| .. |
|
adapters
|
fix(anthropic_adapter.py): fix sync streaming
|
2024-08-03 20:52:29 -07:00 |
|
assistants
|
|
|
|
batches
|
test batches endpoint on proxy
|
2024-07-30 09:46:30 -07:00 |
|
deprecated_litellm_server
|
|
|
|
files
|
fix linting checks
|
2024-07-30 16:55:17 -07:00 |
|
fine_tuning
|
test translating to vertex ai params
|
2024-08-03 08:44:54 -07:00 |
|
integrations
|
Merge pull request #5047 from BerriAI/litellm_log_request_response_gcs
|
2024-08-05 09:05:56 -07:00 |
|
litellm_core_utils
|
fix linting errors
|
2024-08-05 08:54:04 -07:00 |
|
llms
|
fix(ollama_chat.py): fix passing auth headers to ollama
|
2024-08-05 09:33:09 -07:00 |
|
proxy
|
set PROXY_BASE_URL when server root path set
|
2024-08-05 16:47:46 -07:00 |
|
router_strategy
|
control using enable_tag_filtering
|
2024-07-18 22:40:51 -07:00 |
|
router_utils
|
Revert "[Ui] add together AI, Mistral, PerplexityAI, OpenRouter models on Admin UI "
|
2024-07-20 19:04:22 -07:00 |
|
tests
|
fix test fine tuning api azure
|
2024-08-05 15:17:15 -07:00 |
|
types
|
feat(caching.py): enable caching on provider-specific optional params
|
2024-08-05 11:18:59 -07:00 |
|
__init__.py
|
fix(init.py): rename feature_flag
|
2024-08-05 11:23:20 -07:00 |
|
_logging.py
|
|
|
|
_redis.py
|
|
|
|
_service_logger.py
|
use common helpers for writing to otel
|
2024-07-27 11:40:39 -07:00 |
|
_version.py
|
|
|
|
budget_manager.py
|
|
|
|
caching.py
|
fix(init.py): rename feature_flag
|
2024-08-05 11:23:20 -07:00 |
|
cost_calculator.py
|
fix(cost_calculator.py): respect litellm.suppress_debug_info for cost calc
|
2024-08-01 18:07:38 -07:00 |
|
cost.json
|
|
|
|
exceptions.py
|
fix: add type hints for APIError and AnthropicError status codes
|
2024-08-01 18:07:38 -07:00 |
|
main.py
|
feat(caching.py): enable caching on provider-specific optional params
|
2024-08-05 11:18:59 -07:00 |
|
model_prices_and_context_window_backup.json
|
build(model_prices_and_context_window.json): update gpt-4o-mini max_output_tokens
|
2024-08-05 09:30:18 -07:00 |
|
py.typed
|
|
|
|
requirements.txt
|
|
|
|
router.py
|
fix(router.py): move deployment cooldown list message to error log, not client-side
|
2024-08-03 12:49:39 -07:00 |
|
scheduler.py
|
|
|
|
timeout.py
|
|
|
|
utils.py
|
feat(caching.py): enable caching on provider-specific optional params
|
2024-08-05 11:18:59 -07:00 |
