scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-10 03:28:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 85
19565 commits 3393 branches 1449 tags 5.1 GiB
Commit graph

19565 commits

This branch
This branch
All branches
Author SHA1 Message Date
Ishaan Jaff
383e4535b6 test_bedrock_document_understanding 2025-02-22 18:20:16 -08:00
Ishaan Jaff
999fa0ddbe fix model cost map on branch 2025-02-22 18:12:51 -08:00
Ishaan Jaff
b5a171c0a9 test_models_by_provider 2025-02-22 17:42:31 -08:00
Ishaan Jaff
fdd34b9c69 test_basic_rerank_together_ai 2025-02-22 17:18:44 -08:00
Ishaan Jaff
4c9517fd78 bump: version 1.61.12 → 1.61.13 2025-02-20 18:57:19 -08:00
Ishaan Jaff
da510651e0 delete deprecated code test 2025-02-20 18:53:59 -08:00
Ishaan Jaff
d23d4305fb ui new build 2025-02-20 18:40:21 -08:00
Ishaan Jaff
55b938dd6e
(Infra/DB) - Allow running older litellm version when out of sync with current state of DB (#8695) 
* fix check migration

* clean up should_update_prisma_schema

* update test

* db_migration_disable_update_check

* Check container logs for expected message

* db_migration_disable_update_check

* test_check_migration_out_of_sync

* test_should_update_prisma_schema

* db_migration_disable_update_check

* pip install aiohttp
 2025-02-20 18:30:23 -08:00
Ishaan Jaff
300d7825f5
(Observability) - Add more detailed dd tracing on Proxy Auth, Bedrock Auth (#8693) 
* add dd tracer

* fix dd tracing

* add @tracer.wrap() on def user_api_key_auth

* add async_function_with_retries

* remove dead code

* add tracer.wrap on base aws llm

* add tracer.wrap on base aws llm

* fix print verbose

* fix dd tracing

* trace base aws llm

* fix test base aws llm

* fix converse transform

* test base aws llm

* BASE_AWS_LLM_PATH

* BASE_AWS_LLM_PATH

* test dd tracing
 2025-02-20 18:00:41 -08:00
Ishaan Jaff
ccfbb77b73
(Redis fix) - use mget_non_atomic (#8682) 
* use mget_nonatomic

* redis cluster override MGET op

* fix redis cluster + MGET

* test redis cluster
 2025-02-20 17:51:31 -08:00
Ishaan Jaff
bb6f43d12e
(Bug fix) - Cache Health not working when configured with prometheus service logger (#8687) 
* fix serialize on safe json dumps

* test_non_standard_dict_keys_complex

* ui fix HealthCheckCacheParams

* fix HealthCheckCacheParams

* fix code qa

* test_cache_ping_failure

* test_cache_ping_health_check_includes_only_cache_attributes

* test_cache_ping_health_check_includes_only_cache_attributes
 2025-02-20 13:41:56 -08:00
Krrish Dholakia
8f7437b4d9 bump: version 1.61.11 → 1.61.12 2025-02-19 22:22:32 -08:00
Krish Dholakia
f9df01fbc6
fix(utils.py): handle token counter error when invalid message passed in (#8670) 
* fix(utils.py): handle token counter error

* fix(utils.py): testing fixes

* fix(utils.py): fix incr for num tokens from list

* fix(utils.py): fix text str token counting
 2025-02-19 22:21:34 -08:00
Krish Dholakia
982ee4b96b
LiteLLM Contributor PRs (02/18/2025). (#8643) 
* fix: prisma migration script logging #6991 (#8617)

* fix: prisma migration script logging #6991

* chore: refactor usng proxy logger

* remove noqa and move import below abs path

* Fix(litellm-vetexai-gemini): adding the supported files as per gemini documentation (#8559)

* bugfix(litellm-vetexai-gemini): adding the supported files as per gemini documentations

* fix(files.py): correct file type constant from 'text' to 'TXT'

* test: handle internal server error

---------

Co-authored-by: Justin Law <81255462+justinthelaw@users.noreply.github.com>
Co-authored-by: alymedhat10 <48028013+alymedhat10@users.noreply.github.com>
 2025-02-19 21:52:46 -08:00
Krish Dholakia
cc77138b37
Add all /key/generate api params to UI + add metadata fields on team AND org add/update (#8667) 
* feat(create_key_button.tsx): initial commit using openapi.json to ensure all values via api are supported on ui for `/key/generate`

Closes https://github.com/BerriAI/litellm/issues/7763

* style(create_key_button.tsx): put openapi settings inside 'advanced setting' accordion

* fix(check_openapi_schema.tsx): style improvements for advanced settings

* style(create_key_button.tsx): add tooltip explaining what the settings mean

* fix(team_info.tsx): render metadata field on team update

allow updating a team's metadata

* fix(networking.tsx): add 'metadata' field to create team form

* refactor: cleanup dead codeblock

* fix(organization_endpoints.py): fix metadata param support on `/organization/new`

