Ishaan Jaff
|
12a2621ead
|
ui - filter by model names
|
2024-04-24 14:51:14 -07:00 |
|
Ishaan Jaff
|
7a5c07de22
|
fix - show api_base, model in exceptions
|
2024-04-24 14:03:48 -07:00 |
|
Ishaan Jaff
|
2ac3885a50
|
Merge pull request #3277 from BerriAI/litellm_update_deployments
[UI] V0 - Edit Model tpm, rpm, api_base
|
2024-04-24 14:03:00 -07:00 |
|
Ishaan Jaff
|
ca4fd85296
|
fix show api_base, model in timeout errors
|
2024-04-24 14:01:32 -07:00 |
|
Nandesh Guru
|
651ff66d65
|
Merge branch 'main' of https://github.com/greenscale-ai/litellm
|
2024-04-24 13:46:46 -07:00 |
|
Nandesh Guru
|
cdd6013624
|
Greenscale Documentation
|
2024-04-24 13:46:43 -07:00 |
|
Ishaan Jaff
|
8a8ba96831
|
fix build issues
|
2024-04-24 13:29:10 -07:00 |
|
Ishaan Jaff
|
36f8431bf0
|
(ci/cd) testing
|
2024-04-24 13:25:18 -07:00 |
|
Ishaan Jaff
|
31a8270206
|
ui -edit model flow
|
2024-04-24 13:21:22 -07:00 |
|
Ishaan Jaff
|
f8803cb877
|
ui - working edit model flow
|
2024-04-24 13:21:12 -07:00 |
|
Krrish Dholakia
|
1f7abb8d92
|
fix(langfuse.py): fix langfuse environ check
|
2024-04-24 13:21:00 -07:00 |
|
Krish Dholakia
|
263439ee4a
|
Merge pull request #3098 from greenscale-ai/main
Support for Greenscale AI logging
|
2024-04-24 13:09:03 -07:00 |
|
Krrish Dholakia
|
57cd3f482a
|
bump: version 1.35.23 → 1.35.24
|
2024-04-24 11:13:37 -07:00 |
|
Krrish Dholakia
|
3fdb2f0779
|
fix(ui): fix add slack/langfuse logging on ui
|
2024-04-24 10:58:44 -07:00 |
|
Ishaan Jaff
|
efbf85a5ad
|
/model/update endpoint
|
2024-04-24 10:39:20 -07:00 |
|
Krrish Dholakia
|
07793660ea
|
build(ui): add refresh button for model page
prevents need for user to reload page just to see if new model added
|
2024-04-24 10:31:54 -07:00 |
|
Krrish Dholakia
|
26e9ae38ce
|
fix(proxy_server.py): add new flag for disable sharing master key on ui
|
2024-04-24 10:06:01 -07:00 |
|
Ishaan Jaff
|
3d1a158b63
|
feat - update deployments
|
2024-04-24 09:53:42 -07:00 |
|
Krrish Dholakia
|
b918f58262
|
fix(vertex_ai.py): raise explicit error when image url fails to download - prevents silent failure
|
2024-04-24 09:23:15 -07:00 |
|
Simon Sanchez Viloria
|
0d1db1ddaf
|
(docs) added watsonx.ai provider documentation
|
2024-04-24 17:22:17 +02:00 |
|
Simon Sanchez Viloria
|
72cbe369be
|
(docs) updated watsonx cookbook
|
2024-04-24 17:19:02 +02:00 |
|
Krrish Dholakia
|
f800ebc3c1
|
bump: version 1.35.22 → 1.35.23
|
2024-04-24 08:16:33 -07:00 |
|
Krrish Dholakia
|
52d5e02d8b
|
fix(prometheus.py): fix user-id get for prometheus
|
2024-04-24 08:08:42 -07:00 |
|
Krrish Dholakia
|
48c2c3d78a
|
fix(utils.py): fix streaming to not return usage dict
Fixes https://github.com/BerriAI/litellm/issues/3237
|
2024-04-24 08:06:07 -07:00 |
|
David Manouchehri
|
fbe5ba6213
|
(requirements.txt) - Update gunicorn to 22.0.0 for CVE-2024-1135
|
2024-04-24 13:44:54 +00:00 |
|
David Manouchehri
|
d4d3130b38
|
(requirements.txt) - Update langfuse so that we get the latest features.
|
2024-04-24 13:31:51 +00:00 |
|
Simon Sanchez Viloria
|
777b4b2bbc
|
(feat) make manage_response work with request.request instead of httpx.Request
|
2024-04-24 12:55:25 +02:00 |
|
Simon Sanchez Viloria
|
9fc30e8b31
|
(test) Added completion and embedding tests for watsonx provider
|
2024-04-24 12:52:29 +02:00 |
|
Krrish Dholakia
|
70c98617da
|
bump: version 1.35.21 → 1.35.22
|
2024-04-23 22:53:46 -07:00 |
|
Krrish Dholakia
|
a77bb2da5d
|
build(ui): add ui updates to main build
|
2024-04-23 22:53:37 -07:00 |
|
Krish Dholakia
|
2d150e7ac0
|
Merge pull request #3260 from BerriAI/litellm_ui_fixes_5
build(ui): user_dashboard.tsx
|
2024-04-23 22:50:18 -07:00 |
|
Krrish Dholakia
|
afba10c9c3
|
build(ui): fixes
|
2024-04-23 22:49:30 -07:00 |
|
Ishaan Jaff
|
aa08397e34
|
ui - new build
|
2024-04-23 22:23:49 -07:00 |
|
Ishaan Jaff
|
1a785f255e
|
Merge pull request #3259 from BerriAI/litellm_filter_metrics_model_group
UI - filter metrics by model group
|
2024-04-23 22:22:05 -07:00 |
|
Ishaan Jaff
|
b2fdc3fc76
|
ui - show how models were load balanced
|
2024-04-23 22:08:59 -07:00 |
|
Ishaan Jaff
|
59cacf1a3a
|
ui filter by model group
|
2024-04-23 22:04:12 -07:00 |
|
Ishaan Jaff
|
6d828b478d
|
ui - allow filtering by model group
|
2024-04-23 22:03:59 -07:00 |
|
Ishaan Jaff
|
9017d9bb81
|
backend allow filtering by model_group
|
2024-04-23 22:03:20 -07:00 |
|
Krrish Dholakia
|
9e3514fd24
|
fix(langsmith.py): fix streaming langsmith calls
|
2024-04-23 20:47:19 -07:00 |
|
Ishaan Jaff
|
ac6809e9df
|
ui - filter by time and deployments
|
2024-04-23 20:42:15 -07:00 |
|
Krrish Dholakia
|
959f98a41e
|
bump: version 1.35.20 → 1.35.21
|
2024-04-23 20:12:02 -07:00 |
|
Krrish Dholakia
|
cf5721332e
|
docs(anthropic.md): add parallel tool calling example for anthropic
|
2024-04-23 20:11:03 -07:00 |
|
Krrish Dholakia
|
7315bfd5de
|
build(model_prices_and_context_window.json): add anthropic tool use system prompt tokens
anthropic adds a system prompt when making tool calls - this adds to the cost of a tool call with anthropic
|
2024-04-23 20:01:24 -07:00 |
|
Krrish Dholakia
|
ab24f61099
|
fix(utils.py): fix mistral api tool calling response
|
2024-04-23 19:59:11 -07:00 |
|
Krish Dholakia
|
4acdde988f
|
Merge pull request #3250 from BerriAI/litellm_caching_no_cache_fix
fix(utils.py): fix 'no-cache': true when caching is turned on
|
2024-04-23 19:57:07 -07:00 |
|
Ishaan Jaff
|
3b860a7f20
|
Merge pull request #3255 from BerriAI/litellm_refactor_slack_alerting
[Fix] Refactor slack alerting, use one httpx client
|
2024-04-23 19:45:52 -07:00 |
|
Krrish Dholakia
|
e31eb6a6b2
|
test(test_openai_endpoints.py): add unit testing for streaming + logprobs on docker image
|
2024-04-23 19:26:19 -07:00 |
|
Krrish Dholakia
|
df60e475e8
|
build(requirements.txt): pin all dependency versions
|
2024-04-23 19:18:19 -07:00 |
|
Ishaan Jaff
|
c1ea3597bc
|
fix test alerting
|
2024-04-23 19:10:06 -07:00 |
|
Ishaan Jaff
|
9d18e4770d
|
fix using slack alerting through admin ui
|
2024-04-23 19:05:50 -07:00 |
|