ai-workspace-services/litellm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
16,064 Commits 9 Branches 7 Tags 935 MiB
a061d75af8
Commit Graph

16064 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Ishaan Jaff
a061d75af8 auto update the model in cachedContents request 2024-08-08 23:25:27 -07:00
Ishaan Jaff
b911ccba47 add native cachedContents endpoint 2024-08-08 23:25:27 -07:00
Ishaan Jaff
bf38d14201 doc on using litellm proxy with vertex ai content caching 2024-08-08 23:25:27 -07:00
Ishaan Jaff
c723610c59 add example using litellm proxy with gemini context caching 2024-08-08 23:25:27 -07:00
Krrish Dholakia
ec0ea56b8d fix(anthropic.py): fix translation from /v1/messages format to openai format 2024-08-08 23:25:27 -07:00
Krrish Dholakia
b83253be78 fix(internal_user_endpoints.py): expose new 'internal_user_budget_duration' flag 
Relevant to - https://github.com/BerriAI/litellm/issues/5106
 2024-08-08 23:25:27 -07:00
Krrish Dholakia
bc487a2fac test: skip flaky langsmith tests 2024-08-08 23:25:27 -07:00
Krrish Dholakia
26cd9e8485 test(test_langsmith.py): fix test 2024-08-08 23:25:27 -07:00
Krrish Dholakia
ce4c5f8ab8 fix(user_api_key_auth.py): Fixes https://github.com/BerriAI/litellm/issues/5111 2024-08-08 23:25:27 -07:00
Krrish Dholakia
1d39c0fb7d fix(management_helpers/utils.py): use user_default max_budget, budget duration on new user upsert during team member add 
Fixes https://github.com/BerriAI/litellm/issues/5106
 2024-08-08 19:14:43 -07:00
Krrish Dholakia
6af9d9d2b3 test(test_proxy_server.py): unit testing to make sure internal user params don't impact admin 2024-08-08 17:59:30 -07:00
Krrish Dholakia
4b40563be3 fix(proxy_server.py): ensure internal_user params only apply to internal_user role 2024-08-08 17:50:29 -07:00
Krrish Dholakia
d1e6dd3551 build(requirements.txt): pin orjson dep 2024-08-08 17:40:16 -07:00
Krrish Dholakia
97d57b8449 fix(proxy_server.py): respect internal_user_budget_duration for sso user 2024-08-08 17:28:28 -07:00
Krrish Dholakia
0bfe9bee54 fix(utils.py): handle anthropic overloaded error 2024-08-08 17:19:12 -07:00
Ishaan Jaff
ebde2b88bb docs vertex context caching 2024-08-08 17:19:12 -07:00
Ishaan Jaff
67059266ca fix use get_file_check_sum 2024-08-08 17:19:12 -07:00
Krrish Dholakia
df7ffb5595 fix(factory.py): handle openai function message having tool call id 2024-08-08 17:19:12 -07:00
Ishaan Jaff
4c9c871125 docs readme 2024-08-08 17:19:12 -07:00
Ishaan Jaff
b2b505611c docs use (LLM Gateway) in some places 2024-08-08 17:19:12 -07:00
Ishaan Jaff
74af2041cc docs vertex ai 2024-08-08 17:19:12 -07:00
Ishaan Jaff
a1a11b2e08 add default_vertex_config 2024-08-08 17:19:12 -07:00
Ishaan Jaff
de7c667eb5 docs vertex 2024-08-08 17:19:12 -07:00
Ishaan Jaff
c7a3472641 docs cachedContent endpoint 2024-08-08 17:19:12 -07:00
Ishaan Jaff
a0385ff067 auto update the model in cachedContents request 2024-08-08 17:19:12 -07:00
Ishaan Jaff
cf054def4a add native cachedContents endpoint 2024-08-08 17:19:12 -07:00
Ishaan Jaff
0c9f240305 doc on using litellm proxy with vertex ai content caching 2024-08-08 17:19:12 -07:00
Ishaan Jaff
e2e5e46979 add example using litellm proxy with gemini context caching 2024-08-08 17:19:12 -07:00
Ishaan Jaff
3178724579 add tests to make sure correct vertex ai route is used 2024-08-08 17:19:12 -07:00
Ishaan Jaff
ed125b90fd use v1beta1 when using cached_content 2024-08-08 17:19:12 -07:00
Ishaan Jaff
594a71cec3 fix handle case when service logger has no attribute prometheusServicesLogger 2024-08-08 17:19:12 -07:00
Krrish Dholakia
4ac0afef2c fix(anthropic.py): fix translation from /v1/messages format to openai format 2024-08-08 17:19:12 -07:00
Krrish Dholakia
2776d9cb0d fix(internal_user_endpoints.py): expose new 'internal_user_budget_duration' flag 
Relevant to - https://github.com/BerriAI/litellm/issues/5106
 2024-08-08 17:19:05 -07:00
Krrish Dholakia
8831f30e9d test: skip flaky langsmith tests 2024-08-08 17:18:59 -07:00
Krrish Dholakia
d262501344 test(test_langsmith.py): fix test 2024-08-08 17:18:59 -07:00
Krrish Dholakia
f75a31cd11 fix(user_api_key_auth.py): Fixes https://github.com/BerriAI/litellm/issues/5111 2024-08-08 17:18:59 -07:00
Krrish Dholakia
e6a5d43ebc test: skip flaky langsmith tests 2024-08-08 13:44:15 -07:00
Krrish Dholakia
ac601a69fc feat: set max_internal_budget for user w/ sso 2024-08-08 12:44:07 -07:00
Krrish Dholakia
5d664c0441 build(model_prices_and_context_window.json): Fixes https://github.com/BerriAI/litellm/issues/5113 2024-08-08 09:11:59 -07:00
Krrish Dholakia
ee8d2f25b9 build: ui - update to include max budget per team 2024-08-08 09:09:23 -07:00
Krrish Dholakia
2710bec02d docs(scheduler.md): cleanup docs to use /chat/completion endpoint 2024-08-07 21:49:06 -07:00
Krrish Dholakia
381fc213f8 bump: version 1.43.2 → 1.43.3 2024-08-07 20:33:10 -07:00
Krrish Dholakia
a03860b1cf test(test_completion.py): fix merge error 2024-08-07 20:31:38 -07:00
Krish Dholakia
e1610d37b9
Merge pull request #5099 from BerriAI/litellm_personal_user_budgets 
fix(user_api_key_auth.py): respect team budgets over user budget, if key belongs to team
 2024-08-07 20:00:16 -07:00
Krish Dholakia
37ef63f522
Merge pull request #5101 from BerriAI/litellm_router_prioritization 
feat(router.py): allows /chat/completion endpoint to work for request prioritization calls
 2024-08-07 20:00:06 -07:00
Krish Dholakia
baf01b47d8
Merge branch 'main' into litellm_personal_user_budgets 2024-08-07 19:59:50 -07:00
Krrish Dholakia
7e1f296981 docs(self_serve.md): cleanup docs on how to onboard new users + teams 2024-08-07 19:58:36 -07:00
Krrish Dholakia
ec0b511119 fix: use more descriptive flag 2024-08-07 18:59:46 -07:00
Krrish Dholakia
b7e31638fd fix(internal_user_endpoints.py): respect 'max_user_budget' for new internal user's 2024-08-07 18:50:40 -07:00
Ishaan Jaff
e17e959c62 image gen catch when predictions not in json response 2024-08-07 18:50:26 -07:00