Krish Dholakia
707cf24472
Merge branch 'main' into litellm_webhook_support
2024-05-20 18:41:58 -07:00
Krish Dholakia
c6bb6e325b
Merge pull request #3740 from BerriAI/litellm_return_rejected_response
...
feat(proxy_server.py): allow admin to return rejected response as string to user
2024-05-20 17:48:21 -07:00
Krrish Dholakia
867f9300e3
fix(slack_alerting.py): cleanup webhook event
2024-05-20 16:55:01 -07:00
Krrish Dholakia
da0e5d1b8d
feat(slack_alerting.py): support webhook for budget alerts
...
Closes https://github.com/BerriAI/litellm/issues/3743
2024-05-20 15:30:56 -07:00
Ishaan Jaff
b5f8c63875
try/except deployment metrics error
2024-05-20 15:03:04 -07:00
Ishaan Jaff
02fc507b01
fix divide by 0 bug
2024-05-20 14:26:30 -07:00
Krrish Dholakia
1384ee3c57
fix(slack_alerting.py): prevent alert spam within 24 hr period for budget alerts
...
Closes https://github.com/BerriAI/litellm/issues/3738
2024-05-20 13:35:19 -07:00
Krrish Dholakia
f11f207ae6
feat(proxy_server.py): refactor returning rejected message, to work with error logging
...
log the rejected request as a failed call to langfuse/slack alerting
2024-05-20 11:14:36 -07:00
Krrish Dholakia
372323c38a
feat(proxy_server.py): allow admin to return rejected response as string to user
...
Closes https://github.com/BerriAI/litellm/issues/3671
2024-05-20 10:30:23 -07:00
Ishaan Jaff
8281c150f0
Merge pull request #3713 from BerriAI/litellm_ui_infer_azure_prefix
...
[Feat] Admin UI - use `base_model` for Slack Alerts
2024-05-17 21:55:23 -07:00
Krrish Dholakia
4b3551abfc
fix(slack_alerting.py): show langfuse traces on error messages
2024-05-17 18:42:30 -07:00
Ishaan Jaff
be273b3c3b
fix - show correct base_model in slack alerts
2024-05-17 16:07:02 -07:00
Krish Dholakia
d9ce94ae23
Merge pull request #3703 from msabramo/msabramo/make-langsmith-integration-work-with-custom-langsmith
...
Work with custom `LANGSMITH_BASE_URL`
2024-05-16 22:23:09 -07:00
Marc Abramowitz
bf4f08ac30
Work with custom LANGSMITH_BASE_URL
...
This allows working with a custom Langsmith base URL. For example,
I can use this to test against a local Langsmith instance, running on
my laptop with Docker by adding this to the proxy config:
```yaml
litellm_settings:
success_callback: ["langsmith"]
environment_variables:
LANGSMITH_BASE_URL: "http://localhost:1984 "
LANGSMITH_PROJECT: "litellm-proxy"
```
2024-05-16 17:13:01 -07:00
Ishaan Jaff
a292583ff1
fix - allow users to opt into specific alert types
2024-05-16 16:52:44 -07:00
Krrish Dholakia
a7b9a03991
docs(billing.md): add tutorial on billing with litellm + lago to docs
2024-05-16 14:13:39 -07:00
Krrish Dholakia
e273e66618
feat(lago.py): adding support for usage-based billing with lago
...
Closes https://github.com/BerriAI/litellm/issues/3639
2024-05-16 10:54:18 -07:00
Krrish Dholakia
4ff0703a31
fix(slack_alerting.py): fix timezone utc issue
2024-05-14 22:54:33 -07:00
Krrish Dholakia
54587db402
fix(alerting.py): fix datetime comparison logic
2024-05-14 22:10:09 -07:00
Krish Dholakia
b04a8d878a
Revert "Logfire Integration"
2024-05-14 17:38:47 -07:00
Krish Dholakia
adaafd72be
Merge pull request #3599 from taralika/patch-1
...
