phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity
18335 commits 1603 branches 645 tags 320 MiB
Commit graph

18335 commits

This branch
This branch
All branches
Author SHA1 Message Date
Ishaan Jaff
d7afeee71c fix test 2024-09-10 13:15:50 -07:00
Ishaan Jaff
dc63a16a6f
Merge pull request #5616 from BerriAI/litellm_fix_regen_keys 
[Fix-Proxy] Regenerate keys when no duration is passed
 2024-09-10 13:09:57 -07:00
Ishaan Jaff
08f8f9634f use get async httpx client 2024-09-10 13:08:49 -07:00
Ishaan Jaff
0f154abf9e use get_async_httpx_client for logging httpx 2024-09-10 13:03:55 -07:00
Ishaan Jaff
421b857714 pass llm provider when creating async httpx clients 2024-09-10 11:51:42 -07:00
Ishaan Jaff
87bac7c026 fix rps / rpm values on load testing 2024-09-10 11:22:19 -07:00
Jay Alammar
795b29dfc4 Updating Cohere models, prices, and documentation 2024-09-10 13:47:05 -04:00
Ishaan Jaff
a0e4510f53 add enum for all llm providers LlmProviders 2024-09-10 10:44:57 -07:00
Ishaan Jaff
d4b9a1307d rename get_async_httpx_client 2024-09-10 10:38:01 -07:00
Ishaan Jaff
1e8cf9f2a6 fix vertex ai use _get_async_client 2024-09-10 10:33:19 -07:00
Peter Laß
b1ecfe065c
fix #5614 (#5615) 
Co-authored-by: Peter Laß <peter.lass@maibornwolff.de>
 2024-09-10 09:26:44 -07:00
Ishaan Jaff
39a8bb2bc4 add test test_regenerate_key_ui 2024-09-10 09:12:03 -07:00
Ishaan Jaff
428762542c fix regen keys when no duration is passed 2024-09-10 08:04:18 -07:00
Ishaan Jaff
43cd657ac5
Merge pull request #5603 from BerriAI/litellm_allow_turning_off_message_logging_for_callbacks 
[Feat-Proxy] allow turning off message logging for OTEL (callback specific)
 2024-09-09 22:00:09 -07:00
Ishaan Jaff
479b12be09
Merge branch 'main' into litellm_allow_turning_off_message_logging_for_callbacks 2024-09-09 21:59:36 -07:00
Krrish Dholakia
2e5583919a bump: version 1.44.22 → 1.44.23 2024-09-09 21:58:27 -07:00
Krish Dholakia
2d2282101b
LiteLLM Minor Fixes and Improvements (09/09/2024) (#5602) 
* fix(main.py): pass default azure api version as alternative in completion call

Fixes api error caused due to api version

Closes https://github.com/BerriAI/litellm/issues/5584

* Fixed gemini-1.5-flash pricing (#5590)

* add /key/list endpoint

* bump: version 1.44.21 → 1.44.22

* docs architecture

* Fixed gemini-1.5-flash pricing

---------

Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>

* fix(bedrock/chat.py): fix converse api stop sequence param mapping

Fixes https://github.com/BerriAI/litellm/issues/5592

* fix(databricks/cost_calculator.py): handle databricks model name changes

Fixes https://github.com/BerriAI/litellm/issues/5597

* fix(azure.py): support azure api version 2024-08-01-preview

Closes https://github.com/BerriAI/litellm/issues/5377

* fix(proxy/_types.py): allow dev keys to call cohere /rerank endpoint

Fixes issue where only admin could call rerank endpoint

* fix(azure.py): check if model is gpt-4o

* fix(proxy/_types.py): support /v1/rerank on non-admin routes as well

* fix(cost_calculator.py): fix split on `/` logic in cost calculator

---------

Co-authored-by: F1bos <44951186+F1bos@users.noreply.github.com>
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
 2024-09-09 21:56:12 -07:00
Krish Dholakia
4ac66bd843
LiteLLM Minor Fixes and Improvements (09/07/2024) (#5580) 
* fix(litellm_logging.py): set completion_start_time_float to end_time_float if none

Fixes https://github.com/BerriAI/litellm/issues/5500

* feat(_init_.py): add new 'openai_text_completion_compatible_providers' list

Fixes https://github.com/BerriAI/litellm/issues/5558

Handles correctly routing fireworks ai calls when done via text completions

* fix: fix linting errors

* fix: fix linting errors

* fix(openai.py): fix exception raised

* fix(openai.py): fix error handling

* fix(_redis.py): allow all supported arguments for redis cluster (#5554)

* Revert "fix(_redis.py): allow all supported arguments for redis cluster (#5554)" (#5583)

This reverts commit f2191ef4cb.

