Commit graph

190 commits

Author SHA1 Message Date
Ishaan Jaff
7370a994f5 use correct type hints for audio transcriptions 2024-09-05 09:12:27 -07:00
Krish Dholakia
6fdee99632 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.

* refactor: ci/cd run again

---------

Co-authored-by: David Manouchehri <david.manouchehri@ai.moda>
2024-09-04 22:16:55 -07:00
Ishaan Jaff
67510d2c59 dual cache use always read redis as True by default 2024-09-04 08:01:55 -07:00
Ishaan Jaff
b6009233ac fix always read redis 2024-09-02 21:08:32 -07:00
Ishaan Jaff
6b642ef0f0 fix allow qdrant api key to be optional 2024-08-30 11:13:23 -07:00
Krrish Dholakia
b277086cf7 feat(vertex_ai_context_caching.py): check gemini cache, if key already exists 2024-08-26 22:19:01 -07:00
Ishaan Jaff
cad77c5969 fix should_use_cache 2024-08-24 09:37:41 -07:00
Ishaan Jaff
e37fe1f9e0 feat - allow setting cache mode 2024-08-24 09:03:59 -07:00
Krrish Dholakia
33c9c16388 feat(caching.py): redis cluster support
Closes https://github.com/BerriAI/litellm/issues/4358
2024-08-21 15:01:52 -07:00
Ishaan Jaff
b196f41d64 fix qdrant litellm on proxy 2024-08-21 12:52:29 -07:00
Ishaan Jaff
8c83fb3f34 fixes for using qdrant with litellm proxy 2024-08-21 12:36:41 -07:00
Ishaan Jaff
0f3274b074 fix drant url 2024-08-21 12:09:09 -07:00
Ishaan Jaff
a34aeafdb5 Merge pull request #5018 from haadirakhangi/main
Qdrant Semantic Caching
2024-08-21 08:50:43 -07:00
Haadi Rakhangi
9df92923d8 implemented RestAPI and added support for cloud and local Qdrant clusters 2024-08-19 20:46:30 +05:30
Krrish Dholakia
2874b94fb1 refactor: replace .error() with .exception() logging for better debugging on sentry 2024-08-16 09:22:47 -07:00
prd-tuong-nguyen
70f2e84bc4 feat: hash prompt when caching 2024-08-08 16:19:14 +07:00
Ishaan Jaff
5b7d1b0ae4 caching use file_checksum 2024-08-06 13:03:14 -07:00
Krrish Dholakia
d526a12080 fix(init.py): rename feature_flag 2024-08-05 11:23:20 -07:00
Krrish Dholakia
8500f6d087 feat(caching.py): enable caching on provider-specific optional params
Closes https://github.com/BerriAI/litellm/issues/5049
2024-08-05 11:18:59 -07:00
Ishaan Jaff
d122508385 use file name when getting cache key 2024-08-02 14:52:08 -07:00
Haadi Rakhangi
a047df3825 qdrant semantic caching added 2024-08-02 21:07:19 +05:30
Krrish Dholakia
a75b70fbd6 fix(caching.py): support /completion caching by default
updates supported call types in redis cache to cover text_completion caching
2024-07-29 08:19:30 -07:00
Ishaan Jaff
aade38760d use common helpers for writing to otel 2024-07-27 11:40:39 -07:00
Ishaan Jaff
40f9e67be4 move _get_parent_otel_span_from_kwargs to otel.py 2024-07-27 11:12:13 -07:00
Ishaan Jaff
7c489856e3 add doc string to explain what delete cache does 2024-07-13 12:25:31 -07:00
Ishaan Jaff
9d657c42d8 de-ref unused cache items 2024-07-12 16:38:36 -07:00
Krrish Dholakia
a79cb33960 fix(caching.py): fix async redis health check 2024-07-06 09:14:29 -07:00
Ishaan Jaff
a1968eaf3f remove debug print statement 2024-06-27 20:58:29 -07:00
Ishaan Jaff
5977b5be20 ci/cd add debugging for cache eviction 2024-06-25 08:14:09 -07:00
Ishaan Jaff
f800425744 fix default ttl for InMemoryCache 2024-06-24 21:21:38 -07:00
Ishaan Jaff
3ebf1ec7eb feat use custom eviction policy 2024-06-24 20:28:03 -07:00
Ishaan Jaff
4e8f2a57e0 fix install on python 3.8 2024-06-24 17:27:14 -07:00
Ishaan Jaff
5b19aac705 cleanup InMemoryCache 2024-06-24 17:24:59 -07:00
Ishaan Jaff
4f03556af6 use lru cache 2024-06-24 17:15:53 -07:00
Ishaan Jaff
81ef2c38dc fix InMemoryCache 2024-06-24 17:08:30 -07:00
Ishaan Jaff
21fd91fe94 fix use caching lib 2024-06-24 17:03:23 -07:00
Ishaan Jaff
0c4c6bfa5e fix in mem cache tests 2024-06-22 19:52:18 -07:00
Ishaan Jaff
8e3a073323 Merge branch 'main' into litellm_fix_in_mem_usage 2024-06-22 19:23:37 -07:00
Ishaan Jaff
5b2d4da43f fix caching clear in memory cache mem util 2024-06-22 19:21:37 -07:00
Ishaan Jaff
c4ae06576b fix - clean up in memory cache 2024-06-22 18:46:30 -07:00
Krrish Dholakia
0430807178 feat(dynamic_rate_limiter.py): update cache with active project 2024-06-21 20:25:40 -07:00
David Manouchehri
47e3880638 fix(caching.py): Stop throwing constant spam errors on every single S3 cache miss. Fixes #4146. 2024-06-13 20:58:18 +00:00
Ishaan Jaff
786e6b4ae3 feat - final working redis cache otel 2024-06-07 16:36:04 -07:00
Ishaan Jaff
72a6d49b21 feat - working exception logs for Redis errors 2024-06-07 16:30:29 -07:00
Ishaan Jaff
ef99e3e1d0 fix - basic success logging for redis cache 2024-06-07 16:20:23 -07:00
Krrish Dholakia
e391e30285 refactor: replace 'traceback.print_exc()' with logging library
allows error logs to be in json format for otel logging
2024-06-06 13:47:43 -07:00
Krrish Dholakia
2db3819142 fix(proxy_server.py): allow user_api_key_cache_ttl to be a controllable param 2024-05-25 12:07:28 -07:00
Ishaan Jaff
a3fb6e8c34 Merge pull request #3266 from antonioloison/litellm_add_disk_cache
[Feature] Add cache to disk
2024-05-14 09:24:01 -07:00
Rahul Kataria
927b6fa967 [Optimize] Optimize code in caching file 2024-05-12 17:04:18 +05:30
Rahul Kataria
6c16f2924b [Reset Code] 2024-05-12 16:37:50 +05:30