Adrien Fillon
4e29e5460b
update generic SSO login
...
During implementation for Okta, noticed a few things:
- Some providers require a state parameter to be sent
- Some providers require that the client_id is not included in the body
Moreover, the OpenID response converter was not implemented which
was returning an empty response.
Finally, there was an order where there's a fetch of user information
but on first usage, it is not created yet.
2024-02-22 14:34:18 +01:00
ishaan-jaff
80fd55a867
(feat) update non default values
2024-02-20 18:55:20 -08:00
ishaan-jaff
300bab1125
(feat) proxy - view all
2024-02-20 15:37:39 -08:00
Krish Dholakia
e93674638a
Merge pull request #2087 from BerriAI/litellm_llm_guard_integration
...
feat(llm_guard.py): support llm guard for content moderation
2024-02-19 22:48:12 -08:00
ishaan-jaff
42d2dbdf87
(feat) proxy allow user/request_model
2024-02-19 20:56:28 -08:00
Krrish Dholakia
66e4abcb0d
feat(llm_guard.py): support llm guard for content moderation
...
https://github.com/BerriAI/litellm/issues/2056
2024-02-19 20:51:25 -08:00
ishaan-jaff
1a6c64aa66
(fix) user_id_models on sso/callback
2024-02-19 20:39:17 -08:00
ishaan-jaff
9b7ec4e3df
(feat) /user/get_requests
2024-02-19 20:39:17 -08:00
ishaan-jaff
cfcde8bb6e
(feat) use user_notification table
2024-02-19 20:39:17 -08:00
ishaan-jaff
890e2514a0
(feat) proxy - save model access requests
2024-02-19 20:39:17 -08:00
Ishaan Jaff
b4e2690b83
Merge pull request #2066 from BerriAI/litellm_show_if_user_has_model_access
...
[FEAT] /model/info show models user has access to
2024-02-19 15:00:17 -08:00
ishaan-jaff
10c0da389e
(fix) use "/v2/model/info",
2024-02-19 13:29:19 -08:00
ishaan-jaff
8aa134951a
(fix) model/info
2024-02-19 13:27:12 -08:00
ishaan-jaff
11adf1e135
(feat) use /v2/model/info
2024-02-19 13:24:22 -08:00
ishaan-jaff
a1918434e3
(fix) server show models user has access to
2024-02-19 13:17:24 -08:00
ishaan-jaff
4f486de58c
(feat) /model/info show models user has access to
2024-02-19 09:25:32 -08:00
Krish Dholakia
a0ad23a738
Merge pull request #2049 from BerriAI/litellm_return_all_teams_for_user
...
feat(proxy_server.py): return all teams, user is a member of in /user/info
2024-02-17 23:36:45 -08:00
Krish Dholakia
f485e778cb
Merge branch 'main' into litellm_google_text_moderation
2024-02-17 22:10:26 -08:00
Krrish Dholakia
7bd3132b38
feat(proxy_server.py): return all teams, user is a member of in /user/info
...
https://github.com/BerriAI/litellm/issues/2014
2024-02-17 19:18:41 -08:00
Krrish Dholakia
8b166c2eff
feat(presidio_pii_masking.py): allow request level controls for turning on/off pii masking
...
https://github.com/BerriAI/litellm/issues/2003
2024-02-17 19:13:04 -08:00
ishaan-jaff
80d566c869
(fix) litellm bug in
2024-02-17 19:13:04 -08:00
Krrish Dholakia
383afa389f
refactor: rename enterprise specific hooks and callbacks to be more precise
2024-02-17 19:13:04 -08:00
ishaan-jaff
cc50ddb866
(fix) issue with storing model max budget
2024-02-17 19:13:04 -08:00
ishaan-jaff
8c3b897ca3
(feat) set fast api root path
2024-02-17 19:13:04 -08:00
Krrish Dholakia
01ac0418b6
feat(llama_guard.py): add llama guard support for content moderation + new async_moderation_hook endpoint
2024-02-17 19:13:04 -08:00
Ishaan Jaff
ee0d842f31
Merge pull request #2047 from BerriAI/litellm_ui_cost_tracking
...
