tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-06 22:22:23 +00:00
Code Issues Packages Projects Releases Wiki Activity
23,118 Commits 2,072 Branches 1,425 Tags
4b3b4f8dff00a7ebc7b08b65da78e2bf2ff342bb
Commit Graph
23118 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
X4tarGitHubwick.hu
 		2740c8d77d Fix vertex ai claude thinking params (#11796) 
* fix:  vertex_ai/claude-sonnet-4 thinking params can not be accepted

* CHORE: add unit test

---------

Co-authored-by: wick.hu <wick.hu@momenta.ai>
 2025-06-17 22:35:31 -07:00
Ishaan Jaff 84c4c8027f ui new build 2025-06-17 21:02:33 -07:00
Ishaan Jaff 5a5c34c469 MCP docs fix 2025-06-17 20:59:12 -07:00
Ishaan JaffandGitHub 0eb8a3de10 [Feat] v2 Pass through endpoints - Add support for subroutes for pass through endpoints + Cleaned up UI (#11827) 
* fix: add construct_target_url_with_subpath

* add InitPassThroughEndpointHelpers

* added debugging for pass through routes

* add PassThroughGenericEndpoint to include subpath and input_cost_per_request

* polish page

* Add Pass-Through Endpoint

* polish pass through ui

* fixes for initialize_pass_through_endpoints

* PassThroughGenericEndpoint

* test_add_subpath_route

* test_initialize_pass_through_endpoints_with_include_subpath

* fix code QA check
 2025-06-17 20:52:28 -07:00
Nicholas CoutureandGitHub 8bcf163b83 Update bedrock guardrail docs (#11826) 
Added the `aws_region_name` and `aws_role_name` keys to the definition of a guardrail config. 

Without these you will get the error `{\"message\":\"The guardrail identifier or version provided in the request does not exist.\"}`
 2025-06-17 17:41:41 -07:00
Krrish Dholakia 3c7399e7ec docs(document_understanding.md): clarify support for openai models 2025-06-17 17:40:49 -07:00
salah alzubiandGitHub d7e53edc26 Update model_prices_and_context_window.json (#11803) 
-- Updated pricing for Gemini Flash
-- Updated a few Openrouter models
-- Updated pricing for Gemini Flash Lite
 2025-06-17 17:12:08 -07:00
Ishaan JaffandGitHub a8196159b9 [Bug Fixes] MCP - using MCPs defined on config.yaml + fix for MCP error Team doesn't exist in cache (#11824) 
* fix - dont allow missing team to block MCP list response

* use HTTP as default transport

* _generate_stable_server_id

* fix list MCP servers

* ui fix

* test_list_mcp_servers_empty_result

* test_generate_stable_server_id

* _generate_stable_server_id

* fix code QA

* fix code QA
 2025-06-17 16:25:12 -07:00
Ishaan JaffandGitHub bcdb53920a [Fix] Bug Fix for using prom metrics config (#11779) 
* fixes for using config for prom metrics

* test_set_llm_deployment_success_metrics_with_label_filtering

* fixes for deployment failure

* fix code qa checks

* test_async_post_call_success_hook
 2025-06-17 14:44:24 -07:00
Cole McIntosh 3a5b1a404f Update Elasticsearch version and logging exporter configuration in the Elasticsearch logging tutorial 2025-06-17 14:32:59 -06:00
Cole McIntoshandGitHub 0ae5e4b15b Merge branch 'BerriAI:main' into docs/elasticsearch-logging-tutorial 2025-06-17 13:10:53 -06:00
Cole McIntoshandGitHub 36d964a758 Fix JSX syntax error in documentation - Fixed unclosed <token> tag in config_settings.md that was causing Vercel deployment to fail (#11818) 2025-06-17 11:39:57 -07:00
Krrish Dholakia 6fe335ea94 bump: version 1.72.6 → 1.72.7 2025-06-16 22:12:39 -07:00
Krish DholakiaandGitHub cb90f8e613 Allow /models to return correct models for custom wildcard prefixes (#11784) 
* fix(model_checks.py): cleanup logic

support wildcard models with non-provider prefix's for model discovery

Closes https://github.com/BerriAI/litellm/pull/10358

* feat(model_checks.py): delegate wildcard prefix appending to the get_known_models_from_wildcard function

remove from the 'get_provider_models' function

* fix(model_checks.py): don't double add the wildcard prefix

* test: update tests
 2025-06-16 22:11:36 -07:00
Krish DholakiaandGitHub 30b431681e JWT Auth - correctly return user email + UI Model Update - Allow editing model access group for existing model (#11783) 
* fix(handle_jwt.py): check user object, if jwt user is proxy admin

correctly return user role - if jwt user has role updated in UI

* test(test_handle_jwt.py): add unit test for passing correct user role

* feat(model_info_view.tsx): separate UI component for updating edit model component

