Ishaan Jaff
1b42e53e06
allow internal user to view global/spend/models
2024-09-05 12:38:48 -07:00
Ishaan Jaff
0a05c24a9a
allow internal user to view their own spend
2024-09-05 12:35:04 -07:00
Ishaan Jaff
034de5b3cc
add usage endpoints for internal user
2024-09-05 12:34:41 -07:00
Ishaan Jaff
09894204a5
show /spend/logs for internal users
2024-09-05 12:14:03 -07:00
Ishaan Jaff
e0400accca
fix create view - MonthlyGlobalSpendPerUserPerKey
2024-09-05 12:11:59 -07:00
Ishaan Jaff
cc51fd0df9
use helper functions per endpoint
2024-09-05 10:57:12 -07:00
Ishaan Jaff
e6e5fb5843
add /spend/tags as allowed route for internal user
2024-09-05 10:41:43 -07:00
Ishaan Jaff
219fa492dc
fix import
2024-09-05 10:41:13 -07:00
Ishaan Jaff
e9cb1e0853
fix import error
2024-09-05 10:27:35 -07:00
Ishaan Jaff
e1c989ad3d
fix import error
2024-09-05 10:19:10 -07:00
Ishaan Jaff
7d2298d3c1
fix allow internal user and internal viewer to view usage
2024-09-05 10:16:25 -07:00
Ishaan Jaff
25887c1846
fix import error
2024-09-05 10:09:44 -07:00
Krrish Dholakia
e32d4a15b2
test(test_function_call_parsing.py): handle anthropic internal server error
2024-09-05 10:03:07 -07:00
Ishaan Jaff
ed627bc5d2
fix linting error
2024-09-05 09:56:33 -07:00
Ishaan Jaff
81ee1653af
use correct type hints for audio transcriptions
2024-09-05 09:12:27 -07:00
OrangeWolf
773914bcb7
Update utils.py ( #5530 )
...
fix KeyError (cause by typo?)
2024-09-05 08:21:41 -07:00
Krrish Dholakia
a9be7dd79b
docs(pass_through/bedrock.md): add bedrock agents support
2024-09-04 22:30:14 -07:00
Krrish Dholakia
3709a0565e
bump: version 1.44.17 → 1.44.18
2024-09-04 22:22:40 -07:00
Krish Dholakia
ca37bb9de5
fix(pass_through_endpoints): support bedrock agents via pass through ( #5527 )
2024-09-04 22:22:22 -07:00
Krish Dholakia
1e7e538261
LiteLLM Minor fixes + improvements (08/04/2024) ( #5505 )
...
* Minor IAM AWS OIDC Improvements (#5246 )
* AWS IAM: Temporary tokens are valid across all regions after being issued, so it is wasteful to request one for each region.
* AWS IAM: Include an inline policy, to help reduce misuse of overly permissive IAM roles.
* (test_bedrock_completion.py): Ensure we are testing cross AWS region OIDC flow.
* fix(router.py): log rejected requests
Fixes https://github.com/BerriAI/litellm/issues/5498
* refactor: don't use verbose_logger.exception, if exception is raised
User might already have handling for this. But alerting systems in prod will raise this as an unhandled error.
* fix(datadog.py): support setting datadog source as an env var
Fixes https://github.com/BerriAI/litellm/issues/5508
* docs(logging.md): add dd_source to datadog docs
* fix(proxy_server.py): expose `/customer/list` endpoint for showing all customers
* (bedrock): Fix usage with Cloudflare AI Gateway, and proxies in general. (#5509 )
* feat(anthropic.py): support 'cache_control' param for content when it is a string
* Revert "(bedrock): Fix usage with Cloudflare AI Gateway, and proxies in gener…" (#5519 )
This reverts commit 3fac0349c2
2024-09-04 22:16:55 -07:00
Ishaan Jaff
cdc312d51d
mark test_team_logging as flaky
2024-09-04 20:29:21 -07:00
Ishaan Jaff
20a5bbe6a6
fix allow general guardrails on free tier
2024-09-04 19:59:32 -07:00
Ishaan Jaff
f5de7516cc
bump: version 1.44.16 → 1.44.17
2024-09-04 19:46:51 -07:00
Ishaan Jaff
5c1c0134b6
Merge pull request #5521 from BerriAI/litellm_health_checks
...
