litellm-mirror/litellm
Krish Dholakia 4d89da9c97 Deepseek r1 support + watsonx qa improvements (#7907)
* fix(types/utils.py): support returning 'reasoning_content' for deepseek models

Fixes https://github.com/BerriAI/litellm/issues/7877#issuecomment-2603813218

* fix(convert_dict_to_response.py): return deepseek response in provider_specific_field

allows for separating openai vs. non-openai params in model response

* fix(utils.py): support 'provider_specific_field' in delta chunk as well

allows deepseek reasoning content chunk to be returned to user from stream as well

Fixes https://github.com/BerriAI/litellm/issues/7877#issuecomment-2603813218

* fix(watsonx/chat/handler.py): fix passing space id to watsonx on chat route

* fix(watsonx/): fix watsonx_text/ route with space id

* fix(watsonx/): qa item - also adds better unit testing for watsonx embedding calls

* fix(utils.py): rename to '..fields'

* fix: fix linting errors

* fix(utils.py): fix typing - don't show provider-specific field if none or empty - prevents default respons
e from being non-oai compatible

* fix: cleanup unused imports

* docs(deepseek.md): add docs for deepseek reasoning model
2025-01-21 23:13:15 -08:00
..
adapters (code quality) run ruff rule to ban unused imports (#7313) 2024-12-19 12:33:42 -08:00
assistants Revert "fix: add missing parameters order, limit, before, and after in get_as…" (#7542) 2025-01-03 16:32:12 -08:00
batch_completion (code quality) run ruff rule to ban unused imports (#7313) 2024-12-19 12:33:42 -08:00
batches (Feat - Batches API) add support for retrieving vertex api batch jobs (#7661) 2025-01-09 18:35:03 -08:00
caching (litellm SDK perf improvements) - handle cases when unable to lookup model in model cost map (#7750) 2025-01-13 19:58:46 -08:00
files (code quality) run ruff rule to ban unused imports (#7313) 2024-12-19 12:33:42 -08:00
fine_tuning (feat) POST /fine_tuning/jobs support passing vertex specific hyper params (#7490) 2025-01-01 07:44:48 -08:00
integrations fix litellm_overhead_latency_metric 2025-01-21 21:33:31 -08:00
litellm_core_utils Deepseek r1 support + watsonx qa improvements (#7907) 2025-01-21 23:13:15 -08:00
llms Deepseek r1 support + watsonx qa improvements (#7907) 2025-01-21 23:13:15 -08:00
proxy Deepseek r1 support + watsonx qa improvements (#7907) 2025-01-21 23:13:15 -08:00
realtime_api (Refactor) - Re use litellm.completion/litellm.embedding etc for health checks (#7455) 2024-12-28 18:38:54 -08:00
rerank_api (feat) /batches - track user_api_key_alias, user_api_key_team_alias etc for /batch requests (#7401) 2024-12-24 17:44:28 -08:00
router_strategy Litellm dev 12 26 2024 p4 (#7439) 2024-12-27 12:01:42 -08:00
router_utils Improve Proxy Resiliency: Cooldown single-deployment model groups if 100% calls failed in high traffic (#7823) 2025-01-17 20:17:02 -08:00
secret_managers fix: add default credential for azure (#7095) (#7891) 2025-01-21 09:01:49 -08:00
types Deepseek r1 support + watsonx qa improvements (#7907) 2025-01-21 23:13:15 -08:00
__init__.py Litellm dev 01 21 2025 p1 (#7898) 2025-01-21 20:36:11 -08:00
_logging.py (sdk perf fix) - only print args passed to litellm when debugging mode is on (#7708) 2025-01-11 22:56:20 -08:00
_redis.py (code quality) run ruff rule to ban unused imports (#7313) 2024-12-19 12:33:42 -08:00
_service_logger.py fix svc logger (#7727) 2025-01-12 22:00:25 -08:00
_version.py Litellm ruff linting enforcement (#5992) 2024-10-01 19:44:20 -04:00
budget_manager.py (code quality) run ruff rule to ban unused imports (#7313) 2024-12-19 12:33:42 -08:00
constants.py feat(health_check.py): set upperbound for api when making health check call (#7865) 2025-01-18 19:47:43 -08:00
cost.json
cost_calculator.py fixes for img gen cost cal 2025-01-12 16:41:18 -08:00
exceptions.py LiteLLM Minor Fixes & Improvements (12/27/2024) - p1 (#7448) 2024-12-27 19:04:39 -08:00
main.py Litellm dev 01 21 2025 p1 (#7898) 2025-01-21 20:36:11 -08:00
model_prices_and_context_window_backup.json feat: add new together_ai models (#7882) 2025-01-20 14:16:04 -08:00
py.typed feature - Types for mypy - #360 2024-05-30 14:14:41 -04:00
router.py Litellm dev 01 20 2025 p3 (#7890) 2025-01-20 21:46:36 -08:00
scheduler.py (refactor) caching use LLMCachingHandler for async_get_cache and set_cache (#6208) 2024-10-14 16:34:01 +05:30
timeout.py Litellm ruff linting enforcement (#5992) 2024-10-01 19:44:20 -04:00
utils.py Litellm dev 01 21 2025 p1 (#7898) 2025-01-21 20:36:11 -08:00