* feat(model_info_view.tsx): allow updating model access group on UI

show all available access groups in ui component

* docs: minor fixes
 2025-06-16 22:11:04 -07:00
Krish DholakiaandGitHub 87ae2cf3d7 SSO - Allow passing additional headers + Spend Tags - automatically track spend by user agent (allows cost tracking for claude code) (#11781) 
* feat(ui_sso.py): allow admin to specify additional headers for sso provider

some sso providers require special headers to return a json response

* test(test_ui_sso.py): add unit tests to ensure custom headers are respect3ed

* docs(config_settings.md): document new header param

* fix(litellm_pre_call_utils.py): add spend tag tracking by user agent

allows checking spend for cli tools like claude code

* feat(litellm_pre_call_utils.py): track spend by user agent part if user agent contains "/"

allows tracking spend across user agent versions

Better cost tracking for claude cod

* test(test_litellm_pre_call_utils.py): add testing for pre call utils, user agent parsing

* fix: fix linting check
 2025-06-16 21:53:40 -07:00
Ishaan JaffandGitHub 80501b8268 [Feat] Day-0 Support for OpenAI Re-usable prompts Responses API (#11782) 
* add prompt to responses params

* add OpenAI PromptObject

* add prompt param to responses api

* test_get_optional_params_responses_api

* test_openai_responses_litellm_router_with_prompt

* docs Reusable Prompts
 2025-06-16 21:28:50 -07:00
Abinand PandGitHub 99c2a7fb70 feat: update the feature of ollama_embeddings to work on a sync api (#11746) 
* feat: update the feature of ollama_embeddings to work on a sync api

Signed-off-by: Abinand P <abinand0911@gmail.com>

* lint:fixing of the lint file

Signed-off-by: Abinand P <abinand0911@gmail.com>

* fix:test

Signed-off-by: Abinand P <abinand0911@gmail.com>

* chore: added test for ollama embedding and refactored handler

Signed-off-by: Abinand P <abinand0911@gmail.com>

* fix:lint error

Signed-off-by: Abinand P <abinand0911@gmail.com>

---------

Signed-off-by: Abinand P <abinand0911@gmail.com>
 2025-06-16 19:07:33 -07:00
Krrish Dholakia bb907b5ecc test: fix test 2025-06-16 18:49:41 -07:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 		4e313e517b build(deps): bump next from 14.2.26 to 14.2.30 in /ui/litellm-dashboard (#11720) 
Bumps [next](https://github.com/vercel/next.js) from 14.2.26 to 14.2.30.
- [Release notes](https://github.com/vercel/next.js/releases)
- [Changelog](https://github.com/vercel/next.js/blob/canary/release.js)
- [Commits](https://github.com/vercel/next.js/compare/v14.2.26...v14.2.30)

---
updated-dependencies:
- dependency-name: next
  dependency-version: 14.2.30
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2025-06-16 17:33:11 -07:00
MadsRCandGitHub 2224fd96be AWS credentials no longer mandatory (#11765) 2025-06-16 17:32:10 -07:00
Ishaan JaffandGitHub 49b957d14c fix aiohttp version (#11777) 2025-06-16 17:31:14 -07:00
Ishaan JaffGitHubCopilot
 		35d74af5a0 [Fix] Pass through - Langfuse don't log request to Langfuse passthrough on Langfuse (#11768) 
* dont log lf pass through request

* test_is_langfuse_route

* Update litellm/proxy/pass_through_endpoints/success_handler.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
 2025-06-16 17:30:23 -07:00
Ishaan JaffandGitHub 7f11b5b76c [Security] - Add Trivy Security Scan for UI + Docs folder - remove all vulnerabilities (#11778) 
* docs - sec scan

* ui - fix 0 security issues

* fix - 0 medium vuln on docs

* add MEDIUM scan for Docs

* Run Trivy scan on LiteLLM UI
 2025-06-16 17:13:19 -07:00
Ishaan JaffandGitHub 261d56b214 [Security] Fixes for docs (#11776) 
* fix - docs

