phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 11:43:54 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
litellm-mirror/litellm/litellm_core_utils
History
Krish Dholakia 7643b3087c
Litellm dev 12 11 2024 v2 (#7215) 
* feat(bedrock/): add bedrock converse top k param

Closes https://github.com/BerriAI/litellm/issues/7087

* Fix bedrock empty content error (#7177)

* add resolver

* handle empty content on bedrock with default content

* use existing default message, tests

* Update tests/llm_translation/test_bedrock_completion.py

* fix tests

* Revert "add resolver"

This reverts commit c717e376ee.

* fallback to empty

---------

Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>

* fix(factory.py): handle empty content blocks in messages

Fixes https://github.com/BerriAI/litellm/issues/7169

* feat(router.py): add stripped model check to model fallback search

if model_name="openai/gpt-3.5-turbo" and fallback=[{"gpt-3.5-turbo"..}] the fallback should just work as expected

* fix: fix linting error

* fix(factory.py): fix linting error

* fix(factory.py): in base case still support skip empty text blocks

---------

Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>
2024-12-13 12:49:57 -08:00
..
audio_utils fix import error 2024-09-05 10:09:44 -07:00
llm_cost_calc LiteLLM Minor Fixes & Improvements (10/09/2024) (#6139) 2024-10-10 00:42:11 -07:00
llm_response_utils (fix) litellm.text_completion raises a non-blocking error on simple usage (#6546) 2024-11-04 15:47:48 -08:00
prompt_templates Litellm dev 12 11 2024 v2 (#7215) 2024-12-13 12:49:57 -08:00
tokenizers Code Quality Improvement - remove tokenizers/ from /llms (#7163) 2024-12-10 23:50:15 -08:00
asyncify.py build(config.yml): bump anyio version 2024-08-27 07:37:06 -07:00
core_helpers.py Litellm dev 11 07 2024 (#6649) 2024-11-08 19:34:22 +05:30
default_encoding.py Code Quality Improvement - remove tokenizers/ from /llms (#7163) 2024-12-10 23:50:15 -08:00
duration_parser.py (QOL improvement) Provider budget routing - allow using 1s, 1d, 1mo, 2mo etc (#6885) 2024-11-23 16:59:46 -08:00
exception_mapping_utils.py fix(acompletion): support fallbacks on acompletion (#7184) 2024-12-11 19:20:54 -08:00
get_llm_provider_logic.py Litellm merge pr (#7161) 2024-12-10 22:49:26 -08:00
get_supported_openai_params.py fix(get_supported_openai_params.py): cleanup (#7176) 2024-12-11 01:15:53 -08:00
json_validation_rule.py feat(vertex_ai_anthropic.py): support response_schema for vertex ai anthropic calls 2024-07-18 16:57:38 -07:00
litellm_logging.py (feat) add error_code, error_class, llm_provider to StandardLoggingPayload (#7200) 2024-12-12 12:18:10 -08:00
llm_request_utils.py Litellm ruff linting enforcement (#5992) 2024-10-01 19:44:20 -04:00
logging_utils.py (refactor) use helper function _assemble_complete_response_from_streaming_chunks to assemble complete responses in caching and logging callbacks (#6220) 2024-10-15 12:45:12 +05:30
mock_functions.py test(router_code_coverage.py): check if all router functions are dire… (#6186) 2024-10-14 22:44:00 -07:00
README.md (QOL improvement) Provider budget routing - allow using 1s, 1d, 1mo, 2mo etc (#6885) 2024-11-23 16:59:46 -08:00
realtime_streaming.py Litellm dev 10 22 2024 (#6384) 2024-10-22 21:18:54 -07:00
redact_messages.py (feat) Allow enabling logging message / response for specific virtual keys (#7071) 2024-12-06 21:25:36 -08:00
response_header_helpers.py fix(utils.py): guarantee openai-compatible headers always exist in response 2024-09-28 21:08:15 -07:00
rules.py Litellm dev 11 07 2024 (#6649) 2024-11-08 19:34:22 +05:30
streaming_chunk_builder_utils.py LiteLLM Minor Fixes & Improvements (12/05/2024) (#7051) 2024-12-06 14:29:53 -08:00
streaming_handler.py (Refactor) Code Quality improvement - rename text_completion_codestral.py -> codestral/completion/ (#7172) 2024-12-11 00:55:47 -08:00
token_counter.py fix: Support WebP image format and avoid token calculation error (#7182) 2024-12-12 14:32:39 -08:00

README.md

Folder Contents

This folder contains general-purpose utilities that are used in multiple places in the codebase.

Core files:

  • streaming_handler.py: The core streaming logic + streaming related helper utils
  • core_helpers.py: code used in types/ - e.g. map_finish_reason.
  • exception_mapping_utils.py: utils for mapping exceptions to openai-compatible error types.
  • default_encoding.py: code for loading the default encoding (tiktoken)
  • get_llm_provider_logic.py: code for inferring the LLM provider from a given model name.
  • duration_parser.py: code for parsing durations - e.g. "1d", "1mo", "10s"