v1.67.7-stable #10531

krrishdholakia announced in Announcements

krrishdholakia
May 3, 2025
Maintainer

What's Changed

Handle more gemini tool calling edge cases + support bedrock 'stable-image-core' by @krrishdholakia in Handle more gemini tool calling edge cases + support bedrock 'stable-image-core' #10351
[Feat] Add logging callback support for /moderations API by @ishaan-jaff in [Feat] Add logging callback support for /moderations API #10390
[Reliability fix] Redis transaction buffer - ensure all redis queues are periodically flushed by @ishaan-jaff in [Reliability fix] Redis transaction buffer - ensure all redis queues are periodically flushed #10393
[Bug Fix] Responses API - fix for handling multiturn responses API sessions by @ishaan-jaff in [Bug Fix] Responses API - fix for handling multiturn responses API sessions #10415
build(deps): bump axios, @docusaurus/core, @docusaurus/plugin-google-gtag, @docusaurus/plugin-ideal-image and @docusaurus/preset-classic in /docs/my-website by @dependabot in build(deps): bump axios, @docusaurus/core, @docusaurus/plugin-google-gtag, @docusaurus/plugin-ideal-image and @docusaurus/preset-classic in /docs/my-website #10419
docs: Fix link formatting in GitHub PR template by @user202729 in docs: Fix link formatting in GitHub PR template #10417
docs: Improve documentation of phoenix logging by @user202729 in docs: Improve documentation of phoenix logging #10416
[Feat Security] - Allow blocking web crawlers by @ishaan-jaff in [Feat Security] - Allow blocking web crawlers #10420
[Feat] Add support for using Bedrock Knowledge Bases with LiteLLM /chat/completions requests by @ishaan-jaff in [Feat] Add support for using Bedrock Knowledge Bases with LiteLLM /chat/completions requests #10413
Revert "build(deps): bump axios, @docusaurus/core, @docusaurus/plugin-google-gtag, @docusaurus/plugin-ideal-image and @docusaurus/preset-classic in /docs/my-website" by @ishaan-jaff in Revert "build(deps): bump axios, @docusaurus/core, @docusaurus/plugin-google-gtag, @docusaurus/plugin-ideal-image and @docusaurus/preset-classic in /docs/my-website" #10421
fix google studio url by @nonZero in fix google studio url #10095
[New model] Add openai/computer-use-preview cost tracking / pricing by @ishaan-jaff in [New model] Add openai/computer-use-preview cost tracking / pricing #10422
fix(langsmith.py): respect langsmith batch size param by @krrishdholakia in fix(langsmith.py): respect langsmith batch size param #10411
Support x-litellm-api-key header param + allow key at max budget to call non-llm api endpoints by @krrishdholakia in Support x-litellm-api-key header param + allow key at max budget to call non-llm api endpoints #10392
Update fireworks ai pricing by @krrishdholakia in Update fireworks ai pricing #10425
Schedule budget resets at expectable times (Schedule budget resets at expectable times #10331) by @krrishdholakia in Schedule budget resets at expectable times (#10331) #10333
Embedding caching fixes - handle str -> list cache, set usage tokens for cache hits, combine usage tokens on partial cache hits by @krrishdholakia in Embedding caching fixes - handle str -> list cache, set usage tokens for cache hits, combine usage tokens on partial cache hits #10424
Contributor PR - Support OPENAI_BASE_URL in addition to OPENAI_API_BASE (Support OPENAI_BASE_URL in addition to OPENAI_API_BASE #9995) by @ishaan-jaff in Contributor PR - Support OPENAI_BASE_URL in addition to OPENAI_API_BASE (#9995) #10423
New feature: Add Python client library for LiteLLM Proxy by @msabramo in New feature: Add Python client library for LiteLLM Proxy #10445
Add key-level multi-instance tpm/rpm/max parallel request limiting by @krrishdholakia in Add key-level multi-instance tpm/rpm/max parallel request limiting #10458
[UI] Allow adding triton models on LiteLLM UI by @ishaan-jaff in [UI] Allow adding triton models on LiteLLM UI #10456
[Feat] Vector Stores/KnowledgeBases - Allow defining Vector Store Configs by @ishaan-jaff in [Feat] Vector Stores/KnowledgeBases - Allow defining Vector Store Configs #10448
Add low-level interface to client library for doing HTTP requests by @msabramo in Add low-level interface to client library for doing HTTP requests #10452
Correctly re-raise 504 errors and Add gpt-4o-mini-tts support by @krrishdholakia in Correctly re-raise 504 errors and Add gpt-4o-mini-tts support #10462
UI - Fix filtering on key alias + support global sorting on keys by @krrishdholakia in UI - Fix filtering on key alias + support global sorting on keys #10455
[Bug Fix] Ensure Non-Admin virtual keys can access /mcp routes by @ishaan-jaff in [Bug Fix] Ensure Non-Admin virtual keys can access /mcp routes #10473
