* fix(triton/completion/transformation.py): remove bad_words / stop words from triton call
parameter 'bad_words' has invalid type. It should be either 'int', 'bool', or 'string'.
* fix(proxy_track_cost_callback.py): add debug logging for track cost callback error
* fix(model_info_view.tsx): cleanup text
* fix(key_management_endpoints.py): fix filtering litellm-dashboard keys for internal users
* fix(proxy_track_cost_callback.py): prevent flooding spend logs with admin endpoint errors
* test: add unit testing for logic
* test(test_auth_exception_handler.py): add more unit testing
* fix(router.py): correctly handle retrieving model info on get_model_group_info
fixes issue where model hub was showing None prices
* fix: fix linting errors
* fix(openai.py): ensure openai file object shows up on logs
* fix(managed_files.py): return unified file id as b64 str
allows retrieve file id to work as expected
* fix(managed_files.py): apply decoded file id transformation
* fix: add unit test for file id + decode logic
* fix: initial commit for litellm_proxy support with CRUD Endpoints
* fix(managed_files.py): support retrieve file operation
* fix(managed_files.py): support for DELETE endpoint for files
* fix(managed_files.py): retrieve file content support
supports retrieve file content api from openai
* fix: fix linting error
* test: update tests
* fix: fix linting error
* feat(managed_files.py): support reading / writing files in DB
* feat(managed_files.py): support deleting file from DB on delete
* test: update testing
* fix(spend_tracking_utils.py): ensure each file create request is logged correctly
* fix(managed_files.py): fix storing / returning managed file object from cache
* fix(files/main.py): pass litellm params to azure route
* test: fix test
* build: add new prisma migration
* build: bump requirements
* test: add more testing
* refactor: cleanup post merge w/ main
* fix: fix code qa errors
* fix(openai.py): ensure openai file object shows up on logs
* fix(managed_files.py): return unified file id as b64 str
allows retrieve file id to work as expected
* fix(managed_files.py): apply decoded file id transformation
* fix: add unit test for file id + decode logic
* fix: initial commit for litellm_proxy support with CRUD Endpoints
* fix(managed_files.py): support retrieve file operation
* fix(managed_files.py): support for DELETE endpoint for files
* fix(managed_files.py): retrieve file content support
supports retrieve file content api from openai
* fix: fix linting error
* test: update tests
* fix: fix linting error
* fix(files/main.py): pass litellm params to azure route
* test: fix test
* feat(managed_files.py): encode file type in unified file id
simplify calling gemini models
* fix(common_utils.py): fix extracting file type from unified file id
* fix(litellm_logging.py): create standard logging payload for create file call
* fix: fix linting error
* Add date picker to usage tab + Add reasoning_content token tracking across all providers on streaming (#9722)
* feat(new_usage.tsx): add date picker for new usage tab
allow user to look back on their usage data
* feat(anthropic/chat/transformation.py): report reasoning tokens in completion token details
allows usage tracking on how many reasoning tokens are actually being used
* feat(streaming_chunk_builder.py): return reasoning_tokens in anthropic/openai streaming response
allows tracking reasoning_token usage across providers
* Fix update team metadata + fix bulk adding models on Ui (#9721)
* fix(handle_add_model_submit.tsx): fix bulk adding models
* fix(team_info.tsx): fix team metadata update
Fixes https://github.com/BerriAI/litellm/issues/9689
* (v0) Unified file id - allow calling multiple providers with same file id (#9718)
* feat(files_endpoints.py): initial commit adding 'target_model_names' support
allow developer to specify all the models they want to call with the file
* feat(files_endpoints.py): return unified files endpoint
* test(test_files_endpoints.py): add validation test - if invalid purpose submitted
* feat: more updates
* feat: initial working commit of unified file id translation
* fix: additional fixes
* fix(router.py): remove model replace logic in jsonl on acreate_file
enables file upload to work for chat completion requests as well
* fix(files_endpoints.py): remove whitespace around model name
* fix(azure/handler.py): return acreate_file with correct response type
* fix: fix linting errors
* test: fix mock test to run on github actions
* fix: fix ruff errors
* fix: fix file too large error
* fix(utils.py): remove redundant var
* test: modify test to work on github actions
* test: update tests
* test: more debug logs to understand ci/cd issue
* test: fix test for respx
* test: skip mock respx test
fails on ci/cd - not clear why
* fix: fix ruff check
* fix: fix test
* fix(model_connection_test.tsx): fix linting error
* test: update unit tests
* build(pyproject.toml): add new dev dependencies - for type checking
* build: reformat files to fit black
* ci: reformat to fit black
* ci(test-litellm.yml): make tests run clear
* build(pyproject.toml): add ruff
* fix: fix ruff checks
* build(mypy/): fix mypy linting errors
* fix(hashicorp_secret_manager.py): fix passing cert for tls auth
* build(mypy/): resolve all mypy errors
* test: update test
* fix: fix black formatting
* build(pre-commit-config.yaml): use poetry run black
* fix(proxy_server.py): fix linting error
* fix: fix ruff safe representation error
* fix test_moderations_bad_model
* use async_post_call_failure_hook
* basic logging errors in DB
* show status on ui
* show status on ui
* ui show request / response side by side
* stash fixes
* working, track raw request
* track error info in metadata
* fix showing error / request / response logs
* show traceback on error viewer
* ui with traceback of error
* fix async_post_call_failure_hook
* fix(http_parsing_utils.py): orjson can throw errors on some emoji's in text, default to json.loads
* test_get_error_information
* fix code quality
* rename proxy track cost callback test
* _should_store_errors_in_spend_logs
* feature flag error logs
* Revert "_should_store_errors_in_spend_logs"
This reverts commit 7f345df477.
