Commit graph

1273 commits

Author SHA1 Message Date
Krrish Dholakia
fbfcd57798 fix(proxy_server.py): fix linting issue 2024-04-04 19:15:57 -07:00
Krrish Dholakia
e3c2bdef4d feat(ui): add models via ui
adds ability to add models via ui to the proxy. also fixes additional bugs around new /model/new endpoint
2024-04-04 18:56:20 -07:00
Ishaan Jaff
ac5507bd84 ui show spend per tag 2024-04-04 16:57:45 -07:00
Ishaan Jaff
1119cc49a8
Merge pull request #2840 from BerriAI/litellm_return_cache_key_responses
[FEAT] Proxy - Delete Cache Keys + return cache key in responses
2024-04-04 11:52:52 -07:00
Ishaan Jaff
7e1d5c81b4 return cache key in streming responses 2024-04-04 11:00:00 -07:00
Ishaan Jaff
c4cb0afa98 feat - delete cache key 2024-04-04 10:56:47 -07:00
Krrish Dholakia
592241b4eb fix(proxy_server.py): fix linting error 2024-04-04 10:40:32 -07:00
Ishaan Jaff
9dc4127576 v0 return cache key in responses 2024-04-04 10:11:18 -07:00
Krrish Dholakia
4b56f08cbe test(test_models.py): fix delete model test 2024-04-04 08:46:08 -07:00
Krrish Dholakia
346cd1876b fix: raise correct error 2024-04-03 22:37:51 -07:00
Krish Dholakia
6bc48d7e8d
Merge branch 'main' into litellm_model_add_api 2024-04-03 20:29:44 -07:00
Krrish Dholakia
f536fb13e6 fix(proxy_server.py): persist models added via /model/new to db
allows models to be used across instances

https://github.com/BerriAI/litellm/issues/2319 , https://github.com/BerriAI/litellm/issues/2329
2024-04-03 20:16:41 -07:00
Ishaan Jaff
6edaaa92ab fix team update bug 2024-04-03 19:38:07 -07:00
Krrish Dholakia
15e0099948 fix(proxy_server.py): return original model response via response headers - /v1/completions
to help devs with debugging
2024-04-03 13:05:43 -07:00
Krrish Dholakia
8f24202c83 fix(proxy_server.py): support calling public endpoints when jwt_auth is enabled 2024-04-03 07:56:53 -07:00
Ishaan Jaff
8a8233e428 fix safe use token id 2024-04-02 21:40:35 -07:00
Ishaan Jaff
15685a8f53 v0 use token_in /key_generate 2024-04-02 21:31:24 -07:00
Ishaan Jaff
1aeccf3f0a proxy test all-tea-models 2024-04-02 20:50:47 -07:00
Krrish Dholakia
d7601a4844 perf(proxy_server.py): batch write spend logs
reduces prisma client errors, by batch writing spend logs - max 1k logs at a time
2024-04-02 18:46:55 -07:00
Ishaan Jaff
3245d8cdce support all-proxy-models for teams 2024-04-02 16:04:09 -07:00
Ishaan Jaff
b83c452ddd support all-models-on-proxy 2024-04-02 15:52:54 -07:00
Ishaan Jaff
73ef4780f7 (fix) support all-models alias on backend 2024-04-02 15:12:37 -07:00
Ishaan Jaff
3d32567f4c fix show correct team based usage 2024-04-02 13:43:33 -07:00
Ishaan Jaff
327cf73d73 fix left join on litellm team table 2024-04-02 13:36:22 -07:00
Krish Dholakia
7233e5ab25
Merge pull request #2789 from BerriAI/litellm_set_ttl
fix(proxy_server.py): allow user to set in-memory + redis ttl
2024-04-02 08:53:34 -07:00
Ishaan Jaff
92984a1c6f
Merge pull request #2788 from BerriAI/litellm_support_-_models
[Feat] Allow using model = * on proxy config.yaml
2024-04-01 19:46:50 -07:00
Krish Dholakia
da85384649
Merge pull request #2787 from BerriAI/litellm_optional_team_jwt_claim
fix(proxy_server.py): don't require scope for team-based jwt access
2024-04-01 19:16:39 -07:00
Krrish Dholakia
c096ba566f fix(proxy_server.py): fix cache param arg name 2024-04-01 19:14:39 -07:00
Krrish Dholakia
203e2776f8 fix(proxy_server.py): allow user to set in-memory + redis ttl
addresses - https://github.com/BerriAI/litellm/issues/2700
2024-04-01 19:13:23 -07:00
Ishaan Jaff
037b624c89 (fix) allow wildcard models 2024-04-01 19:07:05 -07:00
Krrish Dholakia
c52819d47c fix(proxy_server.py): don't require scope for team-based jwt access
If team with the client_id exists then it should be allowed to make a request, if it doesn't then as we discussed it should return an error
2024-04-01 18:52:00 -07:00
Ishaan Jaff
b14b6083f5
Merge pull request #2785 from BerriAI/litellm_high_traffic_redis_caching_fixes
[Feat] Proxy - high traffic redis caching - when using `url`
2024-04-01 18:38:27 -07:00
Krrish Dholakia
6467dd4e11 fix(tpm_rpm_limiter.py): fix cache init logic 2024-04-01 18:01:38 -07:00
Ishaan Jaff
9accc544e9 add /cache/redis/info endpoint 2024-04-01 16:51:23 -07:00
Ishaan Jaff
d5d800e141 (fix) _update_end_user_cache 2024-04-01 11:18:00 -07:00
Krrish Dholakia
c9e6b05cfb test(test_max_tpm_rpm_limiter.py): add unit testing for redis namespaces working for tpm/rpm limits 2024-04-01 10:39:03 -07:00
Krish Dholakia
1356f6cd32
Merge pull request #2775 from BerriAI/litellm_redis_user_api_key_cache_v3
fix(tpm_rpm_limiter.py): enable redis caching for tpm/rpm checks on keys/user/teams
2024-03-30 22:07:05 -07:00
Krrish Dholakia
f58fefd589 fix(tpm_rpm_limiter.py): enable redis caching for tpm/rpm checks on keys/user/teams
allows tpm/rpm checks to work across instances

https://github.com/BerriAI/litellm/issues/2730
2024-03-30 20:01:36 -07:00
Ishaan Jaff
23a18d4be3 (ui) show proxy spend 2024-03-30 14:02:43 -07:00
Ishaan Jaff
8daca76566 (ui) view spend by team name on usage 2024-03-30 13:25:32 -07:00
Krrish Dholakia
0342cd3b6b fix(proxy_server.py): support azure openai text completion calls 2024-03-30 11:30:06 -07:00
Krrish Dholakia
af2eabba91 fix(proxy_server.py): fix /key/update endpoint to update key duration
also adds a test for this to our ci/cd
2024-03-29 21:47:10 -07:00
Krish Dholakia
6d9887969f
Merge pull request #2757 from BerriAI/litellm_fix_budget_alerts
fix(auth_checks.py): make global spend checks more accurate
2024-03-29 21:13:27 -07:00
Krrish Dholakia
48ac36e70d docs(proxy_server.py): fix example on swagger for team member delete 2024-03-29 20:09:54 -07:00
Krrish Dholakia
3810b050c1 fix(proxy_server.py): increment cached global proxy spend object 2024-03-29 20:02:31 -07:00
Krrish Dholakia
5280fc809f fix(proxy_server.py): enforce end user budgets with 'litellm.max_end_user_budget' param 2024-03-29 17:14:40 -07:00
Krrish Dholakia
786116783f fix(proxy_server.py): fix max budget check to also fire slack alert 2024-03-29 16:24:40 -07:00
Krrish Dholakia
be6481bb36 fix(proxy_server.py): fix checks 2024-03-29 15:34:13 -07:00
Krrish Dholakia
d8c15a5677 fix(auth_checks.py): make global spend checks more accurate 2024-03-29 14:57:44 -07:00
Ishaan Jaff
7df2d7cb33 (fix) show correct spend on ui 2024-03-29 09:41:00 -07:00