tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-06-18 23:40:42 +00:00
Code Issues Packages Projects Releases Wiki Activity
22,954 Commits 2,072 Branches 1,425 Tags
7da4e2197dbdb07f1067f2c35b043b24fd58b429
Commit Graph

3793 Commits

Author SHA1 Message Date
Ishaan Jaff 7da4e2197d Benefits of using gemini-cli with LiteLLM 2025-06-28 21:59:07 -07:00
Ishaan Jaff 50dd9980dc docs - update release notes 2025-06-28 21:56:58 -07:00
Krish Dholakia f7af8902b0 /v1/messages - Remove hardcoded model name on streaming + Tags - enable setting custom header tags (#12131) 
* fix(anthropic/experimental_pass_through): use given model name when returning streaming chunks

don't harcode model name on streaming

confusing for user

* fix(anthropic/streaming_iterator.py): remove scope of import

* feat(litellm_logging.py): allow admin to specify additional headers for using as spend tags

Closes https://github.com/BerriAI/litellm/issues/12129

* test(test_litellm_logging.py): add unit tests

* feat(openweb_ui.md): add custom tag tutorial to docs

* docs(cost_tracking.md): add tag based usage UI screenshot

* test: update test

* fix: fix import
 2025-06-28 21:49:35 -07:00
Krrish Dholakia 123631c93d docs(index.md): update release note with cleaner table for updated models 2025-06-28 21:48:24 -07:00
Krrish Dholakia e77eb82cd6 docs(index.md): initial pre-release note 2025-06-28 13:24:19 -07:00
Guanghui Liu 27849359a9 fix example config.yaml in claude code tutorial (#12133) 2025-06-28 11:07:48 -07:00
Ishaan Jaff 8b73716a66 add docs 2025-06-28 09:26:12 -07:00
Youfu Zhang 1c68c24358 introduce new environment variable NO_REDOC to opt-out Redoc (#12092) 
Signed-off-by: Youfu Zhang <zhangyoufu@gmail.com>
 2025-06-27 21:26:37 -07:00
Ishaan Jaff 7465f062c0 add panw guard docs 2025-06-27 21:13:04 -07:00
Ishaan Jaff bb98f68451 docs fix 2025-06-27 21:09:33 -07:00
ohmeow 9ab7d97b85 adds model to metadata to estimated cost is calculated; corrects how to pass metadata in braintrust in the docs (#12022) 2025-06-27 18:11:07 -07:00
Ishaan Jaff ebf6395bc1 [Feat] Add Eleven Labs - Speech To Text Support on LiteLLM (#12119) 
* add ELEVENLABS as a provider

* add deepgram to main.py

* add ElevenLabsException

* add ElevenLabsAudioTranscriptionConfig

* add transform_audio_transcription_response

* TestElevenLabsAudioTranscription

* add elevenlabs/scribe_v1 to model cost map

* add ElevenLabsAudioTranscriptionConfig

* add AudioTranscriptionRequestData

* add ElevenLabs transform

* use AudioTranscriptionRequestData

* refactoring fixes

* add ProcessedAudioFile util for reading audio files

* test_elevenlabs_diarize_parameter_passthrough

* docs eleven labs

* docs fixes

* fix code qa checks

* fixes - audio transcription

* ui - add ElevenLabs logo

* add elevenlabs logo

* docs - ElevenLabs

* test fix elevenlabs
 2025-06-27 17:50:49 -07:00
Jason Roberts b57cfb8bff Adding Feature: Palo Alto Networks Prisma AIRS Guardrail (#12116) 
* feat: Add PANW Prisma AIRS guardrail integration

- Add PANW_PRISMA_AIRS to SupportedGuardrailIntegrations enum
- Update guardrail registry and initializers
- Add complete documentation with curl examples and response formats
- Support pre_call, post_call, and during_call modes
- Include fail-safe error handling and comprehensive logging
- Integration with official PANW Prisma AIRS API

* feat: Add PANW Prisma AIRS guardrail integration

- Update to test file
- Fail-closed security on API errors

* update fail closed behavior

* fix: Update PANW Prisma AIRS guardrail integration pattern

* fix: Remove unused import

* fix: addressed MyPy error
 2025-06-27 15:17:36 -07:00
Ishaan Jaff f85cd9c54a [Docs] - Show how to use fallbacks with audio transcriptions endpoints (#12115) 
* add overview

* docs audio transcriptions

* docs on fallbacks with audio endpoints
 2025-06-27 12:43:55 -07:00
Ishaan Jaff f1c7024e70 [Feat] Add Bridge from generateContent <> /chat/completions (#12081) 
* add GenerateContentToCompletionHandler

* working - non streaming bridge

* add GoogleGenAIAdapter

* add google gen ai adapter

* working streaming bridge

* working streaming usage for adapter

* tool calling transform for generate content to openai

* fixes for accumulating tool calls

* fix code qa checks

* Best Practices for Production

* fix code qa checks

* test_streaming_partial_tool_calls_accumulation

* linting fixes

* add supported_openai_chat_completion_params

* fix translate_generate_content_to_completion

* test_google_genai_adapter.py
 2025-06-27 11:08:55 -07:00
Cole McIntosh 60bf3c36bf fix(docs): Remove unused dotenv dependency from docusaurus config (#12102) 
* fix(docs): Remove unused dotenv dependency from docusaurus config

The dotenv package was being required in docusaurus.config.js but was listed as
a devDependency, causing build failures. Since no environment variables are
actually used in the config, removed the unnecessary import.