* docs fixes

* fixes for docs

* fixes docs
 2025-06-16 16:20:55 -07:00
Ishaan Jaff 2f322237ca docs - mcp with litellm config.yaml 2025-06-16 12:35:51 -07:00
shagunb-acnandGitHub 441d579d1b #11748: Added Mistral Small to BEDROCK_CONVERSE_MODELS for Converse API support as it supports natively (#11760) 2025-06-16 12:27:26 -07:00
tanjiroandGitHub bc9f111ee8 move buttons to the left (#11771) 2025-06-16 12:27:04 -07:00
Cole McIntosh 11396b936a docs: remove analytics examples from Elasticsearch logging tutorial 2025-06-16 12:01:30 -06:00
Cole McIntosh 05514681cc docs: remove sections from Elasticsearch logging tutorial 2025-06-16 11:48:44 -06:00
Emerson GomesandGitHub b21f4a3f74 Add Vertex Imagen-4 models (#11767) 2025-06-16 10:08:51 -07:00
Cole McIntosh 631f9a8952 docs: update Elasticsearch logging tutorial to include OpenTelemetry setup and configuration 2025-06-16 10:50:17 -06:00
Cole McIntoshandGitHub a7e2f68255 Merge branch 'BerriAI:main' into docs/elasticsearch-logging-tutorial 2025-06-16 10:22:48 -06:00
Cole McIntoshandGitHub 6d373876d2 fix(prometheus.py): always initialize label_filters for PrometheusLogger (#11764) 2025-06-16 09:20:57 -07:00
Cole McIntosh 6fbc79f403 docs: add Elasticsearch logging tutorial and update sidebar 2025-06-16 07:16:18 -06:00
Krrish Dholakia 06519e3f03 docs: specify when users can expect prod version 2025-06-15 01:39:14 -07:00
Krrish Dholakia 48845065f5 docs: specify rc docker version on release notes 2025-06-15 01:38:25 -07:00
Krrish Dholakia 48ac5a940f docs: cleanup 2025-06-15 01:33:49 -07:00
Krrish Dholakia 30827d0522 docs: cleanup docs 2025-06-15 01:33:06 -07:00
Krish DholakiaandGitHub 7a128e2017 VertexAI Anthropic - streaming passthrough cost tracking (#11734) 
* feat(vertex_passthrough_logging_handler.py): initial anthropic passthrough streaming cost tracking support

* fix: fix linting errors

* test: update test
 2025-06-15 01:16:43 -07:00
Krish DholakiaandGitHub bb256c6d83 Release note updates + Responses API Bridge improvements (#11740) 
* docs: track which items need docs

* docs(anthropic.md): add tool_choice="none" to docs

* docs: add docs for new anthropic + perplexity features

* docs: cleanup mistral reasoning docs

* docs: add links to docs

* docs(index.md): update docs

* docs: refactor to add a new 'integrations' tab to docs

* refactor(docs/): create separate tab for integrations

make it easier to highlight new integrations

* docs: sort sidebar

* docs: update

* feat: working claude code with openai codex mini

* docs: add responses api to docs

* feat(index.md): update docs

* fix: fix linting error
 2025-06-15 01:13:10 -07:00
Krish DholakiaandGitHub d15664c8e6 Litellm stable docs 06 14 2025 p2 (#11738) 
* docs: track which items need docs

* docs(anthropic.md): add tool_choice="none" to docs

* docs: add docs for new anthropic + perplexity features

* docs: cleanup mistral reasoning docs

* docs: add links to docs

* docs(index.md): update docs

* docs: refactor to add a new 'integrations' tab to docs

* refactor(docs/): create separate tab for integrations

make it easier to highlight new integrations

* docs: sort sidebar

* docs: update
 2025-06-14 19:38:46 -07:00
Ishaan Jaff 4efdfc00ab docs MCP 2025-06-14 18:13:29 -07:00
Ishaan Jaff 55af010d26 docs mcp 2025-06-14 18:10:37 -07:00
Ishaan Jaff 515e008974 docs mcp 2025-06-14 17:59:28 -07:00
Ishaan Jaff 45a7d1adfe docs mcp 2025-06-14 17:51:45 -07:00
Karthick JandGitHub ac4c29c352 feat(azure): Make Azure AD scope configurable (#11621) 2025-06-14 17:43:01 -07:00
Ishaan Jaff fc57a53a60 docs - cleanup mcp 2025-06-14 17:31:55 -07:00
Ishaan Jaff a4530b49d8 clean up mcp docs 2025-06-14 17:31:22 -07:00
Ishaan Jaff 001e27aede fix typo 2025-06-14 17:29:50 -07:00