* feat(organization_endpoints.py): support updating metadata for organization on api + ui

* test: mark flaky test
 2025-02-19 21:13:06 -08:00
Krish Dholakia
40d1576292
extract <think>..</think> block for amazon deepseek r1 and put in reasoning_content (#8664) 
* feat(amazon_deepseek_transformation.py): extract thinking content and return in same way as deepseek api

* feat(amazon_deepseek_transformation.py): extract thinking block from deepseek r1 streaming block

* fix: suppress linting warning

* fix: fix linting error

* fix: fix linting error
 2025-02-19 21:10:59 -08:00
Krrish Dholakia
9470f57e86 build: extract <think>..</think> block for amazon deepseek r1 and put in reasoning_content 2025-02-19 21:10:38 -08:00
Ishaan Jaff
1dfdad1707 bump: version 1.61.10 → 1.61.11 2025-02-19 21:07:01 -08:00
Ishaan Jaff
1460a79ef9 ui new build 2025-02-19 20:09:51 -08:00
Ishaan Jaff
0d2b0ee1b7
(Bug fix) prometheus - safely set latency metrics (#8669) 
* use safe_duration_seconds

* _safe_duration_seconds

* test_set_latency_metrics_missing_timestamps
 2025-02-19 20:08:46 -08:00
Ishaan Jaff
045cf3f9e2
(Bug Fix Redis) - Fix running redis.mget operations with None Keys (#8666) 
* async_batch_get_cache

* test_batch_get_cache_with_none_keys

* async_batch_get_cache

* fix linting error
 2025-02-19 19:56:57 -08:00
Ishaan Jaff
fff15543d9
(UI + Proxy) Cache Health Check Page - Cleanup/Improvements (#8665) 
* fixes for redis cache ping serialization

* fix cache ping check

* fix cache health check ui

* working error details on ui

* ui expand / collapse error

* move cache health check to diff file

* fix displaying error from cache health check

* ui allow copying errors

* ui cache health fixes

* show redis details

* clean up cache health page

* ui polish fixes

* fix error handling on cache health page

* fix redis_cache_params on cache ping response

* error handling

* cache health ping response

* fx error response from cache ping

* parsedLitellmParams

* fix cache health check

* fix cache health page

* cache safely handle json dumps issues

* test caching routes

* test_primitive_types

* fix caching routes

* litellm_mapped_tests

* fix pytest-mock

* fix _serialize

* fix linting on safe dumps

* test_default_max_depth

* pip install "pytest-mock==3.12.0"

* litellm_mapped_tests_coverage

* add readme on new litellm test dir
 2025-02-19 19:08:50 -08:00
Krrish Dholakia
39db3147e8 fix(spend_tracking_utils.py): move info to debug 2025-02-19 15:36:32 -08:00
Krrish Dholakia
f2c32bb1c7 bump: version 1.61.9 → 1.61.10 2025-02-18 22:56:17 -08:00
Krish Dholakia
0ff56504d7
build: build ui (#8654) 2025-02-18 22:56:01 -08:00
Krish Dholakia
0319559295
fix(team_endpoints.py): allow team member to view team info (#8644) 
* fix(team_endpoints.py): allow team member to view team info

* test: handle model overloaded in tool calling test

* test: handle internal server error
 2025-02-18 22:28:57 -08:00
Ishaan Jaff
0d398c2295 test_message_with_name 2025-02-18 21:53:47 -08:00
Ishaan Jaff
4828fb1544 fix code quality 2025-02-18 21:29:23 -08:00
Ishaan Jaff
ed87739561 bump: version 1.61.8 → 1.61.9 2025-02-18 21:27:24 -08:00
Ishaan Jaff
6cae24ed08 ui new build 2025-02-18 21:26:06 -08:00
Ishaan Jaff
7e722225a1 ui QA fix, adding wildcard models 2025-02-18 21:25:23 -08:00
Ishaan Jaff
c18dd61044 ui linting fix 2025-02-18 21:14:36 -08:00
Ishaan Jaff
889feb2ea8 patch on LiteLLM_AuditLogs 2025-02-18 21:13:14 -08:00
Ishaan Jaff
b88762b63c
(Polish/Fixes) - Fixes for Adding Team Specific Models (#8645) 
* refactor get model info for team models

* allow adding a model to a team when creating team specific model

* ui update selected Team on Team Dropdown

* test_team_model_association

* testing for team specific models

* test_get_team_specific_model

* test: skip on internal server error

* remove model alias card on teams page

* linting fix _get_team_specific_model

* fix DeploymentTypedDict

* fix linting error

* fix code quality

* fix model info checks

---------

Co-authored-by: Krrish Dholakia <krrishdholakia@gmail.com>
 2025-02-18 21:11:57 -08:00
Krish Dholakia
2b7755f8d8
Litellm dev 02 18 2025 p3 (#8640) 
* fix(team_endpoints.py): cleanup user <-> team association on team delete

