 ishaan-jaffandKrrish Dholakia
|
ef32a5da1b
|
(feat) redis-semantic cache
|
2024-02-06 13:30:55 -08:00 |
|
 ishaan-jaffandKrrish Dholakia
|
0c488a7cc7
|
(feat) working semantic-cache on litellm proxy
|
2024-02-06 13:30:55 -08:00 |
|
 ishaan-jaffandKrrish Dholakia
|
ca5f83d5fe
|
(test) async semantic cache
|
2024-02-06 13:30:55 -08:00 |
|
 ishaan-jaffandKrrish Dholakia
|
97fbfc07b4
|
(feat) RedisSemanticCache - async
|
2024-02-06 13:30:55 -08:00 |
|
 ishaan-jaffandKrrish Dholakia
|
05d64acdd3
|
(fix) semantic cache
|
2024-02-06 13:30:55 -08:00 |
|
 ishaan-jaffandKrrish Dholakia
|
5d6af6b7d6
|
(test) semantic caching
|
2024-02-06 13:30:55 -08:00 |
|
 ishaan-jaffandKrrish Dholakia
|
b8a1cc4e42
|
(test) semantic cache
|
2024-02-06 13:30:55 -08:00 |
|
 ishaan-jaffandKrrish Dholakia
|
bc22fda64e
|
(feat) working - sync semantic caching
|
2024-02-06 13:30:55 -08:00 |
|
 ishaan-jaffandKrrish Dholakia
|
fa1681fe7a
|
(feat )add semantic cache
|
2024-02-06 13:30:55 -08:00 |
|
 ishaan-jaffandKrrish Dholakia
|
e6e340cd46
|
(feat) show langfuse logging tags better through proxy
|
2024-02-06 13:30:55 -08:00 |
|
Krrish Dholakia
|
de68cc69a6
|
bump: version 1.22.8 → 1.22.9
|
2024-02-06 13:17:26 -08:00 |
|
Krrish Dholakia
|
67dce555ec
|
fix(utils.py): round max tokens to be int always
|
2024-02-06 13:17:26 -08:00 |
|
 ishaan-jaffandKrrish Dholakia
|
38445ca508
|
(ci/cd) run again
|
2024-02-06 13:17:26 -08:00 |
|
 ishaan-jaffandKrrish Dholakia
|
7c9ada1b19
|
(ci/cd) run again
|
2024-02-06 13:17:26 -08:00 |
|
 ishaan-jaffandKrrish Dholakia
|
47e056d2ea
|
(ci/cd) fix test_config_no_auth
|
2024-02-06 13:17:26 -08:00 |
|
 ishaan-jaffandKrrish Dholakia
|
adb67da026
|
(fix) test_normal_router_tpm_limit
|
2024-02-06 13:17:26 -08:00 |
|
 ishaan-jaffandKrrish Dholakia
|
bdb9fc8f20
|
(fix) parallel_request_limiter debug
|
2024-02-06 13:17:26 -08:00 |
|
 ishaan-jaffandKrrish Dholakia
|
697109b7ec
|
(ci/cd) run again
|
2024-02-06 13:17:26 -08:00 |
|
 ishaan-jaffandKrrish Dholakia
|
3993e1162e
|
(ci/cd) run pytest without -s
|
2024-02-06 13:17:26 -08:00 |
|
 ishaan-jaffandKrrish Dholakia
|
61e5f2a79b
|
(fix) proxy_startup test
|
2024-02-06 13:17:26 -08:00 |
|
 ishaan-jaffandKrrish Dholakia
|
d94d925c3b
|
(fix) rename proxy startup test
|
2024-02-06 13:17:26 -08:00 |
|
 ishaan-jaffandKrrish Dholakia
|
ac31fe0081
|
(ci/cd) run in verbose mode
|
2024-02-06 13:17:26 -08:00 |
|
Krrish Dholakia
|
f1fc2b006c
|
bump: version 1.22.7 → 1.22.8
|
2024-02-06 13:17:26 -08:00 |
|
Krrish Dholakia
|
7055793609
|
fix(ollama.py): support format for ollama
|
2024-02-06 13:17:26 -08:00 |
|
Krrish Dholakia
|
5d224a7e71
|
build(requirements.txt): update the proxy requirements.txt
|
2024-02-06 13:17:26 -08:00 |
|
Krrish Dholakia
|
3afa5230d6
|
fix(utils.py): return finish reason for last vertex ai chunk
|
2024-02-06 09:21:03 -08:00 |
|
Krrish Dholakia
|
f2ef32bcee
|
bump: version 1.22.6 → 1.22.7
|
2024-02-06 07:44:04 -08:00 |
|
Krrish Dholakia
|
9e091a0624
|
