* build(model_prices_and_context_window.json): add bedrock llama4 models to model cost map
* fix template conversion for Llama 4 models in Bedrock (#10557)
* test: add testing to repro https://github.com/BerriAI/litellm/pull/10557
* test: add unit testing
* test(test_main.py): refactor where test is kept
---------
Co-authored-by: aswny <87371411+aswny@users.noreply.github.com>
* Add `litellm-proxy` CLI (#10478)
* First cut at a Python client module for proxy
* Add UnauthorizedError + add_model method
* Add delete_model method
* Add example model_id to delete_model docstring
* Make delete_model raise NotFoundError
* Add get_model
* Add get_all_model_info
* Rename models.list_models to models.list
* Rename models.get_all_model_info to models.info
* Move ModelsManagementClient.get_all_model_group_info to ModelGroupsManagementClient.info
* Rename get_model to get
* Rename add_model to new
* Rename delete_model to delete
* In client classes, rename base_url attribute to _base_url and api_key attribute to _api_key
* Add ModelsManagementClient.updae method
* Add client.chat.completions (ChatClient)
* ruff format litellm/proxy/client
* ruff format tests/litellm/proxy/client/*.py
* Add latest changes
* Rename KeysManagementClient.create to KeysManagementClient.generate
* Add new parameters to KeysManagementClient.generate
* Add CredentialsManagementClient
* Remove api_key parameter from KeysManagementClient.generate
* Fix lint errors
* Add litellm/proxy/client/README.md
* README.md: Remove api_key param to client.keys.generate
* Fix mypy errors
* First cut at litellm-proxy cli
* Add test for `litellm-proxy models list`
* Nicer get_models_info
* get_models_info: --columns option
* Use format_timestamp in list_models
* ruff format litellm/proxy/client
* Simpler JSON printing with rich.print_json
* Move models-related commands to separate file
From `cli.py` to `groups/models.py`
* Improve directory structure
* Cleanup cli/groups/models.py - esp. usage of rich
* Refactoring
* Refactor mocking in cli/test_main.py
* Dedup models commands tests
* Update poetry.lock
* Fix mypy errors
* ruff format litellm/proxy/client/cli
* ruff format tests/litellm/proxy/client/*.py
* Fix timezone issue in test_models_list_table_format
* Add cli/README.md
* Small README.md tweaks
* README.md enhancements
* Add credentials commands
* Add chat commands
* Add http commands
* ruff format litellm/proxy/client/cli
* Fix lint errors in credentials and http commands
* json => json_lib
* test-key => sk-test-key
* Mock HTTP responses so http command tests pass
* Fix mypy error in credentials.py
* bump: version 1.67.5 → 1.67.6
* build: update litellm version
* cli/main.py: show_envvar=True
* Increase test job timeout to 8 minutes
because it looks like maybe the job is getting canceled because it takes
too long with the additional tests?
This probably could be reverted once #10484 is merged, since that speeds
up pytest runs greatly.
* Add keys functionality to library/CLI
* Add info about keys commands to litellm/proxy/client/cli/README.md
* Move Model Information section in CLI README
* Make Model Information a level 4 heading
* Move rich to extras
as suggested by @ishaan-jaff
---------
Co-authored-by: Krrish Dholakia <krrishdholakia@gmail.com>
* pin rich=13.7.1
---------
Co-authored-by: Marc Abramowitz <abramowi@adobe.com>
Co-authored-by: Krrish Dholakia <krrishdholakia@gmail.com>
* fixes for generic api logger
* tests for generic api logger
* test_generic_api_callback_multiple_logs
* allow health checking generic api endpoints
* docs generic api endpoint for logging
* allow setting headers for generic api callback
* fix for test_init_custom_logger_compatible_class_as_callback
* fix linting
* fix(converse_transformation.py): handle meta llama tool call response
Fixes issue where bedrock meta llama would return tool call response as content str
* test(test_converse_transformation.py): add unit testing for new function
* fix: fix linting error
* fix: fix linting error
* fix(model_management_endpoints.py): allow team admin to update model via `/model/{model_id}/update` route
Fixes ui regression where team admin could not modify their own models
* fix(provider_specific_fields.tsx): style fix
* fix(table.tsx): allow expanding multiple rows
* fix(organization_endpoints.py): more robust check if user can give org model access
handle when user has models=["all-proxy-models"]
* fix(organization_endpoints.py): enable proxy admin with 'all-proxy-model' access to create new org with specific models
Fixes LIT-135
* fix: fix linting error
* fix: fix ui linting error
