| .. |
|
anthropic_interface
|
|
|
|
assistants
|
|
|
|
batch_completion
|
|
|
|
batches
|
[Feat] Batches - Add bedrock retrieve endpoint support (#14618)
|
2025-09-16 19:19:02 -07:00 |
|
caching
|
[Memory Leak Fix] Fix InMemoryCache unbounded growth when TTLs are set (#14869)
|
2025-09-24 11:54:06 -07:00 |
|
completion_extras
|
fix: fix import errors
|
2025-09-14 09:32:21 -07:00 |
|
endpoints/speech/speech_to_completion_bridge
|
fix: fix import errors
|
2025-09-14 09:32:21 -07:00 |
|
experimental_mcp_client
|
fix(mcp/): pass oauth2 headers on call tools
|
2025-09-27 09:02:08 -07:00 |
|
files
|
Litellm gemini batch (#14733)
|
2025-09-19 15:22:52 -07:00 |
|
fine_tuning
|
|
|
|
google_genai
|
Litellm gemini cli bug fix (#14451)
|
2025-09-12 11:55:26 -07:00 |
|
images
|
fix(main.py): remove image edit optional param from image generation
|
2025-09-06 11:24:25 -07:00 |
|
integrations
|
Merge branch 'BerriAI:main' into LangfuseUsageDetails
|
2025-09-19 13:54:56 -04:00 |
|
litellm_core_utils
|
Fix: make pondpond as optional dependency for proxy extras, disable object pooling gracefully (#14863)
|
2025-09-24 17:09:30 -07:00 |
|
llms
|
Merge pull request #14816 from leventov/no-streaming-logging
|
2025-09-23 22:53:18 -07:00 |
|
passthrough
|
test fix location of encode bedrock runtime modelid arn
|
2025-08-22 17:34:09 -07:00 |
|
proxy
|
fix: fix ruff check
|
2025-09-27 09:34:01 -07:00 |
|
realtime_api
|
[LLM Translation] Fix Realtime API endpoint for no intent (#13476)
|
2025-08-14 16:24:14 -07:00 |
|
rerank_api
|
Add rerank endpoint support for deepinfra
|
2025-08-20 23:36:05 +05:30 |
|
responses
|
Merge pull request #14675 from tcx4c70/fix/response-price
|
2025-09-18 23:41:08 -07:00 |
|
router_strategy
|
fix: test
|
2025-09-19 16:35:00 -07:00 |
|
router_utils
|
fix: fix import errors
|
2025-09-14 09:32:21 -07:00 |
|
secret_managers
|
[Security] Fix: Ensure .info() logs are not used for request/responses + Add code QA check for possible violations (#14386)
|
2025-09-09 13:55:56 -07:00 |
|
types
|
feat: initial commit for v2 oauth flow
|
2025-09-26 15:25:42 -07:00 |
|
vector_stores
|
[Bug Fix] Bedrock KB - Using LiteLLM Managed Credentials for Query (#13787)
|
2025-08-19 15:39:36 -07:00 |
|
__init__.py
|
[Fix] Priority Reservation: keys without priority metadata receive higher priority than keys with explicit priority configurations. (#14832)
|
2025-09-23 15:45:05 -07:00 |
|
_logging.py
|
[Feat] Add support for returning images with gemini/gemini-2.5-flash-image-preview with /chat/completions (#13983)
|
2025-08-27 16:16:19 -07:00 |
|
_redis.py
|
[Security] Fix: Ensure .info() logs are not used for request/responses + Add code QA check for possible violations (#14386)
|
2025-09-09 13:55:56 -07:00 |
|
_service_logger.py
|
|
|
|
_uuid.py
|
fastuuid optional dependency
|
2025-09-23 23:55:14 +09:00 |
|
_version.py
|
|
|
|
budget_manager.py
|
|
|
|
constants.py
|
feat: New model - Add support for Qwen models family & Deepseek 3.1 to Amazon Bedrock (#14845)
|
2025-09-24 09:58:23 -07:00 |
|
cost_calculator.py
|
Revert "Merge pull request #14797 from BerriAI/litellm_anthopic_token_count_issue"
|
2025-09-23 12:31:02 -07:00 |
|
cost.json
|
|
|
|
exceptions.py
|
[Bug fix] Misclassified 500 error on invalid image_url in /chat/completions request (#14149)
|
2025-09-01 15:26:27 -07:00 |
|
main.py
|
Merge pull request #14721 from dharamendrak/reuse-aiohttp-session-http-handler
|
2025-09-23 18:07:32 -07:00 |
|
model_prices_and_context_window_backup.json
|
fix ci/cd
|
2025-09-24 11:55:34 -07:00 |
|
mypy.ini
|
|
|
|
py.typed
|
|
|
|
router.py
|
Merge branch 'litellm_contributor_prs_09_18_2025_p2' into litellm_dev_09_17_2025_p2_v2
|
2025-09-18 19:50:55 -07:00 |
|
scheduler.py
|
|
|
|
timeout.py
|
|
|
|
utils.py
|
Merge branch 'main' into akshoop/fastuuid-dep-make-optional
|
2025-09-24 10:31:09 +09:00 |
