phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 03:04:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
litellm-mirror/litellm/llms
History
Krish Dholakia 2488e4b45f
Cost tracking improvements (#5828) 
* feat(litellm_logging.py): update standard logging payload to include debug information for cost failures

Also includes fixes for cohere rerank cost tracking + databricks llama2 model cost tracking

 Easier to repro cost failures and improve reliability in prod

* fix(proxy_server.py): emit cost failure debug info for slack alerting

Improves debug information for cost tracking failures, on slack alerting
2024-09-21 21:47:50 -07:00
..
AI21 [Feat] Add max_completion_tokens param (#5691) 2024-09-14 14:57:01 -07:00
anthropic [Feat] Add max_completion_tokens param (#5691) 2024-09-14 14:57:01 -07:00
azure_ai LiteLLM Minor Fixes & Improvements (09/17/2024) (#5742) 2024-09-17 23:00:04 -07:00
AzureOpenAI LiteLLM Minor Fixes & Improvements (09/21/2024) (#5819) 2024-09-21 18:51:53 -07:00
bedrock fix use converse for all llama3 models (#5729) 2024-09-19 09:31:52 -07:00
cerebras [Feat] Add max_completion_tokens param (#5691) 2024-09-14 14:57:01 -07:00
cohere LiteLLM Minor Fixes & Improvements (09/19/2024) (#5793) 2024-09-20 08:19:52 -07:00
custom_httpx LiteLLM Minor Fixes & Improvements (09/18/2024) (#5772) 2024-09-19 13:25:29 -07:00
databricks Cost tracking improvements (#5828) 2024-09-21 21:47:50 -07:00
files_apis feat(batches): add azure openai batches endpoint support 2024-08-22 14:46:51 -07:00
fine_tuning_apis fix case when gemini is used 2024-09-10 17:06:45 -07:00
fireworks_ai [Feat] Add fireworks AI embedding (#5812) 2024-09-20 22:23:28 -07:00
huggingface_llms_metadata add hf tgi and conversational models 2023-09-27 15:56:45 -07:00
mistral LiteLLM Minor Fixes and Improvements (09/13/2024) (#5689) 2024-09-14 10:02:55 -07:00
OpenAI LiteLLM Minor Fixes & Improvements (09/21/2024) (#5819) 2024-09-21 18:51:53 -07:00
prompt_templates LiteLLM Minor Fixes & Improvements (09/18/2024) (#5772) 2024-09-19 13:25:29 -07:00
sagemaker pass llm provider when creating async httpx clients 2024-09-10 11:51:42 -07:00
sambanova sambanova support (#5547) (#5703) 2024-09-14 17:23:04 -07:00
togetherai pass llm provider when creating async httpx clients 2024-09-10 11:51:42 -07:00
tokenizers feat(utils.py): bump tiktoken dependency to 0.7.0 2024-06-10 21:21:23 -07:00
vertex_ai_and_google_ai_studio LiteLLM Minor Fixes & Improvements (09/20/2024) (#5807) 2024-09-20 20:21:32 -07:00
__init__.py add linting 2023-08-18 11:05:05 -07:00
aleph_alpha.py fix: move to using pydantic obj for setting values 2024-07-11 13:18:36 -07:00
azure_text.py LiteLLM Minor Fixes & Improvements (09/21/2024) (#5819) 2024-09-21 18:51:53 -07:00
base.py LiteLLM Minor Fixes and Improvements (09/13/2024) (#5689) 2024-09-14 10:02:55 -07:00
base_aws_llm.py Litellm stable dev (#5711) 2024-09-14 23:22:59 -07:00
baseten.py fix: move to using pydantic obj for setting values 2024-07-11 13:18:36 -07:00
clarifai.py Clarifai : Fixed model name 2024-08-07 16:59:33 +00:00
cloudflare.py fix: move to using pydantic obj for setting values 2024-07-11 13:18:36 -07:00
custom_llm.py fix(custom_llm.py): pass input params to custom llm 2024-07-25 19:03:52 -07:00
gemini.py refactor: replace .error() with .exception() logging for better debugging on sentry 2024-08-16 09:22:47 -07:00
huggingface_restapi.py [Feat] Add max_completion_tokens param (#5691) 2024-09-14 14:57:01 -07:00
maritalk.py fix: move to using pydantic obj for setting values 2024-07-11 13:18:36 -07:00
nlp_cloud.py fix: move to using pydantic obj for setting values 2024-07-11 13:18:36 -07:00
nvidia_nim.py [Feat] Add max_completion_tokens param (#5691) 2024-09-14 14:57:01 -07:00
ollama.py LiteLLM Minor fixes + improvements (08/04/2024) (#5505) 2024-09-04 22:16:55 -07:00
ollama_chat.py [Feat] Add max_completion_tokens param (#5691) 2024-09-14 14:57:01 -07:00
oobabooga.py fix: move to using pydantic obj for setting values 2024-07-11 13:18:36 -07:00
openrouter.py refactor: add black formatting 2023-12-25 14:11:20 +05:30
palm.py LiteLLM Minor fixes + improvements (08/04/2024) (#5505) 2024-09-04 22:16:55 -07:00
petals.py fix: move to using pydantic obj for setting values 2024-07-11 13:18:36 -07:00
predibase.py [Feat] Add max_completion_tokens param (#5691) 2024-09-14 14:57:01 -07:00
README.md LiteLLM Minor Fixes and Improvements (09/13/2024) (#5689) 2024-09-14 10:02:55 -07:00
replicate.py fix: now supports single tokens prediction 2024-07-25 19:06:07 +02:00
text_completion_codestral.py [Feat] Add max_completion_tokens param (#5691) 2024-09-14 14:57:01 -07:00
together_ai.py fix: fix linting errors 2024-07-11 13:36:55 -07:00
triton.py Fix not sended json_data_for_triton 2024-08-14 09:57:48 +07:00
vllm.py fix: move to using pydantic obj for setting values 2024-07-11 13:18:36 -07:00
volcengine.py [Feat] Add max_completion_tokens param (#5691) 2024-09-14 14:57:01 -07:00
watsonx.py fix: move to using pydantic obj for setting values 2024-07-11 13:18:36 -07:00

README.md

File Structure

August 27th, 2024

To make it easy to see how calls are transformed for each model/provider:

we are working on moving all supported litellm providers to a folder structure, where folder name is the supported litellm provider name.

Each folder will contain a *_transformation.py file, which has all the request/response transformation logic, making it easy to see how calls are modified.

E.g. cohere/, bedrock/.