fix(ollama_chat.py): explicitly state if ollama call is streaming or not
|
2024-02-06 07:43:47 -08:00 |
|
Krrish Dholakia
|
c2a523b954
|
fix(utils.py): use print_verbose for statements, so debug can be seen when running sdk
|
2024-02-06 07:30:26 -08:00 |
|
Krrish Dholakia
|
2e3748e6eb
|
fix(ollama_chat.py): fix ollama chat completion token counting
|
2024-02-06 07:30:26 -08:00 |
|
ishaan-jaff
|
47bed68c7f
|
(fix) test_normal_router_tpm_limit
|
2024-02-06 06:46:49 -08:00 |
|
ishaan-jaff
|
9a8abdb1ae
|
(ci/cd) print debug info for test_proxy_gunicorn_startup_config_dict
|
2024-02-05 22:53:31 -08:00 |
|
ishaan-jaff
|
4d625818d6
|
(fix) proxy startup test
|
2024-02-05 22:51:11 -08:00 |
|
 Ishaan JaffandGitHub
|
ed53f34537
|
Merge pull request #1844 from BerriAI/litellm_set_upperbound_budgets
[Feat] Proxy set upperbound params for key/generate
|
2024-02-05 22:42:01 -08:00 |
|
ishaan-jaff
|
71814d8149
|
(feat) proxy - upperbound params /key/generate
|
2024-02-05 22:40:52 -08:00 |
|
ishaan-jaff
|
4d4554b0e4
|
(test) test_upperbound_key_params
|
2024-02-05 22:39:36 -08:00 |
|
ishaan-jaff
|
a712596d46
|
(feat) upperbound_key_generate_params
|
2024-02-05 22:38:47 -08:00 |
|
ishaan-jaff
|
d4fd287617
|
(docs) upperbound_key_generate_params
|
2024-02-05 22:37:05 -08:00 |
|
Krrish Dholakia
|
7a0bccf4d0
|
test(test_key_generate_dynamodb.py): fix test
|
2024-02-05 21:44:50 -08:00 |
|
 Krish DholakiaandGitHub
|
3d29ec126b
|
Merge pull request #1837 from BerriAI/litellm_langfuse_failure_cost_tracking
fix(langfuse.py): support logging failed llm api calls to langfuse
|
2024-02-05 19:46:40 -08:00 |
|
 Ishaan JaffandGitHub
|
82f0eb8cea
|
Merge pull request #1842 from ushuz/admin-ui-title-description
Fix admin UI title and description
|
2024-02-05 17:38:49 -08:00 |
|
 John HUandGitHub
|
f4cdb6d234
|
Fix admin UI title and description
|
2024-02-05 17:30:39 -08:00 |
|
 Krish DholakiaandGitHub
|
b9e6f760eb
|
Update model_prices_and_context_window.json
|
2024-02-05 17:07:57 -08:00 |
|
Krrish Dholakia
|
cdbbedec36
|
bump: version 1.22.5 → 1.22.6
|
2024-02-05 16:26:30 -08:00 |
|
Krrish Dholakia
|
3b9ada07e0
|
fix(main.py): raise better error message for health check models without mode
|
2024-02-05 16:26:25 -08:00 |
|
ishaan-jaff
|
1f7c8e86a7
|
(fix) make sure route is str
|
2024-02-05 16:22:36 -08:00 |
|
 Ishaan JaffandGitHub
|
5ebb1b4447
|
Merge pull request #1836 from BerriAI/litellm_fix_litellm_dashboard_keys
[Fix] UI - Security - Litellm UI Keys meant for litellm-dashboard shouldn't be allowed to make non-management related requests
|
2024-02-05 16:20:33 -08:00 |
|
Krrish Dholakia
|
a1bbb16ab2
|
fix(langfuse.py): support logging failed llm api calls to langfuse
|
2024-02-05 16:16:15 -08:00 |
|
ishaan-jaff
|
2b588a8786
|
(test) litellm-dashboard never allowed to /chat/completions
|
2024-02-05 16:11:33 -08:00 |
|
ishaan-jaff
|
8d7698f24d
|
(fix) litellm-ui keys can never access /chat/completions
|
2024-02-05 16:10:49 -08:00 |
|