Commit graph

168 commits

Author SHA1 Message Date
Ishaan Jaff
fc31209d16 doc fix auto prompt caching 2025-04-15 22:29:26 -07:00
Ishaan Jaff
9e90676058 docs prompt cache controls 2025-04-15 22:22:36 -07:00
Krrish Dholakia
65e18f6abe docs(index.md): update changelog with realtime api cost tracking details 2025-04-12 19:15:40 -07:00
Ishaan Jaff
c86e678809
[Docs] v1.66.0-stable fixes (#9953)
* add categories for spend tracking improvements

* xai reasoning usage

* docs tag management

* docs tag based routing

* [Beta] Routing based

* docs tag based routing

* docs tag routing

* docs enterprise web search
2025-04-12 16:57:25 -07:00
Ishaan Jaff
eb998ee1c0
[v1.66.0-stable] Release notes (#9952)
* release notes

* docs release notes

* docs fix release notes

* docs clean up

* docs clean up

* release notes

* docs sso tag management
2025-04-12 15:32:52 -07:00
Krish Dholakia
25d4cf1c1d
Litellm managed files docs (#9948)
Some checks failed
Helm unit test / unit-test (push) Successful in 27s
Read Version from pyproject.toml / read-version (push) Successful in 43s
Publish Prisma Migrations / publish-migrations (push) Failing after 2m17s
* docs(files_endpoints.md): add doc on litellm managed files

* refactor: separate litellm managed file docs from `/files` docs

clearer

* docs(litellm_managed_files.md): add architecture diagram explaining managed files
2025-04-12 13:02:33 -07:00
Ishaan Jaff
595c0cbb42 docs msft default team settings 2025-04-10 20:22:46 -07:00
Ishaan Jaff
34b1bf2c75 docs msft_default_settings 2025-04-10 20:21:14 -07:00
Ishaan Jaff
f5c5c79ea4 update docs 2025-04-10 20:18:54 -07:00
Ishaan Jaff
98e34cbf5d
[Docs] Tutorial using MSFT auto team assignment with LiteLLM (#9898)
* add default_team_params as a config.yaml setting

* create_litellm_team_from_sso_group

* test_default_team_params

* test_create_team_without_default_params

* docs default team settings

* docs msft entra id tutorial

* commit litellm docs msft group assignment

* litellm MSFT sso

* member, team assignment on litellm

* docs msft auto assignment

* bug fix default team setting

* docs litellm default team settings

* test_default_team_params
2025-04-10 20:07:55 -07:00
Ishaan Jaff
6f7e9b9728
[Feat SSO] Debug route - allow admins to debug SSO JWT fields (#9835)
* refactor SSO handler

* render sso JWT on ui

* docs debug sso

* fix sso login flow use await

* fix ui sso debug JWT

* test ui sso

* remove redis vl

* fix redisvl==0.5.1

* fix ml dtypes

* fix redisvl

* fix redis vl

* fix debug_sso_callback

* fix linting error

* fix redis semantic caching dep
2025-04-09 15:29:35 -07:00
Krrish Dholakia
0137055bad docs: cleanup 2025-04-06 14:39:28 -07:00
Krish Dholakia
792ee079c2
Litellm 04 05 2025 release notes (#9785)
* docs: update docs

* docs: additional cleanup

* docs(index.md): add initial links

* docs: more doc updates

* docs(index.md): add more links

* docs(files.md): add gemini files API to docs

* docs(index.md): add more docs

* docs: more docs

* docs: update docs
2025-04-06 09:03:51 -07:00
Krish Dholakia
34bdf36eab
Add inference providers support for Hugging Face (#8258) (#9738) (#9773)
* Add inference providers support for Hugging Face (#8258)

* add first version of inference providers for huggingface

* temporarily skipping tests

* Add documentation

* Fix titles

* remove max_retries from params and clean up

* add suggestions

* use llm http handler

* update doc

* add suggestions

* run formatters

* add tests

* revert

* revert

* rename file

* set maxsize for lru cache

* fix embeddings

* fix inference url

* fix tests following breaking change in main

* use ChatCompletionRequest

* fix tests and lint

* [Hugging Face] Remove outdated chat completion tests and fix embedding tests (#9749)