* Revert "feature flag error logs"
This reverts commit 0e90c022bb.
* test_spend_logs_payload
* fix OTEL log_db_metrics
* fix import json
* fix ui linting error
* test_async_post_call_failure_hook
* test_chat_completion_bad_model_with_spend_logs
---------
Co-authored-by: Krrish Dholakia <krrishdholakia@gmail.com>
* fix(parallel_request_limiter.py): improve single instance rate limiting by updating in-memory cache instantly
Fixes issue where parallel request limiter had a leak
* fix(parallel_request_limiter.py): fix parallel request limiter to not decrement val on max limit being reached
* test(test_parallel_request_limiter.py): fix test
* test: fix test
* fix(parallel_request_limiter.py): move to using common enum
* test: fix test
* fix(parallel_request_limiter.py): add back parallel request information to max parallel request limiter
Resolves https://github.com/BerriAI/litellm/issues/8392
* test: mark flaky test to handle time based tracking issues
* feat(model_management_endpoints.py): expose new patch `/model/{model_id}/update` endpoint
Allows updating specific values of a model in db - makes it easy for admin to know this by calling it a PA
TCH
* feat(edit_model_modal.tsx): allow user to update llm provider + api key on the ui
* fix: fix linting error
* fix(factory.py): fix bedrock document url check
Make check more generic - if starts with 'text' or 'application' assume it's a document and let it go through
Fixes https://github.com/BerriAI/litellm/issues/7746
* feat(key_management_endpoints.py): support writing new key alias to aws secret manager - on key rotation
adds rotation endpoint to aws key management hook - allows for rotated litellm virtual keys with new key alias to be written to it
* feat(key_management_event_hooks.py): support rotating keys and updating secret manager
* refactor(base_secret_manager.py): support rotate secret at the base level
since it's just an abstraction function, it's easy to implement at the base manager level
* style: cleanup unused imports
* feat(key_management_endpoints.py): allow deleting keys based on key alias
easier for proxy admin to delete known bad key
* fix(key_management_event_hooks.py): fix linting error
* docs(key_management_endpoints.py): document new key_aliases param
* fix(key_management_endpoints.py): return deleted keys to user
fixes return when passing key aliases
* feat(proxy/utils.py): get associated litellm budget from db in combined_view for key
allows user to create rate limit tiers and associate those to keys
* feat(proxy/_types.py): update the value of key-level tpm/rpm/model max budget metrics with the associated budget table values if set
allows rate limit tiers to be easily applied to keys
* docs(rate_limit_tiers.md): add doc on setting rate limit / budget tiers
make feature discoverable
* feat(key_management_endpoints.py): return litellm_budget_table value in key generate
make it easy for user to know associated budget on key creation
* fix(key_management_endpoints.py): document 'budget_id' param in `/key/generate`
* docs(key_management_endpoints.py): document budget_id usage
* refactor(budget_management_endpoints.py): refactor budget endpoints into separate file - makes it easier to run documentation testing against it
* docs(test_api_docs.py): add budget endpoints to ci/cd doc test + add missing param info to docs
* fix(customer_endpoints.py): use new pydantic obj name
* docs(user_management_heirarchy.md): add simple doc explaining teams/keys/org/users on litellm
* Litellm dev 12 26 2024 p2 (#7432)
* (Feat) Add logging for `POST v1/fine_tuning/jobs` (#7426)
* init commit ft jobs logging
* add ft logging
* add logging for FineTuningJob
* simple FT Job create test
* (docs) - show all supported Azure OpenAI endpoints in overview (#7428)
* azure batches
* update doc
* docs azure endpoints
* docs endpoints on azure
* docs azure batches api
* docs azure batches api
* fix(key_management_endpoints.py): fix key update to actually work
* test(test_key_management.py): add e2e test asserting ui key update call works
* fix: proxy/_types - fix linting erros
* test: update test
---------
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
* fix: test
* fix(parallel_request_limiter.py): enforce tpm/rpm limits on key from tiers
* fix: fix linting errors
* test: fix test
* fix: remove unused import
* test: update test
* docs(customer_endpoints.py): document new model_max_budget param
