scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-06 02:48:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103
15504 commits 3198 branches 1436 tags 4.5 GiB
Commit graph

15504 commits

This branch
This branch
All branches
Author SHA1 Message Date
Ishaan Jaff
785081422c
Merge pull request #4705 from BerriAI/litellm_return_internal_cache_usage 
feat mem utils debugging return size of in memory cache
 2024-07-13 18:24:53 -07:00
Ishaan Jaff
31783196c0 feat - return size of in memory cache 2024-07-13 18:22:44 -07:00
Ishaan Jaff
759e02bdaa debug mem issues show growth 2024-07-13 18:05:19 -07:00
Ishaan Jaff
69f74c1e6c fix only use per request tracking if slack alerting is being used 2024-07-13 18:01:53 -07:00
Krrish Dholakia
fde434be66 feat(proxy_server.py): return 'retry-after' param for rate limited requests 
Closes https://github.com/BerriAI/litellm/issues/4695
 2024-07-13 17:15:20 -07:00
Krrish Dholakia
bc9fe23ebf fix: cleanup 2024-07-13 16:36:04 -07:00
Krrish Dholakia
b1be355d42 build(model_prices_and_context_window.json): add azure ai jamba instruct pricing + token details 
Adds jamba instruct, mistral, llama3 pricing + token info for azure_ai
 2024-07-13 16:34:31 -07:00
Ishaan Jaff
5c6e24370e bump: version 1.41.20 → 1.41.21 2024-07-13 16:05:52 -07:00
Krish Dholakia
bc58e44d8f
Merge pull request #4701 from BerriAI/litellm_rpm_support_passthrough 
Support key-rpm limits on pass-through endpoints
 2024-07-13 15:22:29 -07:00
Krrish Dholakia
a6deb9c350 docs(pass_through.md): update doc to specify key rpm limits will be enforced 2024-07-13 15:10:13 -07:00
Ishaan Jaff
1206b0b6a9
Merge pull request #4693 from BerriAI/litellm_bad_req_error_mapping 
fix -  Raise `BadRequestError` when passing the wrong role
 2024-07-13 15:05:54 -07:00
Krrish Dholakia
da4bd47e3e test: test fixes 2024-07-13 15:04:13 -07:00
Krrish Dholakia
77325358b4 fix(pass_through_endpoints.py): fix client init 2024-07-13 14:46:56 -07:00
Ishaan Jaff
c1a9881d5c
Merge pull request #4697 from BerriAI/litellm_fix_sso_bug 
[Fix] Bug - Clear user_id from cache when /user/update is called
 2024-07-13 14:39:47 -07:00
Krrish Dholakia
7e769f3b89 fix: fix linting errors 2024-07-13 14:39:42 -07:00
Ishaan Jaff
fad37a969b ui new build 2024-07-13 14:38:13 -07:00
Ishaan Jaff
b0a1ed72b1
Merge pull request #4692 from BerriAI/ui_fix_cache_ratio_calc 
[UI] Fix Cache Ratio Calc
 2024-07-13 14:36:39 -07:00
Krrish Dholakia
55e153556a test(test_pass_through_endpoints.py): add test for rpm limit support 2024-07-13 13:49:20 -07:00
Krrish Dholakia
0cc273d77b feat(pass_through_endpoint.py): support enforcing key rpm limits on pass through endpoints 
Closes https://github.com/BerriAI/litellm/issues/4698
 2024-07-13 13:29:44 -07:00
Ishaan Jaff
bba748eaf4 fix test rules 2024-07-13 13:23:23 -07:00
Ishaan Jaff
a447e4dd1a delete updated / deleted values from cache 2024-07-13 13:16:57 -07:00
Ishaan Jaff
56b69eba18 test updating user role 2024-07-13 13:13:40 -07:00
Krrish Dholakia
f1fe229bb1 docs(guardrails.md): update guardrail api spec 2024-07-13 12:34:49 -07:00
Ishaan Jaff
