ai-workspace-services/litellm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
9,961 Commits 9 Branches 7 Tags 935 MiB
fd7760d3db
Commit Graph

9961 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Krish Dholakia
fd7760d3db
Merge pull request #2996 from BerriAI/litellm_semaphores 
fix(router.py): initial commit for semaphores on router
 2024-04-12 23:23:36 -07:00
Ishaan Jaff
5856ec03c6 (ci/cd) run again 2024-04-12 20:48:26 -07:00
Ishaan Jaff
96eddf2335 bump: version 1.35.2 → 1.35.3 2024-04-12 20:40:18 -07:00
Ishaan Jaff
f617f5ebb5 fix - test caching atext_completion 2024-04-12 20:37:56 -07:00
Ishaan Jaff
81e8ace20f
Merge pull request #2997 from BerriAI/litellm_fix_failing_health_checks 
fix - use copy.deepcopy on /model/info endpoints
 2024-04-12 20:34:30 -07:00
Ishaan Jaff
081adf87e3 fix - proxy /health checks 2024-04-12 20:30:15 -07:00
Ishaan Jaff
91d89a7b9b fix - use copy.deepcopy on /model/info endpoints 2024-04-12 20:17:11 -07:00
Ishaan Jaff
a2368f9036
Merge pull request #2985 from BerriAI/ui_fix_setting_slack 
ui - fix setting slack alerting
 2024-04-12 20:08:23 -07:00
Ishaan Jaff
0540ca4918
Merge pull request #2991 from BerriAI/litellm_fix_text_completion_caching 
[Feat] Support + Test caching for TextCompletion
 2024-04-12 20:08:01 -07:00
Krrish Dholakia
8179596ebc fix(lowest_tpm_rpm_v2.py): don't fail calls if redis fails to connect 2024-04-12 19:36:59 -07:00
Krrish Dholakia
ea1574c160 test(test_openai_endpoints.py): add concurrency testing for user defined rate limits on proxy 2024-04-12 18:56:13 -07:00
Krrish Dholakia
c03b0bbb24 fix(router.py): support pre_call_rpm_check for lowest_tpm_rpm_v2 routing 
have routing strategies expose an ‘update rpm’ function; for checking + updating rpm pre call
 2024-04-12 18:25:14 -07:00
Krrish Dholakia
2267aeb803 fix(router.py): create a semaphore for each deployment with rpm 
run semaphore logic for each deployment with rpm
 2024-04-12 18:03:23 -07:00
Krrish Dholakia
a4e415b23c fix(router.py): initial commit for semaphores on router 2024-04-12 17:59:05 -07:00
Krrish Dholakia
74aa230eac fix(main.py): automatically infer mode for text completion models 2024-04-12 14:16:21 -07:00
Krrish Dholakia
b0770cf8e2 build(requirements.txt): bump google genai version 2024-04-12 13:52:47 -07:00
Krrish Dholakia
e407ff7ee7 build(ui): allow deleting models from UI + show correct provider in model list 2024-04-12 12:53:22 -07:00
Ishaan Jaff
0cef782ffa fix - support text completion caching 2024-04-12 12:34:28 -07:00
Ishaan Jaff
11cd1ec6cf test - atext_completion + caching 2024-04-12 12:32:21 -07:00
Krrish Dholakia
dc2f57e060 build(ui): allow multi select models when adding them to a model group 2024-04-12 11:48:07 -07:00
Krrish Dholakia
7ee17c97e7 build(ui): dropdown for known provider models 2024-04-12 11:17:09 -07:00
Krrish Dholakia
bdb32a0f42 build(ui): allow setting openai org id when creating new models 2024-04-12 09:34:09 -07:00
Ishaan Jaff
c063a63d15 ui - fix setting slack alerting 2024-04-12 08:52:33 -07:00
Krish Dholakia
e01e9fd764
Merge pull request #2984 from Dev-Khant/slack-msg-truncation 
truncate long slack msg
 2024-04-12 08:30:08 -07:00
Ishaan Jaff
297f272a61
Merge pull request #2977 from BerriAI/litellm_sec_fix 
fix - stop printing api_key in debug mode
 2024-04-12 08:26:35 -07:00
Ishaan Jaff
df2999e0eb
Merge pull request #2982 from bcvanmeurs/patch-1 
Fix .dockerignore
 2024-04-12 08:10:50 -07:00
Dev Khant
5cdcc5895c truncate long slack msg 2024-04-12 17:22:14 +05:30
Bram van Meurs
facdc795bb
Fix .dockerignore 
Prefix slash does work on macos, but I suspect not on linux.