* test: specify unique key alias
* docs(budget_management_endpoints.py): document new model_max_budget param
* test: fix test
* test: fix tests
---------
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
* fix(proxy_track_cost_callback.py): log to db if only end user param given
* fix: allows for jwt-auth based end user id spend tracking to work
* fix(utils.py): fix 'get_end_user_id_for_cost_tracking' to use 'user_api_key_end_user_id'
more stable - works with jwt-auth based end user tracking as well
* test(test_jwt.py): add e2e unit test to confirm end user cost tracking works for spend logs
* test: update test to use end_user api key hash param
* fix(langfuse.py): support end user cost tracking via jwt auth + langfuse
logs end user to langfuse if decoded from jwt token
* fix: fix linting errors
* test: fix test
* test: fix test
* fix: fix end user id extraction
* fix: run test earlier
* fix(edit_budget_modal.tsx): call `/budget/update` endpoint instead of `/budget/new`
allows updating existing budget on ui
* fix(user_api_key_auth.py): support cost tracking for end user via jwt field
* fix(presidio.py): support pii masking on sync logging callbacks
enables masking before logging to langfuse
* feat(utils.py): support retry policy logic inside '.completion()'
Fixes https://github.com/BerriAI/litellm/issues/6623
* fix(utils.py): support retry by retry policy on async logic as well
* fix(handle_jwt.py): set leeway default leeway value
* test: fix test to handle jwt audience claim
* add SecretManager to httpxSpecialProvider
* fix importing AWSSecretsManagerV2
* add unit testing for writing keys to AWS secret manager
* use KeyManagementEventHooks for key/generated events
* us event hooks for key management endpoints
* working AWSSecretsManagerV2
* fix write secret to AWS secret manager on /key/generate
* fix KeyManagementSettings
* use tasks for key management hooks
* add async_delete_secret
* add test for async_delete_secret
* use _delete_virtual_keys_from_secret_manager
* fix test secret manager
* test_key_generate_with_secret_manager_call
* fix check for key_management_settings
* sync_read_secret
* test_aws_secret_manager
* fix sync_read_secret
* use helper to check when _should_read_secret_from_secret_manager
* test_get_secret_with_access_mode
* test - handle eol model claude-2, use claude-2.1 instead
* docs AWS secret manager
* fix test_read_nonexistent_secret
* fix test_supports_response_schema
* ci/cd run again
* fix(dual_cache.py): update in-memory check for redis batch get cache
Fixes latency delay for async_batch_redis_cache
* fix(service_logger.py): fix race condition causing otel service logging to be overwritten if service_callbacks set
* feat(user_api_key_auth.py): add parent otel component for auth
allows us to isolate how much latency is added by auth checks
* perf(parallel_request_limiter.py): move async_set_cache_pipeline (from max parallel request limiter) out of execution path (background task)
reduces latency by 200ms
* feat(user_api_key_auth.py): have user api key auth object return user tpm/rpm limits - reduces redis calls in downstream task (parallel_request_limiter)
Reduces latency by 400-800ms
* fix(parallel_request_limiter.py): use batch get cache to reduce user/key/team usage object calls
reduces latency by 50-100ms
* fix: fix linting error
* fix(_service_logger.py): fix import
* fix(user_api_key_auth.py): fix service logging
* fix(dual_cache.py): don't pass 'self'
* fix: fix python3.8 error
* fix: fix init]
* docs(exception_mapping.md): add missing exception types
Fixes https://github.com/Aider-AI/aider/issues/2120#issuecomment-2438971183
* fix(main.py): register custom model pricing with specific key
Ensure custom model pricing is registered to the specific model+provider key combination
* test: make testing more robust for custom pricing
* fix(redis_cache.py): instrument otel logging for sync redis calls
ensures complete coverage for all redis cache calls
* refactor: pass parent_otel_span for redis caching calls in router
allows for more observability into what calls are causing latency issues
* test: update tests with new params
* refactor: ensure e2e otel tracing for router
* refactor(router.py): add more otel tracing acrosss router
catch all latency issues for router requests
* fix: fix linting error
* fix(router.py): fix linting error
* fix: fix test
* test: fix tests
* fix(dual_cache.py): pass ttl to redis cache
* fix: fix param
