Ishaan Jaff
4ea2bf50b5
[Perf improvement Proxy] Use Dual Cache for getting key and team objects ( #5903 )
...
* use dual cache - perf
* fix auth checks
* fix budget checks for keys
* fix get / set team tests
2024-09-25 19:56:17 -07:00
Ishaan Jaff
4d253e473a
[Feat] Improve OTEL Tracking - Require all Redis Cache reads to be logged on OTEL ( #5881 )
...
* fix use previous internal usage caching logic
* fix test_dual_cache_uses_redis
* redis track event_metadata in service logging
* show otel error on _get_parent_otel_span_from_kwargs
* track parent otel span on internal usage cache
* update_request_status
* fix internal usage cache
* fix linting
* fix test internal usage cache
* fix linting error
* show event metadata in redis set
* fix test_get_team_redis
* fix test_get_team_redis
* test_proxy_logging_setup
2024-09-25 10:57:08 -07:00
Krish Dholakia
f3fa2160a0
LiteLLM Minor Fixes & Improvements (09/21/2024) ( #5819 )
...
* fix(router.py): fix error message
* Litellm disable keys (#5814 )
* build(schema.prisma): allow blocking/unblocking keys
Fixes https://github.com/BerriAI/litellm/issues/5328
* fix(key_management_endpoints.py): fix pop
* feat(auth_checks.py): allow admin to enable/disable virtual keys
Closes https://github.com/BerriAI/litellm/issues/5328
* docs(vertex.md): add auth section for vertex ai
Addresses - https://github.com/BerriAI/litellm/issues/5768#issuecomment-2365284223
* build(model_prices_and_context_window.json): show which models support prompt_caching
Closes https://github.com/BerriAI/litellm/issues/5776
* fix(router.py): allow setting default priority for requests
* fix(router.py): add 'retry-after' header for concurrent request limit errors
Fixes https://github.com/BerriAI/litellm/issues/5783
* fix(router.py): correctly raise and use retry-after header from azure+openai
Fixes https://github.com/BerriAI/litellm/issues/5783
* fix(user_api_key_auth.py): fix valid token being none
* fix(auth_checks.py): fix model dump for cache management object
* fix(user_api_key_auth.py): pass prisma_client to obj
* test(test_otel.py): update test for new key check
* test: fix test
2024-09-21 18:51:53 -07:00
Krish Dholakia
499e442e45
Additional Fixes (09/17/2024) ( #5759 )
...
* fix(auth_checks.py): check if key has all model access via wildcard routing
Fixes issue where key with `openai/*` couldn't call gpt models
* fix(slack_alerting.py): expose flag for disabling failed spend tracking alerts
2024-09-17 23:02:12 -07:00
Krish Dholakia
91c918fd70
LiteLLM Minor Fixes and Improvements (09/12/2024) ( #5658 )
...
* fix(factory.py): handle tool call content as list
Fixes https://github.com/BerriAI/litellm/issues/5652
* fix(factory.py): enforce stronger typing
* fix(router.py): return model alias in /v1/model/info and /v1/model_group/info
* fix(user_api_key_auth.py): move noisy warning message to debug
cleanup logs
* fix(types.py): cleanup pydantic v2 deprecated param
Fixes https://github.com/BerriAI/litellm/issues/5649
* docs(gemini.md): show how to pass inline data to gemini api
Fixes https://github.com/BerriAI/litellm/issues/5674
2024-09-12 23:04:06 -07:00
Ishaan Jaff
bfb0aceeae
add check for admin only routes
2024-09-03 15:03:32 -07:00
Ishaan Jaff
cf66ca89b9
allow setting allowed routes on proxy
2024-09-03 13:59:31 -07:00
Ishaan Jaff
86d4504c7b
fix checking request body
2024-08-28 14:10:09 -07:00
Ishaan Jaff
5ff7e33dd8
add check for is_request_body_safe
2024-08-28 13:40:14 -07:00
Krrish Dholakia
73a5921262
feat(auth_checks.py): allow team to call all models, when explicitly set via /*
2024-08-22 16:38:56 -07:00
Ishaan Jaff
7171efc729
use model access groups for teams
2024-08-17 16:45:53 -07:00
Krrish Dholakia
3d4672ba53
fix(user_api_key_auth.py): Fixes https://github.com/BerriAI/litellm/issues/5111
2024-08-08 10:30:15 -07:00
Krish Dholakia
7d28b6ebc3
Merge branch 'main' into litellm_personal_user_budgets
2024-08-07 19:59:50 -07:00
Krrish Dholakia
228da08b81
fix: fix tests
2024-08-07 15:02:04 -07:00
Krrish Dholakia
57a730095c
fix(user_api_key_auth.py): respect team budgets over user budget, if key belongs to team
...
Closes https://github.com/BerriAI/litellm/issues/5097
2024-08-07 14:32:27 -07:00
Krish Dholakia
0044fd0041
Merge branch 'main' into litellm_support_lakera_config_thresholds
2024-08-06 22:47:13 -07:00
Krrish Dholakia
f76a4bab49
fix(user_api_key_cache): fix check to not raise error if team object is missing
2024-07-30 18:25:04 -07:00
Krrish Dholakia
1915adfc2d
fix(auth_checks.py): fix redis usage for team cached objects
2024-07-30 17:30:00 -07:00
Krrish Dholakia
80c3759719
fix(auth_checks.py): handle writing team object to redis caching correctly
2024-07-29 07:51:44 -07:00
Krrish Dholakia
72387320af
feat(auth_check.py): support using redis cache for team objects
...