Ignore 0 failures and 0s latency in daily slack reports
2024-05-14 11:47:46 -07:00
alisalim17
18bf68298f
Merge remote-tracking branch 'upstream/main'
2024-05-14 18:42:20 +04:00
Anand Taralika
3b0c7d2321
Merge branch 'BerriAI:main' into patch-1
2024-05-13 21:31:00 -07:00
Marc Abramowitz
bfec894f6b
Cast SLACK_DAILY_REPORT_FREQUENCY to int
2024-05-13 17:08:53 -07:00
Marc Abramowitz
01da3b0a7a
Add ability to customize slack report frequency
...
via `SLACK_DAILY_REPORT_FREQUENCY` env var
Addresses one thing that @taralika mentioned in
https://github.com/BerriAI/litellm/issues/3597
2024-05-13 16:39:44 -07:00
Ishaan Jaff
1be6ea0c0d
Merge pull request #3603 from alexanderepstein/langfuse_turn_off_messaging
...
feat(langfuse.py): Allow for individual call message/response redaction
2024-05-13 15:21:41 -07:00
Krrish Dholakia
bd2f46fd75
fix(slack_alerting.py): if 'turn_off_message_logging' enabled, do not log the message to logging integration
2024-05-13 14:02:43 -07:00
Ishaan Jaff
21845bc061
Merge pull request #3609 from BerriAI/litellm_send_daily_spend_report
...
[Feat] send weekly spend reports by Team/Tag
2024-05-13 12:45:37 -07:00
Ishaan Jaff
3fbebe16aa
fix - spend reports on alerts
2024-05-13 10:51:59 -07:00
Ishaan Jaff
55f747fb1d
fix - show monthly spend in slack reports
2024-05-13 10:17:09 -07:00
Krrish Dholakia
13e1577753
fix(slack_alerting.py): don't fire spam alerts when backend api call fails
2024-05-13 10:04:43 -07:00
Ishaan Jaff
b7bbaf1a68
feat - send daily spend reports
2024-05-13 09:25:31 -07:00
Alex Epstein
3bf2ccc856
feat(langfuse.py): Allow for individual call message/response redaction
2024-05-12 22:38:29 -04:00
Anand Taralika
b490c289ca
Removed "5" from the string
...
since it's not guaranteed to always be 5, it will be at most 5, but could be less than 5 (if some values are 0s now that we ignore 0s)
2024-05-12 09:29:23 -07:00
Anand Taralika
9016e29d20
Update a comment about ignoring 0 values in addition to None
2024-05-12 08:53:04 -07:00
Anand Taralika
1dcf7eb06d
Ignore 0 failures and 0s latency in daily slack reports
...
Should fix #3598
2024-05-12 08:47:29 -07:00
Krish Dholakia
1d651c6049
Merge branch 'main' into litellm_bedrock_command_r_support
2024-05-11 21:24:42 -07:00
Krrish Dholakia
d142478b75
fix(langfuse.py): fix handling of dict object for langfuse prompt management
2024-05-11 20:42:55 -07:00
Ishaan Jaff
b9b8bf52f3
Merge pull request #3581 from BerriAI/litellm_log_metadata_langfuse_traces
...
[Feat] - log metadata on traces + allow users to log metadata when `existing_trace_id` exists
2024-05-11 14:19:48 -07:00
Ishaan Jaff
a41bef5297
debug langfuse
2024-05-11 14:12:26 -07:00
Ishaan Jaff
1bf8e7ac75
fix langfuse debug mode
2024-05-11 14:08:39 -07:00
Ishaan Jaff
038522ab24
fix - support debugging litellm params
2024-05-11 14:02:16 -07:00
Krrish Dholakia
4a3b084961
feat(bedrock_httpx.py): moves to using httpx client for bedrock cohere calls
2024-05-11 13:43:08 -07:00
Ishaan Jaff
ebb5c76e37
fix langfuse log clean metadata
2024-05-11 10:19:02 -07:00
Ishaan Jaff
e83743f8e1
fix langfuse - log metadata on traces
2024-05-11 09:59:05 -07:00
Krish Dholakia
3ee61350ed
Merge pull request #3424 from lunary-ai/main
...
Fix tool calls tracking with Lunary
2024-05-11 09:26:26 -07:00
Krish Dholakia
363cdb1a0c
Merge pull request #3576 from BerriAI/litellm_langfuse_fix
...
fix(langfuse.py): fix logging user_id in trace param on new trace creation
2024-05-10 19:27:34 -07:00
Krrish Dholakia
0115c79222
fix(langfuse.py): fix logging user_id in trace param on new trace creation
...
Closes https://github.com/BerriAI/litellm/issues/3560
2024-05-10 18:25:07 -07:00
Ishaan Jaff
4584989a31
fix - langfuse copy metadata
2024-05-10 17:33:29 -07:00
Krrish Dholakia
6575143460
feat(proxy_server.py): return litellm version in response headers
2024-05-08 16:00:08 -07:00