 2024-04-12 11:06:24 +01:00
Krrish Dholakia
775d28a509 docs(token_auth.md): update docs to show org spend tracking 2024-04-11 23:34:34 -07:00
Krish Dholakia
a1cb9a51b9
Merge pull request #2978 from BerriAI/litellm_org_spend_tracking 
fix(proxy_server.py): support tracking org spend
 2024-04-11 23:19:33 -07:00
Krrish Dholakia
c480b5a008 bump: version 1.35.1 → 1.35.2 2024-04-11 23:16:39 -07:00
Krrish Dholakia
7a3821e0f6 fix(gemini.py): log system prompt in verbose output 2024-04-11 23:15:58 -07:00
Krrish Dholakia
77d6b882b8 fix(vertex_ai.py): check if 'response_mime_type' in generation config before passing it in 2024-04-11 23:10:59 -07:00
Krrish Dholakia
c377ba0755 fix(utils.py): vertex ai exception mapping 
fixes check which caused all vertex errors to be ratelimit errors
 2024-04-11 23:04:21 -07:00
Krrish Dholakia
f4c7f4f901 fix(proxy_server.py): support tracking org spend 
currently works when org set for jwt auth
 2024-04-11 23:01:21 -07:00
Krish Dholakia
d89644d46c
Merge pull request #2970 from BerriAI/litellm_keys 
fix(handle_jwt.py): User cost tracking via JWT Auth
 2024-04-11 21:44:15 -07:00
Krrish Dholakia
3665b890f8 build(proxy_server_config.yaml): cleanup config 2024-04-11 20:20:09 -07:00
Krrish Dholakia
77097f8e7d test(test_jwt.py): add testing to make sure user api key auth returns the expected values 2024-04-11 20:18:55 -07:00
Krrish Dholakia
67b5634417 fix(auth_checks.py): raise error if user doesn't exist in db 2024-04-11 19:55:04 -07:00
Krrish Dholakia
36ff593c02 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
Ishaan Jaff
8ba140b09e
Merge pull request #2965 from BerriAI/litellm_fix_key_update 
fix - delete key from inMemory Cache after /key/update
 2024-04-11 18:18:05 -07:00
Krrish Dholakia
e413191493 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
Krish Dholakia
cd834e9d52
Merge pull request #2964 from Manouchehri/gemini-json-mode-2962 
Add JSON mode to Gemini (Vertex AI)
 2024-04-11 17:51:27 -07:00
Krrish Dholakia
3b803b09d9 fix(langfuse.py): remove print statements 2024-04-11 17:23:41 -07:00
Ishaan Jaff
beabec620e fix - delete updated keys from cache 2024-04-11 17:21:44 -07:00
Krrish Dholakia
bdfb74f8a5 test(test_openai_endpoints.py): add local test, for proxy concurrency 2024-04-11 17:16:23 -07:00
David Manouchehri
9c55be3e82
(feat) - Bump version for Vertex AI SDK. 2024-04-12 00:03:32 +00:00
David Manouchehri
05350037be
(feat) - Extreme dirty hack for response_mime_type in Vertex AI. 2024-04-12 00:03:31 +00:00
David Manouchehri
d08674bf2f
(feat) - Dirty hack to get response_mime_type working before it's released in the Python SDK. 2024-04-12 00:03:30 +00:00
David Manouchehri
649c3bb0dd
(feat) - Add support for JSON mode in Vertex AI 2024-04-12 00:03:29 +00:00