LiteLLM Files

What's Changed

• (feat) Milvus - search vector store support + (fix) Passthrough Endpoints - support multi-part form data on passthrough by @krrishdholakia in https://github.com/BerriAI/litellm/pull/16035
• (feat) Azure AI Vector Stores - support "virtual" indexes + create vector store on passthrough API by @krrishdholakia in https://github.com/BerriAI/litellm/pull/16160
• Add custom_llm_provider support for video endpoints (non-generation) by @Sameerlite in https://github.com/BerriAI/litellm/pull/16121
• fix: resolve memory accumulation caused by Pydantic 2.11+ deprecation warnings by @AlexsanderHamir in https://github.com/BerriAI/litellm/pull/16110
• add: minimum resource requirement for production by @AlexsanderHamir in https://github.com/BerriAI/litellm/pull/16146
• Remove minimum validation for cache control injection index by @steve-gore-snapdocs in https://github.com/BerriAI/litellm/pull/16149
• Fix empty assistant message handling in AWS Bedrock Converse API to prevent 400 Bad Request errors by @Sameerlite in https://github.com/BerriAI/litellm/pull/15850
• Add LLM provider response headers to Responses API by @Sameerlite in https://github.com/BerriAI/litellm/pull/16091
• Fix azure doesn't accept extra body param by @Sameerlite in https://github.com/BerriAI/litellm/pull/16116
• Add E2E Container API Support by @Sameerlite in https://github.com/BerriAI/litellm/pull/16136
• Add new model pricing for nemotron-nano-9b-v2 by @timbmg in https://github.com/BerriAI/litellm/pull/16120
• docs - v1.79.1 by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/16163
• UI - Fix regression where Guardrail Entity Could not be selected and entity was not displayed by @ishaan-jaff in https://github.com/BerriAI/litellm/pull/16165
• Fix Anthropic token counting for VertexAI by @steve-gore-snapdocs in https://github.com/BerriAI/litellm/pull/16171
• [Feature] UI - Delete Team Member with friction by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/16167
• [Feature] UI - Add Model Existing Credentials Improvement by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/16166
• [Feature] UI - Guardrail Info Page Show PII Config by @yuneng-jiang in https://github.com/BerriAI/litellm/pull/16164
• strip base64 in s3 by @deepanshululla in https://github.com/BerriAI/litellm/pull/16157
• fix(ui_sso.py): support dot notation on ui sso by @krrishdholakia in https://github.com/BerriAI/litellm/pull/16135
• Support responses API streaming in langfuse otel by @eycjur in https://github.com/BerriAI/litellm/pull/16153
• fix: return the diarized transcript when it's required in the request by @gvioss in https://github.com/BerriAI/litellm/pull/16133
• build: Squashed commit of the following: by @krrishdholakia in https://github.com/BerriAI/litellm/pull/16176
• feat: change guardrail_information to list type by @uc4w6c in https://github.com/BerriAI/litellm/pull/16127
• Milvus - Passthrough API support - adds create + read vector store support via passthrough API's by @krrishdholakia in https://github.com/BerriAI/litellm/pull/16170
• Fix index field not populated in streaming mode with n>1 and tool calls by @Sameerlite in https://github.com/BerriAI/litellm/pull/15962
• Update perplexity cost tracking by @Sameerlite in https://github.com/BerriAI/litellm/pull/15743
• Fix image_config.aspect_ratio not working for gemini-2.5-flash-image by @Sameerlite in https://github.com/BerriAI/litellm/pull/15999

New Contributors

• @steve-gore-snapdocs made their first contribution in https://github.com/BerriAI/litellm/pull/16149
• @timbmg made their first contribution in https://github.com/BerriAI/litellm/pull/16120

Full Changelog: https://github.com/BerriAI/litellm/compare/v1.79.1-nightly...v1.79.1.dev5