* fix(index.tsx): fix linting errors
* Support Llama-api as an LLM provider (#10451)
* init: support llama-api as a llm provider
* docs: fix endpoint url
* fix: rename meta dir to meta-llama
* docs: add meta-llama info
* fix: mv LlamaAPIConfig under chat directory
* feat: add LlamaAPIConfig in ProviderConfigManager
* fix: provider_config from ProviderConfigManager
* feat: add supports_tool_choice param
* fix: remove optional_params using model_info
* fix: rename meta-llama to meta_llama
* init: test for meta_llama
* fix: model names
---------
Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
* fix file naming convention
* fix file naming convention for meta_llama
* docs meta llama api litellm
---------
Co-authored-by: Young Han <110819238+seyeong-han@users.noreply.github.com>
Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
* feat(team_info.tsx): allow user to reassign team to another org
* style(team_info.tsx): fix org id styling
* feat(team_endpoints.py): add validation check before migrating team to another org
ensure model access, budgets and membership is respected
* fix(team_endpoints.py): update model migration validation to check if org has 'all-proxy-models' access
* fix(organization_view.tsx): show teams belonging to org
* feat(team_endpoints.py): handle wildcard model check on org migration
* fix(team_endpoints.py): nest router check
* test: update testing - use model with higher quota
* build: update poetry lock
* refactor KB implementation to use central registry
* allow passing tools when making KB calls
* test fixes
* linting fix
* fix kb tests
* QA for KB stored in DB
* fix, use litellm_credential_name when adding KB on litellm UI
* QA list endpoint vector stores
* allow using UI creds with KBs
* feat(provider_specific_fields.tsx): Use correct form instance
Fixes https://github.com/BerriAI/litellm/issues/10115
* Fix broken pagination by correctly passing page and pageSize to keyListCall (#10498)
* [Organization] Include litellm_budget_table in /organization/list response (#10488)
* join litellm_budget_table in /organization/list endpoint
* update test
---------
Co-authored-by: tanjiro <56165694+NANDINI-star@users.noreply.github.com>
* ensure vector store results are logged in SLP
* fix tests
* fix tests with vector_store_request_metadata
* fix linting
* track duration of vector store, only log content when user opts into it
* working vector store viewer
* fix custom llm provider - Vector Store Requests
* fix vector store viewer
* fix logging redacted vector searches
* testing for storing KB queries in DB
* fix slack alerting with webhooks
* emit correct event group/entity on webhooks
* refactor to use a common class of alerts with abc methods
* fixes for tests
* refactor to use a common class of alerts with abc methods
* Send a budget alert on slack or webhook
* unit test slack alerting
* fix code qa
* added tests
messages_with_counts: Made tolerance explicit for each test. But they match the new implementation(which beats the old)
* new token counter impl
* compare old and new implementation in test
* delete old token counter
* moved tests to /tests/litellm/litellm_core_utils
* use existing types
* docstrings
* warn about using default params on unknown model.
* created type for the token_counter_function
* check key == "content"
* throw error on invalid detail-type, ignore type-warning.
* fix imports
* fix(vertex_and_google_ai_studio.py): fix finish reason to be 'tool_calls' when tool call returned
Vertex returns 'Stop', openai format is 'tool calls'
* test(base_llm_unit_tests.py): bump test to assert tool calls in finish reason
* Update docs for OpenAI compatible providers, add Llamafile docs, include Llamafile in the sidebar
* Add Llamafile as an LlmProviders enum
* Add llamafile as a OpenAI compatible provider (in the list of compatible providers)
* Add Llamafile chat config and tests
* Wire up Llamafile
Co-authored-by: Peter Wilson <peter@mozilla.ai>
* fix(exception_mapping_utils.py): correctly pass through 504 status code
openai also raises a 504 status code
* build(model_prices_and_context_window.json): add gpt-4o-mini-tts to model cost map
Fixes https://github.com/BerriAI/litellm/issues/9591
* fix(cost_calculator.py): fix input cost calculation for gpt-4o-mini-tts
Fixes https://github.com/BerriAI/litellm/issues/9591
* test: testing updates
The client provides access to a low-level HTTP client for making direct
requests to the LiteLLM proxy server. This is useful when you need more
control or when working with endpoints that don't yet have a high-level
interface.
