mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-26 19:24:27 +00:00
1e06ee3162
* add mode: realtime * add _realtime_health_check * test_realtime_health_check * azure _realtime_health_check * _realtime_health_check * Realtime Models * fix code quality * delete OAI / Azure custom health check code * simplest version of ahealth check * update tests * working health check post refactor * working aspeech health check * fix realtime health checks * test_audio_transcription_health_check * use get_audio_file_for_health_check * test_text_completion_health_check * ahealth_check * simplify health check code * update ahealth_check * fix import * fix unused imports * fix ahealth_check * fix local testing * test_async_realtime_health_check |
||
|---|---|---|
| .. | ||
| audio_utils | ||
| llm_cost_calc | ||
| llm_response_utils | ||
| prompt_templates | ||
| tokenizers | ||
| asyncify.py | ||
| core_helpers.py | ||
| default_encoding.py | ||
| duration_parser.py | ||
| exception_mapping_utils.py | ||
| get_llm_provider_logic.py | ||
| get_supported_openai_params.py | ||
| health_check_utils.py | ||
| json_validation_rule.py | ||
| litellm_logging.py | ||
| llm_request_utils.py | ||
| logging_utils.py | ||
| mock_functions.py | ||
| README.md | ||
| realtime_streaming.py | ||
| redact_messages.py | ||
| response_header_helpers.py | ||
| rules.py | ||
| streaming_chunk_builder_utils.py | ||
| streaming_handler.py | ||
| token_counter.py | ||
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 utilscore_helpers.py: code used intypes/- 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"