mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 10:44:24 +00:00
LiteLLM Minor Fixes & Improvements (10/18/2024) (#6320)
* fix(converse_transformation.py): handle cross region model name when getting openai param support Fixes https://github.com/BerriAI/litellm/issues/6291 * LiteLLM Minor Fixes & Improvements (10/17/2024) (#6293) * fix(ui_sso.py): fix faulty admin only check Fixes https://github.com/BerriAI/litellm/issues/6286 * refactor(sso_helper_utils.py): refactor /sso/callback to use helper utils, covered by unit testing Prevent future regressions * feat(prompt_factory): support 'ensure_alternating_roles' param Closes https://github.com/BerriAI/litellm/issues/6257 * fix(proxy/utils.py): add dailytagspend to expected views * feat(auth_utils.py): support setting regex for clientside auth credentials Fixes https://github.com/BerriAI/litellm/issues/6203 * build(cookbook): add tutorial for mlflow + langchain + litellm proxy tracing * feat(argilla.py): add argilla logging integration Closes https://github.com/BerriAI/litellm/issues/6201 * fix: fix linting errors * fix: fix ruff error * test: fix test * fix: update vertex ai assumption - parts not always guaranteed (#6296) * docs(configs.md): add argila env var to docs * docs(user_keys.md): add regex doc for clientside auth params * docs(argilla.md): add doc on argilla logging * docs(argilla.md): add sampling rate to argilla calls * bump: version 1.49.6 → 1.49.7 * add gpt-4o-audio models to model cost map (#6306) * (code quality) add ruff check PLR0915 for `too-many-statements` (#6309) * ruff add PLR0915 * add noqa for PLR0915 * fix noqa * add # noqa: PLR0915 * # noqa: PLR0915 * # noqa: PLR0915 * # noqa: PLR0915 * add # noqa: PLR0915 * # noqa: PLR0915 * # noqa: PLR0915 * # noqa: PLR0915 * # noqa: PLR0915 * doc fix Turn on / off caching per Key. (#6297) * (feat) Support `audio`, `modalities` params (#6304) * add audio, modalities param * add test for gpt audio models * add get_supported_openai_params for GPT audio models * add supported params for audio * test_audio_output_from_model * bump openai to openai==1.52.0 * bump openai on pyproject * fix audio test * fix test mock_chat_response * handle audio for Message * fix handling audio for OAI compatible API endpoints * fix linting * fix mock dbrx test * (feat) Support audio param in responses streaming (#6312) * add audio, modalities param * add test for gpt audio models * add get_supported_openai_params for GPT audio models * add supported params for audio * test_audio_output_from_model * bump openai to openai==1.52.0 * bump openai on pyproject * fix audio test * fix test mock_chat_response * handle audio for Message * fix handling audio for OAI compatible API endpoints * fix linting * fix mock dbrx test * add audio to Delta * handle model_response.choices.delta.audio * fix linting * build(model_prices_and_context_window.json): add gpt-4o-audio audio token cost tracking * refactor(model_prices_and_context_window.json): refactor 'supports_audio' to be 'supports_audio_input' and 'supports_audio_output' Allows for flag to be used for openai + gemini models (both support audio input) * feat(cost_calculation.py): support cost calc for audio model Closes https://github.com/BerriAI/litellm/issues/6302 * feat(utils.py): expose new `supports_audio_input` and `supports_audio_output` functions Closes https://github.com/BerriAI/litellm/issues/6303 * feat(handle_jwt.py): support single dict list * fix(cost_calculator.py): fix linting errors * fix: fix linting error * fix(cost_calculator): move to using standard openai usage cached tokens value * test: fix test --------- Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
This commit is contained in:
Krish Dholakia
GitHub
parent
c58d542282
commit
7cc12bd5c6
19 changed files with 496 additions and 121 deletions
|
|
@ -1834,6 +1834,54 @@ def supports_function_calling(
|
|||
)
|
||||
|
||||
|
||||
def _supports_factory(model: str, custom_llm_provider: Optional[str], key: str) -> bool:
|
||||
"""
|
||||
Check if the given model supports function calling and return a boolean value.
|
||||
|
||||
Parameters:
|
||||
model (str): The model name to be checked.
|
||||
custom_llm_provider (Optional[str]): The provider to be checked.
|
||||
|
||||
Returns:
|
||||
bool: True if the model supports function calling, False otherwise.
|
||||
|
||||
Raises:
|
||||
Exception: If the given model is not found or there's an error in retrieval.
|
||||
"""
|
||||
try:
|
||||
model, custom_llm_provider, _, _ = litellm.get_llm_provider(
|
||||
model=model, custom_llm_provider=custom_llm_provider
|
||||
)
|
||||
|
||||
model_info = litellm.get_model_info(
|
||||
model=model, custom_llm_provider=custom_llm_provider
|
||||
)
|
||||
|
||||
if model_info.get(key, False) is True:
|
||||
return True
|
||||
return False
|
||||
except Exception as e:
|
||||
raise Exception(
|
||||
f"Model not found or error in checking {key} support. You passed model={model}, custom_llm_provider={custom_llm_provider}. Error: {str(e)}"
|
||||
)
|
||||
|
||||
|
||||
def supports_audio_input(model: str, custom_llm_provider: Optional[str] = None) -> bool:
|
||||
"""Check if a given model supports audio input in a chat completion call"""
|
||||
return _supports_factory(
|
||||
model=model, custom_llm_provider=custom_llm_provider, key="supports_audio_input"
|
||||
)
|
||||
|
||||
|
||||
def supports_audio_output(
|
||||
model: str, custom_llm_provider: Optional[str] = None
|
||||
) -> bool:
|
||||
"""Check if a given model supports audio output in a chat completion call"""
|
||||
return _supports_factory(
|
||||
model=model, custom_llm_provider=custom_llm_provider, key="supports_audio_input"
|
||||
)
|
||||
|
||||
|
||||
def supports_prompt_caching(
|
||||
model: str, custom_llm_provider: Optional[str] = None
|
||||
) -> bool:
|
||||
|
|
@ -4601,9 +4649,11 @@ def get_model_info( # noqa: PLR0915
|
|||
] # only for vertex ai models
|
||||
input_cost_per_query: Optional[float] # only for rerank models
|
||||
input_cost_per_image: Optional[float] # only for vertex ai models
|
||||
input_cost_per_audio_token: Optional[float]
|
||||
input_cost_per_audio_per_second: Optional[float] # only for vertex ai models
|
||||
input_cost_per_video_per_second: Optional[float] # only for vertex ai models
|
||||
output_cost_per_token: Required[float]
|
||||
output_cost_per_audio_token: Optional[float]
|
||||
output_cost_per_character: Optional[float] # only for vertex ai models
|
||||
output_cost_per_token_above_128k_tokens: Optional[
|
||||
float
|
||||
|
|
@ -4627,6 +4677,8 @@ def get_model_info( # noqa: PLR0915
|
|||
supports_vision: Optional[bool]
|
||||
supports_function_calling: Optional[bool]
|
||||
supports_prompt_caching: Optional[bool]
|
||||
supports_audio_input: Optional[bool]
|
||||
supports_audio_output: Optional[bool]
|
||||
Raises:
|
||||
Exception: If the model is not mapped yet.
|
||||
|
||||
|
|
@ -4870,7 +4922,13 @@ def get_model_info( # noqa: PLR0915
|
|||
),
|
||||
input_cost_per_query=_model_info.get("input_cost_per_query", None),
|
||||
input_cost_per_second=_model_info.get("input_cost_per_second", None),
|
||||
input_cost_per_audio_token=_model_info.get(
|
||||
"input_cost_per_audio_token", None
|
||||
),
|
||||
output_cost_per_token=_output_cost_per_token,
|
||||
output_cost_per_audio_token=_model_info.get(
|
||||
"output_cost_per_audio_token", None
|
||||
),
|
||||
output_cost_per_character=_model_info.get(
|
||||
"output_cost_per_character", None
|
||||
),
|
||||
|
|
@ -4903,6 +4961,8 @@ def get_model_info( # noqa: PLR0915
|
|||
supports_prompt_caching=_model_info.get(
|
||||
"supports_prompt_caching", False
|
||||
),
|
||||
supports_audio_input=_model_info.get("supports_audio_input", False),
|
||||
supports_audio_output=_model_info.get("supports_audio_output", False),
|
||||
)
|
||||
except Exception:
|
||||
raise Exception(
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue