Krrish Dholakia
|
34c118e5e9
|
feat(ui): show key alias instead of hashed token
|
2024-02-10 15:45:42 -08:00 |
|
Krrish Dholakia
|
6b83001459
|
feat(proxy_server.py): support key lists for /key/info
|
2024-02-10 14:24:12 -08:00 |
|
ishaan-jaff
|
757334c85f
|
(fix) proxy - use bedrock in sync streaming
|
2024-02-10 09:47:33 -08:00 |
|
Krrish Dholakia
|
7409460230
|
fix(ui): export ui npm build
|
2024-02-10 08:43:41 -08:00 |
|
Krish Dholakia
|
a8ef8e12bb
|
Merge branch 'main' into litellm_ui_improvements_time_series
|
2024-02-09 20:54:36 -08:00 |
|
Krrish Dholakia
|
4678c6b936
|
fix(usage.tsx): show top users and top keys driving spend
|
2024-02-09 19:50:07 -08:00 |
|
Ishaan Jaff
|
304e337a59
|
Merge pull request #1922 from BerriAI/litellm_bedrock_proxy_timeout
[FEAT] Set timeout for bedrock on proxy
|
2024-02-09 19:22:25 -08:00 |
|
Krrish Dholakia
|
6710c2ee5d
|
fix(proxy_server.py): fix /spend/logs endpoint
|
2024-02-09 18:11:33 -08:00 |
|
ishaan-jaff
|
640011379c
|
(feat) set timeout on proxy config
|
2024-02-09 17:42:35 -08:00 |
|
ishaan-jaff
|
09c36c6e78
|
(test) llama index VectorStoreIndex
|
2024-02-09 16:49:03 -08:00 |
|
ishaan-jaff
|
924b7db540
|
(feat) support azure deployments for embeddings
|
2024-02-09 16:47:01 -08:00 |
|
Krrish Dholakia
|
43da22ae13
|
feat(proxy_server.py): show admin global spend as time series data
|
2024-02-09 16:31:35 -08:00 |
|
ishaan-jaff
|
782e84a421
|
(test) Proxy llama index request
|
2024-02-09 16:09:03 -08:00 |
|
Krish Dholakia
|
6084e0b25a
|
Merge pull request #1901 from BerriAI/litellm_ui_usage_tiers
fix(proxy_server.py): enable aggregate queries via /spend/keys
|
2024-02-08 22:45:52 -08:00 |
|
Krrish Dholakia
|
3a4ac8be79
|
fix: fixes
|
2024-02-08 21:54:48 -08:00 |
|
Krrish Dholakia
|
b9393fb769
|
fix(test_parallel_request_limiter.py): use mock responses for streaming
|
2024-02-08 21:45:38 -08:00 |
|
ishaan-jaff
|
ab3fe95810
|
(feat) update ui build
|
2024-02-08 21:38:04 -08:00 |
|
Krrish Dholakia
|
e98437104d
|
fix(proxy_server.py): enable aggregate queries via /spend/keys
|
2024-02-08 20:29:08 -08:00 |
|
Krrish Dholakia
|
ff93609453
|
build(schema.prisma): support direct url on prisma schema
|
2024-02-08 17:37:37 -08:00 |
|
ishaan-jaff
|
4cee080e7c
|
(fix) ui /login without sso
|
2024-02-08 10:47:45 -08:00 |
|
Krrish Dholakia
|
0d803e1379
|
fix(proxy_cli.py): fix max connection limit issue on db
|
2024-02-07 22:57:44 -08:00 |
|
Krrish Dholakia
|
551a4c60a7
|
fix(dynamo_db.py): eliminating unneccessary params
|
2024-02-07 22:52:15 -08:00 |
|
ishaan-jaff
|
3837c77df9
|
(feat) slack alerting when track callback fails
|
2024-02-07 20:09:28 -08:00 |
|
ishaan-jaff
|
5dc26b11bf
|
Merge remote-tracking branch 'origin/main' into litellm_aert_when_budget_tracking_fails
|
2024-02-07 18:50:00 -08:00 |
|
ishaan-jaff
|
8462e85792
|
(feat) alert for failing cost tracking
|
2024-02-07 18:49:45 -08:00 |
|
Ishaan Jaff
|
98b0ace2e9
|