[Fixes] Azure OpenAI OIDC - allow using litellm defined params for OIDC Auth by @ishaan-jaff in [Fixes] Azure OpenAI OIDC - allow using litellm defined params for OIDC Auth #10394
Add supports_pdf_input: true to Claude 3.7 bedrock models by @RupertoM in Add supports_pdf_input: true to Claude 3.7 bedrock models #9917
Add llamafile as a provider (Add llamafile as a provider #10203) by @ishaan-jaff in Add llamafile as a provider (#10203) #10482
Fix mcp.md in documentation by @1995parham in Fix mcp.md in documentation #10493
docs(realtime): yaml config example for realtime model by @kmontocam in docs(realtime): yaml config example for realtime model #10489
Fix return finish_reason = "tool_calls" for gemini tool calling by @krrishdholakia in Fix return finish_reason = "tool_calls" for gemini tool calling #10485
Add user + team based multi-instance rate limiting by @krrishdholakia in Add user + team based multi-instance rate limiting #10497
mypy tweaks by @msabramo in mypy tweaks #10490
Add vertex ai meta llama 4 support + handle tool call result in content for vertex ai by @krrishdholakia in Add vertex ai meta llama 4 support + handle tool call result in content for vertex ai #10492
Fix and rewrite of token_counter by @happyherp in Fix and rewrite of token_counter #10409
[Fix + Refactor] Trigger Soft Budget Webhooks When Key Crosses Threshold by @ishaan-jaff in [Fix + Refactor] Trigger Soft Budget Webhooks When Key Crosses Threshold #10491
[Bug Fix] Ensure Web Search / File Search cost are only added when the response includes the too call by @ishaan-jaff in [Bug Fix] Ensure Web Search / File Search cost are only added when the response includes the too call #10476
Fixes for test_team_budget_metrics and test_generate_and_update_key by @S1LV3RJ1NX in Fixes for test_team_budget_metrics and test_generate_and_update_key #10500
[Feat] KnowledgeBase/Vector Store - Log StandardLoggingVectorStoreRequest for requests made when a vector store is used by @ishaan-jaff in [Feat] KnowledgeBase/Vector Store - Log StandardLoggingVectorStoreRequest for requests made when a vector store is used #10509
Don't depend on uvloop on windows (Don't depend on uvloop on windows #10060) by @ishaan-jaff in Don't depend on uvloop on windows (#10060) #10483
fix: PydanticDeprecatedSince20: Support for class-based config is eprecated, use ConfigDict instead. Deprecated in Pydantic V2.0 to be removed in V3.0. by @Elijas in fix: PydanticDeprecatedSince20: Support for class-based config is eprecated, use ConfigDict instead. Deprecated in Pydantic V2.0 to be removed in V3.0. #9372
[Feat] Show Vector Store / KB Request on LiteLLM Logs Page by @ishaan-jaff in [Feat] Show Vector Store / KB Request on LiteLLM Logs Page #10514
Fix pytest event loop warning ([Bug]: DeprecationWarning: There is no current event loop in llm_caching_handler.py #9641) by @msabramo in Fix pytest event loop warning (#9641) #10512
UI - fix adding vertex models with reusable credentials + fix pagination on keys table + fix showing org budgets on table by @krrishdholakia in UI - fix adding vertex models with reusable credentials + fix pagination on keys table + fix showing org budgets on table #10528
Playwright test for team admin (Playwright test for team admin #10366) by @krrishdholakia in Playwright test for team admin (#10366) #10470
[QA] Bedrock Vector Stores Integration - Allow using with registry + in OpenAI API spec with tools by @ishaan-jaff in [QA] Bedrock Vector Stores Integration - Allow using with registry + in OpenAI API spec with tools #10516
UI - allow reassigning team to other org by @krrishdholakia in UI - allow reassigning team to other org #10527
[Models/ LLM Credentials] Fix edit credentials modal by @NANDINI-star in [Models/ LLM Credentials] Fix edit credentials modal #10519

New Contributors

@user202729 made their first contribution in docs: Fix link formatting in GitHub PR template #10417
@nonZero made their first contribution in fix google studio url #10095
@RupertoM made their first contribution in Add supports_pdf_input: true to Claude 3.7 bedrock models #9917
@1995parham made their first contribution in Fix mcp.md in documentation #10493
@kmontocam made their first contribution in docs(realtime): yaml config example for realtime model #10489
@happyherp made their first contribution in Fix and rewrite of token_counter #10409
@Elijas made their first contribution in fix: PydanticDeprecatedSince20: Support for class-based config is eprecated, use ConfigDict instead. Deprecated in Pydantic V2.0 to be removed in V3.0. #9372

Full Changelog: v1.67.4-stable...v1.67.7-stable

This discussion was created from the release v1.67.7-stable.

Replies: 0 comments

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment