fc8d28f7df
docs - DEFAULT_MAX_RECURSE_DEPTH_SENSITIVE_DATA_MASKER
2025-05-14 18:29:31 -07:00
9e06c42f72
test: fix litellm_mapped_tests
2025-05-14 18:29:01 -07:00
abe7b71e6a
Revert "Revert "[Fix] Allow overriding all constants using a .env variable ( #10803 )""
...
This reverts commit cf4b2ebda4
2025-05-14 18:27:43 -07:00
a754a25828
Feat add retention config ( #10815 )
...
* add function to check config flag
* added unit tests
* convert to seconds support
* added in settings.md
* Updated config_settings.md
* remove extra point
* change config var
* resolve conflict
2025-05-14 18:16:25 -07:00
235ae79037
ui new build
2025-05-14 18:01:48 -07:00
91f32cd227
ui linting fixes
2025-05-14 18:00:50 -07:00
be18923250
fix code qa check for OTEL env vars
2025-05-14 17:56:27 -07:00
19b2d70732
bump litellm_enterprise-0.1.3.tar.gz
2025-05-14 17:55:03 -07:00
a30c574f9a
bump litellm_proxy_extras-0.1.21.tar.gz
2025-05-14 17:53:34 -07:00
526e6aaaca
patch: validate_team_org_change ( #10835 )
...
* fix: validate_team_org_change
* test: test_validate_team_org_change_same_org_id
2025-05-14 17:50:41 -07:00
2a994d7016
[Feat] Presidio Improvements - Allow adding presidio api base on UI, Test presidio on Test Key, fixes for running presidio hook ( #10840 )
...
* feat: add GuardrailProviderSpecificParams
* feat: add add apply_guardrail helper for presidio
* ui cleanup
* fixes pii config on ui
* fixes for adding presidio pii
* refactor: InitializeGuardrails
* feat: init guardrails from DB
* allow running guardrails from test key pg
* fix: running a request with guardrails on UI
* fix: types/guardrails.py
* test: test_presidio_pre_call_hook_with_different_call_types
* test: test_initialize_presidio_guardrail
* test: fix custom guardrail tests
2025-05-14 17:41:33 -07:00
63a4287bff
Supper OTLP standard environment variables for configuration ( #10813 )
...
- Environment variables outlined at https://opentelemetry.io/docs/languages/sdk-configuration/otlp-exporter/
- Default to OTLP standard, but fallback to existing so as to not break backwards compatibility
2025-05-14 17:40:28 -07:00
9ac47cd05a
[UI] Fixes for bulk invite users - add validation for bad inputs ( #10836 )
...
* fixes for bulk invite users
* add validation for bulk import
2025-05-14 17:36:30 -07:00
652b5693cc
build: add guardrails table
2025-05-14 14:23:07 -07:00
b9c3a3835c
[Feat UI] Add Guardrails on LiteLLM UI ( #10834 )
...
* feat: add DB Add, Edit, Delete for Guardrails
* feat: endpoints for guardrail management
* add guardrail info helpers
* add presidio logo
* add createGuardrailCall
* basic add guardrails on UI
* fix cleanup form
* feat: working add guardrails
* ui view guardrails
* allow viweing list of guardrails
* fix: show created_at and updated_at for guardrails on UI
* cleanup guardrail view
* use 1 file for guardrail table
* docs adding guardrails
* fix: expose endpoint to show allowed modes, entities, actions
* fix allow adding entity configs for PII
* fixes guardrails
* fix adding guardrails on UI
* feat: add PII_ENTITY_CATEGORIES_MAP
* use categories for pii
* use step based form
* fixes pii configs
* fix pii config
* refactor pii config on ui
* clear form on submit
* add ability to create guardrails
* fix linting error
2025-05-14 14:21:35 -07:00
ee1557afcd
[Feat] Add endpoints for adding, deleting, editing guardrails in DB ( #10833 )
...
* feat: add DB Add, Edit, Delete for Guardrails
* feat: endpoints for guardrail management
* add guardrail info helpers
* add presidio logo
* add createGuardrailCall
2025-05-14 14:19:51 -07:00
007524a972
Update Groq models on model_prices_and_context_window.json ( #10077 )
...
* Update Groq models on model_prices_and_context_window.json
Add support for 6 new models; add deprecations dates to 12 model; and update context-windows/max-tokens for 3 models
* Round model costs to 8 decimal places
2025-05-14 13:08:03 -07:00
1fc5320e9f
Team id + Status filter on logs ( #10831 )
...
* added team_id filter
* improve hook
* pagination fixed
* fix pagination for team id filter
* minor
* added status filter
* fixed pagination
2025-05-14 13:06:42 -07:00
468b881ec5
add support to parse metadata ( #10832 )
...
* add support to parse metadata
* add safe loads
* remove depth checks
2025-05-14 12:03:49 -07:00
d558c223b3
bump resource_class: xlarge
2025-05-14 08:31:53 -07:00
98bed9b698
update resource_class for litellm_mapped_tests
2025-05-14 07:43:56 -07:00
340a0453d3
Migrate cohere to /v2/embed - adds support for output_dimensions param ( #10809 )
...
* feat(cohere/embed): v2 embed api support
adds output_dimensions param support
* fix(cohere/embed): migrate to v2 embedding
Adds output dimension support
* fix: maintain /v1/embedding compatibility for bedrock cohere
Bedrock cohere is still using /v1 endpoints
* fix: fix linting error
* fix: fix passing extra headers
* test: update tests
2025-05-13 23:06:56 -07:00
a421316e56
fix(litellm_logging.py): log custom headers in requester metadata ( #10818 )
...
* fix(litellm_logging.py): log custom headers in requester metadata
allows passing along custom headers from client to logging integration - e.g. `x-correlation-id`
* refactor: move enterprise code out of OSS package
work towards simplified CE version of docker image
* test: update test
* fix: fix linting error
2025-05-13 23:04:37 -07:00
cf4b2ebda4
Revert "[Fix] Allow overriding all constants using a .env variable ( #10803 )"
...
This reverts commit de901bbf24
2025-05-13 21:27:44 -07:00
741ea6e149
ci/cd: remove n -4 change
2025-05-13 21:21:37 -07:00
6b6794a926
fix mapped tests
2025-05-13 21:17:41 -07:00
cab57b2d2f
Fix: Separate Sync/Async Azure Client Cache to Prevent Type Mismatches ( #10781 )
...
* fix: Fix issues when mix sync and async call in AzureOpen
* misc: Keep original format
* misc: Add back missing file
2025-05-13 21:13:46 -07:00
19ca5f7307
test - increase duration of litellm mapped test
2025-05-13 20:56:48 -07:00
33f11f1479
fix arize config tests
2025-05-13 20:21:14 -07:00
18a51a9849
bump: version 1.69.2 → 1.69.3
2025-05-13 19:55:53 -07:00
5e7869a778
[Bedrock] Fixes to only allow accepted fields for tool json schema ( #10062 )
...
* add test_function_calling_with_tool_response to base llm tests
* run test suite for nova
* update test_function_calling_with_tool_response
* allowed ToolJsonSchemaBlock keys
* fix ToolJsonSchemaBlock
* add back pytest fixture
* test: test_prompt_caching
2025-05-13 19:49:30 -07:00
8142c20c98
[Feat] Allow specifying PII Entities Config when using Presidio Guardrails ( #10810 )
...
* refactor: use analyze_text, anonymize_text
* feat: allow defining pii_entities_config for presidio
* feat: use entities config for presidio analyze request
* feat: add test_presidio_pii.py
* testing: add guardrails testing job
* feat: allow blocking specific entities pii
* test: use 1 file for presidio guard tests
* fix: presidio pii tests
* test: presidio blocked entity
* clean up docs
* docs presidio pii parsing
* fix: raise_exception_if_blocked_entities_detected
* fix: linting errors
2025-05-13 19:48:56 -07:00
c5277b6714
test fixes: TestArizePhoenixConfig
2025-05-13 17:27:05 -07:00
b5e864be2e
fixes for presidio checks ( #10197 )
2025-05-13 17:19:55 -07:00
5fbcd22604
[Fix] Allow overriding all constants using a .env variable ( #10803 )
...
* fix: bump: DEFAULT_MAX_RECURSE_DEPTH
* fix: bump: DEFAULT_MAX_RECURSE_DEPTH
* test: test_vertex_ai_complex_response_schema
* fix: allow all constants to be overriden
* fix: allow all numeric constants to be overriden with env vars
* fix: remove dup DEFAULT_MAX_TOKENS in constants.py
* document all constants env vars
* docs - DEFAULT_PROMPT_INJECTION_SIMILARITY_THRESHOLD
2025-05-13 16:10:55 -07:00
a6412cd98a
Add Azure Cohere Embed v4 ( #10806 )
...
Add Azure Cohere Embed v4 to model db
2025-05-13 15:25:35 -07:00
e7ad0b043c
Add Azure gpt-4o-mini-tts ( #10807 )
...
Add Azure gpt-4o-mini-tts to model db
2025-05-13 15:25:22 -07:00
2b5a781fa4
add ollama api base defaults ( #10805 )
2025-05-13 14:58:36 -07:00
3bd2c91164
[Fix] Maximum Vertex Recursion Depth Reached when transforming response_format ( #10798 )
...
* fix: bump: DEFAULT_MAX_RECURSE_DEPTH
* fix: bump: DEFAULT_MAX_RECURSE_DEPTH
* test: test_vertex_ai_complex_response_schema
2025-05-13 14:29:23 -07:00
71d1fabc21
[README] Add Llama API in supported providers table ( #10802 )
...
* docs: add llama-api in supported table
* docs: revert formatting
2025-05-13 13:49:21 -07:00
9ae4185e6d
fix: cleanup print
2025-05-13 11:57:26 -07:00
f1136fd217
fix: URL encode OTEL_EXPORTER_OTLP_TRACES_HEADERS for Phoenix Integration ( #10654 )
...
* fix: URL encode OTEL_EXPORTER_OTLP_TRACES_HEADERS for Arize Phoenix integration
- Add URL encoding for Bearer token in authorization header
- Follow OpenTelemetry Protocol Exporter specification
- Fix header format validation error in Phoenix integration
* add mock test for arize phoenix
2025-05-13 09:45:39 -07:00
3130c4f8f9
[Refactor] Move LLM Guard, Secret Detection to Enterprise Pip packagea ( #10782 )
...
* refactor: move guardrails to pip
* refactor: move guardrails to pip
* testing fix: move guardrails to pip
* git commit setup_litellm_enterprise_pip
2025-05-13 09:42:22 -07:00
e0b49c3b0c
bump: version 1.69.1 → 1.69.2
2025-05-12 22:50:03 -07:00
ff68cbda8e
Fix azure dall e 3 call with custom model name + Handle Bearer $LITELLM_API_KEY in x-litellm-api-key custom header ( #10776 )
...
* fix(main.py): use base model instead of user model if given
Fixes https://github.com/BerriAI/litellm/issues/10760
* feat(azure/image_generation/__init__.py): make azure image gen check more robust
Fixes https://github.com/BerriAI/litellm/issues/10760
* fix(user_api_key_auth.py): support bearer token auth for `x-litellm-api-key` header
Fixes earlier regression on vertex ai passthrough auth
* fix(user_api_key_auth.py): refactor get api key into separate function
enables easier testing
* fix: cleanup
* fix: fix linting error
* fix: cleanup
* test: update tests
2025-05-12 22:49:35 -07:00
53f6514f12
Support Anthropic web search tool + Add more google finish reason mapping ( #10785 )
...
* fix(vertex_and_google_ai_studio_gemini.py): handle additional google finish reasons
Fixes https://github.com/BerriAI/litellm/issues/10768
* test: add more unit tests
* fix(anthropic/chat/transformation.py): support anthropic web search
Fixes https://github.com/BerriAI/litellm/issues/10664
* fix(anthropic/chat/transformation.py): add anthropic web search 'max uses' param support
* docs(anthropic.md): add doc for web search tool calling
Closes https://github.com/BerriAI/litellm/issues/10664
* build(model_prices_and_context_window.json): add search tool pricing for anthropic
* fix: suppress linting error
* test: update tests
* fix: fix ruff check
2025-05-12 22:45:51 -07:00
fea3966d8e
refactor: rename tests
2025-05-12 22:04:55 -07:00
9658d20bc9
build(model_prices_and_context_window.json): update poetry lock
2025-05-12 21:58:15 -07:00
d37cc63250
Add new model provider Novita AI ( #7582 ) ( #9527 )
...
* Add new model provider Novita AI (#7582 )
* feat: add new model provider Novita AI
* feat: use deepseek r1 model for examples in Novita AI docs
* fix: fix tests
* fix: fix tests for novita
* fix: fix novita transformation
* ci: fix ci yaml
* fix: fix novita transformation and test (#10056 )
---------
Co-authored-by: Jason <ggbbddjm@gmail.com >
2025-05-12 21:49:30 -07:00
be9ce96a64
feat: Addded EU Anthropic Inference profile for Claude 3.7 ( #10767 )
...
Co-authored-by: wagnerjt <wagnerjt@github.com >
2025-05-12 20:55:07 -07:00
Ishaan Jaff