* remove or fix tests

* fix link in doc

* fix(config_settings.md): document hf api key

---------

Co-authored-by: célina <hanouticelina@gmail.com>
2025-04-05 10:50:15 -07:00
Ishaan Jaff
82b8eb79c2 doc update 2025-04-02 23:11:22 -07:00
Ishaan Jaff
b48b8366c2 docs new deadlock fixing architecture 2025-04-02 13:24:53 -07:00
Krrish Dholakia
40a792472b build(enterprise.md): add why enterprise to docs 2025-04-01 11:27:03 -07:00
Ishaan Jaff
31082344a4 docs release notes
All checks were successful
Read Version from pyproject.toml / read-version (push) Successful in 21s
Helm unit test / unit-test (push) Successful in 43s
2025-03-29 23:08:20 -07:00
Ishaan Jaff
df01337bd8 docs litellm mcp 2025-03-29 22:28:03 -07:00
Ishaan Jaff
46e5ebe3c7 docs add mcp graphic to stable release notes 2025-03-29 19:00:26 -07:00
Krrish Dholakia
f1f40eba3f docs(index.md): document new team model flow
All checks were successful
Helm unit test / unit-test (push) Successful in 18s
Read Version from pyproject.toml / read-version (push) Successful in 22s
2025-03-27 12:14:29 -07:00
Krrish Dholakia
76df625718 docs(arize_integration.md): update docs with more details 2025-03-22 19:36:37 -07:00
Ishaan Jaff
ed74b419a3
Merge pull request #9436 from BerriAI/litellm_mcp_interface
[Feat] LiteLLM x MCP Bridge - Use MCP Tools with LiteLLM
2025-03-21 20:42:16 -07:00
Ishaan Jaff
b763174326 litellm mcp bridge docs 2025-03-21 17:00:56 -07:00
Ishaan Jaff
f07d127963 add diagram for litellm mcp integration 2025-03-21 16:54:55 -07:00
Krrish Dholakia
f68e27a0c8 docs(image_handling.md): architecture doc on image handling on the proxy 2025-03-21 14:19:05 -07:00
Ishaan Jaff
17e7718efc docs custom prompt management 2025-03-19 20:25:09 -07:00
Ishaan Jaff
f505716499 docs ui credentials
All checks were successful
Helm unit test / unit-test (push) Successful in 20s
Read Version from pyproject.toml / read-version (push) Successful in 40s
2025-03-15 14:38:14 -07:00
Ishaan Jaff
d93f2884d6 ui show logs page 2025-03-15 11:21:38 -07:00
Ishaan Jaff
b6f3d124d9 docs Stop storing Spend Logs in DB 2025-03-15 11:09:24 -07:00
Ishaan Jaff
8c849304be docs ui improvements 2025-03-15 09:47:05 -07:00
Ishaan Jaff
88419db27b docs - working management ui 2025-03-15 08:44:31 -07:00
Krrish Dholakia
ac3e57a501 docs: add images to release notes 2025-03-08 17:39:24 -08:00
Ishaan Jaff
b5eeafdd72
(Docs) OpenWeb x LiteLLM Docker compose + Instructions on spend tracking + logging (#9059)
* docs improve open web ui litellm doc

* docs openweb show teams + keys

* docs open web ui litellm
2025-03-07 17:01:39 -08:00
Ishaan Jaff
958e71b906
(Docs) connect litellm to open web ui (#9040)
* init doc

* working thinking tutorial

* docs open web ui with litellm

* minor edits

* docs one tab for tutorials
2025-03-06 21:13:00 -08:00
Krrish Dholakia
048dd995dc docs: update litellm user management heirarchy doc
All checks were successful
Read Version from pyproject.toml / read-version (push) Successful in 36s
2025-02-16 00:31:13 -08:00
Krish Dholakia
8d3a942fbd
Litellm staging (#8270)
All checks were successful
Read Version from pyproject.toml / read-version (push) Successful in 15s
* fix(opik.py): cleanup

* docs(opik_integration.md): cleanup opik integration docs

* fix(redact_messages.py): fix redact messages check header logic

ensures stringified bool value in header is still asserted to true

 allows dynamic message redaction

* feat(redact_messages.py): support `x-litellm-enable-message-redaction` request header

allows dynamic message redaction
2025-02-04 22:35:48 -08:00
Krish Dholakia
2eaa0079f2
feat(handle_jwt.py): initial commit adding custom RBAC support on jwt… (#8037)
* feat(handle_jwt.py): initial commit adding custom RBAC support on jwt auth

allows admin to define user role field and allowed roles which map to 'internal_user' on litellm

* fix(auth_checks.py): ensure user allowed to access model, when calling via personal keys

Fixes https://github.com/BerriAI/litellm/issues/8029

* feat(handle_jwt.py): support role based access with model permission control on proxy

Allows admin to just grant users roles on IDP (e.g. Azure AD/Keycloak) and user can immediately start calling models

* docs(rbac): add docs on rbac for model access control

make it clear how admin can use roles to control model access on proxy

* fix: fix linting errors

* test(test_user_api_key_auth.py): add unit testing to ensure rbac role is correctly enforced

* test(test_user_api_key_auth.py): add more testing

* test(test_users.py): add unit testing to ensure user model access is always checked for new keys

Resolves https://github.com/BerriAI/litellm/issues/8029

* test: fix unit test

* fix(dot_notation_indexing.py): fix typing to work with python 3.8
2025-01-28 16:27:06 -08:00
Yuki Watanabe
3f053fc99c
Update MLflow calllback and documentation (#7809)
* Update MLlfow tracer