Fixes issue where user table still listed team membership post delete

* test(test_team.py): update e2e test - ensure user/team membership is deleted on team delete

* fix(base_invoke_transformation.py): fix deepseek r1 transformation

remove deepseek name from model url

* test(test_completion.py): assert model route not in url

* feat(base_invoke_transformation.py): infer region name from model arn

prevent errors due to different region name in env var vs. model arn, respect if explicitly set in call though

* test: fix test

* test: skip on internal server error
 2025-02-18 19:14:20 -08:00
Krish Dholakia
ef87b0eaae
Litellm dev 02 18 2025 p2 (#8639) 
* fix(parallel_request_limiter.py): improve single instance rate limiting by updating in-memory cache instantly

Fixes issue where parallel request limiter had a leak

* fix(parallel_request_limiter.py): fix parallel request limiter to not decrement val on max limit being reached

* test(test_parallel_request_limiter.py): fix test

* test: fix test

* fix(parallel_request_limiter.py): move to using common enum

* test: fix test
 2025-02-18 19:12:16 -08:00
Krrish Dholakia
89c8dfc644 test: handle unstable tests 2025-02-18 18:44:12 -08:00
Krish Dholakia
4e38940694
Add OSS license check to ci/cd (#8626) 
* feat: add oss license check for related packages

ensure all packages used are permissable

* ci(config.yml): add check_licenses.py

script to ci/cd

* ci(check_licenses.py): fix license check
 2025-02-18 18:11:08 -08:00
elroy-bot
7f47ae88b7
Add Elroy to projects built with litellm (#8642) 
Co-authored-by: Tom Bedor <tombedor@gmail.com>
 2025-02-18 16:43:30 -08:00
Krish Dholakia
2b71973b17
Litellm dev 02 18 2025 p1 (#8630) 
* fix(filter.tsx): align filter icon to button correctly

* style: style improvements for filter icon

* style(filter.tsx): cleanup filter box

* style(filter.tsx): style improvement for team id box on filter

* Fix timeout bug for SageMaker Messages API completion (#8635)

* fix(model_cost_map): fix json parse error on model cost map + add unit test (#8629)

Fixes https://github.com/BerriAI/litellm/pull/8619#issuecomment-2666693045

* Fix timeout bug for SageMaker Messages API completion

---------

Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>

---------

Co-authored-by: Bobby Lindsey <bobbywlindsey@users.noreply.github.com>
 2025-02-18 15:20:17 -08:00
Ishaan Jaff
d1ba04d9d9
[Feature]: Redis Caching - Allow setting a namespace for redis cache (#8624) 
* use _add_namespace_to_cache_key

* fix cache_control_args

* test_redis_caching_multiple_namespaces

* test_add_namespace_to_cache_key

* test_redis_caching_multiple_namespaces

* docs redis name space

* test_add_namespace_to_cache_key
 2025-02-18 14:47:34 -08:00
Krish Dholakia
ea985dda0b
fix(model_cost_map): fix json parse error on model cost map + add unit test (#8629) 
Fixes https://github.com/BerriAI/litellm/pull/8619#issuecomment-2666693045
 2025-02-18 11:18:16 -08:00
Krish Dholakia
49610485a2
feat: add oss license check for related packages (#8623) 
ensure all packages used are permissable
 2025-02-18 10:40:00 -08:00
HeMuling
369b636b5a
add openrouter/google/gemini-2.0-flash-001 (#8619) 2025-02-18 10:14:49 -08:00
Ishaan Jaff
8d7937fd7a
(Fix) Redis async context usage for Redis Cluster + 94% lower median latency when using Redis Cluster (#8622) 
* fix redis async usage

* re- use redis client across requests
 2025-02-18 09:22:27 -08:00
Krish Dholakia
2340f1b31f
Pass router tags in request headers - x-litellm-tags (#8609) 
* feat(litellm_pre_call_utils.py): support `x-litellm-tags` request header

allow tag based routing + spend tracking via request headers

* docs(request_headers.md): document new `x-litellm-tags` for tag based routing and spend tracking

* docs(tag_routing.md): add to docs

* fix(utils.py): only pass str values for openai metadata param

* fix(utils.py): drop non-str values for metadata param to openai

preview-feature, otel span was being sent in
 2025-02-18 08:26:22 -08:00
Krrish Dholakia
7bfd816d3b build: merge commit 1b15568af7 
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Feb 17 21:37:36 2025 -0800

    fix(proxy/_types.py): fix linting error

commit dc4d5cffa6
Author: Krrish Dholakia <krrishdholakia@gmail.com>
 2025-02-17 21:56:00 -08:00
Ishaan Jaff
e8f387200a ci/cd run again 2025-02-17 21:37:52 -08:00
Ishaan Jaff
52450e9f61 test_openai_fine_tuning 2025-02-17 21:29:59 -08:00
Ishaan Jaff
296013f722 test_openai_fine_tuning 2025-02-17 21:20:09 -08:00