893ed4e5f1 correctly clear cache when updating a user 2024-07-13 12:33:43 -07:00
Ishaan Jaff
bc91025307 use wrapper on /user endpoints 2024-07-13 12:29:15 -07:00
Ishaan Jaff
677db38f8b add doc string to explain what delete cache does 2024-07-13 12:25:31 -07:00
Krrish Dholakia
6b78e39600 feat(guardrails.py): allow setting logging_only in guardrails_config for presidio pii masking integration 2024-07-13 12:22:17 -07:00
Ishaan Jaff
670bf1b98d correctly flush cache when updating user 2024-07-13 12:05:09 -07:00
Krrish Dholakia
f2522867ed fix(types/guardrails.py): add 'logging_only' param support 2024-07-13 11:44:37 -07:00
Krrish Dholakia
caa01d20cb build: re-run ci/cd 2024-07-13 11:41:35 -07:00
Ishaan Jaff
bcc89a2c3a fix testing exception mapping 2024-07-13 11:10:13 -07:00
Krrish Dholakia
9d02d51a17 docs(pass_through.md): cleanup docs 2024-07-13 09:56:06 -07:00
Ishaan Jaff
d0dbc0742b fix exception raised in factory.py 2024-07-13 09:55:04 -07:00
Ishaan Jaff
c7f74b0297 test - test_completion_bedrock_invalid_role_exception 2024-07-13 09:54:32 -07:00
Ishaan Jaff
23cccba070 fix str from BadRequestError 2024-07-13 09:54:32 -07:00
Ishaan Jaff
03933de775 fix exception raised in factory.py 2024-07-13 09:54:32 -07:00
Krish Dholakia
66cedccd6b
Merge pull request #4686 from BerriAI/litellm_custom_chat_endpoints 
docs(pass_through.md): Creating custom chat endpoints on proxy
 2024-07-13 09:45:17 -07:00
Ishaan Jaff
744deaec75 fix cache ratio calc 2024-07-13 08:34:32 -07:00
Ishaan Jaff
8203174faf ci/cd run again 2024-07-12 19:08:59 -07:00
Ishaan Jaff
2758a9165b test_async_response_azure 2024-07-12 19:04:05 -07:00
Krrish Dholakia
0decc36bed fix(factory.py): handle message content being a list instead of string 
Fixes https://github.com/BerriAI/litellm/issues/4679
 2024-07-12 19:00:39 -07:00
Ishaan Jaff
70b96d12e9
Merge pull request #4685 from BerriAI/litellm_return_type_expired_key 
[Fix] Proxy Return type=expire_key on expired Key errors
 2024-07-12 18:52:51 -07:00
Krrish Dholakia
667fd2b376 docs(pass_through.md): add doc on creating custom chat endpoints on proxy 
Allows developers to call proxy with anthropic sdk/boto3/etc.
 2024-07-12 18:48:40 -07:00
Ishaan Jaff
7918f41aca test expired key raises correct exception 2024-07-12 18:45:01 -07:00
Ishaan Jaff
57ced1d25e raise roxyErrorTypes.expired_key on expired key 2024-07-12 18:41:39 -07:00
Ishaan Jaff
34ff0a7e57 raise expired_key error 2024-07-12 18:39:00 -07:00
Ishaan Jaff
92bf98b30f
Merge pull request #4684 from BerriAI/litellm_safe_memory_mode 
[Feat] Allow safe memory mode
 2024-07-12 18:32:16 -07:00
Ishaan Jaff
eb342bbe2c
Merge pull request #4683 from BerriAI/litellm_dealloc_in_mem_cache 
[Fix] Mem Util - De Reference when removing from in-memory cache
 2024-07-12 18:31:56 -07:00
Ishaan Jaff
24918c5041
Merge pull request #4682 from BerriAI/litellm_mem_leak_debug 
show stack trace of 10 files taking up memory
 2024-07-12 18:31:41 -07:00
Ishaan Jaff
cf5f11cc84
Merge pull request #4681 from BerriAI/litellm_mem_usage 
[Fix] Reduce Mem Usage - only set ttl for requests to 2 mins
 2024-07-12 18:31:19 -07:00