| .. |
|
assistants
|
feat(assistants/main.py): support arun_thread_stream
|
2024-06-04 16:47:51 -07:00 |
|
batches
|
docs(customers.md): add customer cost tracking to docs
|
2024-05-29 14:55:33 -07:00 |
|
deprecated_litellm_server
|
refactor: add black formatting
|
2023-12-25 14:11:20 +05:30 |
|
integrations
|
fix(slack_alerting.py): use in-memory cache for checking request status
|
2024-07-02 13:01:59 -07:00 |
|
litellm_core_utils
|
fix(core_helpers.py): map vertex ai 'RECITATION' finish reason to 'content_filter'
|
2024-07-01 12:48:56 -07:00 |
|
llms
|
refactor(azure.py): refactor sync azure calls to httpx
|
2024-07-02 17:06:48 -07:00 |
|
proxy
|
Merge branch 'main' into litellm_support_dynamic_rpm_limiting
|
2024-07-02 17:51:18 -07:00 |
|
router_strategy
|
refactor: replace 'traceback.print_exc()' with logging library
|
2024-06-06 13:47:43 -07:00 |
|
router_utils
|
fix use safe access for router alerting
|
2024-06-14 15:17:32 -07:00 |
|
tests
|
Merge branch 'main' into litellm_support_dynamic_rpm_limiting
|
2024-07-02 17:51:18 -07:00 |
|
types
|
refactor(azure.py): replaces the custom transport logic for just using our httpx client
|
2024-07-02 15:32:53 -07:00 |
|
__init__.py
|
Merge branch 'main' into litellm_support_dynamic_rpm_limiting
|
2024-07-02 17:51:18 -07:00 |
|
_logging.py
|
fix(_logging.py): fix timestamp format for json logs
|
2024-06-20 15:20:21 -07:00 |
|
_redis.py
|
feat(proxy_server.py): return litellm version in response headers
|
2024-05-08 16:00:08 -07:00 |
|
_service_logger.py
|
feat(dynamic_rate_limiter.py): update cache with active project
|
2024-06-21 20:25:40 -07:00 |
|
_version.py
|
(fix) ci/cd don't let importing litellm._version block starting proxy
|
2024-02-01 16:23:16 -08:00 |
|
budget_manager.py
|
feat(proxy_server.py): return litellm version in response headers
|
2024-05-08 16:00:08 -07:00 |
|
caching.py
|
remove debug print statement
|
2024-06-27 20:58:29 -07:00 |
|
cost.json
|
store llm costs in budget manager
|
2023-09-09 19:11:35 -07:00 |
|
cost_calculator.py
|
fix(cost_calculator.py): handle unexpected error in cost_calculator.py
|
2024-06-28 14:53:00 -07:00 |
|
exceptions.py
|
fix(utils.py): support json schema validation
|
2024-06-29 15:05:52 -07:00 |
|
main.py
|
Merge pull request #4519 from BerriAI/litellm_re_use_openai_azure_clients_whisper
|
2024-07-02 16:42:22 -07:00 |
|
model_prices_and_context_window_backup.json
|
feat(vertex_httpx.py): support the 'response_schema' param for older vertex ai models - pass as prompt (user-controlled)
|
2024-06-29 13:25:27 -07:00 |
|
py.typed
|
feature - Types for mypy - #360
|
2024-05-30 14:14:41 -04:00 |
|
requirements.txt
|
Add symlink and only copy in source dir to stay under 50MB compressed limit for Lambdas.
|
2023-11-22 23:07:33 -05:00 |
|
router.py
|
Merge branch 'main' into litellm_support_dynamic_rpm_limiting
|
2024-07-02 17:51:18 -07:00 |
|
scheduler.py
|
feat(scheduler.py): support redis caching for req. prioritization
|
2024-06-06 14:19:21 -07:00 |
|
timeout.py
|
refactor: add black formatting
|
2023-12-25 14:11:20 +05:30 |
|
utils.py
|
refactor(azure.py): replaces the custom transport logic for just using our httpx client
|
2024-07-02 15:32:53 -07:00 |