* fix(router.py): return model alias w/ underlying deployment on router.get_model_list()

Fixes https://github.com/BerriAI/litellm/issues/5524#issuecomment-2336410666

* test: handle flaky tests

---------

Co-authored-by: Jonas Dittrich <58814480+Kakadus@users.noreply.github.com>
 2024-09-09 18:54:17 -07:00
Ishaan Jaff
569f3ddda9 fix test_awesome_otel_with_message_logging_off 2024-09-09 17:59:07 -07:00
Ishaan Jaff
16b6b56c8b fix otel logging test 2024-09-09 17:51:35 -07:00
Ishaan Jaff
c86b333054
Merge pull request #5601 from BerriAI/litellm_tag_routing_fixes 
[Feat] Tag Routing - Allow setting default deployments
 2024-09-09 17:45:24 -07:00
Ishaan Jaff
a6d3bd0ab7
Merge branch 'main' into litellm_tag_routing_fixes 2024-09-09 17:45:18 -07:00
Ishaan Jaff
407bdf10ce run test in verbose mode 2024-09-09 17:43:11 -07:00
Ishaan Jaff
00f1d7b1ff
Merge pull request #5576 from BerriAI/litellm_set_max_batch_size 
[Fix - Otel logger] Set a max queue size of 100 logs for OTEL
 2024-09-09 17:39:16 -07:00
Ishaan Jaff
c57683421b
Merge pull request #5606 from BerriAI/litellm_log_failureS_key_based_logging 
[Feat-Proxy] Allow using key based logging for success and failure
 2024-09-09 17:38:36 -07:00
Ishaan Jaff
e25786ed8e fix test otel message logging off 2024-09-09 17:01:20 -07:00
Ishaan Jaff
949af7be2e fix team based logging doc 2024-09-09 16:49:26 -07:00
Ishaan Jaff
57ebe4649e add test for using success and failure 2024-09-09 16:44:37 -07:00
Elad Segal
da30da9a97
Properly use allowed_fails_policy when it has fields with a value of 0 (#5604) 2024-09-09 16:35:12 -07:00
Ishaan Jaff
bbdcc75c60 fix log failures for key based logging 2024-09-09 16:33:06 -07:00
Ishaan Jaff
b60361fca1 fix otel test 2024-09-09 16:20:47 -07:00
Ishaan Jaff
f742d6162f fix otel defaults 2024-09-09 16:18:55 -07:00
Ishaan Jaff
4592d80f43 add doc on redacting otel message / response 2024-09-09 16:10:13 -07:00
Ishaan Jaff
7c9591881c use callback_settings when intializing otel 2024-09-09 16:05:48 -07:00
Ishaan Jaff
b36f964217 fix init custom logger when init OTEL runs 2024-09-09 16:03:39 -07:00
Ishaan Jaff
12d8c0d0a4 use redact_message_input_output_from_custom_logger 2024-09-09 16:02:24 -07:00
Ishaan Jaff
b86075ef9a refactor redact_message_input_output_from_custom_logger 2024-09-09 16:00:47 -07:00
Ishaan Jaff
715387c3c0 add message_logging on Custom Logger 2024-09-09 15:59:42 -07:00
Ishaan Jaff
15c761a56b
Merge pull request #5599 from BerriAI/litellm_allow_mounting_prom_callbacks 
[Feat] support using "callbacks" for prometheus
 2024-09-09 15:00:43 -07:00
Ishaan Jaff
05210fee6a update test_default_tagged_deployments 2024-09-09 14:48:29 -07:00
Ishaan Jaff
2fceeedd94 add "default" tag 2024-09-09 14:41:22 -07:00
Ishaan Jaff
fe7ab3f3d7 test test_default_tagged_deployments 2024-09-09 14:27:52 -07:00
Ishaan Jaff
c4052ee7d7 support default deployments 2024-09-09 14:23:17 -07:00
Krish Dholakia
b374990c79
build(deployment.yaml): Fix port + allow setting database url in helm chart (#5587) 2024-09-09 14:17:44 -07:00
Ishaan Jaff
f1d0045ae6 fix taf based routing debugging 2024-09-09 14:11:54 -07:00
Ishaan Jaff
a1f0df3cea fix debug statements 2024-09-09 14:00:17 -07:00
Ishaan Jaff
8a3ac60187 fix test_async_prometheus_success_logging_with_callbacks 2024-09-09 11:54:11 -07:00
Ishaan Jaff
7ff7028885 fix create script for pre-creating views 2024-09-09 11:03:27 -07:00
Ishaan Jaff
e253c100f4 support using "callbacks" for prometheus 2024-09-09 08:26:03 -07:00
Ishaan Jaff
3bf6589fab docs architecture 2024-09-07 19:09:33 -07:00