* fix(docs): Remove reference to non-existent spending_monitoring doc

The sidebars.js file was referencing proxy/spending_monitoring which was deleted
in commit ba7463b9c. This was causing the documentation build to fail with missing
document errors.
 2025-06-27 08:20:44 -07:00
Ishaan Jaff ba7463b9c6 docs - spend monitoring 2025-06-26 17:39:13 -07:00
Ishaan Jaff edf416c24f docs - Use LiteLLM with Gemini CLI 2025-06-26 17:31:19 -07:00
Ishaan Jaff 72ecac8962 docs - user agent 2025-06-26 16:23:59 -07:00
Ishaan Jaff 16126f0d6b docs Gemini Text-to-Speech 2025-06-26 15:59:48 -07:00
Ishaan Jaff 80acf6bc97 docs */speech to /chat/completions Bridge** 2025-06-26 15:53:25 -07:00
Ishaan Jaff fc39343599 docs update 2025-06-26 15:32:33 -07:00
Ishaan Jaff e556071544 docs - Use LiteLLM with Gemini CLI 2025-06-26 13:35:33 -07:00
tanjiro bd0a5f7387 Inkeep searchbar and chat added to the Docs (#12030) 
* inkeep chat added

* add prod key
 2025-06-26 10:13:42 -07:00
Ishaan Jaff 22ff3da3cf [Fix] Allow using HTTP_ Proxy settings with trust_env (#12066) 
* allow using trust_env

* add docs on how to use HTTP_PROXY

* docs AIOHTTP_TRUST_ENV

* test_aiohttp_transport_trust_env_setting

* docs fix
 2025-06-26 08:37:22 -07:00
Cole McIntosh 327405ffae Merge pull request #12050 from colesmcintosh/docs/elasticsearch-logging-tutorial 
Fix Elasticsearch tutorial image rendering
 2025-06-26 09:00:00 -06:00
Ishaan Jaff f8f9e2299b docs latency headers 2025-06-26 07:58:23 -07:00
Ishaan Jaff 329f8ec7a6 docs gemini cli 2025-06-25 22:39:50 -07:00
Ishaan Jaff bca94535da docs gemini cli 2025-06-25 22:31:47 -07:00
Cole McIntosh f9ef45474b Fix Elasticsearch tutorial image rendering 
- Replace markdown image syntax with React Image component
- Import @theme/IdealImage for proper image rendering in Docusaurus
- Addresses PR feedback to fix image display issues
 2025-06-25 16:27:14 -06:00
Cole McIntosh 51c1c7bd36 Add Elasticsearch Logging Tutorial (#11761) 
* docs: add Elasticsearch logging tutorial and update sidebar

* docs: update Elasticsearch logging tutorial to include OpenTelemetry setup and configuration

* docs: remove sections from Elasticsearch logging tutorial

* docs: remove analytics examples from Elasticsearch logging tutorial

* Update Elasticsearch version and logging exporter configuration in the Elasticsearch logging tutorial

* Add visualization instructions for LLM telemetry data in Kibana to Elasticsearch logging tutorial

* Add Elasticsearch demo image to documentation

* Move demo image for Elasticsearch logging tutorial
 2025-06-25 15:17:37 -07:00
Cole McIntosh 9111b67950 Move demo image for Elasticsearch logging tutorial 2025-06-25 16:14:27 -06:00
Cole McIntosh b3aa8c980e Add Elasticsearch demo image to documentation 2025-06-25 16:11:41 -06:00
Cole McIntosh c218b62822 Add visualization instructions for LLM telemetry data in Kibana to Elasticsearch logging tutorial 2025-06-25 16:11:32 -06:00
Cole McIntosh d7568a37f0 Merge branch 'BerriAI:main' into docs/elasticsearch-logging-tutorial 2025-06-25 15:42:18 -06:00
Krish Dholakia 24c2cd1bd9 Anthropic /v1/messages - Custom LLM Server support (#12016) 
* fix(handler.py): support routing custom llm's to chat completion handler

Adds custom llm support for anthropic

* test(test_anthropic_experimental_pass_through_messages_handler.py): add unit test confirming custom llm respected

* docs(custom_llm_server.md): document anthropic custom llm translation

* test(volcengine.py): map thinking in extra body

Fixes https://github.com/BerriAI/litellm/issues/11879

* feat(main.py): support `azure/responses/<deployment-name>` model string

this allows us to route the model correctly

Closes https://github.com/BerriAI/litellm/issues/11879

* docs(azure_responses.md): document calling azure responses api models via chat completions bridge

Closes https://github.com/BerriAI/litellm/issues/11917

* fix: fix custom provider check

* test: update tests
 2025-06-24 22:00:44 -07:00
Ishaan Jaff d6cc384780 [Feat] OpenAI/Azure OpenAI - Add support for creating vector stores on LiteLLM (#12021) 
* add create/acreate vector store

* add azure config

* add _base_validate_azure_environment

* fix base test

* add get_base_create_vector_store_args

* use base llm for headers responses api

* add _get_base_azure_url

* fix AzureOpenAIVectorStoreConfig

* TestAzureOpenAIVectorStore

* fix azure openai vector store

* fix test comment

* fix unused imports

* test_validate_environment_azure_api_key_within_secret_str

* test_azure_transformation.py
 2025-06-24 20:46:48 -07:00
Ishaan Jaff 2bb8048864 [Feat] Add OpenAI Search Vector Store Operation (#12018) 
* add BaseVectorStoreTransformation

* fix BaseVectorStoreTransformation

* add OpenAIVectorStoreTransformation

* fix transform

* add search, asearch vector stores

* add skeleton for vector store searching

* fix VectorStoreSearchOptionalRequestParams

* fix VectorStoreRequestUtils

* fix litellm.asearch/litellm.search

* fix BaseVectorStoreConfig

* add vector_store_search_handler to llm http handler

* use llm http handler for searching vector stores

* fix base vector store config

* fix vector_store_search_handler

* async_vector_store_search_handler

* add conftest

* add BaseVectorStoreTest

* move litellm.integrations.vector_store_integrations

* fix working OAI OpenAIVectorStoreConfig

* add Search vector store

* add OpenAI Vector Stores
 2025-06-24 15:52:43 -07:00
Krrish Dholakia 8da22be199 docs(self_serve.md): update doc 2025-06-24 13:25:17 -07:00
Krrish Dholakia c9a8198d12 docs(self_serve.md): clarify team must be created before setting as default team 2025-06-24 13:24:23 -07:00
Krrish Dholakia 330cd4f2a9 docs(self_serve.md): update self serve docs to include default team / member budget information 2025-06-24 09:31:33 -07:00
Krish Dholakia a89397a798 Litellm dev 06 23 2025 p1 (#11989) 
* fix(litellm_logging.py): fix using router model id for logging calls

Fixes https://github.com/BerriAI/litellm/issues/11975#issuecomment-2995882238

* test(test_litellm_logging.py): add unit test for custom price tracking

* fix(vertex_ai/): don't send invalid format parameter to vertex

causes calls to fail

* fix(vertex_ai_context_caching.py): if cached content present and tools in message, cache tools as well

gemini throws errors if tools passed in alongside cached content

* test: add unit tests

* fix: fix linting errors

* test: test_vertex_ai_common_utils.py

update test

* fix(streaming_handler.py): unset response cost when creating model response
 2025-06-23 22:33:06 -07:00
Ishaan Jaff eec0e4d2be docs - web search 2025-06-23 21:25:35 -07:00
Ishaan Jaff b5c48c8c22 [Feat] Add List Callbacks API Endpoint (#11987) 
* add get_callbacks_by_type

* add list_callbacks

* fix _get_callback_string

* add callback_management_endpoints_router

* fix proxy config.yaml

* fixes list callbacks

* TestCallbackManagementEndpoints

* update docs

* docs Response Fields

* docs header format

* docs Dynamic Callback Management
 2025-06-23 15:34:25 -07:00
Ishaan Jaff 8c5fb6f539 [Feat] Enterprise - Allow dynamically disabling callbacks in request headers (#11985) 
* Add support for disabling callbacks via x-litellm-disable-callbacks header

* add _is_callback_disabled_via_headers

* add get_proxy_server_request_headers

* _is_callback_disabled_via_headers

* X_LITELLM_DISABLE_CALLBACKS

* add EnterpriseCallbackControls

* use EnterpriseCallbackControls

* use CustomLoggerRegistry

* use CustomLoggerRegistry

* CustomLoggerRegistry

* EnterpriseCallbackControls

* TestEnterpriseCallbackControls

* docs clean up

* docs dynamic callbacks

* doc fixes

* fix code qa checks

* fix CustomLoggerRegistry

---------

Co-authored-by: Cursor Agent <cursoragent@cursor.com>
 2025-06-23 14:32:05 -07:00
Mukesh Sai Kumar a44ff7c486 Fix markdown table not rendering properly (#11969) 2025-06-23 09:28:51 -07:00
Ishaan Jaff 05b95eb702 docs - Recommended Machine Specifications (#11980) 2025-06-23 08:26:29 -07:00
Cole McIntosh 3c22d52d6c Merge branch 'BerriAI:main' into docs/elasticsearch-logging-tutorial 2025-06-22 12:51:26 -06:00
Ishaan Jaff b36dbb870c fix ghcr 2025-06-22 09:06:58 -07:00
Ishaan Jaff 9e5c97aabd fix pip pkg 2025-06-22 09:05:45 -07:00