```python
In [2]: client.http.request(
...: method="POST",
...: uri="/health/test_connection",
...: json={
...: "litellm_params": {
...: "model": "gpt-4",
...: "custom_llm_provider": "azure_ai",
...: "litellm_credential_name": None,
...: "api_key": "6xxxxxxx",
...: "api_base": "https://litellm8397336933...",
...: },
...: "mode": "chat",
...: },
...: )
Out[2]:
{'status': 'error',
'result': {'model': 'gpt-4',
'custom_llm_provider': 'azure_ai',
'litellm_credential_name': None,
'api_base': 'https://litellm8397336933...',
...
```
* init vector store configs
* working kb init
* add vector store endpoints
* use litellm_credential_name
* working CRUD vector stores litellm
* working creds with vector DB
* ui cleanup
* clean up vector store id
* fix delete button
* refactored vector store component
* working selector for KBs
* ui vector stores
* add vector store tool calls usage on chat ui
* fixes for vector stores litellm
* test fix
* docs Knowledge Bases
* fixes for vector stores litellm
* fix linting
* add managed vectorstores
* fix orjson ci/cd test
* fix linting
* add types.tsx file
* fix: initial commit of v2 parallel request limiter hook
enables multi-instance rate limiting to work
* fix: subsequent commit with additional refactors
* fix(parallel_request_limiter_v2.py): cleanup initial call hook
simplify it
* fix(parallel_request_limiter_v2.py): working v2 parallel request limiter
* fix: more updates - still not passing testing
* fix(test_parallel_request_limiter_v2.py): update test + add conftest
* fix: fix ruff checks
* fix(parallel_request_limiter_v2.py): use pull via pattern method to load in keys instance wouldn't have seen yet
Fixes issue where redis syncing was not pulling key until instance had seen it
* test: update testing to cover tpm and rpm
* fix(parallel_request_limiter_v2.py): fix ruff errors
* fix(proxy/hooks/__init__.py): feature flag export
* fix(proxy/hooks/__init_.py): fix linting error
* ci(config.yml): add tests/enterprise to ci/cd
* fix: fix ruff check
* test: update testing
* build(model_prices_and_context_window.json): add fireworks ai new 0-4b pricing tier
* build(model_prices_and_context_window.json): add more fireworks ai models
* test: update testing
* fix(caching_handler.py): handle str + list cache
Fixes issue on cache hits for embedding when initial cached input was str
* test(test_caching.py): add e2e test on caching with individual item and then list
* fix(caching_handler.py): set usage tokens for cache hits
enables token counting to work
* fix(caching_handler.py): combine usage between cached result and embedding response
Handles case of new input to embedding response
* fix: cleanup
* test: move to gpt-4o-new-test
* test: update test
* Schedule budget resets at expectable times (#10331)
* Enhance budget reset functionality with timezone support and standardized reset times
- Added `get_next_standardized_reset_time` function to calculate budget reset times based on specified durations and timezones.
- Introduced `timezone_utils.py` to manage timezone retrieval and budget reset time calculations.
- Updated budget reset logic in `reset_budget_job.py`, `internal_user_endpoints.py`, `key_management_endpoints.py`, and `team_endpoints.py` to utilize the new timezone-aware reset time calculations.
- Added unit tests for the new reset time functionality in `test_duration_parser.py`.
- Updated `.gitignore` to include `test.py` and made minor formatting adjustments in `docker-compose.yml` for consistency.
* Fixed linting
* Fix for mypy
* Fixed testcase for reset
* fix(duration_parser.py): move off zoneinfo - doesn't work with python 3.8
* test: update test
* refactor: improve budget reset time calculation and update related tests for accuracy
* clean up imports in team_endpoints.py
* test: update budget remaining hours assertions to reflect new reset time logic
* build(model_prices_and_context_window.json): update model
---------
Co-authored-by: Prathamesh Saraf <pratamesh1867@gmail.com>
Krish Dholakia