Merge pull request #1874 from BerriAI/litellm_azure_base_model_pricing
[FEAT] Azure Pricing - based on base_model in model_info
|
2024-02-07 18:37:55 -08:00 |
|
Krrish Dholakia
|
d2dceb3537
|
fix(proxy_server.py): check if prisma client is set before scheduling reset budget
|
2024-02-07 18:14:37 -08:00 |
|
ishaan-jaff
|
9c597cbe0b
|
(feat) use base_model for azure cost
|
2024-02-07 16:33:35 -08:00 |
|
ishaan-jaff
|
258fe63e7d
|
(fix) ui - when request body is None
|
2024-02-07 11:33:43 -08:00 |
|
Krrish Dholakia
|
8939593826
|
fix(proxy_server.py): fix merge errors
|
2024-02-07 00:04:52 -08:00 |
|
Krrish Dholakia
|
184e78772b
|
refactor(proxy_server.py): fix merge error
|
2024-02-06 23:44:23 -08:00 |
|
Krish Dholakia
|
df60edfa07
|
Merge branch 'main' into litellm_spend_logging_high_traffic
|
2024-02-06 23:36:58 -08:00 |
|
Krrish Dholakia
|
fd9c7a90af
|
fix(proxy_server.py): update user cache to with new spend
|
2024-02-06 23:06:05 -08:00 |
|
Krrish Dholakia
|
4174471dac
|
fix(proxy_server.py): fix endpoint
|
2024-02-06 22:09:30 -08:00 |
|
Krish Dholakia
|
2bc710d8e9
|
Merge pull request #1843 from BerriAI/litellm_admin_ui_view_all_keys
feat(ui): enable admin to view all valid keys created on the proxy
|
2024-02-06 22:06:46 -08:00 |
|
Krrish Dholakia
|
0874c17a31
|
fix: export npm build into proxy
|
2024-02-06 20:12:50 -08:00 |
|
Krrish Dholakia
|
4a0df3cb4f
|
fix(proxy_cli.py-&&-proxy_server.py): bump reset budget intervals and fix pool limits for prisma connections
|
2024-02-06 19:39:49 -08:00 |
|
ishaan-jaff
|
5a29f362ee
|
(fix) allow litellm_settings to be None
|
2024-02-06 19:29:39 -08:00 |
|
Krrish Dholakia
|
b6adeec347
|
fix(proxy_server.py): prisma client fixes for high traffic
|
2024-02-06 17:30:36 -08:00 |
|
Ishaan Jaff
|
73c6ce890b
|
Merge pull request #1859 from BerriAI/litellm_allow_using_budgets_without_keys
[Feat] Budgets for 'user' param passed to /chat/completions, /embeddings etc
|
2024-02-06 16:32:25 -08:00 |
|
Krish Dholakia
|
9e9fb747ce
|
Merge branch 'main' into litellm_slack_langfuse_alerting
|
2024-02-06 15:48:52 -08:00 |
|
ishaan-jaff
|
52b864976b
|
(feat) support max_user_budget
|
2024-02-06 15:19:36 -08:00 |
|
ishaan-jaff
|
325ca43946
|
(feat) show semantic-cache on health/readiness
|
2024-02-06 15:17:40 -08:00 |
|
ishaan-jaff
|
f8248b2c79
|
(feat) redis-semantic cache on proxy
|
2024-02-06 15:17:40 -08:00 |
|
ishaan-jaff
|
58f47c9e29
|
(fix) use semantic cache on proxy
|
2024-02-06 15:17:40 -08:00 |
|
ishaan-jaff
|
e0d5c953d6
|
(feat) working semantic cache on proxy
|
2024-02-06 15:17:40 -08:00 |
|
ishaan-jaff
|
97dbf14b32
|
(fix) parallel_request_limiter debug
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
732ac6df49
|
(feat) proxy - upperbound params /key/generate
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
8d0c235004
|
(feat) upperbound_key_generate_params
|
2024-02-06 15:17:35 -08:00 |
|
ishaan-jaff
|
4e3f048967
|
(feat) max_user_budget
|
2024-02-06 15:16:20 -08:00 |
|