Allows team update / check logic to work across instances instantly
2024-07-25 19:35:29 -07:00
Krrish Dholakia
487035c970
feat(auth_check.py): support using redis cache for team objects
...
Allows team update / check logic to work across instances instantly
2024-07-24 18:14:49 -07:00
Krish Dholakia
0cb872cbea
Merge pull request #4810 from BerriAI/litellm_team_modify_guardrails
...
feat(auth_checks.py): Allow admin to disable team from turning on/off guardrails
2024-07-22 22:32:24 -07:00
Ishaan Jaff
5f238f2857
check is_llm_api_route
2024-07-22 14:43:30 -07:00
Krrish Dholakia
a351b7cc3e
feat(auth_checks.py): Allow admin to disable team from turning on/off guardrails.
2024-07-20 18:39:05 -07:00
Krrish Dholakia
548b2fcf4b
fix(user_api_key_auth.py): update valid token cache with updated team object cache
2024-07-19 17:06:49 -07:00
Ishaan Jaff
6891b29444
fix - use helper to check if a route is openai route
2024-07-09 12:00:07 -07:00
Krrish Dholakia
66948d083f
fix(user_api_key_auth.py): ensure user has access to fallback models
...
for client side fallbacks, checks if user has access to fallback models
2024-06-20 16:02:19 -07:00
Krrish Dholakia
6fcad5f199
fix(proxy_server.py): track team spend for cached team object
...
fixes issue where team budgets for jwt tokens weren't asserted
2024-06-18 17:10:12 -07:00
Krrish Dholakia
2a5a30fa7a
fix(proxy_server.py): use consistent 400-status code error code for exceeded budget errors
...
standardizes error code for budget exceeded errors to status code 400
2024-06-11 16:10:58 -07:00
Ishaan Jaff
860c9b52b6
Merge branch 'main' into litellm_svc_logger
2024-06-07 14:01:54 -07:00
Ishaan Jaff
4828e2426f
fix importing Span
2024-06-07 09:55:59 -07:00
Ishaan Jaff
193e71642c
fix - log_to_opentelemetry
2024-06-06 22:28:01 -07:00
Ishaan Jaff
cd125e6309
fix auth checks
2024-06-06 22:13:13 -07:00
Ishaan Jaff
92a3c062a7
fix log_to_opentelemetry
2024-06-06 21:29:40 -07:00
Ishaan Jaff
cb5ebba6fa
feat -v0 parent_otel_span in basic db reads
2024-06-06 19:49:18 -07:00
Ishaan Jaff
c88ba31fa0
feat - enforce enforced_params as a premium feature
2024-06-06 09:03:31 -07:00
Ishaan Jaff
13d24360a4
feat - enforce params in requests
2024-06-06 08:54:59 -07:00
Ishaan Jaff
b7dabe9bed
fix literal usage
2024-05-30 14:28:53 -07:00
Krrish Dholakia
bb3c786194
fix(proxy_server.py): fix end user object check when master key used
...
check if end user max budget exceeded for master key
2024-05-29 17:20:59 -07:00
Krrish Dholakia
7eeb8d6251
fix(proxy_server.py): fix admin allowed routes
2024-05-22 20:55:21 -07:00
Ishaan Jaff
294c105f02
feat - include litellm_budget table when getting end_user
2024-05-22 13:30:08 -07:00
Krrish Dholakia
93cb65dfee
feat(proxy_server.py): support 'user_id_upsert' flag for jwt_auth
2024-05-15 22:19:59 -07:00
Krrish Dholakia
da2ea0ba04
feat(proxy_server.py): make team_id optional for jwt token auth (only enforced, if set)
...
Allows users to use jwt auth for internal chat apps
2024-05-15 21:05:14 -07:00
Krrish Dholakia
29ef2261f9
fix(auth_checks.py): fix 'get_end_user_object'
...
await cache get
2024-05-09 13:05:56 -07:00
Krrish Dholakia
0ea8222508
feat(router.py): enable filtering model group by 'allowed_model_region'
2024-05-08 22:10:17 -07:00
Ishaan Jaff
cb467182a3
fix - only run global_proxy_spend on chat completion calls
2024-04-27 14:11:00 -07:00
Krrish Dholakia
8073155bdf
fix(proxy_server.py): prevent non-admins from creating new keys
2024-04-16 11:22:02 -07:00
Krrish Dholakia
aa5da4346a
fix(proxy_server.py): support tracking org spend
...
currently works when org set for jwt auth
2024-04-11 23:01:21 -07:00
Krrish Dholakia
cdd78b2b12
fix(auth_checks.py): raise error if user doesn't exist in db
2024-04-11 19:55:04 -07:00
Krrish Dholakia
4b2d13322e
feat(proxy_server.py): support cost tracking on user id via JWT-Auth
...
allows admin to track cost for LiteLLM_UserTable via JWT
2024-04-11 18:47:46 -07:00
