache flush on redis
2024-03-26 09:12:30 -07:00
Krrish Dholakia
00d27a324d
fix(router.py): check for context window error when handling 400 status code errors
...
was causing proxy context window fallbacks to not work as expected
2024-03-26 08:08:15 -07:00
Ishaan Jaff
853ed0278f
Merge branch 'main' into litellm_batch_write_redis_cache
2024-03-25 16:41:29 -07:00
Ishaan Jaff
21b9a0ead3
(fix) locust load test use uuid
2024-03-25 15:36:30 -07:00
Krish Dholakia
f8d1d41b34
Merge pull request #2687 from BerriAI/litellm_jwt_auth_fixes_2
...
Litellm jwt auth fixes
2024-03-25 13:27:19 -07:00
Krrish Dholakia
10ecf31827
test(test_jwt.py): add unit tests for jwt auth integration
2024-03-25 13:24:39 -07:00
Krrish Dholakia
30c45b83bf
fix(handle_jwt.py): cache public keys
...
caches jwt public keys - reducing need for making http calls on every request
2024-03-25 12:36:32 -07:00
Krrish Dholakia
72a0f0213d
fix(handle_jwt.py): support scopes being a list
...
allow scopes in jwt to be a list, not just a space-separated string
2024-03-25 12:30:40 -07:00
Krrish Dholakia
fe3a39351f
fix(handle_jwt.py): don't require kid to be set
2024-03-25 12:28:16 -07:00
Krrish Dholakia
38bdf31652
fix(handle_jwt.py): allow setting proxy admin role string for jwt auth
2024-03-25 12:20:14 -07:00
Krrish Dholakia
d3e7376e10
fix(handle_jwt.py): enable user to set jwt admin scope string in config
2024-03-25 11:34:49 -07:00
Ishaan Jaff
a6065e4853
(fix) stop using f strings in verbose logger
2024-03-25 10:55:30 -07:00
Ishaan Jaff
f0992c2dbd
(fix) stop using f strings with logger
2024-03-25 10:47:18 -07:00
Ishaan Jaff
2c01457a4b
(feat) stop eagerly evaluating fstring
2024-03-25 09:01:42 -07:00
Krish Dholakia
c291b0d2d6
Merge pull request #2666 from BerriAI/litellm_model_fix_v_3
...
fix(proxy_server.py): fix model info check
2024-03-23 19:39:03 -07:00
Krish Dholakia
c46de42339
Merge pull request #2669 from BerriAI/litellm_router_pre_call_checks
...
feat(router.py): enable pre-call checks
2024-03-23 19:38:09 -07:00
Krrish Dholakia
4e70a3e09a
feat(router.py): enable pre-call checks
...
filter models outside of context window limits of a given message for a model group
https://github.com/BerriAI/litellm/issues/872
2024-03-23 18:03:30 -07:00
Ishaan Jaff
0aaa5fcfe6
(fix) update locustfile
2024-03-23 17:59:54 -07:00
Ishaan Jaff
40f00cac0d
(feat) update config.yaml
2024-03-23 17:59:16 -07:00
Krrish Dholakia
ed3681d9bd
fix(proxy_server.py): fix model info check
2024-03-23 15:59:17 -07:00
Ishaan Jaff
c6ffd456ff
(fix) add some better load testing
2024-03-22 19:48:54 -07:00
Ishaan Jaff
9bd53cec6a
(fix) update load test used
2024-03-22 19:48:54 -07:00
Krrish Dholakia
d275c1183e
fix(proxy_server.py): enable jwt-auth for users
...
allow a user to auth into the proxy via jwt's and call allowed routes
2024-03-22 17:08:10 -07:00
Krrish Dholakia
6eb0183776
fix(handle_jwt.py): add more logging for jwt header
2024-03-22 16:33:32 -07:00
Krish Dholakia
8df332373a
Merge pull request #2619 from BerriAI/litellm_install_tenacity
...
(fix) include tenacity in req.txt
2024-03-21 20:55:56 -07:00
Krrish Dholakia
6076a31411
build(schema.prisma): use jsonProtocol to fix db connection issues
...
https://github.com/prisma/prisma/discussions/19978
2024-03-21 18:01:45 -07:00
Krrish Dholakia
67f2ebf718
build(networking.tsx): fix trailing slash
2024-03-21 17:50:59 -07:00
Krrish Dholakia
4bf9203436
build(networking.tsx): modify url to prevent redirects
2024-03-21 17:43:41 -07:00
Krrish Dholakia
f535a4498e
fix(proxy_server.py): allow user to disable swagger ui docs via env
...
user can disable swagger ui docs by setting 'NO_DOCS="True"' in their env
2024-03-21 17:15:18 -07:00
Krish Dholakia
2009133d87
Merge branch 'main' into litellm_llm_api_prompt_injection_check
2024-03-21 09:57:10 -07:00
Krrish Dholakia
b872644496
fix(prompt_injection_detection.py): fix type check
2024-03-21 08:56:13 -07:00
Krrish Dholakia
5cfabe9a09
fix: fix linting issue
2024-03-21 08:19:09 -07:00
Ishaan Jaff
3d886aae62
(fix) include tenacity in req.txt
2024-03-21 08:10:12 -07:00
Ishaan Jaff
195783ff07
Merge pull request #2563 from eltociear/patch-2
...
Update proxy_server.py
2024-03-21 07:29:33 -07:00
Krrish Dholakia
e9cc6b4cc9
feat(proxy_server.py): enable llm api based prompt injection checks
...
run user calls through an llm api to check for prompt injection attacks. This happens in parallel to th
e actual llm call using `async_moderation_hook`
2024-03-20 22:43:42 -07:00
Krish Dholakia
e7ff074eab
Merge pull request #2606 from BerriAI/litellm_jwt_auth_updates
...
fix(handle_jwt.py): track spend for user using jwt auth
2024-03-20 19:40:17 -07:00
Krrish Dholakia
feb78b7819
fix(proxy_server.py): fix import
2024-03-20 19:15:06 -07:00
Krrish Dholakia
e9ff51aa70
fix(prompt_injection_detection.py): ensure combinations are actual phrases, not just 1-2 words
...
reduces misflagging
https://github.com/BerriAI/litellm/issues/2601
2024-03-20 19:09:38 -07:00
Krrish Dholakia
f0d8472bfd
fix(caching.py): enable async setting of cache for dual cache
2024-03-20 18:42:34 -07:00
Krrish Dholakia
9a221851d5
fix(handle_jwt.py): track spend for user using jwt auth
2024-03-20 10:55:52 -07:00
Ishaan Jaff
539fc6d7e1
(feat) start proxy with default num_workers=1
2024-03-20 10:46:32 -07:00