[FIX] Spend Tracking bug for Keys made on Admin UI (when role = proxy_admin)
2024-02-17 18:59:02 -08:00
ishaan-jaff
2787611273
(fix) litellm bug in
2024-02-17 18:41:37 -08:00
Krrish Dholakia
ea2632d9f3
feat(google_text_moderation.py): allow user to use google text moderation for content mod on proxy
2024-02-17 18:36:29 -08:00
Krrish Dholakia
423bd4012d
refactor: rename enterprise specific hooks and callbacks to be more precise
2024-02-17 17:52:45 -08:00
Ishaan Jaff
0249ed1476
Merge pull request #2022 from BerriAI/litellm_budgets_per_llm
...
[FEAT] Track spend per model (for Key, User and Team)
2024-02-17 15:35:31 -08:00
ishaan-jaff
9b508280ac
(feat) set fast api root path
2024-02-17 13:03:24 -08:00
Krrish Dholakia
67cd9b1c63
feat(llama_guard.py): add llama guard support for content moderation + new async_moderation_hook endpoint
2024-02-16 18:45:25 -08:00
ishaan-jaff
927187318f
(fix) issue with storing model max budget
2024-02-16 18:18:35 -08:00
ishaan-jaff
4cadc9f947
(feat) budgets per model
2024-02-16 17:19:01 -08:00
ishaan-jaff
5e21ebca31
(fix) setting model_max_budget
2024-02-16 17:00:23 -08:00
ishaan-jaff
85a10ac9ba
(feat) track spend key-model, user-model, team-model
2024-02-16 16:32:17 -08:00
ishaan-jaff
885336a467
(feat) track key spend per model
2024-02-16 16:15:24 -08:00
ishaan-jaff
59110db0a2
(feat) set key-model budgets
2024-02-16 15:44:34 -08:00
Ishaan Jaff
1a0ffe2425
Merge branch 'main' into litellm_fix_generic_sso
2024-02-16 14:51:46 -08:00
Ishaan Jaff
aba2ba7b5e
Merge pull request #2020 from Lunik/feat/generic-sso-scopes
...
✨ Allow to configure scopes in generic SSO
2024-02-16 14:45:09 -08:00
ishaan-jaff
7dff2ed942
(feat) generic sso, set generic_user_id_attribute_name
2024-02-16 14:40:27 -08:00
Lunik
c086f87936
✨ Allow to configure scopes in generic SSO
...
Signed-off-by: Lunik <lunik@tiwabbit.fr>
2024-02-16 23:24:58 +01:00
Krrish Dholakia
4bac9669ce
fix(proxy_server.py): restrict model access for /v1/completions endpoint
2024-02-16 11:54:12 -08:00
ishaan-jaff
59099c2914
(chore) fix spend tracking request tags
2024-02-16 11:54:12 -08:00
Krrish Dholakia
765510ac38
fix(proxy_server.py): re-add /team/info endpoint (fixing merge issue)
2024-02-16 11:54:12 -08:00
Krrish Dholakia
2ec766dd20
fix(proxy_server.py): restrict model access for /v1/completions endpoint
2024-02-16 11:50:07 -08:00
ishaan-jaff
68b533bba2
(feat) view spend per tag
2024-02-16 10:16:48 -08:00
ishaan-jaff
ec302019dc
(feat) view spend per tag
2024-02-16 08:51:23 -08:00
Krrish Dholakia
22bc62c353
fix(proxy_server.py): re-add /team/info endpoint (fixing merge issue)
2024-02-16 08:49:37 -08:00
Krish Dholakia
3c0fc3ea3c
Merge branch 'main' into litellm_moderations_improvements
2024-02-15 23:08:25 -08:00