[Fix-Proxy] show more descriptive error messages on /health checks
2024-09-04 19:42:10 -07:00
Ishaan Jaff
7d0ea3d028
Merge pull request #5518 from BerriAI/litellm_log_request_response
...
[Feat] log request / response on pass through endpoints
2024-09-04 17:57:47 -07:00
Ishaan Jaff
3600b1a229
Merge pull request #5520 from BerriAI/litellm_spend_logs_trace
...
[Fix - Proxy] show error from /spend/tags and /spend/logs on client side
2024-09-04 17:57:33 -07:00
Ishaan Jaff
f725c3a68f
fix /health error
2024-09-04 17:43:15 -07:00
Ishaan Jaff
34cb748c69
show more descriptive error messages on /health checks
2024-09-04 17:35:16 -07:00
Ishaan Jaff
172eb9b9bc
return error from /global/spend endpoint
2024-09-04 17:26:34 -07:00
Ishaan Jaff
3eb0325063
return error client side from spend endpoints
2024-09-04 17:20:47 -07:00
Ishaan Jaff
21a89f15de
show error from /spend/tags
2024-09-04 17:14:49 -07:00
Ishaan Jaff
c364d311b9
rename type
2024-09-04 16:33:36 -07:00
Ishaan Jaff
b8811d5165
add doc on PassthroughStandardLoggingObject
2024-09-04 16:30:47 -07:00
Ishaan Jaff
8eda374d79
feat log request / response on pass through endpoints
2024-09-04 16:26:32 -07:00
Ishaan Jaff
4b9163c7dc
Merge pull request #5514 from BerriAI/litellm_add_presidio
...
[Fix-Refactor] support presidio on new guardrails config
2024-09-04 16:09:54 -07:00
Krish Dholakia
fa2d9002b5
security - Prevent sql injection in /team/update query ( #5513 )
...
* fix(team_endpoints.py): replace `.get_data()` usage with prisma interface
Prevent sql injection in `/team/update` query
Fixes https://huntr.com/bounties/a4f6d357-5b44-4e00-9cac-f1cc351211d2
* fix(vertex_ai_non_gemini.py): handle message being a pydantic model
2024-09-04 16:03:02 -07:00
Stefan Bokarev
258b96211c
stream response ( #5516 )
2024-09-04 16:02:29 -07:00
Ishaan Jaff
7712aa652a
fix init presidio guardrail
2024-09-04 15:22:37 -07:00
Ishaan Jaff
4ab8e52bfa
allow init guardrails with output parsing logic
2024-09-04 14:40:35 -07:00
Krrish Dholakia
aefca63a8c
docs(logging.md): fix name in docs
2024-09-04 14:36:53 -07:00
Ishaan Jaff
f1111f9a1b
handle logging_only logic for guardrails
2024-09-04 13:57:04 -07:00
Ishaan Jaff
528154764b
docs update presidio
2024-09-04 13:43:14 -07:00
Ishaan Jaff
36505058e0
doc setting language per request
2024-09-04 13:23:17 -07:00
Ishaan Jaff
6c30f18f8c
docs new presidio language controls
2024-09-04 13:04:19 -07:00
Ishaan Jaff
9b5164b38d
fix allow setting language per call to presidio
2024-09-04 12:46:59 -07:00
Ishaan Jaff
4e392ebdb2
Merge pull request #5484 from BerriAI/litellm_fix_redis
...
fix proxy server - always read redis for rate limiting logic
2024-09-04 12:39:15 -07:00
Ishaan Jaff
d954413b14
fix presidio calling logic
2024-09-04 12:14:30 -07:00
Ishaan Jaff
f8bcd72994
Merge pull request #5511 from BerriAI/litellm_fix_cohere_chat_get_llm_provider
...
[Fix] get_llm_provider, return provider as `cohere_chat` for cohere chat models
2024-09-04 11:19:59 -07:00
Ishaan Jaff
9c573cda0a
fix test_proxy_logging_setup
2024-09-04 10:59:15 -07:00
Victor Mustar (aider)
f65ceef46a
remove conversational-task
...
deprecated
2024-09-04 19:21:10 +02:00
