| .. |
|
adapters
|
feat(proxy_server.py): working /v1/messages endpoint
|
2024-07-10 18:15:38 -07:00 |
|
assistants
|
add async assistants delete support
|
2024-07-10 11:14:40 -07:00 |
|
batches
|
test batches endpoint on proxy
|
2024-07-30 09:46:30 -07:00 |
|
deprecated_litellm_server
|
|
|
|
files
|
fix(files/main.py): fix linting error
|
2024-07-19 15:50:25 -07:00 |
|
fine_tuning
|
fix type errors
|
2024-07-29 20:10:03 -07:00 |
|
integrations
|
log output from /audio on langfuse
|
2024-07-29 08:21:22 -07:00 |
|
litellm_core_utils
|
fix(utils.py): fix cost tracking for vertex ai partner models
|
2024-07-30 14:20:52 -07:00 |
|
llms
|
fix(ollama.py): correctly raise ollama streaming error
|
2024-07-30 15:01:26 -07:00 |
|
proxy
|
Merge pull request #4975 from BerriAI/ui_switch_off_console_logs_in_prod
|
2024-07-30 13:34:59 -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
|
test(test_streaming.py): handle predibase instability
|
2024-07-30 15:32:36 -07:00 |
|
types
|
fix type errors
|
2024-07-29 20:10:03 -07:00 |
|
__init__.py
|
add create_fine_tuning
|
2024-07-29 18:57:29 -07:00 |
|
_logging.py
|
fix(_logging.py): fix timestamp format for json logs
|
2024-06-20 15:20:21 -07:00 |
|
_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(caching.py): support /completion caching by default
|
2024-07-29 08:19:30 -07:00 |
|
cost.json
|
|
|
|
cost_calculator.py
|
feat(databricks.py): support vertex mistral cost tracking
|
2024-07-27 20:22:35 -07:00 |
|
exceptions.py
|
fix(utils.py): correctly re-raise azure api connection error
|
2024-07-29 12:28:25 -07:00 |
|
main.py
|
docs(main.py): update acompletion_with_retries docstring
|
2024-07-29 15:50:12 -07:00 |
|
model_prices_and_context_window_backup.json
|
build(model_prices_and_context_window.json): update model info for llama3.1 on bedrock - supports tool calling, not tool choice
|
2024-07-29 15:43:16 -07:00 |
|
py.typed
|
feature - Types for mypy - #360
|
2024-05-30 14:14:41 -04:00 |
|
requirements.txt
|
|
|
|
router.py
|
fix(router.py): gracefully handle scenario where completion response doesn't have total tokens
|
2024-07-30 15:14:03 -07:00 |
|
scheduler.py
|
feat(scheduler.py): support redis caching for req. prioritization
|
2024-06-06 14:19:21 -07:00 |
|
timeout.py
|
|
|
|
utils.py
|
fix(utils.py): fix cost tracking for vertex ai partner models
|
2024-07-30 14:20:52 -07:00 |
