Ishaan Jaff
ba56e37244
(refactor) caching use LLMCachingHandler for async_get_cache and set_cache ( #6208 )
...
* use folder for caching
* fix importing caching
* fix clickhouse pyright
* fix linting
* fix correctly pass kwargs and args
* fix test case for embedding
* fix linting
* fix embedding caching logic
* fix refactor handle utils.py
* fix test_embedding_caching_azure_individual_items_reordered
2024-10-14 16:34:01 +05:30
Krish Dholakia
dec53961f7
LiteLLM Minor Fixes and Improvements (11/09/2024) ( #5634 )
...
* fix(caching.py): set ttl for async_increment cache
fixes issue where ttl for redis client was not being set on increment_cache
Fixes https://github.com/BerriAI/litellm/issues/5609
* fix(caching.py): fix increment cache w/ ttl for sync increment cache on redis
Fixes https://github.com/BerriAI/litellm/issues/5609
* fix(router.py): support adding retry policy + allowed fails policy via config.yaml
* fix(router.py): don't cooldown single deployments
No point, as there's no other deployment to loadbalance with.
* fix(user_api_key_auth.py): support setting allowed email domains on jwt tokens
Closes https://github.com/BerriAI/litellm/issues/5605
* docs(token_auth.md): add user upsert + allowed email domain to jwt auth docs
* fix(litellm_pre_call_utils.py): fix dynamic key logging when team id is set
Fixes issue where key logging would not be set if team metadata was not none
* fix(secret_managers/main.py): load environment variables correctly
Fixes issue where os.environ/ was not being loaded correctly
* test(test_router.py): fix test
* feat(spend_tracking_utils.py): support logging additional usage params - e.g. prompt caching values for deepseek
* test: fix tests
* test: fix test
* test: fix test
* test: fix test
* test: fix test
2024-09-11 22:36:06 -07:00
Krrish Dholakia
2c76524a19
build(model_prices_and_context_window.json): add mistral-large on vertex ai pricing
2024-07-27 10:37:18 -07:00
Krrish Dholakia
f6c287640e
fix(team_endpoints.py): check if key belongs to team before returning /team/info
2024-07-16 21:17:05 -07:00
Krrish Dholakia
7eeb8d6251
fix(proxy_server.py): fix admin allowed routes
2024-05-22 20:55:21 -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
ed4315af38
feat(handle_jwt.py): add support for 'team_id_default
...
allows admin to set a default team id for spend-tracking + permissions
2024-05-15 21:33:35 -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
Jean-Luc Duckworth
26db16e61d
Fixed typo. test_jwt.py tests pass
2024-05-07 16:08:36 -04:00
Jean-Luc Duckworth
a04281a478
Expanding jwt access to other RS and PS algos. Updated to resolve merge conflicts.
2024-05-07 15:45:07 -04:00
Sara Ghaemi
8706dd220f
made audience optional and updated docs
2024-05-07 11:37:04 -04:00
Sara Ghaemi
2022a7febb
Updated JWT handler to support PEM public key
2024-05-07 11:22:17 -04:00
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
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
Krrish Dholakia
a9285710d1
fix(handle_jwt.py): support firebase public key format
...
adds support for when the public keys are a json instead of nested inside a json
2024-04-11 18:07:13 -07:00
Krrish Dholakia
6c67fd4cd4
fix(handle_jwt.py): fix linting issue
2024-03-29 21:35:36 -07:00
phuongnd96
115ec7cb5d
fix: still verify kid on single pub key fetched
2024-03-30 10:09:38 +07:00
Krrish Dholakia
46937935d1
feat(proxy/utils.py): enable updating db in a separate server
2024-03-27 16:02:36 -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
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
f0992c2dbd
(fix) stop using f strings with logger
2024-03-25 10:47:18 -07:00
Krrish Dholakia
6eb0183776
fix(handle_jwt.py): add more logging for jwt header
2024-03-22 16:33:32 -07:00
Krrish Dholakia
9a221851d5
fix(handle_jwt.py): track spend for user using jwt auth
2024-03-20 10:55:52 -07:00
Krrish Dholakia
32072f13fd
fix(handle_jwt.py): remove issuer check
2024-03-20 08:35:23 -07:00
Krrish Dholakia
35153cac73
refactor(handle_jwt.py): print jwt version
2024-03-19 17:17:11 -07:00
Krrish Dholakia
4879265d7f
build: build fixes
2024-03-19 16:59:59 -07:00
Krrish Dholakia
9d5de2f3ad
docs(token_based_auth.md): add jwt auth to docs
2024-03-19 16:34:27 -07:00
Krrish Dholakia
386688e5f9
feat(handle_jwt.py): support authenticating admins into the proxy via jwt's
2024-03-19 15:00:27 -07:00
