Ishaan Jaff
|
7cb69c72c8
|
Merge branch 'main' into litellm_add_semantic_cache
|
2024-02-06 11:18:43 -08:00 |
|
ishaan-jaff
|
8175fb4deb
|
(fix) mark semantic caching as beta test
|
2024-02-06 11:04:19 -08:00 |
|
ishaan-jaff
|
405a44727c
|
(ci/cd) run in verbose mode
|
2024-02-06 10:57:20 -08:00 |
|
ishaan-jaff
|
1afdf5cf36
|
(fix) semantic caching
|
2024-02-06 10:55:15 -08:00 |
|
ishaan-jaff
|
54c920c299
|
(docs) litellm semantic caching
|
2024-02-06 10:54:55 -08:00 |
|
ishaan-jaff
|
93504915d7
|
(docs) redis cache
|
2024-02-06 10:53:28 -08:00 |
|
ishaan-jaff
|
c8a83bb745
|
(fix) test-semantic caching
|
2024-02-06 10:39:44 -08:00 |
|
ishaan-jaff
|
2732c47b70
|
(feat) redis-semantic cache on proxy
|
2024-02-06 10:35:21 -08:00 |
|
ishaan-jaff
|
bdc2091838
|
(docs) using semantic caching on proxy
|
2024-02-06 10:32:07 -08:00 |
|
ishaan-jaff
|
a1fc1e49c7
|
(fix) use semantic cache on proxy
|
2024-02-06 10:27:33 -08:00 |
|
ishaan-jaff
|
05f379234d
|
allow setting redis_semantic cache_embedding model
|
2024-02-06 10:22:02 -08:00 |
|
Krrish Dholakia
|
e542aa10cc
|
bump: version 1.22.7 → 1.22.8
|
2024-02-06 10:12:13 -08:00 |
|
Krrish Dholakia
|
d1db67890c
|
fix(ollama.py): support format for ollama
|
2024-02-06 10:11:52 -08:00 |
|
ishaan-jaff
|
751fb1af89
|
(feat) log semantic_sim to langfuse
|
2024-02-06 09:31:57 -08:00 |
|
ishaan-jaff
|
c4e73768cf
|
(fix) add redisvl==0.0.7
|
2024-02-06 09:30:45 -08:00 |
|
ishaan-jaff
|
70a895329e
|
(feat) working semantic cache on proxy
|
2024-02-06 08:55:25 -08:00 |
|
ishaan-jaff
|
a3b1e3bc84
|
(feat) redis-semantic cache
|
2024-02-06 08:54:36 -08:00 |
|
ishaan-jaff
|
6249a97098
|
(feat) working semantic-cache on litellm proxy
|
2024-02-06 08:52:57 -08:00 |
|
ishaan-jaff
|
a125ffe190
|
(test) async semantic cache
|
2024-02-06 08:14:54 -08:00 |
|
ishaan-jaff
|
76def20ffe
|
(feat) RedisSemanticCache - async
|
2024-02-06 08:13:12 -08:00 |
|
Krish Dholakia
|
dd87386cad
|
Merge pull request #1846 from BerriAI/litellm_proxy_update_requirements_txt
build(requirements.txt): update the proxy requirements.txt
|
2024-02-06 07:51:48 -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
|
4a5b635e35
|
build(requirements.txt): update the proxy requirements.txt
|
2024-02-06 07:35:46 -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 Jaff
|
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 Dholakia
|
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-jaff
|
ccc94128d3
|
(fix) semantic cache
|
2024-02-05 18:25:22 -08:00 |
|
ishaan-jaff
|
81f8ac00b2
|
(test) semantic caching
|
2024-02-05 18:22:50 -08:00 |
|
ishaan-jaff
|
cf4bd1cf4e
|
(test) semantic cache
|
2024-02-05 17:58:32 -08:00 |
|
ishaan-jaff
|
1b39454a08
|
(feat) working - sync semantic caching
|
2024-02-05 17:58:12 -08:00 |
|
Ishaan Jaff
|
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 HU
|
f4cdb6d234
|
Fix admin UI title and description
|
2024-02-05 17:30:39 -08:00 |
|
Krish Dholakia
|
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 Jaff
|
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 |
|