Signed-off-by: B-Step62 <yuki.watanabe@databricks.com>

* doc update

Signed-off-by: B-Step62 <yuki.watanabe@databricks.com>

* doc update

Signed-off-by: B-Step62 <yuki.watanabe@databricks.com>

* image rename

Signed-off-by: B-Step62 <yuki.watanabe@databricks.com>

---------

Signed-off-by: B-Step62 <yuki.watanabe@databricks.com>
2025-01-21 20:56:48 -08:00
Ishaan Jaff
bc311b7a47 ui logs - view messages / responses 2025-01-17 20:20:49 -08:00
Hugues Chocart
6fff77d131
[integrations/lunary] Improve Lunary documentaiton (#7770)
* update lunary doc

* better title

* tweaks

* Update langchain.md

* Update lunary_integration.md
2025-01-15 15:00:25 -08:00
Ishaan Jaff
f95439af26 docs v1.57.3 2025-01-08 12:08:19 -08:00
Ishaan Jaff
04eb718f7a update docs 2025-01-07 22:35:07 -08:00
Ishaan Jaff
46d9d29bff
(Feat) Hashicorp Secret Manager - Allow storing virtual keys in secret manager (#7549)
All checks were successful
Read Version from pyproject.toml / read-version (push) Successful in 13s
* use a base abstract class

* async_write_secret for hcorp

* fix hcorp

* async_write_secret for hashicopr secret manager

* store virtual keys in hcorp

* add delete secret

* test_hashicorp_secret_manager_write_secret

* test_hashicorp_secret_manager_delete_secret

* docs Supported Secret Managers

* docs storing keys in hcorp

* docs hcorp

* docs secret managers

* test_key_generate_with_secret_manager_call

* fix unused imports
2025-01-04 11:35:59 -08:00
Ishaan Jaff
cf60444916
(Feat) Add support for reading secrets from Hashicorp vault (#7497)
* HashicorpSecretManager

* test_hashicorp_secret_managerv

* use 1 helper initialize_secret_manager

* add HASHICORP_VAULT

* working config

* hcorp read_secret

* HashicorpSecretManager

* add secret_manager_testing

* use 1 folder for secret manager testing

* test_hashicorp_secret_manager_get_secret

* HashicorpSecretManager

* docs HCP secrets

* update folder name

* docs hcorp secret manager

* remove unused imports

* add conftest.py

* fix tests

* docs document env vars
2025-01-01 18:35:05 -08:00
Ishaan Jaff
e1fcd3ee43
(docs) Add docs on load testing benchmarks (#7499)
* docs benchmarks

* docs benchmarks
2025-01-01 18:33:20 -08:00
Ishaan Jaff
03b1db5a7d
(Feat) - Add PagerDuty Alerting Integration (#7478)
* define basic types

* fix verbose_logger.exception statement

* fix basic alerting

* test pager duty alerting

* test_pagerduty_alerting_high_failure_rate

* PagerDutyAlerting

* async_log_failure_event

* use pre_call_hook

* add _request_is_completed helper util

* update AlertingConfig

* rename PagerDutyInternalEvent

* _send_alert_if_thresholds_crossed

* use pagerduty as _custom_logger_compatible_callbacks_literal

* fix slack alerting imports

* fix imports in slack alerting

* PagerDutyAlerting

* fix _load_alerting_settings

* test_pagerduty_hanging_request_alerting

* working pager duty alerting

* fix linting

* doc pager duty alerting

* update hanging_response_handler

* fix import location

* update failure_threshold

* update async_pre_call_hook

* docs pagerduty

* test - callback_class_str_to_classType

* fix linting errors

* fix linting + testing error

* PagerDutyAlerting

* test_pagerduty_hanging_request_alerting

* fix unused imports

* docs pager duty

* @pytest.mark.flaky(retries=6, delay=2)

* test_model_info_bedrock_converse_enforcement
2025-01-01 07:12:51 -08:00
Ishaan Jaff
8c569899c0 update release note 2024-12-28 20:15:30 -08:00
Ishaan Jaff
8610c7bf93 docs release notes
All checks were successful
Read Version from pyproject.toml / read-version (push) Successful in 41s
2024-12-27 21:41:21 -08:00
Ishaan Jaff
62753eea69
(Feat) Log Guardrails run, guardrail response on logging integrations (#7445)
* add guardrail_information to SLP

* use standard_logging_guardrail_information

* track StandardLoggingGuardrailInformation

* use log_guardrail_information

* use log_guardrail_information

* docs guardrails

* docs guardrails

* update quick start

* fix presidio logging for sync functions

* update Guardrail type

* enforce add_standard_logging_guardrail_information_to_request_data

* update gd docs
2024-12-27 15:01:56 -08:00